<![CDATA[ markn.ca - All posts ]]> https://markn.ca https://markn.ca/content/images/size/w256h256/2025/08/favicon.png markn.ca https://markn.ca Sun, 05 Apr 2026 09:05:12 -0400 60 <![CDATA[ Security is a service business...one star ]]> For posts that explain one of my talks, you'll probably want to view them directly online at, Security is a service business...one star

This talk was delivered at AtlSecCon in Halifax, NS, on 10-Apr-2025

Abstract

When was the last time you felt like you had enough time in the day to get your work done? Are you exhausted by the never ending firehose of security challenges you have to deal with each and every day?

In this session, we are not going to change that reality. Sorry, security work is continuous, but it doesn’t have to be overwhelming.

This session looks at the workflows around your security practice and how it interacts with the business. Security is a service business, but teams are rarely set up in a way to deliver that service successfully.

There’s a lot of history that contributes to the current state of security teams, but that history typically isn’t serving a purpose. More often than not, the way we’ve built out our work leads to delays, frustrated colleagues, and eventually teams that work around us instead of with us.

This isn’t a talk about simply getting “buy in” from other leaders, it’s about breaking down our security goals and learning from other types of teams and businesses and how they are setup.

You’ll learn about the hidden challenges that impede your work, structures and workflows that can accelerate security improvements, and how to build stronger relationship with the rest of your organization.

Are your customers happy?

I'm confident that most of security professionals will answer this in one of three ways;

"I don't know."

"I don't think they are."

"No."

None of those are great answers to the question.

Do you have enough resources?

Nope.

Why are you like this?

...organizationally 😉

When was the last time you designed a process for your team?

No, I don't mean writing down an playbook (though you should be doing that). I mean working through the steps of a systematic effort in order to design a process that works for your team and your customers.

Have you ever done that?

The security team

Let's start with first principles. There's always a reason why things end up in their current state and there's a lot we can learn from that history.

Why do most security teams organize the same way? Is that the best approach? Or just something we ended up with over time due to external factors?

This all started with endpoints.

Acknowledging that there was risk with our desktops (yes, desktops), organizations started to have folks assigned to managing these systems.

Not like we do today, but the first steps were there. Organizing the OS and its updates, anti-virus software, and other steps to help protect the business.

The real nucleus of what we know of as the security team came to be with network controls. Rolling out firewalls, then intrusion prevention, and other controls around the perimeter was enough work that dedicated teams were required.

No more—well, less—side of desk work. We now started to see teams responsibly for the castle wall protecting the "inside" of the business.

As connectivity expanded, we get closer to today. Teams are dealing with endpoint, network, and cloud controls.

While each of these areas contribute to defence in depth, we also approach them based on the security team's level of responsibility or influence.

Endpoint controls are still very much in the "OK, if it doesn't impact anything" bucket. Security teams tread lightly here, so as not to lose trust with the rest of the business.

Network controls are easier to roll out because they are typically entirely within the security team's purview, or at most involve a small handful of infrastructure teams.

Deploying security controls in the cloud can be more direct. WIth all resources available via an API, connecting to systems, monitoring them, and gaining visibility are more straightforward than ever.

But there's more to security than just these three areas. We've expanded to risk practices, compliance activities, and proactive work like threat hunting.

Security teams in medium-sized enterprises, are likely to scale to have one or two—or more—dedicated resources to each of these areas. Larger organizations can even get to the point where they have dedicated teams for each of these areas.

But one thing that tends to hold true—even for the smallest of teams—is that we organize our teams based on function.

This is Francine, she is responsible for our risk practice. Jo takes care of compliance. Etc.

Functional structure

Function structures tend to exhibit these properties:

  • They allocate resources based on their functions
  • Information flows up and down easily (or least by default)
  • Decisions tend to stay within each of the functions
  • Individuals in each function will develop deep expertise in that area over time
  • Explicit workflows are required to break silos

And it's this last point that is the source of most of our challenges.

I don't think this structure is conducive to workflows that will meet your goals. Or the goals of your customers.

Worse, I don't think that we have the time/energy/awareness to step back and examine the link between our team structure and our workflows.

Simply put, we are too busy doing the work to understand how our approach to the work is making it harder for everyone.

A short activity

In this section, the audience is asked to—and politely does—participate in a group activity. They say each of the letters as they appear on screen.

A B C D

E F G

H I J K

Stop.

I'm not sure why y'all are doing it this way. Let's restart.

(In person, the audience almost always nails this part. They are saying each of the letters in English at the same time and nailing the beginnings of the song as well.)

A B C D

Stop.

I ask the audience, "Why are you saying it that way?"

They are confused. I then repeat the beginning of the alphabet in Dutch. The letter sounds are very different than the English ones.

The point of this callout is that I had very different expectations for the activity. Expectations that didn't line up with the audience's assumptions.

On the same page & language, we restart.

A B C D

E F G

I ask the audience, "How many vowels have we said so far?"

This breaks the flow of the recitation and song. It's an unexpected question, even though it's simple one to answer.

We restart for the 3rd time.

A B C D

E F G

H I J K

LMNO P

Inevitably, a North American audience will say L, M, N, and O as "elemenopee"

It's a fun call out and it runs counter to the previous pacing, but it aligns with the song.

The point of this is that it's an unspoken change that everyone just gets. They go along with it because of the ingrained cultural elements, not because they talked about it beforehand.

Everyone in the audience (or enough that the point is made) recites the alphabet using, "The ABC Song" instead of just saying each letter in turn.

There wasn't a discussion or agreement to do this. Outside of the subtle hinting in the visuals, it's just what everyone defaults to.

It's a cultural expectation. It's "the way we've always done it".

It's a direct parallel to a lot of activities in organizations and frequently the security team (me as the speaker in this case) is unaware of that expectation!

For fun, the audience gets to repeat the whole song without interruption.

A fantastic amount will also—always—add the bonus line, "Now I know my A B Cs, next time won't you sing with me?"

For a bonus, unreleased tangent, it's pointed out that most folks also can't repeat a segment of the alphabet without starting at A and ending up in a close approximation of the song as well. Human brains are weird!

What happened?

Everyone knew the song. You default to it, because you learned it and practiced it a lot as a child.

It's a shared experience that reinforces the original experience and understanding.

I restarted the group 4 times. Each time to clarify something for me or to force the group to confirm to my expectations and requirements.

That's a generally frustrating experience. While trying to fulfill my needs, I cost the group time and enjoyment.

...pausing to let that sink in...

Teams generally work well (enough) together.

Don't be the one who disrupts that.

Don't be the one who disrupts that to serve your own needs...even if those needs will help serve the group!

Self-checkouts

Let's pivot to an even more frustrating topic. But it's a topic that we can actually learn a lot from and relate to as a group.

In the beginning...

When they first rolled out, self-checkouts were hailed as technological advancement, a time saver, and an overall benefit to both the business and the customer.

There were some discussions about the balance of those benefits, but outside of the "old man yells at cloud" segment, there wasn't a lot of negativity...at first.

I bring up self-checkouts because I'd like to share a story to help illustrate my overall point of the importance of explicit service design. To help understand how we can all be more effective security practitioners, I'd like to talk to you about my local pharmacy...

Before rolling out self-checkouts about 18 months ago, my pharmacy had six checkout lines.

Each one of the checkouts was staffed. In peak times, they had six employees running the six checkout lines.

If we put ourselves in the owners shoes, the six checkouts—running at a theoretically maximum—would require about $0.59/sale in overhead.

We get to that number by looking at the number of sales each line can process during an hour and the cost to serve that line.

When the pharmacy deployed their self-checkouts, they made a couple of slight adjustments to the traffic flow.

The two middle lanes now were product shelves for those impulse buys. The back wall now housed 3 self-checkouts and so did the left-most checkout line.

The right-most checkout line was kept as a staffed line to help address any customer issues. This employee was also responsible for helping any self-service customers who encounter issues.

Now, when we adjust for the extra time it takes for self-service, the overhead drops significantly for the store.

They are pushing through less sales (120 vs 180), but at 25% of the overhead.

Given the average sale at a pharmacy these days, this probably isn't a great business move. However, the back end costs for employees are going to be significantly higher than maintaining the self-checkout systems.

The self-checkouts also don't have scheduling issues. They are always available and you don't need to try and predict demand. There's a consistency there that simplifies operations.

The problem—ok, a problem—the store encountered quickly was that four of the six self-checkouts weren't seeing much use.

The reason was simple, customers weren't seeing them!

The product displays which were thought to be a clever way to re-purpose the previously staffed checkouts, were interfering with the view of the self-checkouts.

Customers were queueing up like they used to for the staffed checkouts and not taking advantage of the additional self-checkout capacity.

When we look at the throughput from this challenge. The overhead is half of the full service approach, not a quarter of it.

That's a huge impact to the expected savings. This is a problem that needs to be solved.

The solution the pharmacy came up with was to remove the obstructions. This makes perfect sense and really opened up the area.

While it removed the ability to convert the impulse buyers, it made it a lot easier to see the entire set of checkout options.

But there was a problem...

A significant percentage of the customers for the pharmacy are seniors. Seniors who were not having anything to do with the self-checkouts.

When presented with the suite of options, the seniors overwhelmingly selected the full service option. To the point where they were queueing up when almost all—if not all—of the self-checkouts were open.

This reduced the checkout throughput of the store dramatically.

Any guests on how the store "solved" this challenge?

To address this issue, the store put up a new half wall. They physically blocked the direct access to the full service checkout.

The positive (?) aspect to this solution is that it helped to shape the queue. Instead of blocking traffic to the main shopping aisles, the queue now formed in the checkout area.

However, this block reduced the visibility of the full service checkout. The customers who wanted to use it had to now go out of their way to queue up for it...if they saw their preferred option at all.

This also doubled their walk for the workflow. They now had to walk to the queue, move to the full service checkout and then walk past all of the self-checkouts (again) to leave the store.

This is not a good solution and customers complained. To help address this, the store added an additional staff member to help guide more people to the self-checkouts.

In isolation, each of these decisions makes sense. Given problem X, solution Y is a reasonable approach. But, when you examine the overall workflow, the entire problem space, you see how ridiculous these steps are.

From the business perspective, the numbers are better. Overhead is down.

But what about customer satisfaction? This is much harder to measure. Anecdotally, as a customer, I can tell you it's down. How much will that impact their bottom line? I'm not sure.

For our purposes, the key takeaway is that even though the steps taken to address each issue were logical and moved towards the state goal, the result isn't what was intended.

And now...

It's not just my experience or this pharmacy, self-checkout has not been an amazing solution.

Through multiple iterations of the various platforms, a positive and smooth self-checkout is a very rare experience. This is now one more thing that we just put up with...despite the general feeling.

Again, this is a result of a series of logical decisions. The problem is that the context window for those decisions got smaller at each and every step.

The end result is a lot of effort and an outcome that may—or may not—align with the actual business goals.

Service design principles

While there are formal methods of doing service design, at it's core, simply asking questions and listening to the feedback will improve your team's workflow significantly.

However, the principles proposed in "This is Service Design Doing" are a great way to establish a shared understanding of what you're setting out to do.

In the simplest terms, those principles are:

  • Take the customer's perspective (human-centered)
  • Involve a diverse set of stakeholders in development (collaborative)
  • Small experiments, fast feedback loops (iterative)
  • Visualize and orchestrate the whole process (sequential)
  • Get out into the actual environment of the service (real)
  • Address customer needs sustainably throughout (holistic)

"This is Service Design Doing" is an excellent starting point. It's not the only reference out there, but it's very approachable and the Methods book is a great playbook to help you implement changes in your team.

Risk assessments

Assessment frameworks

There are a lot of different frameworks for doing risk and threat assessments. There are advantages and disadvantages to each, though really any will do.

The fact that you're conducting assessment—and regularly updating them!?!—is the most important thing.

How many folks use one of these frameworks? Or something similar?

Assessing risk

Do you conduct the assessment when the team is writing the code and building the solution?

...when they are testing the solution out?

...or maybe when it comes time to run the solution?

Trying to start and then finish an assessment just as things are going to production is far too common. We—the security team—end up in this position often because of some of the service challenges we're talking about here.

Of course the answer is that you should be doing risk assessments as a continuous process. There is assessment activity at all stages of solution development.

But, this only works if you're collaborating with the builder team. If you have the trust of other groups in the business. You have to work together and towards a common—and commonly understood—goal for this to actually work.

Getting there...

How do you end up in this utopia? This fictitious, "it's easy to put on PowerPoint" world?

The honest, open answer is, "Slowly, patiently, with a series of small steps that each get your closer to your shared goals."

Let's start by looking at the service design principles and the questions we can ask ourselves in order to start to find the path forward.

If we take the customer's perspective, we should have answers to the following questions:

  1. What are we doing this?
  2. What do I get from it?
  3. How can I make this easier?

When it comes to risk assessments (and other security work), often the answers are:

  1. Not sure.
  2. No idea.
  3. Just not do it?

Those are not great answers and they are strong indicators that we—the security team—need to be doing a much better job of communicating.

When addressing a good representation of your stakeholders, ask the following of your own team (security):

  1. Will the same process work for everyone?
  2. What are the key outcomes?
  3. Are we removing waste from this process?

Making small changes and getting feedback as quickly as possible is one of the most important things you can do for your work.

  1. When was the last time we asked if this worked?
  2. Do we gather data on our process?
  3. What adjustments have we made?

These are all questions that will help you build your feedback loops and hope you to create a truly iterative process.

In the examples we worked through today, we saw the value of taking the big picture view. Understanding the entire process is the only way to avoid the shrinking context path like we saw with the self-checkout example.

  1. Does our work start and stop at our team "borders"?
  2. How much do we know about our customers?
  3. What happens after the assessment is done?

Visualizing and orchestrating the whole process is key to breaking out of your silo. It's how you counter the limitations of the functional team structure.

Too many teams lay out their workflows based on their understanding and expectations of the customer. While it's possible that this might be accurate, it's unlikely.

Getting out and experiencing your customer's reality will help you understand their perspective. That understanding will lead you to better solutions.

My pharmacy didn't understand the majority of its customers. They missed the fundamental frustration that self-checkouts bring up with their older customers. No one wants to feel like they don't understand or that they are the problem and "don't get" the technology.

  1. Have you sat with your customers? With theirs?
  2. How often do you connect with the business?
  3. Do you know how other teams work?
  4. Have you tried their work, their tools?

  1. Are you working other make things simpler?
  2. Can you help the customer do more on their own?
  3. Is there something working really well? Can you do more of that?

Sustainability in processes is tied to complexity. Do not attempt to design a process that covers 100% of the edge cases. A workflow that solves 80–85% of the most common cases and has an allowance for the remaining 15% will be far more effective.

When making a decision, the simpler path is where you should be aiming.

The is bad

If your customers are unhappy, you have work to do. Frustrated teams work around security workflows. Not because they don't want to be secure, but because they want to get their work done.

Security is in their way. You have to avoid that at all costs.

So, do we think that the structure of our teams is influencing our workflows? And that these workflows are not serving our needs or our customers?

I do. And I think we need to change. I confident we can change and that those changes don't need to be all compassing to start.

We start by choosing to address these gaps.

We build a network of support within the business. Build understanding of how other teams work, how they communicate, and how our shared goals align.

You cannot succeed as a security team without the support of other teams in the business. The numbers simply don't add up. You need to succeed together.

The good news is that you have the same goals, you just may be speaking different languages right now or failing to share each others perspective.

You can address these challenges and improve your security by working together. And that starts with you taking a small step towards that goal.

References

]]>
https://markn.ca/2025/security-is-a-service-business-one-star/ 67f6bbeaaf961b00014432ec Thu, 10 Apr 2025 14:40:31 -0400
<![CDATA[ Let's Talk Cloud ]]> Want to share with others? Formatting issues in your reader? This post is available online, Let's Talk Cloud

As the Vice President, Cloud Research at Trend Micro, I had a mandate to educate others about cloud security and enough leeway to experiment with how I went about it.

We had a fantastic communications team who were eager to try out new platforms and new approaches. With streaming and podcasting really starting to take off, we launched a new episode show, "Let's Talk Cloud".

Right out of the gate, we knew this was going to be a learning experience for us. We kept the show simple to start with. The first show was a discussion between myself and two of our technical leaders in the field, Jeff Westphal and Fernando Cardoso.

Jeff called in from an event where he was presenting and Fernando was in one of the Trend offices. It was a very scrappy setup, but it worked. The conversation flowed well and we were able to draw in a modest live audience.

For the remaining 5 episodes in the first season, we stayed within the Trend Micro family when recruiting guests. This made it a bit easier to justify the rough edges that we were still smoothing down.

By the end of the first season, we had a reasonable smooth running show that was gaining a lot of traction. The view numbers were nice, but what was more important was how often someone—a customer, a colleague, or a random stranger—would tell me how they had watched an episode and it got them thinking.

For the next season, we were a lot more ambitious in going after guests. We had high profile guests like Forrest Brazeal, Patrick Debois, and Tanya Janca.

Sadly, I moved on from Trend Micro before I was able to film another season. However, our work on this show kicked off an ongoing series for the company. Next up was Let's Talk Security hosted by Rik Ferguson and then #TrendTalksBizSec and #TrendTalksThreats.

Sample episodes

All episodes

]]>
https://markn.ca/2025/lets-talk-cloud/ 67f6bbeaaf961b00014432db Mon, 17 Mar 2025 16:20:34 -0400
<![CDATA[ Mornings with Mark ]]> Want to share with others? Formatting issues in your reader? This post is available online, Mornings with Mark

Going back through the archives of "Mornings with Mark" has been quite the experience. I've been both fascinated and a little horrified (the hair, the look, the production…yikes) re-watching some of those nearly 200 episodes.

It's interesting to remember that back then (2018—2019), a regular, dedicated vlog focused on cybersecurity and privacy on social media was pretty rare.

"Mornings with Mark" was really a space for me to explore my thoughts on these crucial topics and share some of what I was learning while traveling and teaching cybersecurity. It was also a bit of an experiment with social media and video platforms.

I ended up regularly multi-streaming to LinkedIn (where I was part of the streaming beta program), Twitter, and YouTube. Social media was very different in 2018 and the consistency of the vlog helped grow the audience over time.

Over its run, the show averaged 250 live viewers and then another 1,000 on-demand within that week. Those numbers may seem modest, but to have that type of reach for such a simple and raw vlog was really touching.

It’s nice to know that I was able to help that many people understand security and privacy just a little bit better.

Sample episodes

All episodes

Nov/2018—9 episodes

Jan/2019—8 episodes

]]>
https://markn.ca/2025/mornings-with-mark/ 67f6bbeaaf961b00014432da Fri, 14 Mar 2025 20:41:07 -0400
<![CDATA[ My years on CBC ]]> Want to share with others? Formatting issues in your reader? This post is available online, My years on CBC

Walking past the display of Leafs memorabilia, I turned the corner, opened the door, and took a seat in the conference tucked away in the Air Canada lounge. I chuckled at the framed magazine covers adorning the walls with a who’s-who of Canada. I set my scorchingly hot Tim Hortons tea on the desk and waited to join the province-wide broadcast on CBC Radio.

In that pause, I took a moment of self-reflection and giggled quietly, half expecting a Mountie on a moose or a Québécois lumberjack with a mountain of syrup-drenched pancakes to pass by.

It felt deeply Canadian. Yes, an unbelievable, absurd, comical amount of Canadian-ness compressed into one moment, but that didn’t diminish my enjoyment. The smile that spread across my face stayed with me the rest of the day.

First steps with the network

My first appearance on the network was specifically Canadian as well. In 2014, the CBC was looking for expert commentary on how the Canadian Revenue Agency (CRA) was responding to the serious, widespread software vulnerability.

Having already started to appear in the media semi-regularly the previous year, I was a good fit for the article with my decade of experience in the Canadian public service. My commentary appeared alongside the director of the Canadian Internet Policy and Public Interest Clinic (CIPPIC) and Dr. Christopher Parsons from—at that time—the Citizen Lab.

I was humbled that my commentary was featured with such prominent experts in the field. Experts that I regularly read and still do!

That piece really sparked a passion in me. I enjoyed doing the analysis and offering a pragmatic voice on technology issues. A voice that I hoped—and still hope—helps to balance out other voices in the field.

Even then, I knew that my opinions often run counter to the louder voices that can grab the headlines. I’m ok with that. I’d rather go on the record saying something I believe in, something that I can stand behind even a decade later.

I’m also ok being that pragmatic voice. It’s not as flashy, but I believe that it can deliver more nuance and help make complex issues accessible to everyone.

Off and running

Over the next 8 years, I would appear more frequently on various CBC properties. From St. John's to Victoria, I always tried to make time to support CBC journalists and hosts who were looking to help Canadians understand what was going on in the world of technology.

I was thrilled when things started to snowball as my comments were published more frequently. This led to a regular spot on TV, appearing on The Exchange with Peter Armstrong. I also covered issues for the CBC News at 6 in cities across the country and was featured in segments on the CBC News Network channel.

Easier—logistically at least—were the radio segments. I've always been an early bird, so when I delivered a couple morning drive-time segments, I started to get called more frequently. I get it, there's not a lot of folks willing to try and distill complicated issues into something easily understandable before 8 am.

CBC Ottawa Morning

Those early morning segments lead to a regular radio column on CBC Ottawa Morning. Once every couple of weeks, I would chat with the host for 6-8 minutes and summarize the news of the moment and try to contextualize it for the audience of 100,000+.

I absolutely loved the challenge of it and got a lot of joy out of helping folks in the region to better understand specific issues.

The process was pretty straight forward. Sometimes the show would reach out the day before and ask if I could talk about a news story. Other times, I would reach out and suggest a topic flying a bit under the radar.

We'd agree on a topic and I would do an initial brief to help the show's researchers start to dig in to prepare the host for the discussion. After that, I would conduct my own research and start to outline the key areas of the issue, its larger context, and try to highlight a few hooks that would help it all land.

I'd circle back to the show with a couple of bullet points to help point the conversation in a productive direction and that was really it for formal preparation. I'd make sure to study my notes and go over key points so that the conversation could flow smoothly while still being informative.

It was great practice for a workflow that continues to help my daily. Being able to identify a topic of interest and then quickly map the landscape around it has been a game changer for me.

This workflow not only satisfies my natural curiosity, but it helps me to consistently contribute to my team and my community.

Eight years of teaching and learning

From 2014 to 2022, I made over 100 appearances on air and in print for the CBC. Each and every time, I tried to help Canadians better understand how technology impacted their lives and communities.

Looking back, I can see how I’ve grown as a communicator. Starting out with safer commentary like a Timbits player taking the field for the first time. With practice, I’ve become more confident expressing my opinions and I’ve found my voice. I moved from just starting facts to crafting explanations that break down complicated issues into simpler, relatable analogies to help everyone understand.

I’ve learned the value of consistently coming back to a topic over and over again. Just because I may be a little tired of talking of security and privacy fundamentals, doesn’t mean everyone is. It’s the patient repetition, the calm explanation of the key issues that truly reaches people.

Technology is complicated. There’s no getting around that. People are hungry to understand the questions technology raises and the questions it helps to answer.

Like that Air Canada lounge seeped in Canadiana, sometimes you need to go above and beyond to get the point across. For me as a security communicator, that means finding the hook inside the story that builds a bridge for the wider audience.

I loved my time on the CBC. It helped me grow as a communicator and touched on a nostalgia I didn't fully appreciate.

Research notes

Here is a sampling of reference notes and materials that I prepared for various segments over the years. These focus in the last few years when I was active with the CBC.

I've archived them here on the site for my own memory, but also to show some of the behind the scenes process that goes into doing a regular technology column on a show.

]]>
https://markn.ca/2025/cbc/ 67f6bbeaaf961b000144313e Thu, 13 Mar 2025 12:09:00 -0400
<![CDATA[ Helping people get the most out of AWS re:Invent ]]> Want to share with others? Formatting issues in your reader? This post is available online, Helping people get the most out of AWS re:Invent

In the fall of 2012, 5,000 people gathered in Las Vegas for the first AWS re:Invent. I was there and spent almost all of my time with my laptop open, surrounded by other builders, working together to try out new techniques and tricks that we were sharing with each other.

That spirit of community was infectious. After the event, a lot of the connected we made shifted online. And year after year, I would see those friendly faces are various events around the world and we all did our best o make it back to Las Vegas in November for the biggest conference in cloud.

Monstrous growth

re:Invent grew almost too big. Every year it would expand to move venues and add more sessions. The event was scaled back in the pandemic, with the 2020 edition moving entirely online.

As the world has moved through the pandemic, the conference has grown back to it's previous size and beyond. Almost 60,000 people attended the 2024 event.

it's at the point now where I don't think the hours in the day will permit anything more to be jammed into the week...though I'm sure I'll be surprised.

What should I do?

I've participated in every edition of the conference. As a builder from the start, an AWS Community Hero for ~6 years, and now as an Amazonian. During the period of rapid growth, I started writing an annual guide to the conference.

It started simply enough. I was trying to remind myself how to prepare for a physically and mentally exhausting week. I love attending this show, seeing my friends, making new ones, and learning a ton. But, it can take a lot out of you.

I started to experiment with how I approached the conference. I figured out little tricks that made my week easier. I genuinely wanted others to get the most out of the week too.

Eight times, I published my guide, starting in 2016:

  1. 5 Ways To Get The Most Out Of AWS re:Invent 2015
  2. 5 Ways To Get The Most Out Of AWS re:Invent 2016
  3. The Ultimate Guide to Your First AWS re:Invent (2017)
  4. The Ultimate Guide to AWS re:Invent 2018
  5. The Ultimate Guide to AWS re:Invent 2019
  6. The Ultimate Guide to AWS re:Invent 2020
  7. The Ultimate Guide to AWS re:Invent 2021
  8. The Ultimate Guide to AWS re:Invent 2022

Define 'ultimate'

You'll notice that the 3rd edition of the guide introduced the adjective, "ultimate". I debated whether or not to do this at the time.

It's a bold claim and I'm deeply uncomfortable drawing attention to myself.

However, that guide is also a 19 minute read. It's comprehensive to say the least. I think the "ultimate" description is accurate. The guides quickly became a months long effort.

Not because they took that long to write, but information about the show changed in the lead up. AWS would announce the basics (where, when, etc.) and then add more details as they locked things in.

In addition to the level of details, the guides started to get a lot of attention. Each year the audience grew. People would reach out to me with great feedback and share how they had come across the guide and how it helped them.

All said, over the eight guides, more than 500,000 people read them. That's a crazy amount of people and inline with the majority of attendees.

Copycats?

While some companies did try to copy the guides, more simply wrote up their schedules and linked to my work. I really appreciated that and tried to keep things as neutral as possible.

The personal recommendation approach resonated with people. I'd like to think that it helped to seed the idea for the official AWS guides to the event. These guides were written by individuals in the community and helped a specific audience select sessions at re:Invent. I wrote the security guide for the first few times and I'm happy to see the effort continuing to this day.

Constant #protips

Looking back at the guides, there are a few tips that still hold up and probably always will:

  1. Wear a good pair of sneakers that you've already broken in
  2. Pack snacks
  3. Hydrate often
  4. Chap stick and hand cream—casinos are absurdly dry
  5. Plan ahead to eat at reasonable times
  6. Don't be shy–take advantage of being there in-person
  7. Have fun!

A fun show

The guides were a way for me to share my excitement for the show. I always feel an odd combination of exhausting and exhilaration when I attend AWS re:Invent.

There is so much to learn. So many people to connect with. It's a great reminder of the unlimited possibilities that drew me into technology in the first place.

While I don't write the guides anymore, I'm happy I did. I'm even happier that I still get to attend re:Invent—and re:Inforce!—even if it's a little more stressful helping to deliver the show vs. trying to take it all in.

Most of all, I'm glad that I was able to contribute to the amazing cloud community in a meaningful way. I'm happy I still get to contribute and more than a little relieved, those contributions don't needs 3+ months of work each year!

]]>
https://markn.ca/2025/helping-people-get-the-most-out-of-aws-re-invent/ 67f6bbeaaf961b00014432eb Mon, 10 Feb 2025 17:08:00 -0500
<![CDATA[ Some small steps towards better security communication and education ]]> For posts that explain one of my talks, you'll probably want to view them directly online at, Some small steps towards better security communication and education

Security is everyone’s responsibility. How is that supposed to work? Our teams have struggled for a long time trying to move away from reactive work to planning and building for a more resilient future.

Is that shift even possible given our small teams and the never ending stream of issues to respond to? How can you scale your security practice in any meaningful way?

Security issues are often deeply technical and nuanced. Delegating work is a constant challenge and it feels like we’re explaining the same things over and over again. Security teams are stuck.

In this talk, we’ll dive deeper in the roles security teams play within most organizations. We’ll explore the common approaches to running a security practice, what works and what doesn’t. 

Then, we’ll start to examine communication techniques that can have a positive impact. We’ll look at how you can shift your work from constant response to more impactful efforts by laying the groundwork for others to succeed.

You’ll walk away with a better understanding of the problem your team is facing and some small steps you can take now to enable other people with your organization to make better security decisions.

You are a dedicated security professional. You understand your area of expertise deeply and are working the best you can to help improve the security of your organization.

You're working on a team of like-minded individuals. While it can be challenging always facing threats and trying to help reduce risk, you generally work well together.

The challenge is that your team is accountable for the security of the organization.

But you work with a lot of teams in the rest of the business. Those teams are responsible for various business goals. They are working just as hard to meet those goals.

It can be hard to keep up.

Why is it hard to keep up?

A few years ago, a couple of different analyst firms looked at the ratios of security professionals to the rest of the business.

They found that there was about one full-time security resource for anywhere from 650 to 1,488 other employees.

That's one person responsible for the tools, processes, and output of at least 650 others. Is that even possible?

In 2022, a report from the UK Department for Digital, Culture, Media & Sport provided a similar metric.

They found that 12% of businesses with 250+ employees had 1 person responsible for cybersecurity...and that wasn't necessarily a full-time assignment.

In 2023, Venture Beat conducted a survey and found that most organizations spend just shy of 10% of their IT budget on cybersecurity.

38% of that spend was on staff. That works out to 3.8% of the overall IT budget spend on security personnel.

That sounds like a lot, but there are some of the most highly compensated individuals on staff. Good for those in the industry, still representative of a disproportionate ratio of security folks to the rest of the business.

The Venture Beat survey provides even more insights. Most of the security spending is going to infrastructure and threat intelligence and detection.

That loosely translates into outer perimeter controls and figuring out what's already causing issues within your systems. Very little directly into scaling up the security team or preventing security issues in the first place.

The result of all of this is a lot of security folks feeling burnt out. Security teams are overworked, constantly fighting fires and trying to answer why a significant chunk of the IT budget is being spent on simply not losing ground.

We should do better. Can we?

Organizational design

...or lack there of

The current workflow for most security teams is simple.

A business team has built or bought something and they want to get it into production as quickly as possible. They do have business goals to meet after all.

You, the security person, is the gate they must pass before that happens.

This works-ish. Sadly, it leads to a lot of "hero" behaviour which prevents the actual challenge from being addressed and piles more pressure on the security team members.

The fundamental challenge comes back to that ratio. There are a very limited number of security team members and way, way more business teams.

Security is almost always the slow down or roadblock for their productivity...even thought security is working at 100% or more of expected capacity.

Keeping things at a high level, there are only 2 ways to smooth out this workflow.

You can slow down the incoming work.

or

You can reduce your security goals.

No security team should accept a reduced security posture as a matter of standard practice.

We need to continue to raise the strength and effectiveness of the security posture of our organizations.

We might be able to slow the incoming work down though...we're come back to that in a few.

Now, you can add more folks to the security team. You can scale up the team to handle more work.

This can help.

But, hiring anyone is an ongoing expense (something about always wanted to be paid 😉) and it takes time for new team members to come up to speed.

And as we've already looked at, the ratio of security team members to the rest of the business is so disproportionate that it's unlikely you'd be able to get it down to anything reasonable to actually address these challenges.

This is not a path that will successfully solve this issue.

So, what approach will work?

We—the security team—need to work with our business teams to reduce the issues upstream.

We need less security issues coming to us before systems are rolled out to production.

How do we do that?

Our general approach will be to use mechanisms to reduce our manual efforts.

A mechanism (in this context) means that we're going to try and create a tool of some sort—a process, an automation, etc.—and get folks using it, all while making sure it's delivering what we actually want.

What we don't want is more process and red tape. If something isn't serving the business' end goals, get rid of it!

Mechanisms and automation

...sort of

There's a lot we could look at here, but for this talk, we're going to look at the communications side of things.

Can we change the way we communicate and reduce the amount of work our teams are receiving? Can we make it easier to communicate in a more productive way?

Yes, we usually lean into technology to solve problems. We eagerly roll out code and additional layers of systems to address issues as we come across them.

That's not necessarily a bad thing. But, more frequently that we'd like to admit, we just end up with more overhead and challenges that are harder to address because the systems we just deployed have added more constraints!

We're going to take a deeper look at a breach notification from here in Canada. Don't worry, this will be a positive example that we'll be examining to see if we can make some tweaks to improve it even further.

But let's start with a general template for a notification...

The formula for a breach notification—e.g. letting people know there was a security incident and they were affected—is very straightforward...at a high or conceptual level.

It is:

  • What happened?
  • What information was affected?
  • What have we done in response to the breach?
  • What does this mean for you?
  • More information and how to make a compliant (with a regulator, etc.)
  • Signed by a representative of the company

Remember, we're not trying to blame anyone. We're trying to learn!

We're going to dive into a breach TransLink had in 2020. TransLink is responsible for the regional transit network in metro Vancouver.

They were breached in 2020 and the entire recovery and review process took 7 months. That includes the clean up and work with the privacy regulator. The initial incident response appeared to be quite quick.

Overall, I think there communications were good. When compared to a lot of security comms, they probably should be seen as excellent.

But, I'm a bit picky and I think TransLink could've made a couple of small tweaks to really knock it out of the park.

From the TransLink primary web page for this incident:

"
In December 2020, TransLink was the victim of a cyberattack. Upon detection, we took immediate action to shut down multiple computer systems as a protective measure and launched an investigation.

Over the course of the investigation, we worked tirelessly with cybersecurity experts to understand what happened and determine what information was unlawfully accessed. We also worked with law enforcement authorities and notified the Office of the Information and Privacy Commissioner for BC.

This investigation has been a complex and time-consuming process that took months to complete. It involved extensive analysis, the use of e-discovery tools, and manual data reviews.

The privacy review concluded in June 2021.
"

As you can see, that is a solid opening. However, it does fall into some very common traps. Let's make a couple of edits...

In December 2020, TransLink was the victim of a cyberattack. Upon detection, we took immediate action to shut down multiple computer systems as a protective measures and launched an investigation.

Over the course of the investigation, wWe worked tirelessly with cybersecurity experts to understand what happened and determine what information was unlawfully accessed. We also worked with law enforcement authorities and notified the Office of the Information and Privacy Commissioner for BC.

Here is what you need to know about your information.

This investigation has been a complex and time-consuming process that took months to complete. It involved extensive analysis, the use of e-discovery tools, and manual data reviews.

The privacy review concluded in June 2021.

Why those changes?

The original was too complicated, not empathetic, and it didn't set a shared context.

The same changes we made shifted the opening to quickly state what had happened, hint at the scale of effort to respond, and then quickly dives into the number one thing the reader of the letter would want to know.

Of all the common traps the original fell into, the most egregious—yes, even in the context of a good communication, there can be things that are egregious!—is that it's written from what the organization wants you know about the situation, not what the reader wants or needs to know!

Yes, breach notifications and other security communications can be used to reduce damage to an organizations reputation. However, it's critical that you remember that both parties in this communication are victims.

The organization—TransLink in this case—was the victim of cybercrime. The intended reader of this letter were also victims of that same crime.

As long as the origination wasn't derelict in their care of the information, this post shouldn't be written with the tone of "it's not my fault!", but one that lands more along the lines of, "we are both impacted here, but let's start to fix this by focusing on you".

Let's go for a complete re-write. We'll start with a strong and direct opener written with the reader and their position in all of this top of mind.

"
In December 2020, TransLink was hacked. When we found this out, we worked as quickly as possible to protect your data.
"

Simple. Straight to the point. With the first sentence, the reader knows what this communication is about and what happened.

The second puts TransLink in a positive light and it's also—without all of the fancy terminology or long-winded explanation—an accurate description of what happened.

We continue...

"
We brought in cybersecurity experts to help. We also contacted law enforcement and the Office of the Information and Privacy Commissioner for BC.
"

This next section is primarily a regulatory requirement. They need to let the reader know that they've complied with the local privacy legislation.

But, we frame it here as a follow-up to the statement about working as quickly as possible to protect your data.

This way, it shows—in plain language—the effort that the organization went to in response to the breach.

The next line is critical and it's often missing from these types of notifications.

"
We’ve contacted the people whose data was accessed during the hack to help them.
"

Remember, the original text that we're rewriting was published on the TransLink website. It went out to everyone. That makes sense due to the scale of the breach and the nature of the organization. This agency is the regional transit authority and its work impacts everyone in the area.

We add this line as a direct answer to the question in every readers mind, "Was my data breached?". This direct statement answers that near the top, helping the reader focus on the rest of the message.

We follow that up with an explanation of what the reader can find on this page.

"
This webpage contains information about what happened. It listed what data was accessed and what steps we’re taking to try and make sure this doesn’t happen again.
"

And finally, we closing this section with a catch-all to help answer any questions the reader may have after reading the rest of the page. This is may be implied, but by stating it, the reader is reminded of the dynamic and that organization is trying to help reduce the overall risk and any potential harms that may come from the breach.

"
If you have any questions after reading this information, we’ve set up a few different ways to get in touch with us directly. Those methods are listed at the bottom of this page.
"

Again, the communication from TransLink during this incident was great. But, with a few small tweaks, I think we've improved it to focus on what matters most to their target audience.

Our updated version heads off a lot of questions by answering them directly. We also reduced the complexity of the writing making the text easier to read. We've dropped the level equivalent from about 2nd year of University to middle school level (as per the Gunning fog index). That makes the entire text much more accessible.

This approach should reduce the number of inbound requests to the organization. And it's an approach you can use internally to do the same for your team.

Clear communication can reduce your workload.

Let's look at another positive example. This one is from CISA, the Cybersecurity and Infrastructure Security Agency in the US. CISA is the national coordinator for critical infrastructure and resilience in the United States and often acts as a cybersecurity centre of excellence for their public service.

We're going to dig into their Log4j vulnerability guidance page. They got this page up quickly when Log4j went public and used it as the single source of truth for the issue. They updated repeatedly with information about the vulnerability as it came to light and made sure that the page was as comprehensive as possible.

Here's a section of the CISA page that we'll be looking at. It's solid.

But, I do want to point out one approach that may create challenges for the intended audience...

Each of the highlighted passages are technical terms or industry specific language.

That's not necessarily a bad thing. CISA was a specific target audience in mind—security experts.

However, given their position within the US public service, they are also going to have a lot of general IT folks and other various interested folks reading this too.

The question is, can we reduce the specific language without reducing the effectiveness of the writing or the technical details?

We won't go through each term point by point, but here's a quick example of what we could swap out:

- "active, widespread exploitation" => "attackers are currently using this"
- "unauthenticated remote actor" => "attackers don't need to login to use this successfully over the internet"

Yes, sometimes a longer sentence is a clearer one. When in doubt, a longer sentence with less niche terms and more straightforward language is probably going to be more effective.

This also required more context. While this page is for a specific vulnerability, it has a wide ranging impact that is crying out for more context.

The second paragraph with, "...is very broadly used in a variety..." doesn't provide enough context. Something like this might've been more effective, "Log4j is a key building block of a lot of software and most people are unaware their systems are using it. It helps developers write log information that's helpful for troubleshooting, that's why it is a part of a lot of unexpected systems."

Last example, again a positive one.

This time, we'll look at an open source project called Prowler. This is "an open-source security tool designed to assess and enforce security best practices across AWS, Azure, Google Cloud, and Kubernetes".

It's a great project and helps a lot of organizations improve their security posture.

In this example, we're going to look a specific detection from the platform and how it aims to help developers and security folks avoid a security issue.

Here's the detection information in full. It's typically delivered as a JSON object in the platform or teams will route these to Slack or some other system where they are typically working.

This is a solid detection. The description is crystal clear. The risk is well constructed and the recommendation isn't too bad.

But two things jump out at me here.

The first is the opening sentence of the risk, "The use of a hard-coded password increases the possibility of password guessing." That doesn't accurately convey the level of risk.

How much does this increase the possibility of the password being guessed? Is that actually the case with this detection? Why is this worth the time to fix?

The second challenge is the recommended fix. Sure, AWS Secrets Manager could help address the issue. But are there other approaches that would work here? Are there other secrets managers that would work?

Again, the original is solid.

But if it provided more of the why in the risk it would be more useful.

"Hard-coded passwords can be stolen by attackers or accidentally exposed in a source code repository. Avoid this pattern if at all possible, as attackers can easily compromise the account the password has access to."

Similarly, the recommendation can be expanded to help the recipient find the best solution for their situation.

"Using a tool to manage secrets—like AWS Secrets Manager—keeps passwords and other secrets out of your code. This partner makes it easier to update that information (e.g., change the password), while keeping it more secure as the function requests the password only when it's needed."

A couple small adjustments and we've reduce the dots the recipient is required to connect!

As we've seen in the examples we've discussion—and again, they are all positive examples!

We can make some small adjustments to our approach to communication to help everyone make better security decisions and help reduce the incoming requests to our team.

For communications:

  • Keep it simple
  • Focus on the reader
  • Create shared context
  • Be empathetic

Working upstream

We've talked about communications with an eye to how clearer communications can reduce incoming requests to your security team.

We're going to take that a step further and talk about education. One gap most security teams have today is a failure to help the rest of the business understand how to prevent security issues.

I'm not talking about security awareness training (don't even get me started on that) or a patch management process. I'm talking about genuinely investing the time required to help other folks outside of the security team understand how security first thinking can help them.

Your team works regularly with a number of business teams.

As we discussed in the intro for this talk, that ratio is heavily weighted towards the business teams. You can't keep up with the work coming from all of the different business teams.

One way to help with this is to recruit other folks within the organization to advocate for more security-first or security-focused decisions.

Programs that help build this type of internal community go by a few different names—Security Champions, Security Guardians, etc.—for simplicity we'll call them "Security Advocates". Folks in this group—either "officially" recognized or not, are the people that other teams lean on for security help.

Most organizations have folks filling these types of roles for a variety of specializations. Whether it's usability, performance, accessibility, a specific framework, data analysis, etc., there's always that "go-to" for a certain topic.

Even when you don't have a specific program to nurture and expand this community, this type of dynamic still manages to surface. Making it an actual recognized effort has a lot of benefit. The foremost being you can track your efforts and invest (time, money, etc.) where it's having the biggest impact.

Once you've identified these folks, you can start to shift the dynamic between your team and the business teams.

Even if you don't identify these advocates, you should try to shift the dynamic between the security team and the business teams.

Your goal as a security team should be to try and teach the business teams about security as often as possible. With few exceptions, you should try to evolve your current workflows to try and move as much of that work to the business teams as possible.

Now, I know what you're thinking. Why would other teams take on our work? Why do would we want to cede these responsibilities to those teams, what are we supposed to do?

For your work, don't worry. There is and will always be more than enough security work to go around. 🤦

For the business teams, the advantage is easy to understand. They are best positioned to understand the full context of the risk decision (what are the risks of this new feature/solution/product?) and understanding how security can help them meet their business goals, helps them to make better decisions. That improvement helps reduce the time it takes to get things out the door and meet their goals more quickly.

Remember, this is not a complete move of security decisions to the business team. The goal of this effort is to move the decisions that are best made by an informed and educated business team to that team. The security team should be contributing to organization-wide challenges and cross-team risks.

As these efforts mature, your team will do less teaching and more sharing with teh security advocates. They in turn will take on more of the teaching role.

This can happen organically. But in each case where I've seen this type of effort succeed, it's been through a well understood and funded program.

That can mean any number of things, but it's common to have some sort of incentive structure for the advocates. Whether that's perks or specific compensation rewards or a faster path to advancement. Find what works for your organization's culture and make sure that this type of program is set up so that everyone involved sees the benefit.

You may see this and think it'll never work for your organization. Business teams don't care enough about security to give it this type of prioritization. The cooperation you see today is only because teams have to deal with security (whether by regulation or policy).

When I've discussed that idea with executives around the world, I see a common problem. Most people think of security as work to stop bad things from happening. While that's part of it, that's only a fraction of the work under the security umbrella.

The goal of security is simple. It's to make sure that what you build works as intended...and only as intended.

That's a positive goal. Stopping bad things is a negative goal and it's impossible to actually track that. The positive goal is easier to get people to rally around.

When you understand that security is trying to make sure that the work a team is doing works and only does what it's supposed to, now everyone understands they are working towards the same goal!

Security and the business have the same goals.

They all want:

  • Low-risk changes to production
  • Resilient systems
  • Visibility into their data and the processes they use

To meet those goals, you need to provide the why.

Why does this request matter? Why is this risk an issue?

If you help people understand the why, they can make better decisions moving forward. We want people to think through each situation that comes up. Technology is too complicated to map out each potential challenger beforehand.

If people understand the context of a requirement, they can make better decisions. As the expert, it's up to you to provide that understanding.

Remember, that you are the security expert. No one shared your context. You have a broad understanding of the thread landscape, the controls within your organization, and the overall risks the business is trying to balance.

The business teams are just trying to get their work done! They have goals they are working towards and are trying to navigate the various systems and processes to the best of their abilities. They are experts in something else entirely and should not be expected to be or become security experts.

Your goal is to make security frictionless. Or maybe a better call out is your goal is to use fiction judicious, helping other people make better decisions.

How can you start? Here are a few ideas for some simple techniques to get the ball rolling:

  • Open office hours
  • Review design docs and ask questions
  • Record quick video explainers for security questions
  • Join team channels and learn!

Let's a take look a how the business team and the security team approach the same issue.

There was a vulnerability in the popular django python framework in 2022. This framework is used to help build web apps and APIs. The vulnerability was an SQL injection—sending bad database requests to generate unexpected results—that could expose data that shouldn't be available.

This was an important issue to fix, but not an emergency. Think weeks, not days.

If we put on our security hat, we see that...

Risk
Exfiltration of all data in connected database

Ease of exploit
Simple. Crafted string input will start attack

Recommendation
Patch all instances of django with available patch to address issues

Likelihood of exploit
???

Recommended timeline
As soon as possible

With our builder/business had on...

Risk
Attackers get all of the data in the django database

Functions impacted
Trunc() & Extract()

Issue
Trunc(kind) & Extract(lookup_name) fail to properly sanitize input

Impact to our app
One use of Trunc() in codebase currently

Recommended timelines
Low priority. Combine with future djano updates

If we line up these perspectives—by working together as we've discussed—here's where we end up:

Impact to our app
Trunc() used once...as of our last code scan

Risk
Access to the entire database

Risk of the fix
Untested changes to access APIs

East of exploit
Simple. One bad input

Recommended timelines
Mitigate now with process changes. Patch within four weeks

Keys

Remember, most security teams are feeling the crunch. They are overloaded and under budget pressures.

A lot of that has to do with the fact that a small number of security professionals are accountable for the security of a large number of business teams!

Often security is blocking other work and tries to work harder to solve the problem.

Focus on building out mechanisms that help reduce the manual effort required to do any security work.

However, focusing first on clear communications can help free up resources because you're helping everyone in the organization to better understand security and specific issues without fielding individual questions.

Streamline the work your team does receive by aiming to reduce issues upstream. By education business teams so that they can make stronger security decisions, you'll reduce what falls to your team to handle.

Communicate

  • Keep it simple
  • Focus on the audience
  • Create shared context
  • Be empathetic

Educate

  • Provide the why
  • Security is one priority
  • You have the same goals
  • Be empathetic

Thank you!

]]>
https://markn.ca/2023/some-small-steps-towards-better-security-communication-and-education/ 688a59e4b62da30001ff52f4 Thu, 20 Apr 2023 10:00:00 -0400
<![CDATA[ The Failure of the Most Desirable Security Control Ever ]]> Want to share with others? Formatting issues in your reader? This post is available online, The Failure of the Most Desirable Security Control Ever

Today Twitter removed the legacy verified checkmark from the platform. Maybe. But also, maybe not?

Who really knows at this point, the specifics and the timeline will be whatever they will be given the current state of the platform. What is crystal clear is that the blue checkmark has now shed the last hints of its original use as a security control.

Are You, You?

The original verified checkmark was either the result of a lawsuit or coincidentally an intention feature launched at the same time. The goal was simple; provide a visual indicator that an account was in fact the person or organization it presented as.

At the time—and somehow once again—there was a flood of accounts pretending to be other people on the network.

This process went through a few iterations and had it’s share of challenges. Throughout it’s history, one thing remained constant, the process was a manual verification of the account.

Just Notable Enough

When I applied—yes, I was a legacy—I submitted a copy of my identification and a list of public references in various media publications.

I was denied the first time I applied. Not notable enough.

What did that mean? There was no clear answer. This was a problem throughout the program’s lifecycle. What was this mysterious “notable” bar?

A few weeks later, I re-applied with an expanded list of public references and was verified. At this point in my career I was regularly appearing on CBC television and radio as technology expert and being interviewed about cybersecurity issues by various media outlets around the world.

This work aligned directly with the goal—at that point—of the program. If someone saw me on TV or quoted in an article, they could have a reasonable assurance that tweets from @marknca were from me.

The Rules

Part of the reason that assurance held up was the rules set out for the accounts with the blue checkmark.

Your profile picture had to be a clear picture of you. While your handle could be anything, your display name needed to be your actual name. You also had to link your phone number to your account—though it was not visible publicly.

You could change your profile picture, but it was supposed to always be a clear picture of you. Any changes to your display name could result in a loss of verification or a re-verification process…though this seemed to be rarely followed up on.

The rules were slightly different for organizations and brands. It wasn’t a perfect setup, but it did a reasonable job of reaching the security goal; helping users spot imposter accounts.

An Unscalable Process

The verification process has been rightly criticized throughout it’s 14 year lifecycle. The biggest complain was the “notable” criteria. It’s always been somewhat hand wavy.

Because an account had to reach some arbitrary level of notoriety, the verification process wasn’t accessible to every user. Scenarios where verification could prevent real harm weren’t addressed and users had to find help—if they could—through other abuse reporting mechanisms on the platform.

At the time and in retrospect, the program would always have this issues because of the manual aspects of verification.

When Twitter launched the program, the platform had somewhere around 35 million active users. Even then, the process wouldn’t scale. Let alone as the platform reached the 450 million users in 2023.

If we do some napkin math, let’s say a full time employee can ‘verify’ 100 accounts per week (about 15 minutes an account). That one employee, only working on verification, will process about 3,800 accounts in a year.

That was 0.0001% of the platform in 2009. And 0.000008% of the platform today.

It was never going to cover everyone.

Social Status

That failure to scale turned this critical security control into a status symbol. The blue checkmark shifted from being a way to ensure that this account was valid to a social status indicator.

“This account is important.” was the takeaway as verified accounts became a smaller and smaller percentage of the platform.

This was made even more pronounced when the program was closed to new applicants a number of times over the years. In the end, only about 420,000 accounts were verified through this process in over a decade. That’s around 0.0009% of the user base.

That tiny blue checkmark shows up on the user profile page and next to their display name on every single one of their tweets. When a public indicator is only available to a tiny fraction of users, it’s not surprising that it become a desirable badge for everyone on the platform.

Security Failure

Now the blue checkmark is part of the paid, Twitter Blue, subscription. The challenge here is one of mismatched perception. There are plenty of stories showing the impact of shifting the visual indicator away from a identify verification to payment verification.

What’s interesting is looking at this from a security point of view.

I can’t think of any other case where a security control has shifted it’s utility so completely.

The underlying expectation by users—at least in the first few months of the new Twitter Blue era—was that the blue checkmark meant an account wasn’t an impostor.

The reality was that the blue checkmark meant the account had paid a subscription fee…or it might not be an impostor.

This is the worst type of security situation. Users are left in the dark as to what an indicator actually means.

If you followed the news about Twitter and took the time to view the profile of the user in question, you could see that the blue checkmark was from the—now—legacy verification program.

If you didn’t take those steps and were simply operating under the same assumption you had been for the past 14 years, you could easily draw the wrong conclusions about the account. Believing that it was legitimate when it was in fact not.

Clarity Is Key

Security is rarely simple. It would be wonderful if decisions sorted neatly into “secure” and “not secure”, but the reality is that almost any decision can be the best security decision if it’s made with a solid understanding of the trade offs being made.

Security decisions are all about context.

The fundamental challenge with the blue checkmark on Twitter for the past few months—and most likely, for years to come—is that it is trying to balance two completely different context.

The first, a strong assurance that this is who you think it is.

The second, that someone is paying a monthly fee to display a little digital icon next to their name.

That a security control became so desirable is an interesting case study. The challenge is that as it shifted to become a status symbol, it’s become the worst type of control. One that no longer provides any tangible security benefits, but it still widely believed to do so.

]]>
https://markn.ca/2023/the-failure-of-the-most-desirable-security-control-ever/ 67f6bbeaaf961b00014432d3 Sat, 01 Apr 2023 10:00:00 -0400
<![CDATA[ ChatGPT Delivers Ideas and Answers on Demand, If You Know How To Ask ]]> Want to share with others? Formatting issues in your reader? This post is available online, ChatGPT Delivers Ideas and Answers on Demand, If You Know How To Ask

Robyn Bresnahan and I chatted about this on CBC Ottawa Morning on 13-Dec-2022.

Machine learning (ML) and artificial intelligence (A.I.) have moved from sci-fi to buzzword to everyday tool. The latest models are making main stream headlines.

Creations from custom art generators like Dall-E 2, Midjourney, and Stable Diffusion have been trending on social media globally by capturing everyone’s imagination. Targeted solutions like custom AI profile avatars and marketing copy generators are finding audiences by creating unique solutions to very specific creative challenges.

Each of these solutions is a type of generative machine learning model. The latest to catch everyone’s attention? ChatGPT.

Machine Learning Models

At the heart of machine learning are models. A model is basically a computer program. But instead of the program delivering very direct results (e.g., click this button to load this webpage), these programs try to predict or infer answers to questions in a specific problem space.

A model is trained on a large amount of data. That training process allows the model (or program) to make connections and identify patterns between various data points. Those patterns are key to the success of the model.

Given new, similar data, the model uses those patterns to predict or infer a result.

Let’s say you train the model on pictures of all sorts of different pets. Dogs, cats, birds, fish, etc. This training is clearly labeled. So, the program looks at the first photo and it is told, “This is a picture of a dog.” Repeat that several hundred thousand or even millions of times.

That builds the pattern of “A dog usually has four legs, fur, a tail, and a long nose.” Another pattern of, “A fish is always in water, has fins, no arms or legs, gills, and a larger tail.”. And so on.

Now, when the program is run, the user gives the model a new picture it’s never seen before. Essentially asking, “What pets are in this photo?”

The model then uses the patterns it knows about to infer what’s in the picture, returning the result of “This is probably a cat and this is probably a dog.” The answer is probably because the model is using inference to basically guess what’s in the picture. It doesn’t actually know what’s in the picture, but based on other picture’s it’s been trained on, these are the most likely answers.

Generative Models

The latest wave of machine learning models work in reverse. Instead of giving them a picture and asking what’s in it, you provide a prompt and the model infers what that might look like or sound like.

Here, I used the prompt, “An odd couple pairing of a cat and a dog. Hayao Miyazaki style, digital painting”

Dall-E prompt, &ldquo;An odd couple pairing of a cat and a dog. Hayao Miyazaki style, digital painting&rdquo;

Based on what the model—in this case, Dall-E 2—knows about cats, dogs, and Hayao Miyazaki’s art style, this is what it came up with.

ChatGPT is a wrapper around the GPT-3 generative large language model. It does the same thing as Dall-E, but with text. You provide a prompt and it will deliver a writing sample to match. When I asked ChatGPT to describe itself, this is what it produced…

ChatGPT is a language model that’s been trained to chat with you. It’s based on GPT-3, which is a really advanced model. ChatGPT can generate responses that sound like they’re coming from a real person, so it’s great for things like chatbots or text-based dialogue systems. It’s not a specific product or tool, but more like a type of model that you can use for different applications.

The results can be quite impressive when they are accurate. Remember the model is designed to produce passable prose, not perfectly accurate text content.

ChatGPT takes things a step further and provides a discussion-like interface to it’s model. Using that interface, I explored the key concepts behind this technology. You can read the results of that below in, “A Quick Chat With ChatGPT

What Problems Does ChatGPT Solve Well?

ChatGPT isn’t the end-all, be-all of generative AI. It isn’t going to replace human creative or human effort. It can help accelerate your work though. Allie K. Miller puts together a great list of areas where ChatGPT excels in this Twitter thread 🧵👇

ChatGPT is changing the game, and I want to share real things you can do with this AI system today.

Please save this thread and start testing this technology NOW so you’re ahead of the curve.— Allie K. Miller (@alliekmiller) December 13, 2022

I agree with most of her key areas, specifically:

  • Summarizing
  • Planning
  • Idea generation

ChatGPT is a wonderful way to get past staring at a blank page! You can check it out at https://chat.openai.com/chat.

A Quick Chat With ChatGPT

Mark: What is machine learning?

ChatGPT: Machine learning is a type of artificial intelligence that allows software applications to become more accurate at predicting outcomes without being explicitly programmed. It is based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention.

Machine learning algorithms use statistical techniques to find patterns in data and use them to make predictions or take actions. This can be used in a wide range of applications, such as image and speech recognition, natural language processing, and even in self-driving cars.

Mark: How do I make my own model?

ChatGPT: To make your own machine learning model, you will need to gather a large amount of data that is relevant to the problem you are trying to solve. This data will be used to train the model, which is the process of feeding the data into the algorithm and adjusting the parameters of the model to improve its accuracy. Once the model is trained, you can then use it to make predictions or take actions based on new data.

There are many different algorithms and techniques that can be used for training a machine learning model, and the choice of which to use will depend on the specific problem you are trying to solve. Some common algorithms include decision trees, support vector machines, and neural networks.

To create a machine learning model, you will need to have some knowledge of programming and statistics, as well as a basic understanding of the problem you are trying to solve. There are many tutorials and online courses available that can help you learn the basics of machine learning and get started with creating your own model.

Mark: What is the difference between a discriminative and a generative model?

ChatGPT: A discriminative model is a type of machine learning algorithm that is used to predict the value of a target variable (such as whether an email is spam or not) based on a set of input features (such as the sender, subject, and content of the email). It does this by directly modeling the relationship between the input features and the target variable, and using this model to make predictions on new data.

A generative model, on the other hand, is a type of algorithm that is used to learn the underlying distribution of the data, and can then generate new samples that are similar to the data it was trained on. This allows the model to capture the underlying patterns and structure of the data, and can be used to make predictions or take actions based on this learned information.

One key difference between discriminative and generative models is that a discriminative model focuses on predicting the target variable based on the input features, while a generative model is more concerned with modeling the underlying distribution of the data. This means that a generative model is often more flexible and can be used to solve a wider range of problems, but may require more data and computational resources to train.

Mark: What are the biggest technical challenges with generative models?

ChatGPT: There are several technical challenges associated with generative models, some of which include:

  1. Data availability and quality: Generative models require a large amount of high-quality data to learn the underlying distribution of the data and generate new samples that are similar to the training data. If the data is not sufficient or is of poor quality, the model may not be able to accurately capture the patterns and structure of the data, which can reduce its performance.
  2. Computational complexity: Generative models can be computationally intensive to train, especially for large datasets or complex data distributions. This can make them difficult to run on standard hardware, and may require specialized hardware or distributed computing systems to handle the large amounts of data and computational workload.
  3. Mode collapse: One of the main challenges with generative models is the phenomenon of mode collapse, where the model only learns to generate a subset of the data, rather than the entire distribution. This can result in poor performance and a lack of diversity in the generated samples.
  4. Evaluation and comparison: Generative models can be difficult to evaluate and compare, as they are often evaluated on their ability to generate realistic samples, rather than on a more traditional metric such as accuracy or error rate. This can make it challenging to determine which model is the best for a particular task or dataset.

Mark: How can i address bias in my models?

ChatGPT: Bias in machine learning models can arise from several sources, including the data used to train the model, the algorithm used to build the model, and the way in which the model is used in practice. To address bias in your models, there are several steps you can take, including:

  1. Collect and use a diverse and representative dataset: Ensuring that the data used to train your model is diverse and representative of the real-world population can help to reduce bias in the model. This means using a dataset that includes examples from a wide range of individuals, with varying characteristics such as age, gender, race, and socio-economic status.
  2. Use fairness metrics and algorithms: There are a number of fairness metrics and algorithms that can be used to measure and address bias in machine learning models. These can help to identify potential sources of bias in your model and provide suggestions for how to mitigate them.
  3. Regularly evaluate and test your model: It is important to regularly evaluate and test your model to ensure that it is performing well and not introducing any bias. This can be done by conducting tests on the model and comparing its performance on different subgroups within the population.
  4. Be transparent and accountable: Being transparent about the data and algorithms used to build your model, as well as the assumptions and limitations of the model, can help to promote accountability and trust in the model. This can include sharing information about the model’s performance and any measures taken to address bias.

Mark: What is the difference between training and inference?

ChatGPT: Training and inference are two distinct phases in the development and use of a machine learning model. Training is the process of building a machine learning model by feeding it a large amount of data and adjusting the model’s parameters to improve its performance.

This is typically done using a labeled dataset, where the input data and the corresponding target values are known. The goal of training is to find the model parameters that best fit the data and enable the model to make accurate predictions on new, unseen data.

Inference, on the other hand, is the process of using a trained model to make predictions or take actions on new data. This involves providing the model with input data and using the model to generate predictions or take actions based on that data. Inference can be performed using either the same data as was used for training, or new, unseen data.

The main difference between training and inference is that training involves building and adjusting the model, while inference involves using the trained model to make predictions or take actions on new data. Training is typically done offline, while inference is typically done in real-time.

Mark: What are some examples of problems that machine learning is ideally suited to solve?

ChatGPT: Machine learning is well-suited to a wide range of problems, including:

  1. Image and speech recognition: Machine learning algorithms can be trained to recognize objects, people, and spoken words in images and audio recordings. This can be used in applications such as face recognition for security systems, or speech-to-text for voice-controlled assistants.
  2. Natural language processing: Machine learning algorithms can be used to process and understand human language, which can be applied to tasks such as language translation, sentiment analysis, and automatic summarization of text.
  3. Fraud detection: Machine learning can be used to detect patterns and anomalies in large datasets, which can be useful for identifying fraudulent transactions in financial systems, or for detecting spam emails.
  4. Predictive maintenance: Machine learning can be used to predict when equipment or machinery is likely to fail, which can help to prevent disruptions and costly downtime.
  5. Recommendation systems: Machine learning can be used to personalize recommendations for products, music, or movies based on a user’s past behavior and preferences.

These are just a few examples of the many problems that machine learning can be used to solve. Machine learning algorithms are highly flexible and can be applied to a wide range of problems in many different fields.

]]>
https://markn.ca/2022/chatgpt-delivers-ideas-and-answers-on-demand-if-you-know-how-to-ask/ 67f6bbeaaf961b000144313d Wed, 14 Dec 2022 09:00:00 -0500
<![CDATA[ AWS re:Invent 2022 Attendee Guide: Security ]]> Want to share with others? Formatting issues in your reader? This post is available online, AWS re:Invent 2022 Attendee Guide: Security

At re:Invent or attending remotely? Check out my “Ultimate Guide to AWS re:Invent 2022” post for some tips and tricks to get the most out of the show.

For the past few years, I’ve had the opportunity to write the “official” guide for attendees of AWS re:Invent that are interested in security. For AWS re:Inforce—the security-focused conference—I get to be a bit more specific.

Each time I create one of the guides for re:Invent my goal is the same; help everyone understand the foundations of cloud security. Regardless of where you are on your cloud journey, there is a ton of value in strong fundamentals.

…and the fundamental truth of cloud security is that it isn’t an isolated discipline. You need to understand how builders are solving problems in the cloud, what AWS has done to deploy strong services, and what options there are available for you to help with your security practice.

Here is the security topic guide for AWS re:Invent 2022 with links to all of the recommended sessions. You can also watch the sessions back-to-back using this handy YouTube playlist.

Introduction

Security is often misunderstood.

That’s understandable given how it’s usually presented. Let’s fix that.

Simply put, security is one of the main areas of focus when building in the AWS Cloud. It works with the other pillars—Operational Excellence, Performance Efficiency, Cost Optimization, Reliability, and Sustainability—to help you deliver robust, resilient solutions.

I’ve built this guide with that approach in mind. These sessions will help security professionals take a cloud-native approach. It will also help builders of all experience levels understand how security fits into the bigger picture.

There’s a ton of great content this year and these sessions are a great starting point for your security journey and a good reminder of the foundations for those of us further down the path.

ARC210, The well-architected way

Quality service delivery is fundamental to a strong security posture. The principles in the AWS Well-Architected Framework will help your teams build better in the cloud.

CMP210, Modern applications: An infrastructure perspective

EC2 is usually a major part of your compute infrastructure. This session focuses on how to EC2 works at a fleet level. Understanding this is critical to expanding your security efforts beyond the instance itself.

CON323, What’s new with Amazon ECS

As happens sometimes, this session was renamed and adjusted to focus on new features in Amazon ECS. The original session name was, “The AWS container services journey: A detailed look”

Containers are ubiquitous. So much so that there are a lot of AWS services that can run them. This session explains the use cases for these services and how your teams can use them to their advantage.

COP301, Observability the open-source way

Observability has massive benefits for all builders, security teams doubly so. Learn about metrics, traces, log data, and OpenTelemetry and how it can help improve visibility into what’s happening in your builds.

COP302, Developing an observability strategy

You have access to mountains of data about how your builds are behaving. This session will help you understand what strategies work to manage that data and how to get the most out of it.

This session hasn’t been published yet

COP304, Cloud compliance, assurance, and auditing

If there is a “trick” to compliance, it’s building evidence collection into everything you do. The good news? A lot of the work you’re doing around observability helps with that. This session will show you how.

COP316, How to monitor applications across multiple accounts

The more accounts your teams use, the more you realize you need a strategy for visibility across accounts. Focusing on application monitoring, the lessons from this session are directly applicable to security.

DOP301, The Amazon Builders’ Library: 25 years of operational excellence at Amazon

The Amazon Builders’ Library is a gold mine of hard fought knowledge about building in the cloud. This session takes a deep dive into how Amazon runs technical operations and what they’ve learned.

This session hasn’t been published yet

ENT218, The architect elevator: Connecting IT and the boardroom

You can’t communicate the same information to a development team and your executives. The contexts are completely different. This session maps out how to tackle those differences effectively.

ENT220, Shipping securely: How strong security can be your strategic advantage

This session explains the business advantages to a strong security approach. Take notes, lots of notes, and use this within your organization. Strong security helps everyone reach their goals faster.

This session hasn’t been published yet

NET207, A deep dive on the current security threat landscape with AWS

This session was originally titled, “2022 AWS Threat Landscape Report”

AWS Security has a unique perspective on the threat landscape. Learn about what they are seeing and how it impacts your organization…or more importantly, doesn’t impact your organization because of their hard work.

SEC201, Proactive security: Considerations and approaches

AWS’s approach to security is one worth replicating. The way they’ve distributed responsibility throughout teams that are building in the cloud is highly effective. Learn how you can do the same in this talk.

SEC203, Revitalize your security with the AWS Security Reference Architecture

The AWS Security Reference Architecture is a good starting point for any build. This is a great technical foundation session, as it takes a closer look at the why and how of that design.

SEC212, AWS data protection: Using locks, keys, signatures, and certificates

Encryption is a critical security control. Looking at its application for data at rest and in transit, this session lays the groundwork for a robust data strategy that will underpin your entire security strategy.

]]>
https://markn.ca/2022/aws-re-invent-2022-attendee-guide-security/ 67f6bbeaaf961b0001443266 Fri, 02 Dec 2022 09:00:00 -0500
<![CDATA[ Werner Vogels Keynote Play-by-play ]]> Want to share with others? Formatting issues in your reader? This post is available online, Werner Vogels Keynote Play-by-play

At re:Invent or attending remotely? Check out my “Ultimate Guide to AWS re:Invent 2022” post for some tips and tricks to get the most out of the show.

Thursday at AWS re:Invent 2022 brought yet another amazing keynote from Dr. Werner Vogels. As is his custom, Werner challenges builders to think more broadly about their approach, to push beyond existing perceived constraints and to build better.

My reaction to the keynote in this Twitter thread 👇.

Twitter Thread 🧵

Tweet 1/135 👇 Next tweet

what will the theme of @werner’s #reinvent keynote be this year? who’s the musical act for @AWSEvents re:Play tonight? what will be your favourite t-shirt of his? let’s find out now… /🧵

Tweet 2/135 👇 Next tweet 👆 Start

dark & stormy, Matrix-style intro video... #reinvent

Tweet 3/135 👇 Next tweet 👆 Start

“The world is asynchronous”, @Werner #reinvent

Tweet 4/135 👇 Next tweet 👆 Start

“Would you like to see a more world ordered? Synchronous?” @werner, “Nope” 🤣🤣🤣 #reinvent

Tweet 5/135 👇 Next tweet 👆 Start

the theme of this video is synchronous processing old school serial work #reinvent


Tweet 6/135 👇 Next tweet 👆 Start

“This place is crazy”, @werner “No. This place is sycnrhonous" “No, this place sucks”, @werner #reinvent

Tweet 7/135 👇 Next tweet 👆 Start

love that intro video! #reinvent

Tweet 8/135 👇 Next tweet 👆 Start

@werner up now, rocking the Matrix look to connect w/the video…then to just the straight up @awscloud Lambda t-shirt #reinvent

Tweet 9/135 👇 Next tweet 👆 Start

continuing to hit on the synchronous/asynchronous differences * I am not going to keep typing out the full word 🤣 #reinvent

Tweet 10/135 👇 Next tweet 👆 Start

original @awscloud S3 design principles included “asychrony” #reinvent

Tweet 11/135 👇 Next tweet 👆 Start

big differences between these four… - classic synchrony - parallel synchrony - asynchrony - asynchrony + parallel #reinvent



Tweet 12/135 👇 Next tweet 👆 Start

original @awscloud S3 design principles called out “controlled concurrency” and “controlled parallelism” as well! #reinvent

Tweet 13/135 👇 Next tweet 👆 Start

cool real world examples: bird flock/swaming - looks like central control, isn’t - simple rules for each bird creates this effect #reinvent

Tweet 14/135 👇 Next tweet 👆 Start

some of this is covered in “Swarm Intelligence” by Eberhart, Shi, and Kennedy, https://t.co/XpIzYQDcVt #reinvent

Tweet 15/135 👇 Next tweet 👆 Start

👆 that reference is from me, not Werner 😉 #reinvent

Tweet 16/135 👇 Next tweet 👆 Start

“The world is asynchronous”, @werner #reinvent

Tweet 17/135 👇 Next tweet 👆 Start

Synchronous is… - a simplification - a conviencance - an illusion #reinvent


Tweet 18/135 👇 Next tweet 👆 Start

“Systems are asynchronous”, @Werner #reinvent

Tweet 19/135 👇 Next tweet 👆 Start

@werner currently walking through some early examples of systems that were built around async principles #reinvent

Tweet 20/135 👇 Next tweet 👆 Start

“Synchrony leads to tightly coupled systems” …and we all know (or should know) how @werner feels about that type of system design! #reinvent

Tweet 21/135 👇 Next tweet 👆 Start

“Asynchrony leads to loosely coupled systems”, @werner #reinvent

Tweet 22/135 👇 Next tweet 👆 Start

benefits of async / loose coupling: - fewer dependencies - failure isolation - evolvable architecture #reinvent

Tweet 23/135 👇 Next tweet 👆 Start

@awscloud S3 at launch was 8 micro services, it’s grown to 235+ now the loosely coupled design allowed for this type of evolution over time #reinvent

Tweet 24/135 👇 Next tweet 👆 Start

again, this was on the 2006 original design principles for @awscloud S3 #reinvent

Tweet 25/135 👇 Next tweet 👆 Start

at @amazon, they went through the same evolution that lots of customers are going through now moving away from a monolith to an eventual loosely coupled architecture that can continue to evolve #reinvent

Tweet 26/135 👇 Next tweet 👆 Start

@Amazon Distribute Computing Manifesto is up at https://www.allthingsdistributed.com/2022/11/amazon-1998-distributed-computing-manifesto.html it’s a fantastic read #reinvent

Tweet 27/135 👇 Next tweet 👆 Start

ooohhh, I ❤️ when @werner talks patterns! I always learn a ton these all help solve your challenges with a loosely coupled approach #reinvent

Tweet 28/135 👇 Next tweet 👆 Start

two key @awscloud services to help here #reinvent

Tweet 29/135 👇 Next tweet 👆 Start

always excellent advice: “Listen, learn, improve”, @werner #reinvent

Tweet 30/135 👇 Next tweet 👆 Start

more on @awscloud Step Functions at https://aws.amazon.com/step-functions/ #reinvent

Tweet 31/135 👇 Next tweet 👆 Start

more on @awscloud EventBridge at https://aws.amazon.com/eventbridge/ #reinvent

Tweet 32/135 👇 Next tweet 👆 Start

NEW: AWS Step Functions Distributed Map - orchestrate large-scale parallel workloads in #serverless applications - available today #reinvent

Tweet 33/135 👇 Next tweet 👆 Start

“Event-driven architectures lead to loosely coupled systems”, @werner #reinvent

Tweet 34/135 👇 Next tweet 👆 Start

more details on some event-driven patterns... (btw, all supported by @awscloud EventBridge) #reinvent

Tweet 35/135 👇 Next tweet 👆 Start

an example used often by @martinfowler, https://martinfowler.com/ #reinvent

Tweet 36/135 👇 Next tweet 👆 Start

another event-driven architecture example from @werner. more details at https://aws.amazon.com/blogs/apn/integrating-readme-with-amazon-api-gateway-to-keep-your-developer-hub-up-to-date/ #reinvent

Tweet 37/135 👇 Next tweet 👆 Start

👆 that’s the blog @werner mentioned #reinvent

Tweet 38/135 👇 Next tweet 👆 Start

❤️ the “oh, want to add to this? ok” evolution examples #reinvent

Tweet 39/135 👇 Next tweet 👆 Start

“All complex systems that work evolved from simple systems that worked”, Gall’s law quoted by @werner #reinvent

Tweet 40/135 👇 Next tweet 👆 Start

“work” is the key part of that law. make it simple. make it work. evolve from there #reinvent

Tweet 41/135 👇 Next tweet 👆 Start

damn #reinvent

Tweet 42/135 👇 Next tweet 👆 Start

fun projects are a great way to learn more details on #serverless-presso at https://serverlessland.com/reinvent2021/serverlesspresso the workshop: https://workshop.serverlesscoffee.com/ #reinvent

Tweet 43/135 👇 Next tweet 👆 Start

building to something... #reinvent

Tweet 44/135 👇 Next tweet 👆 Start

NEW: @awscloud Application Composer - visually design and build #serverless applications quickly - in preview today #reinvent

Tweet 45/135 👇 Next tweet 👆 Start

Tweet 46/135 👇 Next tweet 👆 Start

@werner stressing just how much easier @awscloud Application Composer for anyone to start building #serverless apps #reinvent

Tweet 47/135 👇 Next tweet 👆 Start

would have loved to be a fly on the wall in the marketing meeting where @awscloud EventBridge got linked to the concept of being a spider in the web 🤣 💯 true though! #reinvent

Tweet 48/135 👇 Next tweet 👆 Start

@werner talking now about the power of composing solutions using smaller pieces. shouting the UNIX philosophy around modular software | #reinvent


Tweet 49/135 👇 Next tweet 👆 Start

stdin / stdout / stderr has held up for 40+ years #reinvent

Tweet 50/135 👇 Next tweet 👆 Start

great question #reinvent

Tweet 51/135 👇 Next tweet 👆 Start

NEW: Amazon EventBridge Pipes - connected event producers and consumers in seconds - available today! “Easily stitch services together”, @werner #reinvent

Tweet 52/135 👇 Next tweet 👆 Start

I am so f—king excited for this 👆 service, I can’t even begin to explain it #reinvent

Tweet 53/135 👇 Next tweet 👆 Start

this starts... #reinvent

Tweet 54/135 👇 Next tweet 👆 Start

@werner trying to explain a ticketing app example…get’s distracted by football ⚽ #reinvent

Tweet 55/135 👇 Next tweet 👆 Start

first customer speaker up now. it’s Angela Timofte from @Trustpilot #reinvent

Tweet 56/135 👇 Next tweet 👆 Start

Tweet 57/135 👇 Next tweet 👆 Start

back on stage, Angela explains how trust is at core of what @Trustpilot is building #reinvent


Tweet 58/135 👇 Next tweet 👆 Start

must not get distracted by @awscloud EventBridge Pipes…there is more goodness to follow in this @werner keynote #reinvent

Tweet 59/135 👇 Next tweet 👆 Start

Angela walking through the @Trustpilot journey. started w/a monolith…until that was breaking things #reinvent

Tweet 60/135 👇 Next tweet 👆 Start

Christmas party outage. among the top five worst times for outages 😉 #reinvent

Tweet 61/135 👇 Next tweet 👆 Start

over time Angela & the @Trustpilot team moved to an event-driven architecture tons of benefits, has enabled the business to scale. hopefully reduced those Christmas party outages too #reinvent

Tweet 62/135 👇 Next tweet 👆 Start

side note: I like the design of these slides. nice and bold. the cards are clear for the event-driven architecture #reinvent

Tweet 63/135 👇 Next tweet 👆 Start

event-driven has made it way easier for Angela & @trustpilot team to deal w/spikes in traffic. things scale was easier and have lower ops burden #reinvent


Tweet 64/135 👇 Next tweet 👆 Start

see what I mean about the slide design? #reinvent

Tweet 65/135 👇 Next tweet 👆 Start

some key benefits to moving to an event-driven architecture: - scale, adapt, react - protect platform integrity - teams working in parallel #reinvent

Tweet 66/135 👇 Next tweet 👆 Start

nice customer segment from Angela @Trustpilot. hit the right level of technical depth. cool slides. practical example #reinvent

Tweet 67/135 👇 Next tweet 👆 Start

Angela’s Hero page: https://aws.amazon.com/developer/community/heroes/angela-timofte/ …and Twitter handle that I didn’t find in time: @AngelaTimofte #reinvent

Tweet 68/135 👇 Next tweet 👆 Start

profiles and some publications from the @awscloud Heroes at https://aws.amazon.com/developer/community/heroes/ #reinvent

Tweet 69/135 👇 Next tweet 👆 Start

“Event-driven architecture enable global scale”, @Werner #reinvent

Tweet 70/135 👇 Next tweet 👆 Start

Werner diving into @awscloud DynamoDB as an example #reinvent

Tweet 71/135 👇 Next tweet 👆 Start

speaking of @awscloud Heroes, @alexbdebrie is THE expert for DynamoDB. check out his canonical reference https://www.dynamodbbook.com/ this book has saved me and a ton of teams I know mountains of time, and headaches, and stress, and frustration #reinvent

Tweet 72/135 👇 Next tweet 👆 Start

back on stage, @werner is talking about the challenges of active-active and various failure scenarios more on DynamoDB streams at https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Streams.html #reinvent



Tweet 73/135 👇 Next tweet 👆 Start

Tweet 74/135 👇 Next tweet 👆 Start

event-driven architecture patterns: - change data capture - asynchronous coupling - self-healing replicators #reinvent

Tweet 75/135 👇 Next tweet 👆 Start

Tweet 76/135 👇 Next tweet 👆 Start

specific paper called out, “Using dependency isolation to contain concurrency overload”, by @dyanacek https://aws.amazon.com/builders-library/dependency-isolation/ #reinvent

Tweet 77/135 👇 Next tweet 👆 Start

specific paper called out, “My CI/CD pipeline is my release captain”, by @clare_liguori https://aws.amazon.com/builders-library/cicd-pipeline/ #reinvent

Tweet 78/135 👇 Next tweet 👆 Start

NEW: Amazon CodeCatalyst - unified software development service that makes it faster to build and deliver on @awscloud - in preview today #reinvent


Tweet 79/135 👇 Next tweet 👆 Start

I’m intrigued. @awscloud CodeCatalyst looks like it’s automating a massive amount of the heavily lifting that builders are struggling with as always, will need to see the edges & opinions of the service… #reinvent

Tweet 80/135 👇 Next tweet 👆 Start

very promising. @awscloud extends to other existing tools…like @github #reinvent

Tweet 81/135 👇 Next tweet 👆 Start

back to the main theme, now talking about the speed that event-driven architectures unlock for builders #reinvent

Tweet 82/135 👇 Next tweet 👆 Start

…shows the architecture for @cinchuk… #reinvent

Tweet 83/135 👇 Next tweet 👆 Start

... #reinvent

Tweet 84/135 👇 Next tweet 👆 Start

Tweet 85/135 👇 Next tweet 👆 Start

@werner currently talking about using 3d tech to get properly fitting shoes. not sure who was first with this, but I know you’ve been able to get hockey skates customized this was for a few years 🇨🇦 #reinvent

Tweet 86/135 👇 Next tweet 👆 Start

👆 < he says ironically, as a non-hockey playing, barely skating Canadian > 🤣🤣🤣 #reinvent

Tweet 87/135 👇 Next tweet 👆 Start

the aim of this segment, seems to be to tie the use of AR/VR to help bridge the gap between current experiences in interaction and what would be way more effective #reinvent

Tweet 88/135 👇 Next tweet 👆 Start

@werner explaining the requirements to build a 3d asset from 2d images a/k/a photogrammetry #reinvent

Tweet 89/135 👇 Next tweet 👆 Start

related note: cool paper from @AmazonScience, “LipNeRF: What is the right feature space to lip-sync a NeRF” at https://www.amazon.science/publications/lipnerf-what-is-the-right-feature-space-to-lip-sync-a-nerf #reinvent

Tweet 90/135 👇 Next tweet 👆 Start

... #reinvent

Tweet 91/135 👇 Next tweet 👆 Start

good point from @werner about the 3d placement for some shopping apps. you don’t just need the model of the object, but you need to map the space too #reinvent

Tweet 92/135 👇 Next tweet 👆 Start

details on o3DE at https://www.o3de.org/ #reinvent

Tweet 93/135 👇 Next tweet 👆 Start

Tweet 94/135 👇 Next tweet 👆 Start

@werner talking about spatial intelligence, uses the “pack the boot for the vehicle” example. we’ve all felt that pain at the start of a roadtrip… #reinvent


Tweet 95/135 👇 Next tweet 👆 Start

talking now about the complexities of spatial intelligence. autonomous driving is the current use case #reinvent



Tweet 96/135 👇 Next tweet 👆 Start

“Visualize everything”, @werner << rightfully calls out that visualization isn’t for the systems, it’s for us, the ppl #reinvent

Tweet 97/135 👇 Next tweet 👆 Start

next customer speaker up. it’s Nathan Thomas from @EpicGames #reinvent


Tweet 98/135 👇 Next tweet 👆 Start

nice callback to the intro video with the Matrix Awakensexperience on the Unreal 5 engine watch more of that at https://www.youtube.com/watch?v=WU0gvPcc3jQ&feature=youtu.be #reinvent

Tweet 99/135 👇 Next tweet 👆 Start

@UnrealEngine metahuman creator is at https://www.unrealengine.com/en-US/metahuman #reinvent

Tweet 100/135 👇 Next tweet 👆 Start

all of that 👆 👆 is running on @awscloud #reinvent

Tweet 101/135 👇 Next tweet 👆 Start

more on @Twinmotion from @EpicGames at https://www.twinmotion.com/en-US …all running on @awscloud services #reinvent

Tweet 102/135 👇 Next tweet 👆 Start

Tweet 103/135 👇 Next tweet 👆 Start

it’s been a while since we’ve seen a customer example that leverages @awscloud EC2 so much don’t get me wrong, tons of customers are using EC2 constantly, it’s just not usually the “interesting” story that gets top billing like this #reinvent

Tweet 104/135 👇 Next tweet 👆 Start

btw, @EpicGames announced that RealityScan is available on iOS now #reinvent

Tweet 105/135 👇 Next tweet 👆 Start

lots of cool tooling from @epicgames & @UnrealEngine around building & integrating 3d works. tons to dive into and explore #reinvent



Tweet 106/135 👇 Next tweet 👆 Start

Tweet 107/135 👇 Next tweet 👆 Start

Tweet 108/135 👇 Next tweet 👆 Start

@werner calls out one of the critical patterns for @awscloud: Experiment, measure, learn #reinvent

Tweet 109/135 👇 Next tweet 👆 Start

it’s harder to experiment in some scenarios. in those cases, you need to simulate #reinvent

Tweet 110/135 👇 Next tweet 👆 Start

@werner going way back on this one... #reinvent


Tweet 111/135 👇 Next tweet 👆 Start

getting closer to now in the timeline… #reinvent

Tweet 112/135 👇 Next tweet 👆 Start

…and today simulation is run in a ton of different places #reinvent

Tweet 113/135 👇 Next tweet 👆 Start

reasons for simulation: - physical limitations - hazardous scenarios - manipulation of time #reinvent

Tweet 114/135 👇 Next tweet 👆 Start

👆 some reasons for simulation. these are the ones @Werner is focusing on today #reinvent

Tweet 115/135 👇 Next tweet 👆 Start

moving to spatial simulation now... #reinvent

Tweet 116/135 👇 Next tweet 👆 Start

more on @awscloud SimSpace Weaver at https://aws.amazon.com/simspaceweaver/ #reinvent

Tweet 117/135 👇 Next tweet 👆 Start

the episode of “Now Go Build” that @werner is referencing is up at https://www.youtube.com/watch?v=W_ningGJBGw&feature=youtu.be #reinvent

Tweet 118/135 👇 Next tweet 👆 Start

for the simulation example, it’s to answer the question, “What is we plant here?” the simulation allows for rapid experimentation, results are then used to optimize real-world efforts #reinvent


Tweet 119/135 👇 Next tweet 👆 Start

simulations also allow for solution prototyping. example here is if a fence is put in place to restrict animal movement to protect tree growth cool stuff! #reinvent


Tweet 120/135 👇 Next tweet 👆 Start

“Simulation plays a crucial role in innovation”, @werner #reinvent

Tweet 121/135 👇 Next tweet 👆 Start

Tweet 122/135 👇 Next tweet 👆 Start

... #reinvent

Tweet 123/135 👇 Next tweet 👆 Start

… #reinvent

Tweet 124/135 👇 Next tweet 👆 Start

@werner talking now about the limits of simulation 👆 #reinvent

Tweet 125/135 👇 Next tweet 👆 Start

a little thought experiment now…let’s look ahead 20 years #reinvent

Tweet 126/135 👇 Next tweet 👆 Start

if quantum computing pans out, that could increase the usefulness of simulation significantly #reinvent

Tweet 127/135 👇 Next tweet 👆 Start

current state has a long way to go. these orgs are working on problems in the space 👇 #reinvent

Tweet 128/135 👇 Next tweet 👆 Start

more on @awscloud Braket at https://aws.amazon.com/braket/ #reinvent

Tweet 129/135 👇 Next tweet 👆 Start

some quick math for the challenge of simulation in some spaces #reinvent

Tweet 130/135 👇 Next tweet 👆 Start

@werner politely declines to pronounce this on stage 🤣 #reinvent

Tweet 131/135 👇 Next tweet 👆 Start

quantum computing could enable simulation at scale. current computing can’t handle the sheer number 👆 of object required to be tracked & computed #reinvent

Tweet 132/135 👇 Next tweet 👆 Start

interview with Dr. John Preskill that @werner is talking about is up at https://www.youtube.com/watch?v=tcTF_ag_wWU&feature=youtu.be #reinvent

Tweet 133/135 👇 Next tweet 👆 Start

Martin Garrix is the headliner for @awscloud re:Play tonight! #reinvent

Tweet 134/135 👇 Next tweet 👆 Start

… #reinvent

Tweet 135/135 👇 Next tweet 👆 Start

@werner ends with a call to build bigger, better, bolder systems much faster! now go build. #reinvent /🧵

]]>
https://markn.ca/2022/werner-vogels-keynote-play-by-play/ 67f6bbeaaf961b0001443265 Thu, 01 Dec 2022 09:00:00 -0500
<![CDATA[ Accelerating innovation at AWS Security ]]> Want to share with others? Formatting issues in your reader? This post is available online, Accelerating innovation at AWS Security

At re:Invent or attending remotely? Check out my “Ultimate Guide to AWS re:Invent 2022” post for some tips and tricks to get the most out of the show.

The security leadership session at AWS re:Invent 2022 was called, “What we can learn from customers: Accelerating innovation at AWS Security”. CJ Moses, CISO of AWS, used this session to explain what AWS is doing to help everyone with security, to highlight some key releases in 2022, and what we can expect in 2023 when it comes to security.

CJ definitely put his own stamp on the leadership sessions. More in this Twitter thread 👇.

Twitter Thread 🧵

Tweet 1/57 👇 Next tweet

the @awscloud #security leadership session featuring @mosescj58 is starting now… What we can learn from customers: Accelerating innovation at AWS Security #reinvent

Tweet 2/57 👇 Next tweet 👆 Start

@mosescj58 up now, rocking some killer kicks 👟 #reinvent

Tweet 3/57 👇 Next tweet 👆 Start

@mosescj58 celebrating 15 years with @awscloud 🥳🥳🥳 congrats CJ! #reinvent

Tweet 4/57 👇 Next tweet 👆 Start

“Everyday I get to learn about the problems we can solve for customers, and how we can do that”, @mosescj58 #reinvent

Tweet 5/57 👇 Next tweet 👆 Start

@mosescj58 drawing the parallels between his sport—racing—and #security - both driven by data - safety is a key factor for success #reinvent

Tweet 6/57 👇 Next tweet 👆 Start

good Bezos quote, “Customers are always wonderfully, beautifully unsatisfied.” #reinvent

Tweet 7/57 👇 Next tweet 👆 Start

more than 90% of all the things @awscloud creates is directly from customers…the other 10% was built on behalf of those customers 😉 #reinvent

Tweet 8/57 👇 Next tweet 👆 Start

@mosescj58 sharing some of his previous roles in law enforcement and the parallels in his role with @AWSSecurityInfo today both looking for one tiny indicator amid a torrent of data #reinvent

Tweet 9/57 👇 Next tweet 👆 Start

@awscloud has the scale to enable security pre-AWS @mosescj58 was working with @jeffbarr back in 2007. those conversations kicked off a ton of security work …which brought CJ to AWS #reinvent

Tweet 10/57 👇 Next tweet 👆 Start

1st challenge: isolate workloads in a data center …wow, think about that vs. what we heard in Peter DeSantis’ keynote on Monday about @awscloud Lambda function isolation #reinvent

Tweet 11/57 👇 Next tweet 👆 Start

@mosescj58 reminiscing about the scrappy startup days of @AWSSecurityInfo bean bag chairs => hand me down cube from AOL (!) in a dingy corner…working together as a small team cracking on a deeply interesting & challenging problem #reinvent

Tweet 12/57 👇 Next tweet 👆 Start

experiments lead to virtualizing the network layer. that was what provided the isolation needed #reinvent

Tweet 13/57 👇 Next tweet 👆 Start

that 👆 was the start of @awscloud VPC #reinvent

Tweet 14/57 👇 Next tweet 👆 Start

“We’ve grown a tiny bit”, @mosescj58 aims for understatement of the show #reinvent

Tweet 15/57 👇 Next tweet 👆 Start

by, the main “home” for @AWSSecurityInfo is https://aws.amazon.com/security/ …though there’s a ton of info everywhere in the service docs/whitepapers/etc. #reinvent

Tweet 16/57 👇 Next tweet 👆 Start

events seen on the @awscloud global network…. …that’s a lot of zeros #reinvent

Tweet 17/57 👇 Next tweet 👆 Start

that’s a new visual for the shared responsibility model. I think that’s much clearer than the older one w/way too many layers shown #reinvent

Tweet 18/57 👇 Next tweet 👆 Start

great reference on the shared responsibility model: https://aws.amazon.com/compliance/shared-responsibility-model/ #reinvent

Tweet 19/57 👇 Next tweet 👆 Start

“If you have access or control, you have responsibility”, @mosescj58 << great summary and ‘cheatsheet’ for the @awscloud shared responsibility model #reinvent

Tweet 20/57 👇 Next tweet 👆 Start

getting a bit of a peek behind the @AWSSecurityInfo curtain here from @mosescj58 #reinvent

Tweet 21/57 👇 Next tweet 👆 Start

more on @awscloud Shield at https://aws.amazon.com/shield/ …AWS WAF at https://aws.amazon.com/waf/ #reinvent

Tweet 22/57 👇 Next tweet 👆 Start

@AWSSecurityInfo saw more than 224M malware samples in six months! #reinvent

Tweet 23/57 👇 Next tweet 👆 Start

all of the data that @AWSSecurityInfo gathers from their perspective informs new @awscloud services and features that’s why we’re seeing so many new feature advances in things like Amazon Macie and Amazon GuardDuty #reinvent

Tweet 24/57 👇 Next tweet 👆 Start

more on @awscloud Macie at https://aws.amazon.com/macie/ …Amazon GuardDuty at https://aws.amazon.com/guardduty/ #reinvent

Tweet 25/57 👇 Next tweet 👆 Start

exposed credentials are a continuing challenge. IAM helps reduce the blast radius (good ol’ principle of least privilege) and @awscloud Security Hub helps shine a light on those issues #reinvent

Tweet 26/57 👇 Next tweet 👆 Start

@mosescj58 calls out—again, and will do again & again—how valuable MFA or multi-factor authentication is more details at https://aws.amazon.com/iam/features/mfa/ remember if you’re onsite, you can pick up a hardware MFA key…and you can always use an MFA app #reinvent

Tweet 27/57 👇 Next tweet 👆 Start

details on getting an MFA key onsite 👇 https://twitter.com/AWSSecurityInfo/status/1597263326589120514 #reinvent

Tweet 28/57 👇 Next tweet 👆 Start

get an MFA key online (with some restrictions) at https://aws.amazon.com/security/amazon-security-initiatives/free-mfa-security-key/ #reinvent

Tweet 29/57 👇 Next tweet 👆 Start

@mosescj58 moving into six 🔑 learnings for @AWSSecurityInfo: 1. educate everyone about #security 2. build a security-first culture 3. hire & develop the best #reinvent



Tweet 30/57 👇 Next tweet 👆 Start

...continuing the six 🔑 learnings... 4. shift left & automate 5. invest in a dynamic workforce 6. make security the department of “yes, and…” #reinvent



Tweet 31/57 👇 Next tweet 👆 Start

btw, @mosescj58’s voice is toast 🍞, but he’s powering through like a champ hang in there CJ! #reinvent

Tweet 32/57 👇 Next tweet 👆 Start

moving on to predictions for 2023 now... #reinvent

Tweet 33/57 👇 Next tweet 👆 Start

increasing threat continue to drive the shift to the cloud …this is a data problem. @awscloud Security Lake is designed to help remove barriers in analyzing that data and drawing insights from it #reinvent

Tweet 34/57 👇 Next tweet 👆 Start

more on @awscloud Security Lake in this blog post by @channyun…but you already knew that 😉 https://aws.amazon.com/blogs/aws/preview-amazon-security-lake-a-purpose-built-customer-owned-data-lake-service/ #reinvent

Tweet 35/57 👇 Next tweet 👆 Start

next prediction: we need more #security professionals. broaden your search net. we need more diversity and neurodiversity in our community more perspectives only make things better #reinvent

Tweet 36/57 👇 Next tweet 👆 Start

next prediction: automate everything why? there’s just too much data that needs protecting…and too much security data that needs to be processed. the only way is automation #reinvent


Tweet 37/57 👇 Next tweet 👆 Start

the new automated data discovery from Amazon Macie aims to help with this session SEC209, “Continuous innovation in AWS threat detection & monitoring services” covers this in more depth (on the @AWSEvents YouTube channel soon) #reinvent

Tweet 38/57 👇 Next tweet 👆 Start

the blog post on Macie is up at https://aws.amazon.com/blogs/aws/automated-data-discovery-for-amazon-macie/ #reinvent

Tweet 39/57 👇 Next tweet 👆 Start

another feature that helps here is external key store (XKS) for @awscloud KMS (key management system) blog post on that is available at https://aws.amazon.com/blogs/aws/announcing-aws-kms-external-key-store-xks/ #reinvent

Tweet 40/57 👇 Next tweet 👆 Start

s/service/system/👆 #reinvent

Tweet 41/57 👇 Next tweet 👆 Start

more on @awscloud KMS at https://aws.amazon.com/kms/ #reinvent

Tweet 42/57 👇 Next tweet 👆 Start

Tweet 43/57 👇 Next tweet 👆 Start

another @AWSSecurityInfo IAM feature: multiple MFA devices for root users and IAM users blog at https://aws.amazon.com/blogs/security/you-can-now-assign-multiple-mfa-devices-in-iam/ #reinvent

Tweet 44/57 👇 Next tweet 👆 Start

btw, Verified Permissions is part of the broader “provable security” initiative from @AWSSecurityInfo tons of great features/services have come from this push program page is up at https://aws.amazon.com/security/provable-security/ #reinvent

Tweet 45/57 👇 Next tweet 👆 Start

@mosescj58 diving into some post-quantum cryptography details. lots of work going on here in the community blog post: https://aws.amazon.com/about-aws/whats-new/2022/03/aws-kms-acm-support-latest-hybrid-post-quantum-tls-ciphers/ #reinvent

Tweet 46/57 👇 Next tweet 👆 Start

@mosescj58 takes a quick pause as we get a video to intro @united #reinvent

Tweet 47/57 👇 Next tweet 👆 Start

now to a fireside chat between @mosescj58 and @deneendefiore, CISO @united #reinvent

Tweet 48/57 👇 Next tweet 👆 Start

@deneendefiore is speaking to the resiliency challenges with technology. every traveller interaction @united crosses a lot of different systems, #security and resiliency are critical at each stage #reinvent

Tweet 49/57 👇 Next tweet 👆 Start

on automation, @deneendefiore talks about leveraging @AWSSecurityInfo services and automating their own systems to ensure that builders @united are starting from strong, secure-by-default positions #reinvent

Tweet 50/57 👇 Next tweet 👆 Start

@deneendefiore @AWSSecurityInfo @united on culture: @deneendefiore points out that aviation is already a safety aware culture. it’s an “easy” bridge to #security …when compared to other verticals that common understanding makes collaboration a lot easier if you don’t have it, you can build that culture #reinvent

Tweet 51/57 👇 Next tweet 👆 Start

another great call out that everyone can use: find the cultural points in your organization that are already there. use those as #security entry points @deneendefiore & @united use regular safety briefings that are already in place ❤️👆 #reinvent

Tweet 52/57 👇 Next tweet 👆 Start

@deneendefiore @united @mosescj58 calls out @awscloud's approach with #security learning/education check out and use their solution at https://t.co/TNoUHSzX8i #reinvent

Tweet 53/57 👇 Next tweet 👆 Start

@deneendefiore @united @mosescj58 @awscloud @deneendefiore's focus for 2023: - be brilliant at the basics - advance capabilities as your environment changes (tech/biz/regulatory/etc.) - enable the business! #reinvent

Tweet 54/57 👇 Next tweet 👆 Start

@deneendefiore @united @mosescj58 @awscloud on to the challenges around recruiting, developing, and maintaining #security talent... #reinvent

Tweet 55/57 👇 Next tweet 👆 Start

@deneendefiore is a great example of a lot of #security career path...from anywhere. there's no one path to get into security if you're hiring, understand that. yes, it's more work, but so, so worth it #reinvent

Tweet 56/57 👇 Next tweet 👆 Start

@deneendefiore key point from @mosescj58: you can hire a diverse set of ppl, but if you don't have a culture of inclusion...they aren't going to stay or succeed! #reinvent

Tweet 57/57 👇 Next tweet 👆 Start

@deneendefiore @mosescj58 ...and that's a wrap from the #security leadership session by @mosescj58 at #reinvent 2022! hopefully, he's now off to get some tea 🍵 for his voice

]]>
https://markn.ca/2022/accelerating-innovation-at-aws-security/ 67f6bbeaaf961b0001443264 Thu, 01 Dec 2022 09:00:00 -0500
<![CDATA[ Swami Sivasubramanian Keynote Play-by-play ]]> Want to share with others? Formatting issues in your reader? This post is available online, Swami Sivasubramanian Keynote Play-by-play

At re:Invent or attending remotely? Check out my “Ultimate Guide to AWS re:Invent 2022” post for some tips and tricks to get the most out of the show.

The data and machine learning keynote at AWS re:Invent is always full of surprised. Swami Sivasubramanian brings a ton of energy to the stage and always have a strong theme and narrative for this talks. This year was no exception.

The keynote was a mix of new features, great use cases, and a call to action for builders. Below is my reaction as it happened 👇.

Twitter Thread 🧵

Tweet 1/119 👇 Next tweet

here we go... @SwamiSivasubram with a data/ml 🧠 focused keynote at @awscloud #reinvent 2022! /cc @AWSEvents /🧵

Tweet 2/119 👇 Next tweet 👆 Start

very, very dramatic opening to this keynote #reinvent


Tweet 3/119 👇 Next tweet 👆 Start

if @SwamiSivasubram gets lowered from the ceiling, I’m going to lose it... #reinvent

Tweet 4/119 👇 Next tweet 👆 Start

apparently the team at @awsevents has realized they own @mgmstudios. crazy dramatic and intriguing intro! #reinvent

Tweet 5/119 👇 Next tweet 👆 Start

@SwamiSivasubram up now. starting with a great prompt from his daughter, “How do scientists come up with these inventions?” #reinvent

Tweet 6/119 👇 Next tweet 👆 Start

@SwamiSivasubram covering some key historical discoveries #reinvent



Tweet 7/119 👇 Next tweet 👆 Start

“Are these ‘ah ha!’ moments really that fast? No. They assimilate information gathered over time”, @SwamiSivasubram Swami walks through the actual timeline for the microwave discovery (30 years) #reinvent

Tweet 8/119 👇 Next tweet 👆 Start

@SwamiSivasubram diving into how our brains work. how they combine disparate facts and experiences to draw new conclusions in different contexts #reinvent

Tweet 9/119 👇 Next tweet 👆 Start

pivoting now to the lack of parallel with our organizations. they don’t store and process data like our 🧠 #reinvent

Tweet 10/119 👇 Next tweet 👆 Start

this is s great way to set up the central—or what I assume will be the central—theme of the keynote today key issues: - data isn’t centralized - …isn’t automatically process - …doesn’t naturally flow - …isn’t easy to visualize #reinvent

Tweet 11/119 👇 Next tweet 👆 Start

... #reinvent

Tweet 12/119 👇 Next tweet 👆 Start

if you don’t solve 👆 👆, you aren’t going to see the benefits of all that data you create/ingest #reinvent

Tweet 13/119 👇 Next tweet 👆 Start

nice summary slide of @awscloud / @amazon successes rooted in data analysis and insights #reinvent

Tweet 14/119 👇 Next tweet 👆 Start

I think a lot of ppl sleep on @SwamiSivasubram’s keynote each year there’s a tendency to think, “I don’t do data/ml that much”, that’s a mistake this section is a great proof point that data insights drive EVERYTHING #reinvent

Tweet 15/119 👇 Next tweet 👆 Start

good customer reference highlights #reinvent


Tweet 16/119 👇 Next tweet 👆 Start

three core elements of a strong data strategy: - future-proof foundation - weave connective tissue - democratize data with tools & education #reinvent

Tweet 17/119 👇 Next tweet 👆 Start

@SwamiSivasubram is starting with “building a future-proof” data foundation #reinvent

Tweet 18/119 👇 Next tweet 👆 Start

4 key elements to that foundation: - tools for every workload - performance at scale - remove heavy lifting - flexibility and scalability #reinvent

Tweet 19/119 👇 Next tweet 👆 Start

“We believe that every customer should have access to a wide variety of tools…a one-size fits all approach simply doesn’t work in the long run”, @SwamiSivasubram #reinvent

Tweet 20/119 👇 Next tweet 👆 Start

the updated datastore & analytics overview slides #reinvent

Tweet 21/119 👇 Next tweet 👆 Start

the ml 🧠 layer cake makes a reappearnace * remember, stay at the top for as long as possible. tread into the dungeon layer at your own peril! #reinvent

Tweet 22/119 👇 Next tweet 👆 Start

the whole #! #reinvent

Tweet 23/119 👇 Next tweet 👆 Start

nerds get the joke 👆 😉🤣🤦 (sorry, had to) #reinvent

Tweet 24/119 👇 Next tweet 👆 Start

back to @SwamiSivasubram giving a nice shout out to Athena. I ❤️ because everything just stays in S3…very efficient and cost effective #reinvent

Tweet 25/119 👇 Next tweet 👆 Start

more on @awscloud Athena at https://aws.amazon.com/athena/ take some time to check it out if you haven’t already #reinvent

Tweet 26/119 👇 Next tweet 👆 Start

NEW: Amazon Athena for Apache Spark - get started with interactive analytics on Apache Spark in under a second - available today #reinvent


Tweet 27/119 👇 Next tweet 👆 Start

RECAP: Amazon Redshift Integration for Apache Spark - run Apache Spark on Amazon Redshift data up to 10x faster vs. existing more at : https://aws.amazon.com/blogs/aws/new-amazon-redshift-integration-with-apache-spark/ #reinvent

Tweet 28/119 👇 Next tweet 👆 Start

strong focus on @ApacheSpark this year #reinvent

Tweet 29/119 👇 Next tweet 👆 Start

@SwamiSivasubram moving to performance at scale (in the foundations sections) now... #reinvent

Tweet 30/119 👇 Next tweet 👆 Start

some crazy @awscloud scale highlights #reinvent



Tweet 31/119 👇 Next tweet 👆 Start

more details on @awscloud DocumentDB at https://aws.amazon.com/documentdb/ #reinvent

Tweet 32/119 👇 Next tweet 👆 Start

@SwamiSivasubram calling out some of the challenges scaling DocumentDB. not enough capacity or performance in current cluster structures #reinvent

Tweet 33/119 👇 Next tweet 👆 Start

NEW: Amazon DocumentDB Elastic Clusters - fully managed solution to scale document workloads of virtually any size and scale - available today #reinvent

Tweet 34/119 👇 Next tweet 👆 Start

call back to @awscloud Athena for Apache Spark. more details in this blog post: https://aws.amazon.com/blogs/aws/new-amazon-athena-for-apache-spark/ #reinvent

Tweet 35/119 👇 Next tweet 👆 Start

@SwamiSivasubram now into some customer scale examples #reinvent


Tweet 36/119 👇 Next tweet 👆 Start

first customer speaker up now. Rathi Murthy from @Expedia #reinvent

Tweet 37/119 👇 Next tweet 👆 Start

scale context for @Expedia #reinvent

Tweet 38/119 👇 Next tweet 👆 Start

btw, @QuinnyPig’s thread on this keynote starts at https://twitter.com/QuinnyPig/status/1597993393740619778 #reinvent

Tweet 39/119 👇 Next tweet 👆 Start

👆 more colour, more snark, more of what’s going on in your 🧠 in @QuinnyPig’s thread I tend to stick mainly to what’s on stage + adding in extra resources w/a little bit of Canadian 🇨🇦 colour 😉 #reinvent

Tweet 40/119 👇 Next tweet 👆 Start

back on stage, Rathi is explaining just how much data her teams are digging through …it’s a lot. tons of interesting engineering and data science problems in there #reinvent

Tweet 41/119 👇 Next tweet 👆 Start

nice shout out of the impact of travel on people, culture, and understanding using data to drive better insights for ppl is what drives Rathi #reinvent

Tweet 42/119 👇 Next tweet 👆 Start

btw, the @awscloud + @Expedia case study is up at https://aws.amazon.com/solutions/case-studies/expedia/ #reinvent

Tweet 43/119 👇 Next tweet 👆 Start

Rathi is currently walking through the high level of price predictions and recommendations for travellers #reinvent

Tweet 44/119 👇 Next tweet 👆 Start

the examples Rathi cites in this segment are really interesting. would’ve like to see some specific call outs about the challenges or a pointer to more technical follow-ups @Expedia did a talk yesterday (CON322) but it was about #kubernetes #reinvent

Tweet 45/119 👇 Next tweet 👆 Start

@SwamiSivasubram back up now talking about removing heavy lifting from customers #reinvent

Tweet 46/119 👇 Next tweet 👆 Start

more on @awscloud DevOps Guru at https://aws.amazon.com/devops-guru/ #reinvent

Tweet 47/119 👇 Next tweet 👆 Start

... #reinvent

Tweet 48/119 👇 Next tweet 👆 Start

while other services are getting ml boosts, @awscloud SageMaker continues to do a massive amount of heavy lifting more on SageMaker at https://aws.amazon.com/sagemaker/ #reinvent

Tweet 49/119 👇 Next tweet 👆 Start

unstructureed data continues to be a persistent challenge for most organizations @SwamiSivasubram its geospatial data as a real pain point #reinvent


Tweet 50/119 👇 Next tweet 👆 Start

more on @awscloud SageMaker Ground Truth at https://aws.amazon.com/sagemaker/data-labeling/ #reinvent

Tweet 51/119 👇 Next tweet 👆 Start

NEW Amazon SageMaker now supports Geospatial ML - making it easier to build, train, and deploy ml models using geospatial data 🌍 #reinvent

Tweet 52/119 👇 Next tweet 👆 Start

call back: more details on Amazon DocumentDB Elastic Clusters in this blog post https://aws.amazon.com/blogs/aws/announcing-amazon-documentdb-elastic-clusters/ #reinvent

Tweet 53/119 👇 Next tweet 👆 Start

Kumar Chellapilla, GM ML/AI services @awscloud, up now to demo the new geospatial functionality use case is predicting dangerous road contusion due to rising water levels #reinvent


Tweet 54/119 👇 Next tweet 👆 Start

interesting demo using some built-in models & easily access 3rd party and open data sources #reinvent



Tweet 55/119 👇 Next tweet 👆 Start

if my count is correct, Kumar is up to 4 different data sources added into this solution? that’s super cool! #reinvent

Tweet 56/119 👇 Next tweet 👆 Start

looks like SUS201, Detecting deforestation with geospatial images and Amazon SageMaker, covers some of these topics not sure if it includes the new features, but conceptually lots of overlap seating is full, so catch it on YouTube sometime after Thursday #reinvent

Tweet 57/119 👇 Next tweet 👆 Start

@SwamiSivasubram back up now, diving into reliability and security #reinvent

Tweet 58/119 👇 Next tweet 👆 Start

lots of reliability and security features built into @awscloud services. some use cases need even more... as @SwamiSivasubram foreshadows an announcement 😉 #reinvent

Tweet 59/119 👇 Next tweet 👆 Start

NEW: Amazon Redshift Multi-AZ - delivering high availability and reliability to support mission-critical analytics workloads #reinvent

Tweet 60/119 👇 Next tweet 👆 Start

Tweet 61/119 👇 Next tweet 👆 Start

@SwamiSivasubram moving on to PostgreSQL security… #reinvent

Tweet 62/119 👇 Next tweet 👆 Start

NEW: Trusted Language Extensions for PostgreSQL - new open-source project to support PostgreSQL extensions on Amazon RDS and Amazon Aurora - available today! #reinvent

Tweet 63/119 👇 Next tweet 👆 Start

on to the good ol’ reliable Shared Responsibility Model #reinvent

Tweet 64/119 👇 Next tweet 👆 Start

… #reinvent

Tweet 65/119 👇 Next tweet 👆 Start

NEW: Amazon GuardDuty RDS Protection - protect you data in Aurora with intelligent threat detection - currently preview #reinvent

Tweet 66/119 👇 Next tweet 👆 Start

I did not expect a #security launch during this keynote. really pumped about it. @AWSSecurityInfo GuardDuty is absolutely crushing it! #reinvent

Tweet 67/119 👇 Next tweet 👆 Start

need to focus on @SwamiSivasubram at the moment though. we’ve moved on to the connective tissue principle/aspect of a data strategy this is the 2nd major pillar, we’re done with a data foundation for now #reinvent

Tweet 68/119 👇 Next tweet 👆 Start

@SwamiSivasubram uses a really interesting real-world example of living root bridges. that bridges (see what I did there?) to: - quality tools and data - governance - connectivity #reinvent



Tweet 69/119 👇 Next tweet 👆 Start

…and now Amazon Security Lakes too! more at https://aws.amazon.com/about-aws/whats-new/2022/11/amazon-security-lake-preview/ #reinvent

Tweet 70/119 👇 Next tweet 👆 Start

#protip: anytime you see the word “manual” on an @awscloud slide, you’re about to get something cool... #reinvent

Tweet 71/119 👇 Next tweet 👆 Start

NEW: AWS Glue Data Quality - automatically measure, monitor, and manage data quality in your data lake - available in preview today #reinvent

Tweet 72/119 👇 Next tweet 👆 Start

👆 should’ve been called, “AWS Glue Happy Data Boo” #reinvent

Tweet 73/119 👇 Next tweet 👆 Start

@SwamiSivasubram on to governance now #reinvent


Tweet 74/119 👇 Next tweet 👆 Start

ohh, he said “manual” again… #reinvent

Tweet 75/119 👇 Next tweet 👆 Start

more on @awscloud Lake Formation at https://aws.amazon.com/lake-formation/ #reinvent

Tweet 76/119 👇 Next tweet 👆 Start

NEW: Centralized Access Controls for Redshift Data Sharing - govern access to Redshift data using AWS Lake Formation - available in preview today #reinvent

Tweet 77/119 👇 Next tweet 👆 Start

🧠 machine learning has it’s own unique set of governance challenges < a massive understatement #reinvent

Tweet 78/119 👇 Next tweet 👆 Start

I also love how an hour in, @SwamiSivasubram’s smile is only getting wider. amazing energy #reinvent

Tweet 79/119 👇 Next tweet 👆 Start

NEW: Amazon SageMaker ML Governance - governance and audibility for end-to-end ML development - available today #reinvent

Tweet 80/119 👇 Next tweet 👆 Start

@SwamiSivasubram recapping Amazon DataZone more on the new service at: https://aws.amazon.com/datazone/ #reinvent

Tweet 81/119 👇 Next tweet 👆 Start

Shikha Verma (@_Shikha_Verma_), Head of Product, Amazon DataZone up now for a demo #reinvent



Tweet 82/119 👇 Next tweet 👆 Start

call back: the blog post for Trusted Language Extensions for PostgreSQL on Amazon Aurora is up now at https://aws.amazon.com/blogs/aws/new-trusted-language-extensions-for-postgresql-on-amazon-aurora-and-amazon-rds/ #reinvent

Tweet 83/119 👇 Next tweet 👆 Start

@_shikha_verma_ is laying out the scenario for the demo. a data producer (sales team) needs to share data with a data consumer(marketing team) in order to complete a campaign analysis #reinvent


Tweet 84/119 👇 Next tweet 👆 Start

I ❤️ the timeline view on the left of the slide. the screen captures could use a bigger scaling size to help with readability but @_Shikha_Verma_’s talk track is spot on makes it easier to understand the advantages of DataZone this demo is really well constructed #reinvent


Tweet 85/119 👇 Next tweet 👆 Start

for reference, this demo starts around 1h 8m into the keynote #reinvent

Tweet 86/119 👇 Next tweet 👆 Start

excellent demo. @_Shikha_Verma_ absolutely nailed it the service looks cool tool, but this segment is worth studying if you ever give presentations #reinvent

Tweet 87/119 👇 Next tweet 👆 Start

@SwamiSivasubram back up, talking about connected data sources #reinvent

Tweet 88/119 👇 Next tweet 👆 Start

back on to ETL and “Zero ETL” mirroring the “Zero Trust” #security push #reinvent

Tweet 89/119 👇 Next tweet 👆 Start

re: Zero ETL (or even Zero Trust) #reinvent

Tweet 90/119 👇 Next tweet 👆 Start

though both concepts are excellent. I just get hung up on terms and how they get diluted over time as more and more ppl “bend” (being generous there) the term to server their needs…and sales #reinvent

Tweet 91/119 👇 Next tweet 👆 Start

@SwamiSivasubram recaps the Amazon Aurora zero-ETLA integration with Amazon Redshift. more on that at https://aws.amazon.com/about-aws/whats-new/2022/11/amazon-aurora-zero-etl-integration-redshift/ #reinvent

Tweet 92/119 👇 Next tweet 👆 Start

NEW: Amazon Redshift auto-copy from S3 - simplify and automate file ingestion into Redshift - available in preview today #reinvent

Tweet 93/119 👇 Next tweet 👆 Start

this slide is probably nicknamed, “Redshift all the thingz” #reinvent

Tweet 94/119 👇 Next tweet 👆 Start

continuing the “weave” theme #reinvent

Tweet 95/119 👇 Next tweet 👆 Start

more on Amazon Kinesis Data Firehose at https://aws.amazon.com/kinesis/data-firehose/ #reinvent

Tweet 96/119 👇 Next tweet 👆 Start

more on Amazon SageMaker Data Wrangler at https://aws.amazon.com/sagemaker/data-wrangler/ #reinvent

Tweet 97/119 👇 Next tweet 👆 Start

more on Amazon AppFlow at https://aws.amazon.com/appflow/ #reinvent

Tweet 98/119 👇 Next tweet 👆 Start

👆..and Amazon AppFlow just got 50+ new connectors. tons of really useful ones here for a lot of different customers #reinvent

Tweet 99/119 👇 Next tweet 👆 Start

Amazon SageMaker Data Wrangler gets some of that 👆 goodness too. 40+ new data sources there #reinvent

Tweet 100/119 👇 Next tweet 👆 Start

lots of connections to various data sources from various data sources…weave is definitely the correct word for this section #reinvent

Tweet 101/119 👇 Next tweet 👆 Start

next customer speaker up. this time it’s Anna Berg Åsberg, global VP, R&D @AstraZeneca #reinvent

Tweet 102/119 👇 Next tweet 👆 Start

Anna covering the @AstraZeneca @awscloud case: research at scale #reinvent


Tweet 103/119 👇 Next tweet 👆 Start

remember that @aselipsky announced Amazon Omics during his keynote yesterday more details at https://aws.amazon.com/omics/ #reinvent

Tweet 104/119 👇 Next tweet 👆 Start

Tweet 105/119 👇 Next tweet 👆 Start

@SwamiSivasubram back up for the 3rd main pillar: democratize data #reinvent

Tweet 106/119 👇 Next tweet 👆 Start

call back: the blog post for @awscloud Glue Data Quality is up now at https://aws.amazon.com/blogs/aws/join-the-preview-aws-glue-data-quality/ #reinvent

Tweet 107/119 👇 Next tweet 👆 Start

Tweet 108/119 👇 Next tweet 👆 Start

back to the keynote, @SwamiSivasubram walking through the challenges around education and training for ML/data science #reinvent


Tweet 109/119 👇 Next tweet 👆 Start

this is part of the first area of this section: a wider net for innvation: - education - training - low-code tools #reinvent


Tweet 110/119 👇 Next tweet 👆 Start

to help address the education gap... NEW AWS Machine Learning University now provides educator training - train educators in community colleges and MSIs nationwide - available today #reinvent

Tweet 111/119 👇 Next tweet 👆 Start

more details on the AI & ML scholarship program is available at https://aws.amazon.com/machine-learning/scholarship/ #reinvent

Tweet 112/119 👇 Next tweet 👆 Start

@SwamiSivasubram points out that we need to help professionals get educated and train as well. lots going on there too #reinvent

Tweet 113/119 👇 Next tweet 👆 Start

on to low-code and no-code tools now... #reinvent

Tweet 114/119 👇 Next tweet 👆 Start

shout out for https://t.co/jIzVGVd3kJ. lots of new features have been added this year and this week #reinvent

Tweet 115/119 👇 Next tweet 👆 Start

more on @awscloud SageMaker Canvas at https://aws.amazon.com/sagemaker/canvas/ #reinvent

Tweet 116/119 👇 Next tweet 👆 Start

understand but don’t like the focus on no-code/low-code tools for builders who don’t write code I’ve been coding for a very long time & I ❤️ this type of tooling. it’s a level of automation these tools speed up my solutions, let me code only the really tough bits #reinvent

Tweet 117/119 👇 Next tweet 👆 Start

@SwamiSivasubram back up after a good WarnerBros gaming video. Swami is retiring the three main pillars of today’s keynote - build future-proof foundations - weave connective tissue - democratize data #reinvent

Tweet 118/119 👇 Next tweet 👆 Start

no surprise, @SwamiSivasubram ends it with a smile! #reinvent

Tweet 119/119 👇 Next tweet 👆 Start

that’s it for the data/ml keynote. the partner keynote is up later on today remember that session are being uploaded to the @AWSEvents YouTube channel (https://www.youtube.com/@AWSEventsChannel) regularly /🧵 #reinvent

]]>
https://markn.ca/2022/swami-sivasubramanian-keynote-play-by-play/ 67f6bbeaaf961b0001443263 Wed, 30 Nov 2022 09:00:00 -0500
<![CDATA[ Ruba Borno AWS Partner Keynote Play-by-play ]]> Want to share with others? Formatting issues in your reader? This post is available online, Ruba Borno AWS Partner Keynote Play-by-play

At re:Invent or attending remotely? Check out my “Ultimate Guide to AWS re:Invent 2022” post for some tips and tricks to get the most out of the show.

Ruba Borno delivered a great AWS Partner keynote at this year’s AWS re:Invent. This keynote is very different than the others. I always think of it like a series of sound bites. In small bites, it makes sense. As a whole it can be tough to find the common thread.

That thread is really that AWS is focusing on partner success. They are putting effort behdin partners because it’s driving customer success. My reaction in this Twitter thread 👇.

Twitter Thread 🧵

Tweet 1/74 👇 Next tweet

2nd #reinvent keynote of the day is kicking off now this time it’s @rubaborno with a focus on Partners!

Tweet 2/74 👇 Next tweet 👆 Start

this montage is focusing on the value of partnership and teamwork #reinvent


Tweet 3/74 👇 Next tweet 👆 Start

@rubaborno up now! #reinvent

Tweet 4/74 👇 Next tweet 👆 Start

it’s the 10th anniversary of @awsmarketplace and @AWS_Partners + the 1 year anniversary of @rubaborno at @awscloud lot’s to celebrate 🥳 #reinvent

Tweet 5/74 👇 Next tweet 👆 Start

also celebrating all of the @AWS_Partners who won awards for their efforts this year /cc @AWSEvents #reinvent

Tweet 6/74 👇 Next tweet 👆 Start

Tweet 7/74 👇 Next tweet 👆 Start

@rubaborno continues to cite the need for @awscloud and @AWS_Partners to work together to help customers succeed #reinvent

Tweet 8/74 👇 Next tweet 👆 Start

lots at stake for customers in the coming years #reinvent

Tweet 9/74 👇 Next tweet 👆 Start

btw, if you haven’t figured it out yet, this #reinvent keynote is very specific to @AWS_Partners and @awsmarketplace 😉 #reinvent

Tweet 10/74 👇 Next tweet 👆 Start

first @AWS_Partners speaker up now: @Atos #reinvent

Tweet 11/74 👇 Next tweet 👆 Start

there will be lots of “business statements” in this keynote. they may not seem like much in the context of a keynote, but they will be clipped and use as social proof for @AWS_Partners in the future and to help establish trust with customers #reinvent

Tweet 12/74 👇 Next tweet 👆 Start

@rubaborno doing a good job keeping the energy up... #reinvent

Tweet 13/74 👇 Next tweet 👆 Start

on to transformation as a topic of focus for customers #reinvent

Tweet 14/74 👇 Next tweet 👆 Start

btw, if you on the customer-side of transformation, you really should read the @awscloud Cloud Adoption Framework it’s available at https://aws.amazon.com/professional-services/CAF/ and will help you map your business workflows and how you can move and improve them in the cloud #reinvent

Tweet 15/74 👇 Next tweet 👆 Start

shout out from @rubaborno about the @awscloud Competency Program. it’s where you—the customer—should start your search for an @AWS_Partners to work with more on the framework at https://aws.amazon.com/partners/programs/competencies/ #reinvent

Tweet 16/74 👇 Next tweet 👆 Start

now on to a panel discussion hosted by Julia Chen, VP, @awscloud Core Partner Programs featuring @Heineken and Schuberg Philis. nice to see a customer success story from the Nederlands 🇳🇱! #reinvent


Tweet 17/74 👇 Next tweet 👆 Start

tl:dr for this panel: @AWS_Partners can help with the technology, but—maybe—more importantly help transform how your teams think about the technology culture is always the hardest part. seeing another team work differently & deliver can help accelerate your results #reinvent

Tweet 18/74 👇 Next tweet 👆 Start

also a tl:dr from this panel 👇 🤣🤣🤣 #reinvent

Tweet 19/74 👇 Next tweet 👆 Start

serious note, here’s the case study for this collab: https://aws.amazon.com/partners/success/heineken-schuberg-philis/ #reinvent

Tweet 20/74 👇 Next tweet 👆 Start

@rubaborno back up. talking about the value to customers, but also highlighting the value to @AWS_Partners #reinvent

Tweet 21/74 👇 Next tweet 👆 Start

61% of that 👆 is realized in the first year. that’s a massive win-win-win (@awscloud, @AWS_Partners, & customers) #reinvent

Tweet 22/74 👇 Next tweet 👆 Start

…and that value 👆 keeps on rolling #reinvent

Tweet 23/74 👇 Next tweet 👆 Start

@rubaborno points out some key @AWS_Partners support programs #reinvent

Tweet 24/74 👇 Next tweet 👆 Start

more on @awscloud Partner Paths at https://aws.amazon.com/partners/paths/ #reinvent

Tweet 25/74 👇 Next tweet 👆 Start

more on @awscloud SaaS Factory at https://aws.amazon.com/partners/programs/saas-factory/ #reinvent

Tweet 26/74 👇 Next tweet 👆 Start

NEW: @AWS_Partners Solution Factory - industry specific pre-built, support solutions - available in preview now #reinvent

Tweet 27/74 👇 Next tweet 👆 Start

👆this program helps you make a proven solution more broadly available and accessible. you get support from @awsclodu to built it out and more huge for @AWS_Partners #reinvent

Tweet 28/74 👇 Next tweet 👆 Start

getting a little partner montage video for @VodafoneGroup… #reinvent

Tweet 29/74 👇 Next tweet 👆 Start

….had to step away…back now to another panel discussion with @interbr and @IBM #reinvent

Tweet 30/74 👇 Next tweet 👆 Start

Tweet 31/74 👇 Next tweet 👆 Start

about that panel 👇 https://twitter.com/sarbjeetjohal/status/1598098711749750785 #reinvent

Tweet 32/74 👇 Next tweet 👆 Start

@rubaborno back up now to talk about #security #reinvent

Tweet 33/74 👇 Next tweet 👆 Start

speaking on holistic view of security related data: @awscloud Security Lake https://aws.amazon.com/about-aws/whats-new/2022/11/amazon-security-lake-preview/

Tweet 34/74 👇 Next tweet 👆 Start

@rubaborno points out that this was designed with @AWS_Partners in mind. using Open Cybersecurity Schema Framework (OCSF) and @AWSSecurityInfo Security Hub #reinvent

Tweet 35/74 👇 Next tweet 👆 Start

if you’re curious about the technical details for Open Cybersecurity Schema Framework, check out https://github.com/ocsf/ #reinvent

Tweet 36/74 👇 Next tweet 👆 Start

went super widescreen for #security @AWS_Partners testimonials & OCSF 👆 quotes #reinvent



Tweet 37/74 👇 Next tweet 👆 Start

#security tools—for too long—always want their own formats and live in a world where it’s only their stuff running…that’s just NOT how it works orgs use tools from lots of vendors. Amazon Security Lake & OCSF help & build on the work @awscloud Security Hub started #reinvent

Tweet 38/74 👇 Next tweet 👆 Start

talking about helping @AWS_Partners sell into the public sector. tons of red tape there, @awscloud programs can help cut through it driven home with another genomics example, lots of that this year #reinvent


Tweet 39/74 👇 Next tweet 👆 Start

if you’ve never dealt with FEDRAMP, congrats! you’re probably somewhat sane. enjoy that for the rest of us, any help you can get is very much appreciated #reinvent

Tweet 40/74 👇 Next tweet 👆 Start

here are the guidelines for US government FedRAMP: https://www.fedramp.gov/ #reinvent

Tweet 41/74 👇 Next tweet 👆 Start

@awscloud data on FedRAMP: https://aws.amazon.com/compliance/fedramp/ #reinvent

Tweet 42/74 👇 Next tweet 👆 Start

btw, standards like FedRAMP are critical to #security success. yes, they are arduous and frustrating to deal with …but they deliver results #reinvent

Tweet 43/74 👇 Next tweet 👆 Start

@rubaborno moving on to the success from @awsmarketplace now #reinvent


Tweet 44/74 👇 Next tweet 👆 Start

did you know that @awsmarketplace has an #ml section? you can buy models, access to data and more crazy stuff https://aws.amazon.com/marketplace/solutions/machine-learning #reinvent

Tweet 45/74 👇 Next tweet 👆 Start

NEW: @awsmarketplace Data Visualization Dashboards - track, analyze, and grow your business without requiring any technical integration - available in preview - for @AWS_Partners selling on the marketplace #reinvent

Tweet 46/74 👇 Next tweet 👆 Start

NEW: @awsmarketplace Vendor Insights - simplify software risk assessments and increase buyer confidence - available today! #reinvent

Tweet 47/74 👇 Next tweet 👆 Start

another panel discussion, this one hosted by Chris Grusz, GM WW ISV Alliances & Marketplace, @awscloud @AWS_Partners are: - @Infor - @confluentinc - @Nasdaq #reinvent


Tweet 48/74 👇 Next tweet 👆 Start

call out from @confluentinc for the @awscloud ISV Accelerate co-selling program. more details at https://aws.amazon.com/partners/programs/isv-accelerate/ #reinvent

Tweet 49/74 👇 Next tweet 👆 Start

…still panel-ing… #reinvent

Tweet 50/74 👇 Next tweet 👆 Start

@rubaborno back up now, calling out the @awscloud Data Exchange #reinvent

Tweet 51/74 👇 Next tweet 👆 Start

the actual exchange is up at https://aws.amazon.com/data-exchange/ #reinvent

Tweet 52/74 👇 Next tweet 👆 Start

@rubaborno calls out an interesting use case. Wine Access using weather data to ensure timely delivery on their product to customers 🍷 #reinvent

Tweet 53/74 👇 Next tweet 👆 Start

NEW x2 Amazon Data Exchange For... ...AWS Lake Formation - ready to use AWS Glue Tables - available in preview today …Amazon S3 - find, subscribe to, and use 3rd party files directly from provider’s S3 buckets - available in preview today #reinvent

Tweet 54/74 👇 Next tweet 👆 Start

@rubaborno points out that support of @AWS_Partners and @awsmarketplace success comes right from the top …and then she welcomes @aselipsky to the stage #reinvent


Tweet 55/74 👇 Next tweet 👆 Start

@StevenJBurke interviewing @aselipsky about his plans & vision for @AWS_Partners & @awsmarketplace #reinvent

Tweet 56/74 👇 Next tweet 👆 Start

side note: details on the @AWS_Partners Profitability Framework available in this blog post https://aws.amazon.com/blogs/apn/aws-partner-profitability-framework-deepen-and-diversify-your-offerings/ #reinvent

Tweet 57/74 👇 Next tweet 👆 Start

side note: details on a new @awscloud Conversational AI Competency for @AWS_Partners in this blog post https://aws.amazon.com/blogs/apn/implement-high-quality-chatbot-solutions-with-aws-conversational-ai-competency-partners/ #reinvent

Tweet 58/74 👇 Next tweet 👆 Start

I don’t think either of 👆 👆 were announced in the keynote, but the posts went up during this session #reinvent

Tweet 59/74 👇 Next tweet 👆 Start

@StevenJBurke and @aselipsky are talking about the success of @AWS_Partners in the past year+ and how much potential there is moving forward when everyone focuses on customer success, it all falls into place #reinvent

Tweet 60/74 👇 Next tweet 👆 Start

@aselipsky uses the example of work done with @ibmconsulting to highlight partner win-wins from unexpected places #reinvent

Tweet 61/74 👇 Next tweet 👆 Start

moving on to sustainability now. more on @awscloud’s efforts up at https://aws.amazon.com/sustainability/ #reinvent

Tweet 62/74 👇 Next tweet 👆 Start

if you’re looking to focus on sustainability while building in the @awscloud, check out the Well-Architected Framework details at https://docs.aws.amazon.com/wellarchitected/latest/sustainability-pillar/sustainability-pillar.html #reinvent

Tweet 63/74 👇 Next tweet 👆 Start

@StevenJBurke and @aselipsky wrap by reiterating @awscloud's commitment to the @AWS_Partners community #reinvent

Tweet 64/74 👇 Next tweet 👆 Start

@rubaborno back up talking about @awscloud training and education commitments #reinvent


Tweet 65/74 👇 Next tweet 👆 Start

more on @awscloud Skill Builder at https://explore.skillbuilder.aws/learn #reinvent

Tweet 66/74 👇 Next tweet 👆 Start

more on @awscloud Educate at https://aws.amazon.com/education/awseducate/ #reinvent

Tweet 67/74 👇 Next tweet 👆 Start

@awscloud re/start details can be found at https://aws.amazon.com/training/restart/ #reinvent

Tweet 68/74 👇 Next tweet 👆 Start

info on @awscloud Skills Center: https://aws.amazon.com/training/skills-centers/ #reinvent

Tweet 69/74 👇 Next tweet 👆 Start

into a case study now, talking about efforts in Brazil to help provide education and skills to help ppl find employment with cloud skills #reinvent

Tweet 70/74 👇 Next tweet 👆 Start

another quick discussion, this one relating to the case study about Escola da Nuvem #reinvent


Tweet 71/74 👇 Next tweet 👆 Start

side note: great data point for impact of APN (@awscloud Partner Network) https://twitter.com/AWS_Partners/status/1598109722271485958 #reinvent

Tweet 72/74 👇 Next tweet 👆 Start

@rubaborno back up to bring this all home. calling out the advantages of team work. using a peloton as a real-world example 🚴‍♂️ #reinvent

Tweet 73/74 👇 Next tweet 👆 Start

…mandatory call back to the four main points: - transformation - innovation - opportunity - impact #reinvent

Tweet 74/74 👇 Next tweet 👆 Start

round of thanks to customers and @AWS_Partners to finish this keynote from @rubaborno #reinvent /🧵

]]>
https://markn.ca/2022/ruba-borno-aws-partner-keynote-play-by-play/ 67f6bbeaaf961b0001443262 Wed, 30 Nov 2022 09:00:00 -0500
<![CDATA[ Adam Selipsky Keynote Play-by-play ]]> Want to share with others? Formatting issues in your reader? This post is available online, Adam Selipsky Keynote Play-by-play

At re:Invent or attending remotely? Check out my “Ultimate Guide to AWS re:Invent 2022” post for some tips and tricks to get the most out of the show.

AWS re:Invent 2022 is truly rolling now. CEO Adam Selipsky gave a fantastic keynote that covered a number of service launches, new features, and great customer stories. I live tweeted the keynote providing my reaction to each segment 👇.

Twitter Thread 🧵

Tweet 1/145 👇 Next tweet

here we go! @aselipsky up for today’s @awscloud #reinvent keynote… /🧵

Tweet 2/145 👇 Next tweet 👆 Start

@aselipsky takes the stage to Sweet Child of Mine 🎸🎵 #reinvent

Tweet 3/145 👇 Next tweet 👆 Start

50K in person, ~300K remote attendees #reinvent

Tweet 4/145 👇 Next tweet 👆 Start

tons of stuff on tap this week. lots of great customer stories too @aselipsky highlights a few, short customer highlights #reinvent



Tweet 5/145 👇 Next tweet 👆 Start

“Can’t go to the cloud? B—s**t” …I’m paraphrasing @aselipsky here 😉 #reinvent

Tweet 6/145 👇 Next tweet 👆 Start

83% of the 1,000 🦄’s are running in @awscloud. similar number of the cloud top 100! #reinvent

Tweet 7/145 👇 Next tweet 👆 Start

@aselipsky hits some of the high notes for @awscloud’s efforts around sustainability. it’s the top problem of our time more on those efforts at https://aws.amazon.com/sustainability/ #reinvent

Tweet 8/145 👇 Next tweet 👆 Start

you can include sustainability in your practice by using the @awscloud Well-Architected Framework. the sustainability pillar helps you make decisions that better align with sustainability goals more at https://docs.aws.amazon.com/wellarchitected/latest/sustainability-pillar/sustainability-pillar.html #reinvent

Tweet 9/145 👇 Next tweet 👆 Start

btw, @QuinnyPig is also live tweeting this (I think). his 🧵 starts at https://twitter.com/QuinnyPig/status/1597629764885356544 #reinvent

Tweet 10/145 👇 Next tweet 👆 Start

@aselipsky listing out a bunch of key innovation stories building the cloud success story…remember it’s not all (or even primarily) about the tech, but how you use it #reinvent

Tweet 11/145 👇 Next tweet 👆 Start

you can run @awscloud like a 1990’s data center. that’s ridiculous but you COULD do it please don’t #reinvent

Tweet 12/145 👇 Next tweet 👆 Start

if you realize that the structure of the @awscloud technologies allows you to change how you build and run your business, you really start to see huge gains you can create unique solutions that get you closer to your goals …that’s why I’m so up on cloud #reinvent

Tweet 13/145 👇 Next tweet 👆 Start

back to @aselipsky, we’re going to space now! #reinvent

Tweet 14/145 👇 Next tweet 👆 Start

@awscloud Ground Station 2.0? maybe we’ll finally get the `sol-orbit-1` region? 🤣 https://aws.amazon.com/ground-station/ #reinvent

Tweet 15/145 👇 Next tweet 👆 Start

back to the actual talk, we’re looking at space through the lens of a data problem. tons of amazing stuff to dig into here #reinvent

Tweet 16/145 👇 Next tweet 👆 Start

looking at images of the “pillars of creation” with images from the JWST amazing piece on JWST from @shannonmstirone via @nytimes: https://t.co/C58uirveyn #reinvent

Tweet 17/145 👇 Next tweet 👆 Start

lots of space science and exploration happening right now… [ side note: I need to focus and not nerd out on space now ] #reinvent

Tweet 18/145 👇 Next tweet 👆 Start

@aselipsky brings the story back to the main point: we are gathering and creating more data than ever we need scalable, modern tools to manage that data and gain insights from it #reinvent

Tweet 19/145 👇 Next tweet 👆 Start

Exploring the vast data realm, you need: - right tools - integration - governance - insights #reinvent

Tweet 20/145 👇 Next tweet 👆 Start

digging into tools now… there are a—um—few on @awscloud 😉 #reinvent

Tweet 21/145 👇 Next tweet 👆 Start

@awscloud Aurora continues to grow: https://aws.amazon.com/rds/aurora/ my only gripe: confusing naming in the “sub” services within Aurora…otherwise, it’s amazing #reinvent

Tweet 22/145 👇 Next tweet 👆 Start

a ton of analytics services to match those data store options #reinvent

Tweet 23/145 👇 Next tweet 👆 Start

Redshift keeps growing. last year, @aselipsky announced the #serverless option for it more on that at https://aws.amazon.com/redshift/redshift-serverless/ #reinvent

Tweet 24/145 👇 Next tweet 👆 Start

NEW FEATURE/SERVICE: OpenSearch #serverless - now in preview - rounds out the analytics services offerings, all now how server less options! #reinvent

Tweet 25/145 👇 Next tweet 👆 Start

now on to AI/ML 🧠 #reinvent

Tweet 26/145 👇 Next tweet 👆 Start

pay attention to the layers here. stay up top as long as possible. then to @awscloud SageMaker (it’s a whole environment & ecosystem at this point) very rarely enter the dungeon of the low level layer! #reinvent

Tweet 27/145 👇 Next tweet 👆 Start

some customer highlights for Amazon SageMaker more details on SageMaker at https://aws.amazon.com/sagemaker/ tons to learn there #reinvent

Tweet 28/145 👇 Next tweet 👆 Start

remember, SageMaker Studio Lab is a free service to help learn & experiment with the service(s) more at: https://aws.amazon.com/sagemaker/ #reinvent

Tweet 29/145 👇 Next tweet 👆 Start

first customer speaker up now Biljana Kaitović (@biljkai) from @ENGIEgroup #reinvent

Tweet 30/145 👇 Next tweet 👆 Start

tl:dr so far, we’re using a ton of energy. we need to make sure it’s sustainable #reinvent



Tweet 31/145 👇 Next tweet 👆 Start

@biljkai ties the energy sustainability issue back to a data problem would love to see more details on these solutions. there was a talk two years ago (?) from a California utility on how they used drones & AI to detect line issues in the system, super interesting #reinvent



Tweet 32/145 👇 Next tweet 👆 Start

Tweet 33/145 👇 Next tweet 👆 Start

based on this architecture slide, they are using a data lake at the core of their business there are tons of solutions around @awscloud data lakes. a great starting point is https://aws.amazon.com/solutions/implementations/data-lake-solution/ #reinvent

Tweet 34/145 👇 Next tweet 👆 Start

nice call out from @biljkai of @ENGIEgroup about how they are using @awscloud only when necessary, scaling up & down smartly to reduce energy consumption and impact that’s a key part of the sustainability pillar! #reinvent

Tweet 35/145 👇 Next tweet 👆 Start

nice customer segment from @ENGIEgroup. reasonable level of technical depth & minimal sales-y-ness for a main keynote I would love a req that all of these customer stories have a deeper technical dive. you got our attention on the possibilities, follow through! #reinvent

Tweet 36/145 👇 Next tweet 👆 Start

@aselipsky back up now, moving to the second section of the data realm: integration #reinvent

Tweet 37/145 👇 Next tweet 👆 Start

quick slide of the available tools from @awscloud around data/analytics/ml #reinvent

Tweet 38/145 👇 Next tweet 👆 Start

setting up the pain of ETL (extract, transform, load) of data analysis/science great customer quote about that type of work, “..thankless, unsustainable black hole” 🤣🤦😔👍 #reinvent

Tweet 39/145 👇 Next tweet 👆 Start

new service announcement in 3, 2, 1… #reinvent

Tweet 40/145 👇 Next tweet 👆 Start

curveball…more story 😄 #reinvent

Tweet 41/145 👇 Next tweet 👆 Start

needless build up for anyone who’s ever gone anywhere near an ETL challenge at scale. much needed for ppl who haven’t! #reinvent

Tweet 42/145 👇 Next tweet 👆 Start

NEW SERVICE: Amazon Aurora zero-ETL integration with Amazon Redshift - available in preview - this is going to be HUGE #reinvent

Tweet 43/145 👇 Next tweet 👆 Start

call back from 5m ago, here are the details on the OpenSearch #serverless preview: https://aws.amazon.com/about-aws/whats-new/2022/11/announcing-amazon-opensearch-serverless-preview/ #reinvent

Tweet 44/145 👇 Next tweet 👆 Start

back to ETL + data, Apache Spark is 3x faster on @awscloud. a lot of that ties back to the points Peter was making last night more on that keynote at https://markn.ca/2022/monday-night-live-with-peter-desantis/ #reinvent

Tweet 45/145 👇 Next tweet 👆 Start

NEW FEATURE: Amazon Redshift integration for Apache Spark - available today - another removal of barriers between services - lots of this is enabled by the @awscloud Global Infrastructure improvements #reinvent

Tweet 46/145 👇 Next tweet 👆 Start

moving to section 3, governance: #reinvent

Tweet 47/145 👇 Next tweet 👆 Start

good call out for the issues around #security and internal usability. need to strike the right balance…and yes, it can be done! #reinvent

Tweet 48/145 👇 Next tweet 👆 Start

governance may sound like a snoozer of a topic, but it’s important to making sure that you reach the ultimate goal of #security: make sure that what you build does what you intend, and ONLY what you intend #reinvent

Tweet 49/145 👇 Next tweet 👆 Start

NEW SERVICE: Amazon DataZone - a data management service to catalog, discover, share, and govern data - coming soon #reinvent

Tweet 50/145 👇 Next tweet 👆 Start

DataZone has APIs to enable integrations with 3rd party services and (hopefully) to automate some key pieces #reinvent

Tweet 51/145 👇 Next tweet 👆 Start

into the 4th section: insights #reinvent

Tweet 52/145 👇 Next tweet 👆 Start

shout out for my favourite @awscloud service: QuickSight! https://aws.amazon.com/quicksight/ they’ve launched a bunch of new features in the past few days #reinvent


Tweet 53/145 👇 Next tweet 👆 Start

NEW FEATURE: ML-powered forecasting with Q - available today - just ask and Q will forecast out based on your data #reinvent

Tweet 54/145 👇 Next tweet 👆 Start

NEW FEATURE: “Why” questions with Q - available today - literally ask “why” and Q will help bubble up the data that explains changes in trends - probably more important that the ML-powered forecasting #reinvent

Tweet 55/145 👇 Next tweet 👆 Start

@aselipsky summarizes the data story tl:dr > data is critical to your business. you need modern tools to acquire, generate, manage, analyze, and act on it. @awscloud continues to roll out new features/services to help with it all #reinvent

Tweet 56/145 👇 Next tweet 👆 Start

we’ve flipped 180° and are heading straight down now. talking about oceans. not sure where this one is going... #reinvent


Tweet 57/145 👇 Next tweet 👆 Start

@aselipsky walking through the innovations made to help humans explore the oceans in case you didn’t know, we can’t go very deep on our own. lots of deep sea thrillers have drilled that point home for me 🤣 #reinvent


Tweet 58/145 👇 Next tweet 👆 Start

tools like sonar have given humans the confidence to explore #reinvent

Tweet 59/145 👇 Next tweet 👆 Start

which is the statement @aselipsky uses to bridge to a #security push? #reinvent

Tweet 60/145 👇 Next tweet 👆 Start

@aselipsky calls out (rightly) that the #security bar @awscloud sets is a key reason for their success not sure why/how we pivoted from space > oceans > security, but given my focus, I’m happy to any main stage talk about about security! #reinvent

Tweet 61/145 👇 Next tweet 👆 Start

in case you were wondering (hopefully you weren’t), #security is another one of the pillars of the @awscloud Well-Architected Framework more on that at: https://docs.aws.amazon.com/wellarchitected/latest/security-pillar/welcome.html #reinvent

Tweet 62/145 👇 Next tweet 👆 Start

a quick overview of some of the @AWSSecurityInfo services on offer #reinvent

Tweet 63/145 👇 Next tweet 👆 Start

I know @aselipsky is talking about Amazon GuardDuty right now. but did you know that Amazon Inspector launch support for @awscloud Lambda last night?!?! I haven’t jumped in yet, but there are details at https://aws.amazon.com/blogs/aws/amazon-inspector-now-scans-aws-lambda-functions-for-vulnerabilities/ #reinvent

Tweet 64/145 👇 Next tweet 👆 Start

Tweet 65/145 👇 Next tweet 👆 Start

NEW FEATURE: Amazon GuardDuty added container runtime thread detection - coming soon #reinvent

Tweet 66/145 👇 Next tweet 👆 Start

more on GuardDuty in general: https://www.amazonaws.cn/en/guardduty/ #reinvent

Tweet 67/145 👇 Next tweet 👆 Start

nice shout out for the @awsmarketplace. here’s the direct link to the #security section: https://aws.amazon.com/marketplace/solutions/security tons of great solutions there #reinvent

Tweet 68/145 👇 Next tweet 👆 Start

to manage the data (nice callback there), @awscloud helped found the Open Cybersecurity Schema Framework (OCSF) details: https://github.com/ocsf/ #reinvent

Tweet 69/145 👇 Next tweet 👆 Start

NEW SERVICE: Amazon Security Lake - automatically collect, combine, and analyze security data - based on OCSF 👆 - preview soon #reinvent

Tweet 70/145 👇 Next tweet 👆 Start

❤️ the data sources right out of the gate: - VPC flow logs - CloudTrail logs - Route53 - GuardDuty - IAM Access Analyzer - key APN partners …then analyze with the @awscloud tools like Athena + QuickSight #reinvent

Tweet 71/145 👇 Next tweet 👆 Start

this is big @AWSSecurityInfo! blog post soon? #reinvent

Tweet 72/145 👇 Next tweet 👆 Start

also, too many of you are sleeping on the data lake + QuickSight combo. it’s crazy powerful #reinvent

Tweet 73/145 👇 Next tweet 👆 Start

on to Antarctica now... got it now, @aselipsky is using exploration of extreme environments to show how data and the right tools have made advancements possible …took me a few, I’ve only had 1 tea so far today ☕ #reinvent

Tweet 74/145 👇 Next tweet 👆 Start

in these extreme environments, “Good enough simply isn’t good enough” #reinvent

Tweet 75/145 👇 Next tweet 👆 Start

see, Holger got it faster than I did 🤣 https://twitter.com/holgermu/status/1597646324346019841 #reinvent

Tweet 76/145 👇 Next tweet 👆 Start

some key customer examples for deep long term investments paying off #reinvent


Tweet 77/145 👇 Next tweet 👆 Start

um, at some point, maybe we need a different way of selecting resources? #reinvent

Tweet 78/145 👇 Next tweet 👆 Start

@aselipsky is now talking about key @awscloud hardware innovations, especially silicon - AWS Nitro - Graviton3 #reinvent

Tweet 79/145 👇 Next tweet 👆 Start

more on Nitro: https://aws.amazon.com/ec2/nitro/ ( be sure to watch the talk on that page ) #reinvent

Tweet 80/145 👇 Next tweet 👆 Start

more on Graviton: https://aws.amazon.com/ec2/graviton/ #reinvent

Tweet 81/145 👇 Next tweet 👆 Start

... #reinvent

Tweet 82/145 👇 Next tweet 👆 Start

on to machine learning 🧠 now. recap of some of what Peter covered last night #reinvent


Tweet 83/145 👇 Next tweet 👆 Start

tl:dr > custom silicon and network improvements have made machine learning more performant combine it with @awscloud SageMaker and almost anyone can take advantage of these approaches #reinvent

Tweet 84/145 👇 Next tweet 👆 Start

more 🧠🧠🧠! #reinvent

Tweet 85/145 👇 Next tweet 👆 Start

while @aselipsky is queueing up HPC solutions and advancements, here’s the @AWSSecurityInfo post on the new Amazon Security Lake: https://aws.amazon.com/blogs/aws/preview-amazon-security-lake-a-purpose-built-customer-owned-data-lake-service/ #reinvent

Tweet 86/145 👇 Next tweet 👆 Start

back to keynote, HPC workloads are where a lot of things break. they need a ton of different performance and compsci advancements more on building these workloads in the High Performance Computing Lens for the AWS Well-Architected Framework: https://docs.aws.amazon.com/wellarchitected/latest/high-performance-computing-lens/welcome.html #reinvent

Tweet 87/145 👇 Next tweet 👆 Start

more HPC-specific instances for help 🚀 🚀 🚀 #reinvent

Tweet 88/145 👇 Next tweet 👆 Start

next customer up now... #reinvent

Tweet 89/145 👇 Next tweet 👆 Start

@NeikeCedrik from @Siemens. Cedrik is starting with space tourism #reinvent


Tweet 90/145 👇 Next tweet 👆 Start

the right tooling and data has enabled this type of solution. simple wasn’t possible before #reinvent

Tweet 91/145 👇 Next tweet 👆 Start

Cedrik pivoting to the core of why he’s on stage right now. @Siemens is one of those companies that has a tech everywhere. lots of critical components of the modern world come from their innovations #reivnent

Tweet 92/145 👇 Next tweet 👆 Start

key push for @Siemens: dream it ♾️ make it …but sustainably. ❤️ the focus on sustainability #reinvent

Tweet 93/145 👇 Next tweet 👆 Start

the collab between @awscloud and @Siemens is making key industrial software available to everyone #reinvent

Tweet 94/145 👇 Next tweet 👆 Start

surprising no one (hopefully at this point), OT [ operational technologies ] produce a ton of data too you need to be able to ingest, analyze, and draw insights from it in order to innovate #reinvent

Tweet 95/145 👇 Next tweet 👆 Start

keynote #protip: select a tea that holds up when cold. you’re going to forget to drink it while it’s hot because there is just too much cool new stuff! #reinvent

Tweet 96/145 👇 Next tweet 👆 Start

call back, more details on the new Amazon EC2 Inf2 instances (now in preview): https://aws.amazon.com/about-aws/whats-new/2022/11/aws-announces-amazon-ec2-inf2-instances-preview/ #reinvent

Tweet 97/145 👇 Next tweet 👆 Start

hadn’t heard of @Mendix before. seems interesting. check it out at https://t.co/z8vWOqk0B7 #reinvent


Tweet 98/145 👇 Next tweet 👆 Start

nice summary from @NeikeCedrik from @Siemens #reinvent

Tweet 99/145 👇 Next tweet 👆 Start

btw, @awscloud has a no-code/low-code offer as well. Honeycode has a very different focus thank Mendix but is probably more broadly applicable if you need a custom business app, start here: https://www.honeycode.aws/ #reinvent

Tweet 100/145 👇 Next tweet 👆 Start

..and if Honeycode doesn’t provide enough for you, move to @AWSAmplify Studio. more on that at https://aws.amazon.com/amplify/studio/ Amplify Studio is well worth digging into…after this week 😉 #reinvent

Tweet 101/145 👇 Next tweet 👆 Start

@aselipsky is on to simulations and the challenges around modelling #reinvent

Tweet 102/145 👇 Next tweet 👆 Start

shock: scale and data are problems here too! 🤣🤣🤣 #reinvent

Tweet 103/145 👇 Next tweet 👆 Start

NEW SERVICE: @awscloud SimSpace Weaver - run massive spatial simulations without managing infrastructure - available today - lets engineers focus on the problem #reinvent

Tweet 104/145 👇 Next tweet 👆 Start

this is a great time to remind you all that not all @awscloud services are targeted at you HOWEVER, you can almost always learn something from the use cases and solutions that IS applicable to what you’re working on #reinvent

Tweet 105/145 👇 Next tweet 👆 Start

“All you extremes” leads into @aselipsky conclusion for this keynote #reinvent

Tweet 106/145 👇 Next tweet 👆 Start

..but we’re taking a detour into the world of imagination first! #reinvent


Tweet 107/145 👇 Next tweet 👆 Start

🎨 🧠 #reinvent

Tweet 108/145 👇 Next tweet 👆 Start

imagination removes constraints #reinvent

Tweet 109/145 👇 Next tweet 👆 Start

another shout out for Rings of Power watch (later) at: https://t.co/kaILOWDPE6 #reinvent

Tweet 110/145 👇 Next tweet 👆 Start


Tweet 111/145 👇 Next tweet 👆 Start

technology is enabling some interesting collaboration around how we explore our imaginations #reinvent

Tweet 112/145 👇 Next tweet 👆 Start

key aspects of imagination #reinvent

Tweet 113/145 👇 Next tweet 👆 Start

I did not think this was going to pivot into call centres 🤦 #reinvent

Tweet 114/145 👇 Next tweet 👆 Start

very confident that @QuinnyPig’s thread has a comment along the lines of “Call centres, where imagination goes to ☠️” #reinvent

Tweet 115/145 👇 Next tweet 👆 Start

new stuff for Amazon Connect. not what I would link to imagination but hugely helpful for customers in this space thus the cheers from the crowd…or product team plant? 😉 #reinvent

Tweet 116/145 👇 Next tweet 👆 Start

now talking about supply chain complexity #reinvent

Tweet 117/145 👇 Next tweet 👆 Start

NEW SERVICE: AWS Supply Chain - cloud application that improves supply chain visibility and provides actionable insights - in preview #reinvent

Tweet 118/145 👇 Next tweet 👆 Start

oddly enough (for a @AWSEvents keynote), this is first demo of any kind for this session #reinvent

Tweet 119/145 👇 Next tweet 👆 Start

key term: “No up front licensing” #reinvent

Tweet 120/145 👇 Next tweet 👆 Start

call back, more on AWS SimSpace Weaver at https://aws.amazon.com/blogs/aws/new-aws-simspace-weaver-build-large-scale-spatial-simulations-in-the-cloud/ * still not part of the Sim series of games 😔 #reinvent

Tweet 121/145 👇 Next tweet 👆 Start

NEW SERVICE: AWS Clean Rooms - analyze and collaborate on datasets with business partners without revealing the underlying data - preview coming soon #reinvent

Tweet 122/145 👇 Next tweet 👆 Start

very curious about this one. feels like (only feels, no blog post up yet) this automates & simplifies a lot of the things that customers were having to build by hand…and lots of mistakes have been made given the complexities this sounds like a very welcome new offer #reinvent

Tweet 123/145 👇 Next tweet 👆 Start

another thing we need more info on, Identity Resolution #reinvent

Tweet 124/145 👇 Next tweet 👆 Start

next customer speaker up now, Liz Homans from Lyell #reinvent

Tweet 125/145 👇 Next tweet 👆 Start

topic is cancer research. tough topic, but one where data makes a massive impact on healthcare outcomes #reinvent


Tweet 126/145 👇 Next tweet 👆 Start

more on Lyell at https://lyell.com/ #reinvent

Tweet 127/145 👇 Next tweet 👆 Start

Tweet 128/145 👇 Next tweet 👆 Start

the advancements in biotech in the past decade is mind-blowing. tons of amazing things happening and a lot of tech powering it all #reinvent

Tweet 129/145 👇 Next tweet 👆 Start

lots of complexity in the process/workflow. this is a concrete example of how data and tooling make a real business (and healthcare) impact #reinvent

Tweet 130/145 👇 Next tweet 👆 Start

btw, a huge part of bio research is based on shared data. if you weren’t already aware, @awscloud hosts a registry of open data amazing resources up at https://aws.amazon.com/quickstart/biotech-blueprint/biotech-blueprint/ #reinvent

Tweet 131/145 👇 Next tweet 👆 Start

💯 @IanMmmm. we need more stories like this. even when the results aren’t raging successes…though this one is trend up and super promising https://twitter.com/IanMmmm/status/1597658004354400256 #reinvent

Tweet 132/145 👇 Next tweet 👆 Start

remember, it’s not just the tech but how you use it. great call out from Tim here: https://twitter.com/tcrawford/status/1597658667628736512 #reinvent

Tweet 133/145 👇 Next tweet 👆 Start

inspiring talk from Liz. awesome to see the medical advancements and research #reinvent

Tweet 134/145 👇 Next tweet 👆 Start

@aselipsky back up calling out some of the @awscloud health offerings more details at: https://aws.amazon.com/health/ #reinvent

Tweet 135/145 👇 Next tweet 👆 Start

“omics” #reinvent

Tweet 136/145 👇 Next tweet 👆 Start

NEW SERVICE: Amazon Omics - store, query, analyze, and generate insights from genomic and other comics data #reinvent

Tweet 137/145 👇 Next tweet 👆 Start

hopefully they talked to Lynn Langit when building this out. see some of Lynn’s work at https://lynnlangit.com/ she’s done a ton of amazing work helping make biotech/bio-research more accessible in the cloud #reinvent

Tweet 138/145 👇 Next tweet 👆 Start

pivoting to retail now, “Just Walk Out” technology by Amazon #reinvent

Tweet 139/145 👇 Next tweet 👆 Start

I tried this once. it worked like a charm and freaked me out! amazing set of technologies #reinvent

Tweet 140/145 👇 Next tweet 👆 Start

hmmm, “Amazon One” details: https://one.amazon.com/ * will reserve judgement #reinvent


Tweet 141/145 👇 Next tweet 👆 Start

Tweet 142/145 👇 Next tweet 👆 Start

@aselipsky wrapping things up now… hitting on the transformation theme. how @awscloud enables innovation & change through technology & helping you change how you use it all #reinvent


Tweet 143/145 👇 Next tweet 👆 Start

solid keynote from @aselipsky lots of announcements, cool stories, interesting themes that should get your 🧠 moving to start the day! #reinvent

Tweet 144/145 👇 Next tweet 👆 Start

remember to give yourselves time to move from session to session, especially from property to property. it always takes longer that you expect more tips in my #reinvent guide at https://acloudguru.com/blog/business/the-ultimate-guide-to-aws-reinvent-2022

Tweet 145/145 👇 Next tweet 👆 Start

…now off to code/explore the new features and services! /🧵

]]>
https://markn.ca/2022/adam-selipsky-keynote-play-by-play/ 67f6bbeaaf961b0001443261 Tue, 29 Nov 2022 09:00:00 -0500
<![CDATA[ The Five Most Interesting AWS (p)re:Invent Announcements for Cloud Security ]]> Want to share with others? Formatting issues in your reader? This post is available online, The Five Most Interesting AWS (p)re:Invent Announcements for Cloud Security

At re:Invent or attending remotely? Check out my “Ultimate Guide to AWS re:Invent 2022” post for some tips and tricks to get the most out of the show.

Every year, AWS launches a lot of new features and functionality leading up to and during AWS re:Invent.

As we kick off day one of this year’s show, here are my top five cloud security-related announcements for pre:Invent.

1. More Flexibility Administering AWS Organizations

AWS Organizations is the only thing that keeps me sane when managing all of my AWS accounts. I have a few personal accounts, but it’s enough to see the benefits of the central management through AWS Organizations.

Multiple that challenge/relieve by a few hundred and you’ll quickly start to grasp the challenge of most businesses.

An AWS account is a wonderful, free security boundary. You should be using a lot of them.

This latest feature in AWS Organizations makes it easier to delegate administrative access. You can now delegate policy management to specific member accounts as needed.

This should make things a lot easier and help you maintain separation of duties within your security practice.

2. Amazon CodeWhisperer Gets Much Needed Identity Controls

As is the case with any new AWS service, Amazon CodeWhisperer has been steadily improving since its announcement.

It’s getting to the point where more and more builders are going to want to try it out. That raises some interesting questions within your organization. Questions that are well worth debating.

See the discussions and posts around GitHub CoPilot for more.

This latest feature release allows you enable CodeWhisperer within your Single Sign-On (SSO) authentication systems. They’ve also added the ability to deliver this service to users that don’t have an AWS account via AWS Builder ID.

These are much needed to controls to help you enable builders within your organization safely.

3. A Safety Net For Log Data

“I would never log sensitive information”, said the developer about to inevitably 🤦.

It happens. We’ve all done it at some point.

This new feature from Amazon CloudWatch Logs uses a ton of pattern matching and machine learning in order to find any sensitive data that just happen to make it into your logs.

Once found, the service will automatically mask the data based on the policy you configure.

IAM policies dictate who can get the unmasked data with a specialize query via CloudWatch Logs.

I love features like this. There’s a minimal impact on workflow, but a huge boost to your security posture.

4. Watch Across Accounts…Finally

Sticking with Amazon CloudWatch, you can now (finally) search analyze, and correlate telemetry accounts accounts!

Dubbed cross-account observability, this feature follows the model of a lot of the AWS Security Services (like AWS Security Hub).

You can declare an AWS account a monitoring account and connect other accounts (source accounts) to view their data.

This integrates with AWS Organizations and IAM to give you a ton of flexibility right out of the gate.

Better still, no extra charges for logs or metrics. Tracing does have additional charges cross-account though.

5. AWS Backup Matures

A trifecta of improvements from AWS Backup. And yes, that’s an actual service name.

Side note, the most amazing AWS service name hands-down is: AWS Managed Services. Which expands to Amazon Web Services Managed Services the service 👨‍🍳

AWS Backup now:

  1. Offers delegation of organization-wide administration
  2. Adds legal holds for extended data retention
  3. Provides application-aware data protection for AWS CloudFormation stacks

Each of these helps integrate AWS Backup into your cloud environment. Backups are a critical part of resiliency and anything that makes that process easier to manage (and test!) is a welcome addition.

More To Come…

These are just a few of the announcements from the pre:Invent build up. I expect more security announcements during the week.

Remember, with few exceptions, these announcements are usually laser focused on solving a specific problems. We’re at the point now where I don’t expect too many completely new services…though I’m happy to see new ones launch!

Realistically, every new feature that makes it easier to implement key features of a security practice are a welcome addition.

In addition to these features, AWS announced the AWS Digital Sovereignty Pledge.

This is a clear statement of how your data moves in the AWS Cloud and where it is stored. It’s worth reading through it to understand what AWS has been building for the past 15+ years. None of this happened overnight, but where the state of security is the cloud is now is a very good place.

]]>
https://markn.ca/2022/the-five-most-interesting-aws-p-re-invent-announcements-for-cloud-security/ 67f6bbeaaf961b0001443260 Mon, 28 Nov 2022 09:00:00 -0500
<![CDATA[ New Features That Will Help You Build Better From Day One at AWS re:Invent ]]> Want to share with others? Formatting issues in your reader? This post is available online, New Features That Will Help You Build Better From Day One at AWS re:Invent

At re:Invent or attending remotely? Check out my “Ultimate Guide to AWS re:Invent 2022” post for some tips and tricks to get the most out of the show.

You’ve probably read it in the guide 👆 or heard me saying it a bunch in person or on Twitter, AWS pushes out a lot of updates during AWS re:Invent.

When I shared this thread 👇 on Twitter just before 2pm eastern, AWS had already published 52 different updates. WTF?!? That’s crazy. Good crazy, but still crazy.

More on the way for sure…

Twitter Thread

Tweet 1/10 👇 Next tweet

a few notable, new @awscloud announcements so far today from #reinvent 👇 /cc @AWSEvents /1

Tweet 2/10 👇 Next tweet 👆 Start

Amazon S3 multi-region access points get new functionality that allows you to shift data access requests to different regions as things hit the fan #reinvent https://aws.amazon.com/blogs/aws/new-failover-controls-for-amazon-s3-multi-region-access-points/ /2 #reinvent

Tweet 3/10 👇 Next tweet 👆 Start

GAME CHANGER*: @awscloud Config _finally_ allows for proactive rules that can be run BEFORE spinning something up to catch issues * changes the game in that we can all remove a bunch of Lambda/EventBridge stuff now https://aws.amazon.com/blogs/aws/new-aws-config-rules-now-support-proactive-compliance/ /3 #reinvent

Tweet 4/10 👇 Next tweet 👆 Start

@awscloud Glue increments it's inexplicable version number to 4.0, brining a bunch of new features & data formats along with it headline should've been: "AWS Glue out of the blue with features new to you" https://aws.amazon.com/blogs/aws/new-aws-glue-4-0-new-and-updated-engines-more-data-formats-and-more/ /4 #reinvent

Tweet 5/10 👇 Next tweet 👆 Start

@awscloud Wickr finally launches after the acquisition in 2021 e2e enterprise messaging feels like a better fit than the consumer facing version that is being retired https://aws.amazon.com/blogs/aws/aws-wickr-a-secure-end-to-end-encrypted-communication-service-for-enterprises-with-auditing-and-regulatory-requirements/ /5 #reinvent

Tweet 6/10 👇 Next tweet 👆 Start

AWS Control Tower launches a preview of comprehensive controls management honestly, there's so much stuff in Control Tower, I get lost trying to sort it all out tl:dr: it's got more stuff now. use it to help keep your accounts standardized https://aws.amazon.com/blogs/aws/new-for-aws-control-tower-comprehensive-controls-management-preview/ /6 #reinvent

Tweet 7/10 👇 Next tweet 👆 Start

@awsmarketplace for Containers can now deploy directly into an @awscloud EKS Cluster most ppl assumed this was possible (if they knew the marketplace existed) already. it wasn't it is now. I consider this a fix, not a launch https://aws.amazon.com/blogs/aws/new-aws-marketplace-for-containers-now-supports-direct-deployment-to-amazon-eks-clusters/ /7 #reinvent

Tweet 8/10 👇 Next tweet 👆 Start

not often you see a solution get prominent billing, but here's a cool one. this post 👇 describes how to use @awslambda as an endpoint for your ML 🧠 experimentation https://aws.amazon.com/blogs/machine-learning/deploy-an-mlops-solution-that-hosts-your-model-endpoints-in-aws-lambda/ /8 #reinvent

Tweet 9/10 👇 Next tweet 👆 Start

the @awscloud Glue team continues to deliver some great features. you can now launch @raydistributed jobs from the service still 🤦 that the team continues to miss amazing headline opportunities... https://aws.amazon.com/blogs/big-data/introducing-aws-glue-for-ray-scaling-your-data-integration-workloads-using-python/ /9 #reinvent

Tweet 10/10 👇 Next tweet 👆 Start

last one to call out for now @awscloud RDS gets blue/green deployments for Aurora with MySQL, RDS for MySQl, and RDS for MariaDB a couple clicks to safely deploy changes? yes, please https://aws.amazon.com/about-aws/whats-new/2022/11/amazon-rds-blue-green-deployments-safer-simpler-faster-updates/ /🧵 #reinvent

]]>
https://markn.ca/2022/new-features-that-will-help-you-build-better-from-day-one-at-aws-re-invent/ 67f6bbeaaf961b000144325f Mon, 28 Nov 2022 09:00:00 -0500
<![CDATA[ Monday Night Live With Peter DeSantis ]]> Want to share with others? Formatting issues in your reader? This post is available online, Monday Night Live With Peter DeSantis

At re:Invent or attending remotely? Check out my “Ultimate Guide to AWS re:Invent 2022” post for some tips and tricks to get the most out of the show.

Monday Night Live with Peter DeSantis is always a fantastic talk. Peter talks us behinds the scenes of AWS and shows how various technical improvements are enabling the features and functionality that we know and love.

I live tweeted the keynote. Frustratingly in a split thread, but here are both parts…

First Twitter Thread 🧵

Tweet 1/3 👇 Next tweet

here we go! Monday Night Live with Peter DeSantis is about to kick off at @awscloud #reinvent 2022! a 🧵👇 (/cc @AWSEvents)

Tweet 2/3 👇 Next tweet 👆 Start

@awscloud @AWSEvents I love how much fun Peter has with this keynote! #reinvent

Tweet 3/3 👇 Next tweet 👆 Start

Peter reminds everyone that this keynote is all about "how" @awscloud does things. lots of behind the scenes info in this one.. #reinvent

Second Twitter Thread 🧵

Tweet 1/71 👇 Next tweet

big focus on performance tonight. Peter reminds us it's not all about what you can see "Great performance is the result of innovation from the ground up and investing over time" #reinvent

Tweet 2/71 👇 Next tweet 👆 Start

starting with a dive into @awscloud Nitro... more on Nitro at https://aws.amazon.com/ec2/nitro/ #reinvent

Tweet 3/71 👇 Next tweet 👆 Start

here’s a great talk from Abby Fuller on the technical details of AWS Nitro: https://www.youtube.com/watch?v=e1_UJTgyFqM&feature=youtu.be #reinvent

Tweet 4/71 👇 Next tweet 👆 Start

Peter announces a new version of Nitro (v5), with big gains behind the scenes. continued innovation behind the scenes from @awscloud here #reinvent


Tweet 5/71 👇 Next tweet 👆 Start

NEW INSTANCE TYPE: C7gn uses the new Nitro v5 chip under the hood. lots of benefits. tip of the iceberg here #reinvent

Tweet 6/71 👇 Next tweet 👆 Start

NEW CPU: Graviton3E custom tuned Graviton3 silicon. lots of benefits for the targeted use cases #reinvent

Tweet 7/71 👇 Next tweet 👆 Start

NEW INSTANCE TYPE (coming soon): HPC7g …combines the Graviton3E + Nitro v5 for some big boosts for HPC applications #reinvent

Tweet 8/71 👇 Next tweet 👆 Start

not sure I’m digging the graphic style for these slides... #reinvent

Tweet 9/71 👇 Next tweet 👆 Start

typography with Amazon Ember is on point though. nice and clean. super clear. great typeface #reinvent

Tweet 10/71 👇 Next tweet 👆 Start

back to the tech, here’s a great summary of the new instance types just announce from @jeffbarr: https://aws.amazon.com/blogs/aws/new-amazon-ec2-instance-types-in-the-works-c7gn-r7iz-and-hpc7g/ #reinvent

Tweet 11/71 👇 Next tweet 👆 Start

btw, more on the Graviton processor at https://aws.amazon.com/ec2/graviton/ #reinvent

Tweet 12/71 👇 Next tweet 👆 Start

Peter has moved on to how the @awscloud Global Infrastructure is designed and built specifically talking about SRD (scalable reliable datagram) more on that at: https://aws.amazon.com/blogs/hpc/in-the-search-for-performance-theres-more-than-one-way-to-build-a-network/ #reinvent

Tweet 13/71 👇 Next tweet 👆 Start

more on the @awscloud global infrastructure at https://aws.amazon.com/about-aws/global-infrastructure/ #reinvent

Tweet 14/71 👇 Next tweet 👆 Start

Peter is giving a great high level overview of TCP as a protocol tl:dr it works great, but focuses on “getting there” vs. performance at @awscloud scale, they need something more efficient and focused on hyper scale issues #reinvent


Tweet 15/71 👇 Next tweet 👆 Start

key benefits of SRD on the @awscloud network: - multi-pathing - retries in microseconds - runs on nitro (dedicated hardware) #reinvent

Tweet 16/71 👇 Next tweet 👆 Start

remember, @awscloud runs at a completely different scale. very few companies run at this size. it’s a completely different set of problems, requiring completely different solutions #reinvent

Tweet 17/71 👇 Next tweet 👆 Start

SRD is helping deliver better performance for Amazon EBS, especially for “tail latency” …average latency doesn’t matter if you just need the data! #reinvent

Tweet 18/71 👇 Next tweet 👆 Start

teal line is SRD performance. big improvement overall, but massive in the edge cases …btw, all new EBS io2 volumes will get this performance boost in the new year (stay tuned, they are just saying “coming soon") #reinvent


Tweet 19/71 👇 Next tweet 👆 Start

NEW LAUNCH: ENA Express, brings SRD to ENA…available today! more details on ENA (basic, not express): https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/enhanced-networking-ena.html #reinvent

Tweet 20/71 👇 Next tweet 👆 Start

here’s the SRD boost for ENA with ENA Express (needs to be enabled on your ENAs) #reinvent

Tweet 21/71 👇 Next tweet 👆 Start

lots of improvements backed by the move to SRD in the @awscloud network #reinvent

Tweet 22/71 👇 Next tweet 👆 Start

“A veritable hoedown of machine learning”, Peter DeSantis 🤦🤦🤦

Tweet 23/71 👇 Next tweet 👆 Start

oh Peter…. #reinvent

Tweet 24/71 👇 Next tweet 👆 Start

this graphic redeems part of the hoedown comment… would have been better if he drove it out on stage 😉 #reinvent

Tweet 25/71 👇 Next tweet 👆 Start

gist of this section: 🧠 machine learning models are getting MASSIVE they need more performance (processing, storage, network, etc.) in order to train properly. @awscloud innovations in performance engineering like SRD are helping drive these advances #reinvent


Tweet 26/71 👇 Next tweet 👆 Start

here are the details on the @awscloud Trn1 instance type that Peter referenced: https://aws.amazon.com/ec2/instance-types/trn1/ #reinvent

Tweet 27/71 👇 Next tweet 👆 Start

while they make the point, graphs without units and numbers are tough for me to look at that said, numbers and more specifics would actual make these slides weaker and muddle the point Peter is making #reinvent

Tweet 28/71 👇 Next tweet 👆 Start

“Just as a refresher. Stochastic rounding is probabilistic rounding”, Peter #reinvent

Tweet 29/71 👇 Next tweet 👆 Start

why is that important 👆? it helps train the more faster with less loss. @awscloud accomplishes this with hardware acceleration in the Trainium silicon more on that chip at https://aws.amazon.com/machine-learning/trainium/ #reinvent

Tweet 30/71 👇 Next tweet 👆 Start

also, here’s a mathematical primer on stochastic rounding: https://nhigham.com/2020/07/07/what-is-stochastic-rounding/ you know, because MATH! 🤣 #reinvent

Tweet 31/71 👇 Next tweet 👆 Start

the tl:dr of this section is that @awscloud has been focusing on a lot of deeply interesting (to me at least!) performance engineering problems so that we can build & train ml 🧠 models faster and more accurately #reinvent

Tweet 32/71 👇 Next tweet 👆 Start

how else would we get fun/weird avatar pics in different styles? 🤣🤣🤣 #reinvent


Tweet 33/71 👇 Next tweet 👆 Start

Peter is currently giving a great explanation of how to scale out a workload across multiple processors. I can’t explain it in 280 character chunks 🤦 basically: many hands make light work? #reinvent

Tweet 34/71 👇 Next tweet 👆 Start

you’re going to have to watch this segment for yourself. it starts at 35m into this keynote with this slide 👇 #reinvent

Tweet 35/71 👇 Next tweet 👆 Start

Peter brings this back home using a Rings of Power reference. btw, the show is very much worth watching https://t.co/kaILOWDPE6 #reinvent

Tweet 36/71 👇 Next tweet 👆 Start

lots of work to average out the results, but the “ring of rings” works much faster than “one ring” …as long as you don’t give 9 to the race of man, 3 to the Elves, 7 for the Dwarves, and one to Sauron 🤦 #reinvent


Tweet 37/71 👇 Next tweet 👆 Start

new instance type coming soon to help speed things up even more: Trn1n - faster networking - faster training #reinvent

Tweet 38/71 👇 Next tweet 👆 Start

Jock Clear up now talking about the technical complexity of F1 racing more details on @awscloud + F1 at https://aws.amazon.com/sports/f1/ #reinvent

Tweet 39/71 👇 Next tweet 👆 Start

three key aspects of making zoom-y cars zoom faster... (somewhere @mosescj58 just felt a chill 🤣) #reinvent

Tweet 40/71 👇 Next tweet 👆 Start

with @awscloud, Jock and the team built a virtual ground speed sensor it’s an AI/ML tool that provides more accurate data faster…and more importantly with less weight …would love to see more technical details on that one #reinvent

Tweet 41/71 👇 Next tweet 👆 Start

btw, @QuinnyPig is also live tweeting this keynote. honestly, probably with a lot more—and funnier—jokes check out his thread at https://twitter.com/QuinnyPig/status/1597430775330537472?s=20&t=reKJgcbkR9LjU2gLMZeRXg #reinvent

Tweet 42/71 👇 Next tweet 👆 Start

Jock continues to lay out the challenges that F1 teams face outside of the race and the onslaught of challenges within a race lots of engineering challenges and trade offs… #reinvent



Tweet 43/71 👇 Next tweet 👆 Start

I’m not a car person (see the previous “zoom-y” comment), but I do love engineering challenges. lots of crazy ones here Jock is constantly calling out the sheer number of decisions the team needs to make. they need data & analysis to make those decisions #reinvent

Tweet 44/71 👇 Next tweet 👆 Start

they are launching an app with a bunch of race/interview content …was hoping for an engineering data app like the real time MLB analysis: https://aws.amazon.com/blogs/machine-learning/calculating-new-stats-in-major-league-baseball-with-amazon-sagemaker/ ..it’s not that, but I’m sure F1 fans will enjoy it #reinvent

Tweet 45/71 👇 Next tweet 👆 Start

Peter is back up now. new topic: #serverless computing #reinvent

Tweet 46/71 👇 Next tweet 👆 Start

“Behind me you can see a youthful @Werner announcing @awscloud Lambda”, Peter 😬🤣 #reinvent

Tweet 47/71 👇 Next tweet 👆 Start

Lambda has grown a LOT since it’s launch in 2014 thanks again @timallenwagner for setting us on this path! #reinvent

Tweet 48/71 👇 Next tweet 👆 Start

Peter is diving into the technical details and some of the performance engineering that goes into @awscloud Lambda in order to reach this scale... #reinvent

Tweet 49/71 👇 Next tweet 👆 Start

if you are interested in not only #serverless compute, but the whole concept. check out https://serverlessland.com/ #reinvent

Tweet 50/71 👇 Next tweet 👆 Start

#reinvent

Tweet 51/71 👇 Next tweet 👆 Start

Peter using a castle 🏰 analogy for virtual machines. key point: small number of access points. built for defence #reinvent

Tweet 52/71 👇 Next tweet 👆 Start

“Mostly secure isn’t good enough”, Peter #reinvent

Tweet 53/71 👇 Next tweet 👆 Start

#reinvent

Tweet 54/71 👇 Next tweet 👆 Start

“At @awscloud, we always use an isolated virtual machine for customer compute workloads”, Peter >> thus Nitro! #reinvent

Tweet 55/71 👇 Next tweet 👆 Start

back to Lambda… think of it as a cache. a big pool of compute #reinvent

Tweet 56/71 👇 Next tweet 👆 Start

each slot was specific to a customer function. new function? new virtual machine if a VM is up for the customer function, great. if not, initialize a new instance (empty & waiting) to handle it >> a/k/a cold starts …it works, but there’s room for improvement #reinvent

Tweet 57/71 👇 Next tweet 👆 Start

more graphs #reinvent

Tweet 58/71 👇 Next tweet 👆 Start

so cold starts are a cache miss. that happens, caching isn’t perfect #reinvent

Tweet 59/71 👇 Next tweet 👆 Start

obvious solution: bigger cache on the @awscloud backend that’s more expensive and less efficient enter Firecracker #reinvent

Tweet 60/71 👇 Next tweet 👆 Start

Tweet 61/71 👇 Next tweet 👆 Start

moving to Firecrack provides more efficient use of the existing hardware. it also spins up faster, allowing things to sit in the cache longer! #reinvent

Tweet 62/71 👇 Next tweet 👆 Start

results are Firecracker, bigger arrow, less bump numbers would be helpful here. Peter mentioned one but I’m not sure I heard it right assumption: things got better with the move to Firecracker #reinvent

Tweet 63/71 👇 Next tweet 👆 Start

even with these improvements, you’ll see still cache misses (a/k/a cold starts) need to make them faster. where is that time going? for Java devs? a lot of it is in initialization #reinvent

Tweet 64/71 👇 Next tweet 👆 Start

solution is to save the initialized start. think opening up your MacBook’s lid and working vs. turning it on from completely off #reinvent

Tweet 65/71 👇 Next tweet 👆 Start

this feature is called AWS Lambda SnapStart and it’s available today! bye bye cold starts…at least most of them #reinvent

Tweet 66/71 👇 Next tweet 👆 Start

places where SnapStart _won’t_ work/help #1: - some cryptography use cases where uniqueness is required - can adjust with code changes #reinvent #serverless

Tweet 67/71 👇 Next tweet 👆 Start

interesting division of snapshot-ing here. separating out the uniqueness to improve performance even further #reinvent

Tweet 68/71 👇 Next tweet 👆 Start

last piece of the puzzle, predictive snapshot loading get the pieces needed to start the function up and running as quickly as possible…before it’s even asked for #reinvent

Tweet 69/71 👇 Next tweet 👆 Start

pumped to see the benefits of @awscloud Lambda SnapStat. love that I really don’t have to do anything to get those benefits #reinvent #serverless

Tweet 70/71 👇 Next tweet 👆 Start

Peter signs off with some great session recommendations for performance engineering #reinvent

Tweet 71/71 👇 Next tweet 👆 Start

great keynote from Peter DeSantis.hoping we’re going to see some @AmazonScience or @awscloud papers on these innovations soon lots of great advancements & engineering work to deliver more features & functionality to builders …more tomorrow as #reinvent kicks into high gear!

]]>
https://markn.ca/2022/monday-night-live-with-peter-desantis/ 67f6bbeaaf961b000144325e Mon, 28 Nov 2022 09:00:00 -0500
<![CDATA[ Mastodon's Promising Federated Approach Will Frustrate You More Than Twitter ]]> Want to share with others? Formatting issues in your reader? This post is available online, Mastodon's Promising Federated Approach Will Frustrate You More Than Twitter

I had a great chat Robyn Bresnahan on CBC Ottawa Morning on 08-Nov-2022 to try and explain Mastodon. Listen to our discussion 👇

Twitter is currently a dumpster fire heading over a cliff.

In what can only be described as a chaotic festival of irrational whimsy, the site has seen drastic content and technical changes in the past few weeks.

This has people looking for alternatives.

There aren’t any.

…at least there aren’t any other Twitter’s out there. There are other social media platforms that have made different decisions over time, build up different cultures, and deliver fundamentally different experiences.

Enter Mastodon.

Open Alternative

In 2016 Eugen Rochko formed the open source project and the organization of volunteers to help develop and promote it. Over time, that became Mastodon gGmbH, a non-profit registered in Germany.

The idea behind Mastodon is simple: a social media platform that centres around user choice.

With Twitter (and Facebook, Instagram, LinkedIn, etc.), there’s just “Twitter.” Everyone’s tweets are on the same platform and a series of algorithms help determine what content you see.

You can influence those algorithmic decisions by following different accounts, engaging with specific content, and using the platform more and more.

You can always go find specific content from accounts on Twitter, but you’ll have to work for it.

With Mastodon, those choices are far more explicit. There is no algorithm promoting content based on data analysis.

The Fediverse

There isn’t one “Mastodon” system. The network is made up of a number of servers. Each server is it’s own island. Those islands can

You—the user—select a server as your “home base.” This decision will influence your experience significantly.

Pick a server that has a theme or primary topic that interests you…or one of the many generic servers out there.

Once you’re set up on a server, you login and see…nothing.

This wall of nothingness is one of the biggest blockers for new users joining Mastodon. It’s also one of the systems biggest strengths.

Control What You See

As a Mastodon user, you can follow the content from almost any account on any server. If you choose to follow an account, you’re going to start to see their posts (or toots 🤦) on home timeline.

Over time, you will follow more and more accounts, slowly building out the timeline of content you see. You can also view the local timeline for the server (posts from everyone on that server) or the federated, which is a combination of other servers local timelines.

If you’re still looking for more content, you can search by hashtag (#), but not by the content of the post. That’s an important limitation and another place where users struggle as they move to this platform.

To summarize what’s available for content:

  • your home timeline with the posts of accounts you follow
  • your servers local timeline with the posts of the accounts on than server
  • your servers federated timeline with the all of posts of the servers that your server knows about

When you toot (post, it’s a post…🤦), accounts who follow you will see it. If one of those accounts boosts (essentially a share/retweet) that post, their followers will see it. It will also be added to the servers local timeline and any servers that have your server in their federated timeline.

Notice what’s missing? There is no algorithm promoting content or showing it to people to gauge their reactions.

The Gap

This is both an advantage and disadvantage for Mastodon. If you know the goals of the system, it makes sense.

You—the user—are in control of what you see.

This is also why there’s a very strong content warning culture within the platform.

If you think of Mastodon as somewhere between Twitter and a forum or chat platform like Discord, it makes a lot more sense.

If you are moving to Mastodon thinking it’s a Twitter replacement, you’re going to be frustrated. Very frustrated…and lonely.

Mastodon can help you maintain and build a community online. But it is its own unique animal. Keep that in mind as your explore and reach out.

References

]]>
https://markn.ca/2022/mastodons-promising-federated-approach-will-frustrate-you-more-than-twitter/ 67f6bbeaaf961b000144313c Fri, 25 Nov 2022 09:00:00 -0500
<![CDATA[ Has the EU Finally Made the U in USB-C Actually Stand for Universal? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Has the EU Finally Made the U in USB-C Actually Stand for Universal?

I spoke with Robyn Bresnahan on CBC Ottawa Morning on 06-Oct-2022 about the announcement.

Wrong Cable, Wrong Way

We all have that drawer or box of cables and chargers for different devices. Which charger goes with which device? Who knows. You’ll figure it out in five or six tries.

USB launched in 1996 with two connectors. The “A” rectangle we all associate with USB, the “B” square-ish end. Mini-A and mini-B followed in 1998. 2001 brought USB 2.0 with increased speeds and new connection options mini-AB, micro-A, micro-B, and micro-AB.

Each made sense in turn. They were smaller and better suited for phones and other portable devices.

A sampling of USB connector types

But they were the start of a very real problem. The “U” in USB quickly changed meaning from universal to ungainly.

The EU Puts Its Foot Down

The EU passed a revision to the Radio Equipment Directive that includes a couple small changes that will have a very real and very large impact.

The revision pass with a 602 to 13 vote (with 8 abstaining) and can be summarized as:

  • All common consumer electronic devices will use the USB-C connector for charging
  • …will use a harmonized fast charging technology
  • …will allow for the un-bundling the charger at time of sale
  • …will provide consumers with clear information about charging performance

The biggest and most immediate impact will be with Apple devices using the proprietary lightning connector, but this directive is broader than that.

Useful, But Time To Move On

As much frustration as some users are expressing about Apple’s lightning connector, it was a big win for users when introduced in 2012. Starting with the iPhone 5, iPod Nano, iPod Touch, and 4th generation iPad, all Apple devices and accessories would use one simple connector.

Named “Lightning” it provided the same speed as the USB 2.0 spec of the time, 480 Mbps. Lightning is a perfect marketing name. The new connector didn’t provide any transfer speed boosts and, in fact, added a layer that Apple controlled in direct the ecosystem around it’s devices.

For users, the new connector did solve a very real problem. It was—and is—very simple to actually plug in.

We’ve all had that frustration with USB-A connectors where you just can’t get it oriented in the correct direction. It often takes 3 tries to pick the right orientation from the 2 choices. Lightning works in either orientation.

Click…and you’re connected.

The ripple effect that standardizing the connector had was that the user could be confident that any accessory purchases would properly connect with any of these devices and their successors for the foreseeable future.

Immediately, charging became a lot easier.

Investing in a new charger was easier to justify when you knew it was going to work for a few years. Up until this, APple and others had a bad habit of changing connector types randomly. Each time that happened, you need to either buy adapters or new accessories.

Outdated, Outclassed

In 2014, the USB-C connector was finalized. It was formally adopted by the standard-setting body, International Electrotecnical Commission (IEC) in 2016.

This new connector type fixed the, “Which was does this connect?” problem is a small form factor and with enough capacity—pins—in the connector to allow for complex data transfers. It was, and still is, a well designed solution that solves most—if not all—physical connectivity issues.

While a bit more technically complex, this is a straight forward physical connection standard that has all of the pieces required to put the universal back in USB.

Most Android device vendors started switching over to the physical USB-C connector. Other electronics have slowing starting moving over as new versions hit the market.

It wasn’t until 2018, that Apple released it’s first non-laptop with a physical USB-C connection, the iPad Pro.

Physical Connector vs. Protocol

A quick aside, you’ll notice that I’ve been using the term “physical connector” and it’s variants throughout this post. That’s because the prootcol to run power and data over USB is different than the physical connectors.

The connectors impact which protocols can be run but not nearly as much as other factors. Fair warning, USB naming conventions are an absolutely disaster. I’ll spare you the history and tears. The easiest way to think of it is:

  1. USB 1.x (started at 1.5 Mbps and then was increased to 12 Mbps)
  2. USB 2.x (maximum speed of 480 Mbps)
  3. USB 5 Gbps (a/k/a USB 3.0)
  4. USB 10 Gbps (a/k/a USB 3.1)
  5. USB 20 Gbps (a/k/a USB 3.2)
  6. USB 40 Gbps (a/k/a USB 4.0)

As you move through the generations, each version can typically provide all of the features of the previous generations. Right now and for the foreseeable future, we’re using USB 5—40 Gbps.

This means that while physically two devices might connect (yay USB-C!), they may not be able to communicate fast enough to actually work. If you try to connect an external dock to your laptop, it might not have enough bandwidth to talk to all of the devices you connect to it.

Don’t even get me started on [Thunderbolt](https://en.wikipedia.org/wiki/Thunderbolt_(interface), which is another protocol that works over USB-C physical connectors but requires different device support and cables!

Power Up

Making this even more complicated is power delivery over USB-C. Thankfully, adding clarity here is part of the EU directive. USB-C is capable of delivering up to 240W of power. That should be enough to run a modern laptop, especially with efforts there to reduce power consumption.

The latest gaming laptop from Razor comes with a 230W power supply. That is pushing the limits of the USB-C spec, but it’s also the extreme.

The top end 16" MacBook Pro, for contrast, comes with a 160W adapter. There should be enough headroom in the USB-C spec for a while. And there might be the opportunity to increase the current limit without changing the physical connector.

A Win

The EU’s move is going to have worldwide implications. No company wants to make multiple versions of it’s product with slightly different connectors. The EU market has enough weight to push this change globally…and that’s a good thing.

USB-C physical connectors will simplify a lot of things for users. There will be some confusion over the speed and power capacity of the protocol used by various devices but that’s solvable with simple labelled and clear requirements.

While Apple was resistant to this move, they have been moving to USB-C connectors for more and more of their iPad line-up. They need the added speed and power for accessories. The delay helped them wring out more value from their investment and to start scaling up the supply chain required to deliver millions of units with USB-C.

Most people won’t really notice as this directive comes into effect. It’s a smart move whose impact will be realized when you look back in five years and say, “Oh, I remember that connector…haven’t used it in years.”

References

]]>
https://markn.ca/2022/has-the-eu-finally-made-the-u-in-usb-c-actually-stand-for-universal/ 67f6bbeaaf961b000144313b Sun, 09 Oct 2022 10:00:00 -0400
<![CDATA[ Why is it so hard to law enforcement to track down harassers? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Why is it so hard to law enforcement to track down harassers?

I spoke with Hallie Cotnam on CBC Ottawa Morning on 26-Aug-2022 about this issue.

The promise of the internet is that it can connect us all. It’s also a threat.

There are wonderful use cases of technology. Especially over the past few years with various lockdowns and travel restrictions. Being able to work remotely, connected with friends and family, and to stay entertained and informed has been invaluable.

The negative stories range from frustration to outright horror. Recently, Canadian journalist Raisa Patel had an experience that borders on outright horror.

Online Harassment

Raisa shares the start of her story in this Twitter thread.

🧵Long thread, but a summary of the past day: Yesterday, @angelynsayshi, @_jennamoon & I were targeted in the latest violent, misogynistic, racist campaign against Canadian journalists. We have decided to post it without censoring anything. TW for violence, racism, sexual assault pic.twitter.com/Do8ndP526v— Raisa Patel (@R_SPatel) August 11, 2022

Making matters worse is that when Raisa turned to the police for help, bureaucracy and poor experiences kicked in…

My police reporting update is that I spent a total of four hours on hold with the Ottawa Police Service today across two different attempts. On one call I was not able to speak to anyone after 1.5 hours on the line. Same result after spending 2.5 hours waiting on another attempt.— Raisa Patel (@R_SPatel) August 12, 2022

This experience is what prompted my conversation with Hallie. Is this common? Why are these hurdles in place? Is there actually any point in reporting these types of crime to police?

Why I’m qualified to write about this issue? I did my graduate work in digital forensics and worked as an investigator for several years. I continue to research and apply digital forensics techniques in my work. While my focus isn’t online harassment, the technological aspects are the same.

The social impacts are quite different which is why I refer to other experts in that space down below.

Technical Breadcrumbs

To identify and then track down a suspect in a case like this, a technical trail must be followed.

Using Ms. Patel’s case as an example, we start with an email. From the screenshots posted, that email came from an email account with the provider Proton.

Email providers will have differing amounts of information on their account holders. Proton is a privacy-focused provider offering free and paid accounts. By design, they store a minimal amount of information about their users.

For a free account, only a username and password is required. Paid accounts require some level of billing information. There’s a near endless list of email providers out there. When a suspect is looking to abuse the system, Proton’s design doesn’t actually impact the case much. Other providers might have more information, but the odds are good that it’s false.

Why would a suspect put in their actual name when “Sam Samington” or another made up name would work just as well?

The victim already has the actual email, so what we’re looking for from the provider is an IP address or other information that might lead to the person behind the malicious account.

Assuming that information is available. The IP address leads us to the next step in the trail.

Misdirection Connection

If you’ve been on YouTube in the last year, you’ve probably seen an ad for virtual private network or VPN . While positioned as privacy-protecting and an easy way to get access to geo-locked content, what a VPN really does it route all of your internet requests through the providers servers.

It’s a misdirect.

In a cybercrime situation, that means the IP address linked to the account at the email provider probably belongs to a VPN provider. That’s another round of requests and hopefully some account information for our investigation. It’ll depend on the provider and information associated with the account if anything useful comes from this step.

Odds a good—in a bad way—that there’s only another IP address at this step…that might lead to an internet service provider or ISP.

At this (hopefully) final step, the investigation might actually lead to an account information with accurate information linking all of this activity to an actual individual.

Who, Me?

…maybe.

An ISP or mobile provider account is actually just a link to who paid for the connection to the internet. The trail we’ve compiled so far has linked from a the offending email to a VPN to an ISP to an account.

This may or may not link to a specific device. For a mobile account, the technical information can more easily be linked to a specific device. It’s done that way for a billing purposes.

For a home or residential internet connection, that will link to a router.

This is the device that connects to everything in the residence to the internet. If there are several or several dozen devices in the house, which one sent the email?

This is when the technical investigation needs to move to the forensic examination of the all of the potential devices. The hope here is evidence that is sufficient to link a person to the action.

Until that happens, you don’t know which person actually sent the email. If could be anyone with access to that connection…which could include more than just the people authorized to access that connection.

That lack of certainty makes charging someone and being successful in their prosecution very difficult.

Paperwork, Paperwork, and More Paperwork

We’ve followed a typical technical trail for cases like this.

It’s complicated, involves multiple systems, lots of opportunity for data to be lost, and requires a lot of technical expertise to properly follow this trail. An even higher level of expertise is required to follow the trail with enough rigour and process to testify with credibility in court.

And that’s where the other set of challenge lie; the law.

The internet connects our planet. That’s often just accepted but really comes to light in situations like this. Imagine for a second that each of these steps lands the investigation in a different country.

For Raisa, this is what’s happening.

The email was sent through the Proton service. This service is run by a company in Switzerland and they follow Swiss law. That includes extremely strong privacy protections for individuals and depending on the situation, the European General Data Protection Regulation (GDPR) could also apply .

Here’s a great call out of the Swiss data protections by data hosting provider Artmotion. That’s easier to dig through than the actual legal statutes.

In order to get whatever information Proton has about the suspect, Canadian law enforcement must make a request in Switzerland under Swiss land. IANAL, but the long and short of it is that this is another layer of paperwork and another set of standards to apply.

Generally, at each step in the technical trail the following questions must be answered;

  • Is what happened a crime in the country in question?
  • Have the required standards been met for law enforcement/court ordered action to be taken?
  • Are these sufficient resources in the country in question to address the issue?
  • Can/will law enforcement in the originating question work through the process?

In our scenario so far, there’s at least two (Canada and Switzerland) and most likely four jurisdictions involved. How did we get to five?

  1. The victim is in Canada
  2. The original email was sent from Switzerland
  3. A VPN provider in another country
  4. The ISP/mobile provider in yet another country
  5. The suspect most likely is in the same jurisdiction as the ISP/mobile provider

Numbers 3—5 are assumptions, but given the pattern in the cases I’ve seen over the years they are most likely true.

That’s a lot.

Lack of Resources

The technical issues and bureaucracy are not insurmountable. They require patient and commitment to navigate, but it can be done.

A bigger, over-arching issue is the lack of available resources. This is technical law enforcement work. That’s a skillset in high demand both from a recruiting and deployment perspective.

Every country has this challenge. Here are a sample set of reporting from Canada, the USA, and Ireland. Many more are just an online search away. No one has enough resources to address crimes like this.

There is a finite set of resources that can be deployed to help solve crimes with an online component. We need to have a discussion in our communities as to what those resources should be prioritized for.

Right now, we’re not.

Occasionally we talk about harassment and cyberbullying. Child endangerment comes up often, but often as a club to push through laws that weaken encryption and reduce everyone’s digital security. Not to actually address long term protections.

Cybercrimes with financial impacts are in the news frequently, but only a few times a year do we see any successful legal actions being taken. It’s not from a lack of desire or bad intentions. It’s a systematic issue that’s only being addressed in a fragments.

Are victims like Raisa Patel, Angelyn Francis, Jenna Moon, and countless others left by the way side?

Steps To Protect Yourself

No. There are steps you can take to help reduce your online risk and the potential impacts from issues like this.

These steps are better laid out by experts in this space like Leigh Honeywell. Leigh is the CEO of Tall Poppy. Tall Poppy offers a set of tools from an amazing team that help “stop online harassment from escalating to hacking.” Organizations can—and should—add this to their benefits package to help their staff be safe and secure online.

No, I don’t work for Tall Poppy but I’m a huge fan of their work. This is a critical issue and they’re making it easier for people to get help while building a sustainable business. That’s to be admired

If you are responding to harassment like this and in immediate crisis, I’ll refer to Tall Poppy’s advice;

For anyone in the US, UK, CA, or IE the crisis text line is available 24/7:\n\nUS: Text 'HOME' to 741741\nUK: Text 'SHOUT' to 85258\nCA: Text 'HOME' to 741741\nIE: Text 'HOME' to 50808\n\nFor workplace issues:\n\nText 'HELLO' to 510-674-1414 for support with workplace issues from Empower Work. Available 24/7.\n\nFor ppl experiencing image-based sexual abuse;\n\nCall the CCRI Crisis Helpline at 844-878-CCRI (2274). Available 24/7\n\nFor gamers and folks in the game industry:\n\nText 'SUPPORT' to 23368 to get emotional support from the Games and Online Harassment Hotline. Available 3pm-7pm Pacific.

From Tall Poppy’s site, available https://www.tallpoppy.com/resources

In you’re not in immediate crisis, you should always take screenshots and document everything that’s happening. This record can be invaluable during any of the possible process that follow.

There are several in-depth guides available freely online that list resources, apps, and allies available to help you. Here are the ones I’d recommend;

Each of these will help you understand your options at each step of the way. If you’re not dealing with harassment currently, these are a lot of preventative steps you can take to help reduce your risk.

Take the time to read through these guides and implement their advice.

Learn More

If you’re interested in learning more about these issues and the challenges in addressing them. These links will help;

Researching for this segment was frustrating. Both because of the rate at which online harassment happens and because it’s been hard to find reputable resources specifically for harassment. Especially on the law enforcement side.

There’s a lot out there aimed at cyberbullying education and prevention but not much for adults or about more serious crimes like harassment, hate speech, and direct threats made online.

This issue needs to be discussed out in the open. It impacts our communities and our friends. We need solutions that span technology, law enforcement, social media, and many more areas.

We need solutions that can have a real impact. We’ll only get there if we acknowledge the problem and more forward together.

]]>
https://markn.ca/2022/why-is-it-so-hard-to-law-enforcement-to-track-down-harassers/ 67f6bbeaaf961b000144313a Fri, 26 Aug 2022 10:00:00 -0400
<![CDATA[ The Ultimate Guide to AWS re:Invent 2022 ]]> Want to share with others? Formatting issues in your reader? This post is available online, The Ultimate Guide to AWS re:Invent 2022

Ping me, if you spot a problem or if something is missing @marknca.

As always, the event site is the ultimate source of truth (though I try to provide more context here). The site is available at https://reinvent.awsevents.com
Thank you to A Cloud Guru for cross-publishing this guide again this year. The continued support is always appreciated!

Index

The Goal

My goal with this guide is simple: help you get the most out of AWS re:Invent.

It started with just a few tips in the early days. As the show grew, and grew, and grew, so did the guide. An entire week in Las Vegas is tricky any time. At a conference with hundreds of sessions and with a mountain of new things to learn? It’s a real challenge.

I’ve been to a lot of conferences over the years and to every re:Invent (with the slight exception-ish of attending only virtually in 2021). The guide is my way of giving back to the community and helping myself to keep it all straight!

History

This is probably the longest running guide to AWS re:Invent. I’ve been writing this guide since 2015. The eighth version will follow closely to the layout of the last couple years as a lot of people have found it useful.

For nostalgia’s shake, here are the previous guides:

Code of Conduct

This is the most important part of the whole guide. Honestly. The code of conduct sets the baseline for community expectations. AWS re:Invent is all about learning and having a shared experience. The key to that is making sure that environment is inviting, safe, and supportive.

The AWS Community Codes of Conduct applies to both the physical and digital space surrounding AWS re:Invent…and to all other AWS events.

I would say that it’s all common sense and following the golden rule but with tens of thousands of people from around the world sharing the experience for the week, it’s best to call this out explicitly.

READ THE CODE OF CONDUCT AND LIVE BY IT.

If you encounter an issue or problem that runs counter to the code or if you in any way feel unsafe, please reach out for help. Amazon Security can be reached at [email protected] for live events. In addition, any one of the on-site staff or security can help resolve any issues.

No system is perfect but this is a great start at creating a safe, inclusive community at this fantastic event.

Who Am I?

I’m an AWS Community Hero, a long time AWS re:Invent attendee and a big fan of the show.

I teach a few courses over on the A Cloud Guru/Pluralsight platform (AWS Business Essentials, Introduction to the AWS Marketplace, and Mastering the AWS Well-Architected Framework), tweet regularly, and post a lot here on my site.

Health Measures

Any gathering in 2022 needs health measures in place to be successful. AWS has posted their requirements on the event site. As with everything, these measures may change as we get closer to the show.

The key aspects are:

  • Masks are not required for attendees
  • Hand sanitizing stations will be available throughout the event space

Science and recent history show that masking up is a very good idea in shared spaces. Yes, even if you are fully vaccinated. This requirement may change leading up to the event.

As of Monday, 08-Sep-2022, AWS has removed the vaccination requirement for this event. This is inline with updated guidance for the US Center for Disease Control (CDC)

If masking and other health measures are optional, please respect everyone’s individual choice…even if you don’t agree with it.

Remember the code of conduct? Respect is a massive part of it. Response to COVID-19 is a sensitive subject for some, please be aware of that.

Registration

Registration for AWS re:Invent 2022 is open now.

Full badges go for $1,799 USD. Virtual access (live streams for the keynotes and the leadership sessions) is free.

Register on the event site.

Hotels

This show is big enough that AWS actually calls the conference space a “campus.” Honestly, I don’t blame them. Here’s a look at the campus 👇

AWS re:Invent 2022 campus map

Current AWS re:Invent 2022 campus (via AWS)

When it comes to hotels, the key is to understand what you want from an experience point of view. If you want to be in the thick of the action, the yellow/amber properties are where you want to stay. These are locations where AWS is hosting the event itself.

The light blue properties are where AWS has negotiated room blocks and discounts. They also provide transportation between these properties and the locations where the event is happening.

If you’ve never been to Vegas, there isn’t really a “quiet” place listed here…with the possible exception of the Signature at MGM. This location is behind the MGM Grand and is a bit quieter than the rest as it’s only a hotel. No casino or theatre.

To learn more about each property, here are the direct links. Remember to book through the AWS re:Invent registration process (or afterwards through the event site) in order to get the discounted rates.

  • Venetian / Palazzo remains the center fo AWS re:Invent. This year it’ll host breakouts, AWS Certification exams, the lounge(s), Content Hub, the Expo, keynotes, leadership sessions, registration, self-paced labs, and SWAG
  • Caesars Forum for breakout content, a Content Hub, and meals
  • Encore for breakout content and bookable meeting space
  • Wynn has breakout content and meals
  • Mandalay Bay is hosting breakout content, a Content Hub, and meals
  • MGM Grand has breakout content, badge pickup, a Content Hub, and meals covered

Venues included in campus but not hosting events;

Mandalay Bay and the MGM Grand are the outliers when it comes to hosting content. Most of the action is down in the Venetian, Palazzo, Wynn, Encore, and Caesars Forum area. If you’re looking to reduce your walking times (if only slightly), that may be the best choice.

No matter where you choice to lay your head at the end of the day, you’re going to be moving between venues…a lot. That means there’s no wrong choice when it comes to hotel.

Making sure that you’ve got a room at a rate you can manage is the most important thing at this point.

Virtual Attendance

Not too much to say about attending virtually. This year’s show is back to an in-person focus which means that the bare minimum is available during the week remotely.

Given the ongoing and ever changing situation COVID-wise, if you aren’t comfortable or cannot attend in person, there isn’t really an option.

You can watch the keynotes and leadership sessions on the stream and follow along on social. That’s about it.

How to re:Invent

AWS knows re:Invent is a lot to wrap your head around. The past few years they have brought us the show, “How to re:Invent.”

This show helps break down specific aspects of the event. It’s definitely worth watching.

All six episodes are up for viewing now on the event site.

  • Episode 1 covers booking your hotel and gives a general preview
  • Episode 2 talks about the campus, getting around, and how to get the most out of your stay
  • Episode 3 is all about connecting with the community
  • Episode 4 dives into the keynotes, leadership sessions, and some must see breakouts
  • Episode 5 looks at the virtual experience for those that won’t be in Las Vegas
  • In Episode 6 Annie and Kelley are joined by Jeff Barr, Chief Evangelist AWS to talk about onsite networking and some tips from a re:Invent veteran

Reserved Seating

Reserved seating opened on 11-Oct-2022.

In-person attendees will want to take advantage of the reserved seating system in place for this years event. It opened Tuesday, 11-Oct-2022 and allows you to lock-in a seat in your preferred sessions…assuming you can get a spot.

Fingers crossed 🤞 that the reservation system works well this year. It’s always been a pain to deal with. You might not think it’s an issue but the most popular sessions can fill up very quickly when reserved seating opens up and any issues with the system can reduce your overall experience.

The good news? Any issues that pop up are quickly fixed and after the initial rush, it’s really a non-issue.

Session times are mainly scheduled now, but more will be added as we get closer to the show. Remember, even with reserved seating, AWS usually holds back some seating for walk ups on the day.

Also, all breakout sessions (not chalk talks, workshops, or other session types) are recorded and posted to YouTube shortly after re:Invent.

Keep that in mind as you build out your week.

Mobile App

It’s doesn’t suck now. That’s about all you need to know. 🤣

For years the mobile app was super frustrating. Now it’s improved to the point where it’s a handy companion for your week. Find the latest sessions, maps, timing of transportation, ways to connect with the community, and more.

Make sure you’ve downloaded it (iOS / Android) and set it up before heading to the event.

Agenda

The official agenda is up on the event site. It’s a handy way to see the high level flow of what happens throughout the week.

Sunday kicks things off. It’s a great day to get oriented and get your badge and swag before the lines get busy. The Help Desks and AWS Training and Certification Information Booth are both open at noon. The only official event is the Midnight Madness. That runs 10:00pm to midnight.

Monday is jam packed with content. Everything is open logistics-wise. Bootcamps and breakout sessions start in the morning. Of note, the Welcome Reception runs from 4:00pm to 7:00pm in The Venetian.

Tuesday, Wednesday, and Thursday are “standard” days, if that’s even a thing at this show. Content all day and something unique each evening. Tuesday and Wednesday have community events in after the content. Thursday brings back the legendary re:Play party.

Friday is a half day. Content runs up until 12:30pm which is the official close of the show.

Phew, there is a lot going on!

Keynotes

The last few re:Invent’s have expanded to five keynotes. Yup, five. That’s crazy.

The first keynote is usually on the Monday and comes as part of “partner day.” This year, Ruba Borno (VP, Worldwide Channels and Alliances, AWS) will deliver this one. This keynote is focused on the AWS Partner Network and various programs and efforts focused on AWS partners. If you’re not a partner, you can safely skip this one. (The 2021 partner keynote.)

Adam Selipsky (CEO, AWS) will deliver the “main” keynote this year. This will give us a broad business update, some key launches, and important customer use cases. (Here’s Adam’s keynote from 2021.)

Swami Sivasubramanian (VP, Amazon Machine Learning) will give the ML and database keynote. This one has gotten steadily more interesting each year. There’s always some cool use cases and new functionality announced. (The ML/database keynote from 2021.)

Monday Night Live became Tuesday Night Live and finally “Peter’s Keynote.” The eponymous Peter DeSantis (SVP, AWS Utility Computing and Apps) is back with this deep dive into how AWS works. Don’t expect any new features but each time Peter takes the stage we learn more about how AWS achieves the scale they do. There’s always an insiders look at some of the technology innovations that AWS has created and how they impact AWS as an environment. (Peter delivering the 2021 keynote.)

Finally, Dr. Werner Vogels (CTO, Amazon) will deliver a keynote focused on builders. Werner always has a strong call to action to help everyone build better in the cloud. This keynote usually features more technical launches and new services. (The 2021 keynote from Werner.)

The keynotes outline the structure for week’s content. I strongly recommend watching at least Adam, Werner, and Peter’s.

Leadership Sessions

The leadership sessions are essentially mini-keynotes. They are delivered by a senior AWS leader and focus on a specific area of the business. The sessions this year at re:Invent are:

  • Diversity, Equity, and Inclusion by Candi Castleberry (VP, Global Diversity, Equity, and Inclusion, Amazon)
  • Executive Cloud Insights by Francesca Vasquez (VP, Technology and Customer Solutions)
  • AWS Storage by Mai-Lan Tomsen-Bukovec (VP, Object Storage, Monitoring and Observability, Messaging and Streaming Services)
  • AI/ML by Bratin Saha (VP of Machine Learning and AI Services)
  • Analytics by G2 Krishnamoorthy (VP, AWS Analytics)
  • Architecture by Francesca Vasquez (VP, Technology and Customer Solutions)
  • Business Applications by Diego Pantoja-Navajas (VP, New Products)
  • Cloud Operations by Nandini Ramani (VP, AWS Monitoring and Observability) and Kurt Kufeld (VP, AWS Platform)
  • Compute by David Brown (VP, Amazon EC2)
  • Containers by Deepak Singh (VP, Compute Services)
  • Databases by Jeff Carter (VP, Databases and Migration Services)
  • Developer by Ken Exner (Director, AWS Developer Tools)
  • Enterprise and Migration by Miriam McLemore (Director, Enterprise Strategy) and Al Opher (VP, AWS Professional Services)
  • IoT by Yasser Alsaied (VP, IoT)
  • Networking and Content Delivery by David Brown (VP, Amazon EC2)
  • Public Sector by Max Peterson (VP, AWS Worldwide Public Sector)
  • Public Sector Partners by Jeff Kratz (GM, Worldwide Public Sector Partners…and a lot more)
  • Security, Compliance, and Identity by CJ Moses (VP and CISO)
  • Serverless by Holly Mesrobian (VP, AWS Lambda)
  • Training and Certification by Maureen Lonergan (VP, AWS Training and Certification)

This is a very similar set of sessions to last year. Some of the leaders have changed and some of the areas have either merged or grown enough to be called out on their own. You can view last year’s leadership sessions on the AWS YouTube channel.

Leaderships sessions generally follow the same format. A quick review of the biggest announcements from the past year for this area of focus. They a new announcements or launches and they wrap with some sort of call to action.

Announcements in the leadership sessions are ones that aren’t quite big enough to make the main keynotes. But for those with an interest in the topic, they can be just as important.

Hero Guides

Now an annual tradition, a collection of AWS Heroes have created guides to help you navigate the sessions at AWS re:Invent 2022. Each guide follows a theme and helps you find a great set of sessions to dive deeper on that theme.

Attending AWS #reInvent? Don't miss the #AWSCommunity session track, led by AWS Heroes!

⭐️ Favorite in the re:Invent session guide now, & grab a seat when reserved seating launches October 11, 10AM PDT: https://t.co/ovcDIf0ek4 pic.twitter.com/iIul1KR3k5— Ross Barich (@rossbarich) October 6, 2022

This year, the available guides are:

There are also some industry and partner guides available by other authors (AWS folks, APN partners, etc.)

Outside of the official guides 👆, a number of people inside of AWS and out have compiled some great guides to session at AWS re:Invent. Here are a few I’ve found useful:

Bootcamps

Bootcamps are half or full day session that provide a deep dive, hands on experience.

There are three main types of bootcamps; exam prep, technical, and partner. Each of them provides a different experience.

These camps are typically offered for an additional fee. That can be a very smart investment, especially if you’re making that last push for an exam or need more guidance on a specific technical area.

Gamified Learning

New-ish this year is “gamified learning”. This is a collection of activities that have been popular throughout the year at re:Invent. This includes several AWS GameDays and Jams.

This year, the options are:

  • AWS GameDay: The New Frontier
  • AWS GameDay Quest Fest
  • AWS Jam: Security
  • AWS Jam: DevOps & Modernization
  • AWS Jam: Data & Analytics

These are all hands-on challenges where you work in teams to solve problems together. Each problem is scored and there’s a nice friendly competition vibe to the whole event. It’s a great way to learn and apply some critical skills.

There’s just enough pressure to pump teams up and push you further in order to beat out the competition!

Announcements

Every year AWS releases a tidal wave of new functionality leading up to and during AWS re:Invent. It’s a foundational piece of their culture. What does that mean for you?

For the three weeks leading up to the show and during the week, you’re going to get overwhelmed with the announcements. Seriously, it’s a crazy amount of effort to keep up.

Don’t believe me? Here’s a chart of the average number of AWS announcements per week over the years they’ve held AWS re:Invent.

In the AWS re:Invent “window” (the 3 weeks before and the week of), there is a 245% increase in the volume of announcements. That means there’s an average of 56 announcements each week during the window.

No wonder I always joking with Jeff Barr about his keyboard usage!

how many keyboards worn through? 😉🤣— Mark Nunnikhoven (@marknca) November 28, 2021

You are not going to be able to keep up with all of these announcements. That’s ok.

My suggestion? In your notes, have a dedicated space for “look up later.” Anytime you hear about a new announcement, cool session, or see a great write-up/discussion, add the URL or reference to your note.

After the show, set aside a little time each day to review one or two announcements until you’ve caught up.

PeerTalk

AWS is introducing a new program this year called, PeerTalk. The call to action is, “Expand your mind and your network.”

From what I can tell, this program is going to leverage your attendee profile to help you better connect with people in the community. Once you’ve identified someone or a couple people you’d like to connect with, you can chat online or request an in-person meeting.

If you immediately got a little nervous, the next part should help put you at ease, “…request in-person meetings of 2-4 people in designated public spaces located across the campus.”

This program was just announced and more details will be coming soon from AWS.

Sponsors and the Expo

AWS re:Invent is when sponsors—APN partners—put their best foot forward. Partners will pop up all over the event. Some sponsor lounges, pub crawls, the mobile app, and more.

Where you will see most of the sponsors is in the Expo. In addition to the sponsor booths, there is also a massive AWS presence in the hall. It’s so big, they actually call is the “AWS Village” now.

This presence includes the AWS Jam Lounge (an area for short hands-on experiences), the Community Developer Lounge, the AWS DeepRacer League arena, Builder’s Fair, and more.

It’s well worth checking out these areas and speaking with some of the sponsors while you’re at it. The welcome reception on Monday, 28-Nov (4:00—7:00pm pacific) is held in the Expo hall and a great opportunity to get some snacks while touring the area.

In additional to the Welcome Reception, one of teh best ways to see the Expo is the un-AWS-official Nature Walk hosted by Corey Quinn as part of his re:Quinnevent 2022. That’s going down on Wednesday, 30-Nov (1:00pm pacific).

If you’re curious as to who will be in the Expo, you can view the complete list of sponsors on the event site.

Managing The Day

AWS re:Invent is a hard show to attend. There is too much content, spread across too many properties, and too much going on in the evenings. And that’s just the primary AWS approach. The sponsoring APN companies have a parade of events that they host as well.

You are not going to be able to take it all in. You’re not even going to get to 20% of it all. It’s just not possible.

Here are some concrete tips to manage each day to get the most out of the conference and everything that surrounds it.

  • Pay attention to where things are taking place. The conference has three main areas; Mandalay Bay, MGM Grand, and the Encore/Wynn/Venetian/Palazzo/Caesar’s Forum cluster
    • Leave yourself at least 30 minutes to move within the cluster
    • …at least an hour to move between the main areas
  • When you get to Las Vegas, visit one of the big drug stores/pharmacies. You need to make sure you have supplies in your backpack to get through each day. The Venetian/Palazzo has a 24/7 Walgreens. Pick up the following for your daily carry:
    • Protein bars and trail mix for the week
    • Fresh fruit (apples travel well) for the week
    • Eye drops
    • Lip balm
    • Hand sanitizer
    • Tissues/Kleenex
  • Make sure you have a multi-port charger/portable battery. You will run out of battery during the day. You will not find a charging port
  • Hydrate. Keep a water bottle with you at all times. Take advantage of the refilling stations throughout the event space. You’re going to be walking a lot. A constant level of exertion, dry air in the casinos, and an offbeat eating schedule all combine to increase your risk of dehydration. If you’re drinking in the evenings, that goes up further. Hydrate
  • 👟 Wear supportive sneakers and good socks. You are going to be walking 10—15 Km (6—9 miles) everyday. Your feet—and everything else—will thank you for the smart footwear choice. Practical has to win out over fashion here. Make sure those kicks are broken in before you get to Las Vegas

Public Spaces

Every year there a bunch of spaces throughout the campus where you can recharge and grab a snack, see a demo of a cool project, chat with some folks around a whiteboard, and more.

This year the event team has finally listed most of these spaces in one place, the Public Space Activations page on the event site. Check ’em out!

re:Play

re:Play is the legendary party that goes down Thursday, 01-Dec from 7:30pm—12:00am pacific.

It’s hard to describe this party. It’s really something you need to experience to understand.

AWS does a great job of making sure there’s something for everyone. There’s always a couple of amazing, world class music acts. Werner will typically announce the headliner at the end of his keynote that morning.

In addition to that, there’s a ton of food and treats. Lots of games to play. And plays to step away from the sensory overload.

Even if you’re not one for parties, it’s worth going to re:Play just to check it out. You might be surprised about how much fun you have!

Learn and Have Fun

One this AWS re:Invent nails year after year is a fun and inviting atmosphere. It manages to strike the balance between being jam packed with new things to learn and providing environments to connect with the community.

Hopefully this guide will help you get the most out of your week!

Please check back regularly for updates! Ping me, if you spot a problem or if something is missing @marknca.

]]>
https://markn.ca/2022/the-ultimate-guide-to-aws-re-invent-2022/ 67f6bbeaaf961b000144326f Sun, 21 Aug 2022 10:00:00 -0400
<![CDATA[ Canadians Are Reliant on Rogers Whether We Like It or Not ]]> Want to share with others? Formatting issues in your reader? This post is available online, Canadians Are Reliant on Rogers Whether We Like It or Not

I spoke with Hallie Cotnam on CBC Ottawa Morning on 07-Aug-2022 about this issue.

On Friday, 08-Jul-2022, the Rogers network suffered a massive outage. Rogers is a major ISP and cellular provider in Canada. Just how massive might surprise anyone not living here. They have 35% of the national market share for mobile connections and 30% of all Canadian home internet connections.

On top of that, they have 2.25 million retail internet customers and another 7,000 enterprise customers.

Over a third of the country is online because of Rogers. Over a third of the country went dark for the entire day.

Much has been made of the outage (just check the references section at the end of this post) but when you wade through all of the opinions, it appears that the issue was the result of one mistake.

It’s the type of mistake that keeps network engineers and operations teams up at night. A simple misconfiguration that threads the wrong needle and is extremely difficult to rollback.

Cloudflare has a great summary of the issue as seen from the internet.

Cloudflare BGP data showing Rogers network drop off the internet on the day of the outage, 08-Jul-2022

Cloudflare BGP data showing Rogers network drop off the internet on the day of the outage, 08-Jul-2022

👆 that big cliff? That’s not good.

Network Access

Most people will never see the inside of a data centre, including a lot of that network’s engineers. Most of the work is done remotely. That requires a secure access path into systems that can update the network resources in question.

Care to guess where simple mistakes escalate out of control?

If you said, “Remote access and update configurations?”, you win! …and by that, we all lost on July 8th.

Someone, somewhere made a simple mistake that apparently closed much needed update pathways and took most of the network offline.

How? These types of changes usually have both technical and process guardrails in place but they aren’t infallible. Mistakes still make it to production. It happens…thankfully rarely.

The good news? The root cause of the issue was probably located quickly.

The bad news? The issue had already taken enough of the network offline that bringing it back up presented its own, unique challenge.

While this network outage lasted almost 17 hours. All indications seem to point to the original issue being resolved reasonably quickly and then the rest of the time spent unravelling the nightmare of legacy systems.

Rogers took a lot of heat for this outage. Their stock drop 1.17% on the day. But while it’s easy to blame them, the reason the outage was so long was written in a thirty year build up of technical debt, business incentives, and the geographical challenges of the Canadian market.

Are There Any Takeaways?

Everyone impacted has called for change. The Government called Rogers, Bell, and others to the carpet to figure out how to prevent another outage this significant. Those efforts won’t drive any significant changes.

Canada is just too big and our population is too small to have a diverse set of telecommunications providers. That’s ok. We have reasonable—if expensive—coverage today. We need significantly better coverage in the Territories and some rural areas but most Canadians have access to reasonably fast internet.

Do we need change in this sector? Yes.

Lower costs would help. Regulation that prevents bundling of multiple services (discounts for more services from one provider) which forces Canadians to put all of eggs in one basket. Subsidized access to rural and northern areas.

But at the end of the day, this massive outage was from a mistake. A mistake that happened despite technical and process safeguards. Why? Because 💩 happens. 🤷

Thoughts On The Day

A Twitter thread from me on the day with my initial reactions;

as the @rogers outage rolls towards hour 18, the msg on their website keeps getting more empathetic

"catastrophic" isn't an exaggeration here

nationwide networks are complex. lots of opportunities for cascade faults that require rebuilds#nointernet #rogersoutage 🧵 pic.twitter.com/biCsycpr1E— Mark Nunnikhoven (@marknca) July 9, 2022

References

]]>
https://markn.ca/2022/canadians-are-reliant-on-rogers-whether-we-like-it-or-not/ 67f6bbeaaf961b0001443139 Sun, 07 Aug 2022 10:00:00 -0400
<![CDATA[ It’s Official, Serverless Is Now Meaningless and That’s...Ok? ]]> Want to share with others? Formatting issues in your reader? This post is available online, It’s Official, Serverless Is Now Meaningless and That’s...Ok?

There’s a million different ways to build in the cloud. Ok, not a million, but there’s a lot. For the past few years, the serverless movement has been growing but what, exactly, is serverless?

Turns out, we can’t agree on what it is. Or at least we used to agree, but don’t now?

Corey & Vlad Are Right

Corey Quinn wrote a fantastic piece calling out Amazon Aurora Serverless v2 for not actually being serverless. He points out that even doing nothing, the service will run you about $43.20 USD each month.

That violates a key service tenant; don’t pay for idle resources.

Corey’s right.

Vlad Ionesco replied with an epic Twitter thread that basically sums as, labels don’t matter, the solution does.

Rant: can we please stop pretending that serverless in 2022 is the same thing as serverless in 2016?

We're intellectually masturbating about what "serverless" means and we're confusing people, all while we're like on serverless v3!

Of course v3 products don't fit in v1 boxes!— Vlad Ionescu (he/him) (@iamvlaaaaaaad) June 21, 2022

Vlad’s right.

The community has tried to define serverless for years. The closest I could come up with was this dictionary-esque entry from 2018 👇;

As the community has grown, the technologies matured, and the use cases expanded, the definition of serverless has gone from hazy too absent.

Serverless is a spectrum

The original vision for serverless was systems that are event-driven. As a request is processed, the system kicks into gear and then lies dormant—with no idle costs—waiting for the next event.

This grew out of AWS Lambda’s popularity as a compute platform. You pay for AWS Lambda based on the amount of compute you use for a specific amount of time measured in milliseconds.

If you’re not processing an event, you’re not paying. Linked with other services that match that pricing and operational model, it’s very possible to have a solution that’s directly aligned with the business value it delivers.

That’s a good thing.

Noted cloud bard Forrest Brazeal sums it up nicely in this mini-review;

“Serverless” compute services ranked from most serverless to least serverless, in my opinion:

1. AWS Lambda
2. Google Cloud Run
3. AWS Fargate
4. AKS virtual nodes— Forrest Brazeal (@forrestbrazeal) June 23, 2022

Operations Is a Critical Concern

But out of this push, teams finally realized that design choices directly impacted operational efforts. You can make smarter design choices and lower the effort required to keep the lights on.

This mirrored the growth of the observability movement (another term starting to dilute) as teams were trying to build more resilient systems and avoid being paged at 2 AM to fix outages.

What Corey has noticed and rightfully called out is that builders now need to see the label of serverless and then figure out just how serverless something is.

You can’t just assume a service fits your idea of serverless.

Read the Label

Frustrating? Yeah, a bit.

A good sign? 100%.

The spectrum of serverless offerings is a sign that the more builders are seeking these more efficient solutions. The applicable use cases are expanding. People are building better.

…just make sure you aren’t going to get hit with an unexpectedly large bill (which is a rant for another day).

]]>
https://markn.ca/2022/its-official-serverless-is-now-meaningless-and-thats-ok/ 67f6bbeaaf961b000144328a Fri, 24 Jun 2022 10:00:00 -0400
<![CDATA[ Is Google LaMDA Sentient? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Is Google LaMDA Sentient?

I spoke with Hallie Cotnam on CBC Ottawa Morning on 20-Jun-2022 about this issue.

Has the “I” in A.I. Finally Come True?

Recently, an AI ethics researcher from Google was placed on administrative leave after publicly claiming that Google’s LaMDA system was sentient. A claim that has been denounced by Google and others in the AI community.

It’s a bold claim and there simply isn’t enough evidence to support it.

Is Google LaMDA sentient? No.

What is LaMDA?

If it’s not an actual intelligence, what is it? LaMDA actually stands for Language Model for Dialogue Applications. This is a system that is designed to hold a conversation in a natural manner.

Sundar Pichai, CEO of Google and Alphabet, revealed the latest version at Google I/O 2022 and hit on three key aspects of the system. He phrased it as the system being able to;

  • “Imagine tt”, the ability to synthesize new ideas and topics
  • “Talk about it”, extrapolate ideas around a specific topic and keep the conversation on topic
  • “List it”, take a complex goal and break it down into lists of tasks to do

These three areas of focus allow the system to present as if it’s having an intelligent conversation. In reality, it’s using all of it’s vast inputs—Google Search, YouTube, Google Maps, Google Books, etc.—to find groups of relevant responses and create something that is plausible.

What Impact Will LaMDA Have?

If you’re asking yourself, “Why would Google create such a system?” The answer is actually very straight forward; efficiency.

Digital systems are often the first interface for many businesses (through online chat or phone calls) and a lot of tools like Google Home. We’ve all had that frustrating interactive voice response (IVR) experience when calling a big company’s customer support…

“Hello and welcome to BigCorp. What can I help you with today?”, 🤖

“Customer service”, 😀

“I heard, ‘Sales.’ Is that correct?”, 🤖

“No, I want customer service”, 😀

“Oh, I’m sorry that I misheard you. Forwarding you to ‘Sales’”, 🤖

👆 That’s the type of interaction—whether voice or chat—that LaMDA aims to get rid of forever. The results so far are promising.

There are definitely issues around the ethics of using a system like this. We won’t dive into them here but those discussions need to be had in our communities.

At a minimum, these systems would be forced to identify as digital. You should always know if you’re talking to a digital system.

But overall, LaMDA should be a big win for the most use cases.

References

LaMDA

A.I. Tests

Other Models

]]>
https://markn.ca/2022/is-google-lamda-sentient/ 67f6bbeaaf961b0001443138 Wed, 22 Jun 2022 10:00:00 -0400
<![CDATA[ Twitter To Add Edit Button...Finally ]]> Want to share with others? Formatting issues in your reader? This post is available online, Twitter To Add Edit Button...Finally

I spoke with Robyn Bresnahan on CBC Ottawa Morning on 07-Apr-2022 about the announcement and it’s implications.

In Development

now that everyone is asking…

yes, we’ve been working on an edit feature since last year!

no, we didn’t get the idea from a poll 😉

we're kicking off testing within @TwitterBlue Labs in the coming months to learn what works, what doesn’t, and what’s possible.— Twitter Comms (@TwitterComms) April 5, 2022

This statement from Twitter comes as no surprise. Shock is probably a better word. The “edit” button has long been requested with many rumours swirling about it.

While it feels like a simple change, behind the scenes there’s a ton of engineering work that needs to be done. Twitter was designed as a write once, read many system. Changing that fundamental truth won’t be easy.

It’s like building a one story house and then deciding you actually want a two story home. It’s possible, but takes a lot of time and work to do properly.

So Twitter can make this change but it’ll take time…and has taken a long time.

Safety

In addition to the engineering challenges, there are safety and misinformation concerns. Lots of them.

2/ Edit has been the most requested Twitter feature for many years. People want to be able to fix (sometimes embarrassing) mistakes, typos and hot takes in the moment. They currently work around this by deleting and tweeting again.— Jay Sullivan (@jaysullivan) April 5, 2022

This thread 👆 from Jay Sullivan dives into some of the issues in this thread.

Think of it this way. Without safeguards, if a country’s leader replies to a tweet with, “I agree with this” and then the original tweet is edited to something completely different, misinformation will spread. Yes, corrections can be made but corrections rarely get the same attention as the original.

This is why Twitter is working on and discussing what safeguards to add. A “blank cheque” edit just won’t work. It would upend what little credibility is left in the Twitterverse.

]]>
https://markn.ca/2022/twitter-to-add-edit-button-finally/ 67f6bbeaaf961b0001443137 Fri, 08 Apr 2022 10:00:00 -0400
<![CDATA[ NFTs, Web3, and The Blockchain Have Their Place…Maybe ]]> Want to share with others? Formatting issues in your reader? This post is available online, NFTs, Web3, and The Blockchain Have Their Place…Maybe

If you manage to push the hype to the side for a minute, you might be able to glimpse the start of a useful set of technologies.

The negative blowback hitting NFTs and this space right now (and rightfully so) is often due to a combination of misunderstand the technology and a misapplication of the technology.

Early Blockchain

In the earliest days of the blockchain, the hype claimed it would solve all of our problems. On top of the multitude of failed projects, there were scams left, right, and center.

But as a technology, blockchains have their place.

The core value a blockchain provides is distributed, publicly verifiable ledge of transactions.

In simpler terms, the technology makes it easier to make sure that no one entity controls the records of transactions and those transactions are much easier to verify.

These aspects are what make it appealing (but not perfect) for digital currencies. The technology is also an excellent solution to challenges where voting is required or in use cases like supply chain verification.

Web3 Principles

Thinking about the blockchain, lead to the core ideas of Web3. This group of technologies isn’t formed yet but they are starting to come together in some experiments.

Web3 aims to deliver a distributed and robust system for building applications and distributing information. This system would also have a native ability for financial transactions.

A big push behind Web3 is to break up the titans of tech powering today’s internet. This movement takes aim at Facebook/Meta, Google, Apple, Amazon, and more.

The biggest challenge with the current direction is that it ignores many of the simple economic realities of the modern web. There is an unbelievable amount of resources that power the sites and services we use everyday.

In order to justify the use of those resources, some type of business model is required. I don’t agree with the methods or assumptions behind adtech but it certainly has powered some amazing innovation.

Web3 has a long way to go and it’s too early to know if it’ll pan out.

NFT Challenges

That brings the last of the big three of these technologies; NFTs.

Casey Newton has a great run down of two major communities—gaming and music—with very different reactions to the technology.

This demonstrates the conflicted nature of NFTs. We know that they are simply data files that point to something online. Anyone can verify who issued them and who currently owns them.

This is a useful thing to be able to prove but it required other structures—like copyright, property laws, and licensing agreements—to actually work.

Right now, NFTs are being tried out in any number of scenarios. Some will work, others will fail. Some require the efficiencies of centralization which runs counter to the Web3 ethos.

One Truth

The one undeniable truth of blockchain, Web3, and NFTs is that these technologies are still in their early days.

We need more experimentation. More thought. And more discussion around how they are best used.

]]>
https://markn.ca/2022/nfts-web3-and-the-blockchain-have-their-place-maybe/ 67f6bbeaaf961b00014432d1 Sun, 06 Feb 2022 09:00:00 -0500
<![CDATA[ Hype & Money Are Testing The Idea of NFTs ]]> Want to share with others? Formatting issues in your reader? This post is available online, Hype & Money Are Testing The Idea of NFTs

NFTs continue to pop up everywhere. There’s a lot of hype around them and a lot of money is involved in the NFT and Web3 ecosystem.

Technologies Mature

Believe it or not, the hype part is a common pattern for technologies. Research & analysis company Gartner has a famous research methodology around, “The Gartner Hype Cycle.”

Simply put, new technology comes on the scene, there’s a ton of hype, massive frustration, then gradually it settles into reasonable usage.

Not all technologies make it through the hype cycle but we learn something from every one that tries.

NFTs are nearing the top of the their hype…hopefully.

Nothing For You?

A NFT is just a data file recorded on a blockchain. This data file follows a standard that lays out the minimum requirements.

That standard states that at its core, an NFT is just a name, description, and a link to something.

That doesn’t magically grant you a license or ownership over something. Other mechanism or tools do that.

I am not a lawyer but it’s actually the terms and conditions of the NFT project that dictate what the NFT signifies. Reading through these contracts are critical.

Sing Another Tune

Recently, a project called HitPiece claimed to be selling unique NFTs for music. The project promised a one-to-one relationship between an NFT and a hit song.

They promised that artists would earn royalties every time an NFT changed hands and that owners of the NFT would gain “access and experiences.”

Of course there was immediate outrage. This project had nothing to do with the artists whose work it was trying to sell. Within hours the site was taken down and now displays the message, “We Started The Conversation And We’re Listening.”

Now, the Record Industry Associate of America is taking legal measures against the project.

Buyer Beware

HitPiece is one of all-to-many scams associated with cryptocurrencies and NFTs. While we’ve seen lots of hyped up technologies fail spectacularly, we’ve never seen this much money and this many people be hurt by those failures.

That doesn’t rule out the future or potential utility of NFTs.

But as with any technology, we need to move through the hype cycle before we see that potential realized. If you view these early efforts as experiments, that might help you better evaluate the risks.

]]>
https://markn.ca/2022/hype-money-are-testing-the-idea-of-nfts/ 67f6bbeaaf961b00014432d0 Sat, 05 Feb 2022 09:00:00 -0500
<![CDATA[ Why Multi-Factor Authentication Is Critical To Stopping Hackers From Getting Into Your Accounts ]]> Want to share with others? Formatting issues in your reader? This post is available online, Why Multi-Factor Authentication Is Critical To Stopping Hackers From Getting Into Your Accounts

A recent study from Microsoft showed that only 22% of the Azure Active Directory customers are using multi-factor authentication. That’s a much better result than Twitter, which after a major push had 2.3% of their accounts enable this feature.

What Is Multi-Factor Authentication?

Authentication is the term the security community uses to to verify who you are. To do that, we usually ask you to provide at least one of the following;

  • Something you know
  • Something you have
  • Something you are

There are called factors.

More sites—like Twitter—ask you for a username and a password. The password is a “something you know” factor.

Passwords Suck

Passwords are a frustrating solution to a really challenge problem. There’s a lot of misconceptions about passwords out there that have built up from a lot of bad implementations.

The tl:dr on passwords is the longer the better. Think passphrase not password.

But, the reality is that passwords can and are regularly compromised. You need a better way to prove that you are in fact, you.

More Factors

Enter two factor (2FA) or multi-factor authentication (MFA). This is when instead of just asking for one thing you know, the system asks for more proof.

Ideally, these additional factors are in different categories.

Most multi-factor systems use either a smartphone app to generate a unique, temporary code or they text you one. This proves “something you have” …the phone you set up for your second factor.

Stronger Authentication

Adding this second factor adds a little bit of friction to the act of logging in. However, it’s a major frustration for hackers.

It’s so frustrating, that Microsoft claims it’ll stop 99.9% of attacks on user accounts. I don’t know if that number will hold up but it certainly makes compromising your user account significantly harder with minimal effort on your part.

Knowing that, it’s time to take five minutes and setup multi-factor on all of your accounts; like Gmail, Facebook, LinkedIn, and Twitter.

]]>
https://markn.ca/2022/why-multi-factor-authentication-is-critical-to-stopping-hackers-from-getting-into-your-accounts/ 67f6bbeaaf961b00014432cf Fri, 04 Feb 2022 09:00:00 -0500
<![CDATA[ What Is A Bug Bounty And Why Are They Important? ]]> Want to share with others? Formatting issues in your reader? This post is available online, What Is A Bug Bounty And Why Are They Important?

Cybersecurity research has a long and interesting history. The dynamics between researchers, mischief makers, hackers, and companies is complex to say the least.

Reputation & Security Posture

Understandably, companies don’t want to look bad. Most spend huge swathes of their budget on marketing and positioning themselves in a positive light.

Having security holes exposed to the public can have a negative impact on a companies reputation and their bottom line.

Countering that, most companies also want to ensure that their technology works as intended and only as intended.

How can an organization balance these needs?

Enter The Bug Bounty

In most jurisdictions, the laws around computers and hacking are overly broad and out of date.

This can—and has—lead to lots of legal trouble for well-intentioned researchers.

These laws have also led to convictions for cybercriminals who have taken advantage of thousands.

The bug bounty system emerged to provide guardrails for the interaction between security researchers and the company hosting the bug bounty program.

The program lays out the types of research that are acceptable and how that research can be conducted. Furthermore, it creates a structure that usually defines compensation for the researcher and how and when—or even if—the issue can be discussed publicly.

For researchers, a public record of accomplishments is a critical aspect of career progression.

While not perfect, bug bounty programs are much better than the unstructured approach of the past.

Keys To Success

The keys to a successful bug bounty is clear communications. The boundaries and process needs to be established before any research is done.

Why? Because looking at just the technological steps taken, there’s isn’t much of a line between security research and hacking. Yet the difference between the two is night and day.

Security research is done with understanding and consent. It’s a process where the goal is security improvements and gained knowledge.

Bug bounties can help protect companies and researchers alike. They establish a working relationship and set the proper expectations on both sides.

They aren’t perfect. But they are a strong move in the right direction.

]]>
https://markn.ca/2022/what-is-a-bug-bounty-and-why-are-they-important/ 67f6bbeaaf961b00014432ce Thu, 03 Feb 2022 09:00:00 -0500
<![CDATA[ A 326 Million Dollar Smart Contract Bug ]]> Want to share with others? Formatting issues in your reader? This post is available online, A 326 Million Dollar Smart Contract Bug

Another hack. Another setback for Web3. Another code quality issue costs millions.

What Happened

Wormhole is a service that helps you move value from one blockchain to another. So if you want to take 1 SOL from the Solana blockchain to the Ethereum blockchain, Wormhole will help make that happen.

The way it does this is through smart contracts.

A smart contract on one blockchain makes sure you have the funds and then holds them. On the destination blockchain, another smart contract buys the necessary funds and transfers them to the purchaser.

Conceptually, this is very straightforward.

Code Quality vs. Hacker

Smart contracts are code. Code almost always has bugs.

If a malicious actor finds those bugs before the developer does, bad things usually happen.

That’s exactly what happened to Qubit Finance recently. And that’s exactly what just happened to Wormhole.

A malicious actor found the bug in the smart contract system Wormhole uses and leverage that bug to steal cryptocurrency on three different blockchains worth an estimated total of $326 million dollars.

Test, Test, Test

What happened to Qubit Finance and Wormhole was unfortunate and it was wrong. In both cases, it appears that the actions were malicious and ill-intentioned.

Both of these cases highlight the need for extremely details and rigorous testing of the code that runs smart contracts.

Developers working in Web3 and specifically in the DeFi (Decentralized Finance) areas need to understand the risk that error in the code pose.

It’s one thing if a video game you write has a bug in it. The consequences are usually a bit of player frustration that goes away when you fix the bug.

If the Web3 world, a bug can cost you millions.

]]>
https://markn.ca/2022/a-326-million-dollar-smart-contract-bug/ 67f6bbeaaf961b00014432cd Wed, 02 Feb 2022 09:00:00 -0500
<![CDATA[ Why Do Amazon S3 Data Breaches Keep Happening? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Why Do Amazon S3 Data Breaches Keep Happening?

3TB of data involving airport staff across Colombia and Peru was exposed to anyone on the internet. The report called out an “unsecured AWS server” as the source of the breach.

Digging a little deeper, we find that the data was stored in Amazon S3, not an unsecured AWS server.

Why does it matter?

Operational Overhead

Running a server takes a lot of work. There are updates to run regularly, resources to monitor, configurations to tweak, and threats to monitor for.

A server has a high operational cost.

They should be avoided whenever possible. Technologies like serverless, containers, or managed services are almost always a better choice for your solutions.

Amazon S3 is a managed service. This reduces the operational cost of managing your data and should made having a strong security posture easier.

Why Is It Always S3?

In Amazon S3, you create a bucket and you put objects inside that bucket. Think folders and files.

The shared responsibility model that runs the entire cloud dictates that you are responsible for the data you store in S3 and the configuration of S3 as a service.

This is where the challenge lies.

By default, an S3 bucket is only accessible to the user or system that created it. It’s locked down and you have to explicitly choose to provide access.

This access is typically provided through a service called IAM or Identity and Access Management. This is an immensely powerful service that allows you to create all sorts of different access scenarios.

Unfortunately, it can be tricky to wrap your head around this system and how to configure it to match your intentions.

Mistakes here are what leads to these types of data breaches.

If you’re wondering why it’s always Amazon S3 and not another CSPs offering, it’s simply a matter of scale. S3 is one of the most popular cloud services out there.

Least Privilege

When using a system like IAM, you want to apply the principle of least privilege. This concept means that you only grant the permissions required to the people or systems required to complete specific tasks.

If you only need to write a file, you only get write access to that specific file.

Unfortunately, this principle seems to be in direct opposite of idea of “get it working ASAP.” 🤦

This leads to a lot of permissions being set to “anyone can do anything.”

Sadly, given the flexibility of the system, even when you try to set least privilege permissions, mistakes still happen.

This is when you should use a tool called that Access Analyzer for S3. This free tool helps ensure that what you’ve set as permissions matches what you want as permissions.

That’s a critical step to protecting your data and staying out of the headlines.

]]>
https://markn.ca/2022/why-do-amazon-s3-data-breaches-keep-happening/ 67f6bbeaaf961b00014432cc Tue, 01 Feb 2022 09:00:00 -0500
<![CDATA[ Can You Own A Colour? Can You Try? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Can You Own A Colour? Can You Try?

The deeper I dive into the world of Web3, NFTs, and the blockchain, the more I’m fascinating. This is a compelling confluence of technology, communities, grifts, and possibilities.

Color.museum came across my Twitter feed recently. After reading and re-reading their proposal, I’m still not sure if this is a serious endeavour or an elaborate joke.

Own What Now?

The projects tagline is, “Own the building blocks of new art/the future/the metaverse.”

If you participate, you select your desired colour, give it a name, and then a short description. This is then minted as an NFT on the Ethereum blockchain.

The claim is that you will “own your color for eternity.”

That’s a bold claim. One for which there’s absolutely no evidence to support.

The Actual NFT

Based on the information provided by the project, what you actual get is an NFT with the following unique information. There is other data in the NFT but it isn’t related to it’s unique-ness.

{
  "name": "The Name You Provided",
  "hex": "#000000", // the colour value you chose
  "description": "Description you provided",
  "imageSocial": "https://LINKED-TO-AN-IMAGE.png",
  "dateMinted": "13 December 2021, 13:54 GMT",
  "image": "https://LINKED-TO-AN-IMAGE.png"
}

This data is stored on the blockchain under a token ID that is the decimal value of the “hex” field…assuming that’s available.

If you follow URL in the “image” fields, you arrive a nice colour tile that shows the token ID, hexadecimal value, name of the colour, the Color.Museum logo, and a big splash of the colour.

That’s it.

Ownership & Licensing

The structure above 👆 isn’t that different from any other NFT. You’re buying some type of license for the artwork or data stored at the URL. Some NFTs also offer benefits that apply while you own the NFT, things like membership to a club.

With Color.Museum, the implication is that you would own this colour. That’s an amazing deal…if it was possible. You can’t own a colour.

This project is positioning itself as “a Meta NFT.” They state that this is “a building block to spawn new NFTs, or derivative NFTs.”

The implication is that is someone else wants to mints an NFT using this colour, it would reference your Color.Museum NFT and there would be some sort of renumeration.

I’ve read through all of the materials available. There is not method by which to enforce this structure. Nor does this project have any legal position to own or license colours.

The Web3/NFT space is truly the wild west and this is one wild idea. At the end of the day, it looks like—yet again—all you’re buying is a license to an image.

…and these ones aren’t even that creative.

]]>
https://markn.ca/2022/can-you-own-a-colour-can-you-try/ 67f6bbeaaf961b00014432cb Mon, 31 Jan 2022 09:00:00 -0500
<![CDATA[ The Number One Problem With Web3 Smart Contracts ]]> Want to share with others? Formatting issues in your reader? This post is available online, The Number One Problem With Web3 Smart Contracts

The concept of a smart contract is exciting. It’s a program that runs on the blockchain executing the terms of an agreement.

Unlike physical contracts, the code in the smart contract is much clearer. In a physical contract, language can have unintended consequences. This is reason why there are so many lawyers involved in our systems.

They are present to provide the guardrails and guidance to ensure that the language in a contract reflects the intention of the parities involved.

Logical Code

One of the goals of a smart contract is clarity.

The code in the contract evaluates the various conditions to validate is they are true before executing the contract.

If the agreements states that 10 Ethereum (ETH) are required in order to transfer ownership of an NFT, the contract validates that 10 ETH are in fact involved in the transaction.

This greatly implies these agreements. It doesn’t make them bulletproof though.

Code almost always has bugs. And in a smart contract, that can mean the difference between a successful agreement and one party losing everything.

500,000 Gone

A user on reddit recently posted a story where they lost half a million dollars of ETH through a smart contract.

This quote is telling, “Sent ETH to WETH contract and got WETH back (after some googling I found this is how the contract works).

Here in lies one of the major problems. The everyday user will not or cannot read the code in the smart contract.

Just like legalese in physical contracts, the code obscures that actually will happen from most parties.

Even if you can read the code, that doesn’t mean there aren’t bugs in it.

When building software, we constantly test. These tests check to see what happens when the code gets unexpected inputs. When it’s run multiple times. When it’s called out of order. And all sorts of other conditions.

The goal is to exercise the goal is all different ways to find out how it reacts. Software is complicated. Testing helps us better understand the code we’ve written.

Testing of smart contracts is still in its infancy. Just like the coding language that runs these contracts. This is an area that needs a lot of work…and fast before more people lose more assets.

]]>
https://markn.ca/2022/the-number-one-problem-with-web3-smart-contracts/ 67f6bbeaaf961b00014432ca Sun, 30 Jan 2022 09:00:00 -0500
<![CDATA[ Is A Bug In A Web3 Smart Contract Part of the Contract? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Is A Bug In A Web3 Smart Contract Part of the Contract?

An interesting aspect of Web3 is the smart contract. These are simple programs that run on the blockchain when certain conditions are met.

For decades, we’ve been creating more and more software and one thing has always held true: there will be bugs.

A bug in the code is simply a mistake. Given the complexity of the environment that mistake could be minor or it could be catastrophic.

Security issues are a very special class of bug. These bugs allow a malicious actor to manipulate the code in order to produce a result that the actor desires…not what the programmer intended.

Smart Contract Bugs

Recently, Qubit Finance, a DeFi/Web3 platform, was attacked. Their incident report details the bug that the attacker took advantage of.

This bug allowed them to abscond with almost $80 million in cryptocurrency.

Coverage of the attack uses the term hacker to describe the malicious actor. Unlike some other cases, this use of the term is accurate. Though cybercriminal is even more specific.

Intention

Why would this attacker be a hacker when another isn’t? Intention.

The compromise of the OpenSea marketplace used the system in the way it was intended to be use. The actor bought an NFT from a valid listing on the platform through a valid transaction.

It went against the intention of the seller but the issue was with the platform, not the use of it.

In the Qubit Finance case, the technical specifics are very different. Qubit’s platform is designed to bridge one cryptocurrency to another.

Take X of Ethereum and convert it to Y Binance Coin.

The attacker used a bug in the Qubit smart contract to take 0 Ethereum to convert to almost $80 million in Binance Coin.

While a conversion was done, the intention was to convert a non-zero amount of one cryptocoin at fair market rates to another. That didn’t happen here.

Quality Coding Required For Smart Contracts

As smart contracts start to proliferate, code quality is paramount. The argument has been made here that the Qubit case is a cybercrime.

A strong case also exists that it this smart contract executed as designed.

After all, is the blockchain supposed to be the single source of truth? And that contract executed as written.

This issue highlights just how much work needs to be done in the Web3/DeFi world before it’s ready for mainstream adoption.

]]>
https://markn.ca/2022/is-a-bug-in-a-web3-smart-contract-part-of-the-contract/ 67f6bbeaaf961b00014432c9 Sat, 29 Jan 2022 09:00:00 -0500
<![CDATA[ When Is a Hacker Not a Hacker? ]]> Want to share with others? Formatting issues in your reader? This post is available online, When Is a Hacker Not a Hacker?

The word “hacker” gets throw around a lot. Anytime there’s a cybersecurity issue, the malicious actor is labelled a hacker.

Most of the time, it’s an accurate label.

However, the line can be very blurry very quickly.

What Is A Hacker?

Hacker originally didn’t refer to a cybercriminal.

The word was used as a label for someone who loves to breakdown computing problems and systems and solve them in creative ways.

This definition is still listed in the dictionary but has fallen out of use. We—the original hacking culture—lost control of it over time as it was used again and again in the mainstream to refer to malicious activities, not acts of creation.

Edge Case Confusion

As with science, economics, or any complex technical topics, simplifications must be made in order to make any issues accessible to a broad audience.

In the case of cybersecurity, that simplification is “Anything unintended == hacker.”

Honestly, it’s not a bad trade off. But it’s also not always accurate.

NFTs…Again

NFT marketplace OpenSea recently had an issue where some NFTs were sold at a dramatically reduced price compared to their current trading value.

Due to the nature of the blockchain, these transactions were considered valid.

Of course, it’s a hack right? Some hacker broke into OpenSea and committed a crime (probably fraud or maybe theft?) in order to pull this scheme off.

Not so fast.

Single Source of Truth

It turns out—in this case—that there were multiple listings for the same NFTs. Earlier listings that the owners thought removed, were only removed from the web interface.

These listings were still accessible via the API or application programming interface. The unexpected transactions were conducted via the API using the lower price listing.

OpenSea treats the API as the single source of the truth. Users (buyers and sellers) see the web interface as the single source of truth.

The hacker in this case took advantage of that and completed a completely valid transaction on the platform.

So are they a hacker or a smart buyer?

]]>
https://markn.ca/2022/when-is-a-hacker-not-a-hacker/ 67f6bbeaaf961b00014432c8 Fri, 28 Jan 2022 09:00:00 -0500
<![CDATA[ If Apple’s FaceID Works With Masks On, Will That Reduce Your Security? ]]> Want to share with others? Formatting issues in your reader? This post is available online, If Apple’s FaceID Works With Masks On, Will That Reduce Your Security?

Apple’s FaceID technology has made it a lot easier for you to get into your iPhone or iPad. Swipe up while looking at the device.

It doesn’t get much easier than that.

FaceID Must See Your Face

It comes as no surprise (hopefully) that FaceID needs to see you face in order to work. If you’re wearing a scarf or mask, it won’t work.

This has been a challenge for those of us who have deep winters since the start. But with the onset of the pandemic, everyone else started to be impacted.

To be clear, that impact isn’t very significant.

Instead of looking at the device and swiping up, you now have to swipe up and type in your passcode.

Most people don’t use a passphrase which means they are typing in six digits. More work than a look, but hardly a show stopper.

Detecting Masks

The most frustrating part of the process wasn’t so much typing in your passcode but the delay as your iPhone tries to figuring out if you are actually you by scanning your face.

A few months back in iOS 13.5, Apple added mask detection to FaceID. When the system determined that you were wearing a mask, it would prompt you for your passcode.

This saved only a second but that made a world of difference.

FaceID Using A Mask

Now, Apple is in the late stages of testing an update to FaceID. This will allow you to login fully wearing a mask.

This opt-in feature will reduce the accuracy of FaceID but shouldn’t impact your security in any meaningful way.

Right now, FaceID uses the TrueDepth camera to map your face using over 30,000 different data points.

That data is then mapped to a specific model that trades perfect accuracy to allow for a reasonable amount of variation. If you’ve had a rough night, didn’t shave, or just paid a visit to the dentist, FaceID still works.

Those trade offs means that there’s a one in a million chance of someone else being able to unlock your phone with their face.

Smart Trade Off

Using FaceID with a mask combines the mask detection feature with a more generous tolerance for matching your face. This will increase those odds an unspecified amount.

However, combined with the limit of five FaceID attempts before prompting for a passcode, requiring a passcode after a reboot, and other protections, this feature should only improve the usability of your device without significantly increasing your risk.

]]>
https://markn.ca/2022/if-apples-faceid-works-with-masks-on-will-that-reduce-your-security/ 67f6bbeaaf961b00014432c7 Thu, 27 Jan 2022 09:00:00 -0500
<![CDATA[ Why You Should Build Less, Not More ]]> Want to share with others? Formatting issues in your reader? This post is available online, Why You Should Build Less, Not More

I try to solve to many problems and it’s making most of those problems worse.

Similar to the challenge I’ve had with “good enough”, as a technologist I suffer from NIH syndrome.

Its Ok To Use Someone Else’s Solution

I’ve been learning to code for thirty five years. In that time I’ve written code that has never seen the light of day and code that’s been used by millions of people.

To this day, I still see useful tools and think, “I can build something like that.”

Yes, I Could Build Something Like That

The deviousness of that statement is it’s true. I could probably build something like whatever tool I’m looking at.

However it misses the key question, “Should I build something like that?”

Very often, the answer is “No.”

Developers And Engineers Constantly Undervalue Their Time

I create a ton of content. To keep that pace, I use a lot of very handy tools. Most of these tools do one thing very well. Focus is a great attribute for a tool.

It also moves that tool close to the “I can build it” zone.

This isn’t just a “me” problem. This comes up constantly with teams building technologies. Teams always feel that urge to write their own solution instead of leveraging a great open source project or paying for a tool.

Teams that fail give in and spend time reinventing the wheel. And then maintaining wheel 2.0. Great teams can push through this urge and put an importance on their time.

Focus On What Matters

The biggest frustration with this issue is that it often occurs in areas that aren’t tied to the core problem that I’m trying to solve.

It’s often the technological equivalent of trying to make your own butter when you’re trying to make chocolate chip cookies.

Could you? Sure. Should you? No.

Just use the off the shelf butter and focus on getting those delicious chocolate chip cookies in the oven and then into your belly!

When building technology and writing code, you need to constantly remind yourself to focus on what matters.

Focus on what gets you closer to your goals and not whats simply possible.

…now I have to go make chocolate chip cookies 😉

]]>
https://markn.ca/2022/why-you-should-build-less-not-more/ 67f6bbeaaf961b00014432c6 Wed, 26 Jan 2022 09:00:00 -0500
<![CDATA[ An Uncomfortable Admission On Work ]]> Want to share with others? Formatting issues in your reader? This post is available online, An Uncomfortable Admission On Work

I had a conversation with a friend today about accepting “good enough” as a result. For year, I’ve absolutely f**king hated “good enough” when it comes to my work.

…and that’s held me back in a number of ways.

I constantly fight the urge to continue to work on something. To put just a little bit more time into it. To make it just a little bit closer to perfect.

Of course, no matter how much time or effort I put into the work, it’s never perfect. Perfect is impossible.

Ironically, there is always a point where I’ve put too much work into something and it suffers because of it.

It’s taken year and years of mental effort to push past my aversion to “good enough.” It’s still there. I still cringe when I stop working on something and declare “good enough.”

This was one of the motivations for my joining the effort in #Ship30for30, to push through “good enough.” Writing 30 atomic essays in 30 days requires me to just let go a “good enough.”

I don’t have the time to keep making those changes to the work. You can only iterate so much in the time allotted before you’ve got to move onto the next essay.

I’m still deeply uncomfortable shipping things when I still view them as incomplete. But I’m also often shooting for a 7 when a 3 would do.

And honestly, In the moment when I can objectively evaluate what I’ve done, most of the time good enough actually is.

]]>
https://markn.ca/2022/an-uncomfortable-admission-on-work/ 67f6bbeaaf961b00014432c5 Tue, 25 Jan 2022 09:00:00 -0500
<![CDATA[ Is Digital Privacy Important? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Is Digital Privacy Important?

It’s the first day of data privacy week.

Those in the community will spend the week trying to raise awareness within the general public and advocating for various acts of privacy legislation or reform.

For most, though, it’ll pass without even a nod of the head.

Do You Care About Privacy?

That raises the critical question, “Is Digital Privacy Important?” If the general public isn’t calling their representatives or voting with their wallet to ensure their privacy rights, is that a key indicator?

Is the answer simply, “No.”?

Awareness

I don’t believe so. I believe that most people care about their digital privacy. They want awareness and control of their data online.

The problem is that this is such a complex and nuanced issue that it’s extremely difficult to understand the scale at which you’ve lost control of your data.

User Data vs. Data About a User

Once hair that is split all too often is the idea of “user data.” When the everyday person refers to user data, they mean data that they have and data about them.

When a company in the data market—collectors, brokers, etc.—talk about user data, they mean data that you have explicitly shared. The photos that you upload to your social network, your posts, the profile information to added. Things like that.

The data about you and your behaviours aren’t included in their definition of user data. They file that under “data about a user.”

This is a useful dodge when dealing with the public. Doubly so when dealing with legislators.

Take Action

I wish I could make a call to action that would change the situation but there’s isn’t any one thing. Time and time again, when people are aware of how data about them is created and handled, they want change.

The best thing that you can do is to inform yourself about how the services and apps you use handle and harvest your data.

Understanding that, you can make different choices for some services and ask the services you can’t change why they are collecting so much data about you.

]]>
https://markn.ca/2022/is-digital-privacy-important/ 67f6bbeaaf961b00014432c4 Mon, 24 Jan 2022 09:00:00 -0500
<![CDATA[ How To Explain Complex Technology Topics To A Broad Audience ]]> Want to share with others? Formatting issues in your reader? This post is available online, How To Explain Complex Technology Topics To A Broad Audience

The USA made headlines last week as a number of international airlines cancelled flights into the country. The President of Emirates airlines described it as, “…one of the most delinquent, utterly irresponsible issue…I’ve seen in my aviation career.”

If you’re interested, you can read more about it.

This issue reminded me of the challenge of breaking down a complex, technical topic for a broad audience. This is how I do it…

Research First

The first step to research to topic to a reasonable depth. The goal here is to hit ~85—90% awareness of the topic. After that point, the knowledge you gain is too specific and not applicable to the core idea you are going to communicate.

While you’re researching, make sure to keep notes on the key points that keep recurring. This is going to help you in the next step.

Key Points

Research done, I look through my notes. I’m trying to find the key points that are referenced often. What are the key points of this issue?

The trick here is to make sure that you boil it down to just the essentials.

It’s tempting to address the nuance. Don’t.

At least don’t the first time you explain the issue. You can always dive deeper later on.

Create The Storyline

Now it’s time to weave these key points into a narrative. When discussing technical topics, this storyline is going to be aligned to timing of an event and the layers required to understand the issue.

Make sure you are only communicating the key pieces that are required for the audience to understand the issue and no more.

Connect those pieces together in a way that tells the story of the issue. What happened is only part of if, the audience needs to care about the why too!

]]>
https://markn.ca/2022/how-to-explain-complex-technology-topics-to-a-broad-audience/ 67f6bbeaaf961b00014432c3 Sun, 23 Jan 2022 09:00:00 -0500
<![CDATA[ Risk Analysis (And Essays) Shouldn’t End in “Um” ]]> Want to share with others? Formatting issues in your reader? This post is available online, Risk Analysis (And Essays) Shouldn’t End in “Um”

Yesterdays atomic essay ended with the line “…um…”

That line probably broke a number of English grammar “rules” and left things on a bit of a cliffhanger.

Neither is a good thing for a risk analysis.

No Conclusion?

Why didn’t I draw a conclusion or provide the read with a tip to help the read figure out how likely an app is to have security problems?

Because it’s simply not possible.

And that’s a big problem.

A Best Guess Is Still A Guess

For years we saw security claims like “military-grade encryption” or “security seal” from a recognizable name in the security space.

Those claims don’t really mean anything. There are some claims—certifications—that can provide insights into a company’s security if you understand what they are

But you’ll need a deep understanding of the cybersecurity space to grasp their importance.

Verified compliance with frameworks like ISO27001, HITRUST, PCI-DSS, and others set a bar for security and require third party validation that a company meets that bar.

But if you’re not a cybersecurity practitioner, who’s heard of those?

Certainly not the everyday user.

Is There A Way Forward?

If there isn’t a simple way to determine the likelihood of a security incident happening, how can you make an informed risk decision?

You can make a reasonable determination about the data you’re trusting a company with, after all you’ve provided most of it.

To complete the second half of the function, you could assume 100% chance of your data being exposed and then act accordingly.

For sensitive data, this is a reasonable way forward. For data that’s not sensitive, it’s not a crazy approach either.

The problem is that we should have better information. In this case, better guarantees that companies are required to take cybersecurity seriously.

That would start to provide us with the data we need to determine the probability of an issue instead of just guessing.

]]>
https://markn.ca/2022/risk-analysis-and-essays-shouldnt-end-in-um/ 67f6bbeaaf961b00014432c2 Sat, 22 Jan 2022 09:00:00 -0500
<![CDATA[ How Can You Figure out How Likely an App Is to Have Security Problems? ]]> Want to share with others? Formatting issues in your reader? This post is available online, How Can You Figure out How Likely an App Is to Have Security Problems?

If we know how to evaluate the privacy impact of a mobile app. How do we determine the second part of the risk function, probability?

Challenges

There’s no data about the probability of an incident listed in the App Store alongside the app. There’s no metric, information, or even a hint of how seriously this developer—or any other—takes security anywhere near the app listing.

Striking out on the App Store, where can you turn to?

Search Results

You can search the app/service/developer name to see if there’s any mention or history of security or privacy issues in the past.

This only takes a minute.

Unfortunately, this doesn’t produce any level of assurance unless an issue was big enough or handled poorly enough to get noticed.

Legislation

Maybe there’s some protection in the law? The US is a major exception here as they don’t have strong, federal privacy legislation (it’s state by state and hit or miss).

Other jurisdictions like Australia, Canada, Japan, and the EU all have overarching privacy legislation that mandates some level of security effort by a company that collects personal data.

The challenge here is that it’s almost always worded as “make a reasonable effort” and the penalties for failing aren’t significant.

The notable exception is the EU where penalties for poor security are up to 2% of an organizations global turnover (and another 4% if they mishandle a breach).

Um, So?

Ok, so what’s the trick then? How can someone who’s about to download something like a mobile app understand what measures are taken to protect their data.

…um…

]]>
https://markn.ca/2022/how-can-you-figure-out-how-likely-an-app-is-to-have-security-problems/ 67f6bbeaaf961b00014432c1 Fri, 21 Jan 2022 09:00:00 -0500
<![CDATA[ How The App Privacy Card in the Apple App Store Matters To You ]]> Want to share with others? Formatting issues in your reader? This post is available online, How The App Privacy Card in the Apple App Store Matters To You

Risk is a function of the potential impact of something happen and the likelihood that the thing will happen.

We also know that digital privacy is the assurance that the system you are using only uses the data you intend in the way that you consent.

Let’s apply these concepts by examining the privacy disclosures in an Apple App Store listing.

The App

We’ll use the App of the Day for Apple’s iOS as our example.

Today, it’s Explain Everything Whiteboard. This app is an award winner and aims to help you “teach, present, sketchnote, record videos, and work together.”

App Store Disclosure

A required part of the App Store listing is the “App Privacy” card. This critical tool that helps you evaluate the potential impact of a breach or issues with the app.

“Explain Everything Whiteboard” tracks some data that isn’t directly linked to you; contact info, usage data, identifiers, diagnostics.

Digging deeper we find out that they collect a user ID, device ID, email address, diagnostics data (like crash data), and product interactions.

This “App Privacy” card is really a cheat sheet. For specifics, we’ll have to read the developer’s privacy policy (yes, really). This is a legal document that explains what’s legally possible from the app.

Impact

Given that the app allows you to collaborate with others and share your whiteboards, it’s reasonable to expect the collection of information in order to enable that.

The device ID, user ID, and email address are the pieces of information that are needed to do that.

If this data was exposed would it impact you?

Probably not. Your email address is public. You enter it everywhere. The device ID and user ID are also reasonably public as any app on your device is potentially going to have access to those as well.

The other information collection by the app is data designed to help optimize the app and focus the developers efforts. There’s nothing really sensitive there.

The App Privacy card has given us the information we need to understand how this app uses our data. With that, we’ve made a reasonable evaluation of the impact this app could have on our privacy…which is negligible.

Rinse and repeat this process for any app you’re interested in using from the App Store.

]]>
https://markn.ca/2022/how-the-app-privacy-card-in-the-apple-app-store-matters-to-you/ 67f6bbeaaf961b00014432c0 Thu, 20 Jan 2022 09:00:00 -0500
<![CDATA[ Do You Care About Data Privacy? Does Anyone? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Do You Care About Data Privacy? Does Anyone?

Data Privacy Day is coming up on the 28th of January. Privacy and security are closely linked and both issues that I care deeply about.

And while I’ve been preparing content for the day, one question continues to haunt me.

Does anyone care about digital privacy?

What Is Privacy?

The broader concept of privacy has many interpretations and is very different across cultures.

When it comes to digital or data privacy, we’re talking about how information about you is collected, processed, and used.

At the speed and scale that our technology works today, this is a major issue. Or at least it should be…right?

Social Media Pressure

The rise of social media at the dawn of the millennia changed how we view information about ourselves. We started to share freely with the world things that we only used to tell our close friends.

Whether or not this has been a positive change is a debate for another time.

The fact remains that 2.9 billion people log into Facebook each month. The amount of content they are sharing is mind boggling.

Does the normalization of sharing like this mean that privacy isn’t a concern?

Facebook—and other social networks—allow the user to control who sees their posts but public is the default for most networks.

Complexity Prevents Awareness

In order to preserve some sense of value to my privacy advocacy work over the year—and hopefully actually valid if you could ever measure it—I have a theory.

The complexity of the technology involved prevents most people from understanding the issues around data privacy.

It’s not that people don’t want control over their data, it’s that they don’t realize the extent to which they’ve lost control already.

It’s not immediately obvious to most people the amount of data that your devices and the software running on them have broadcast publicly. All so you can (ironically?) read this essay on privacy.

Every year I hope that Data Privacy Day moves the needle towards a more secure technology future where people are aware of and have control of their data online.

I’m honestly hopefully that’ll happen.

But I’m pragmatic enough to realize that it’ll take a lot of small steps to get there.

]]>
https://markn.ca/2022/do-you-care-about-data-privacy-does-anyone/ 67f6bbeaaf961b00014432bf Wed, 19 Jan 2022 09:00:00 -0500
<![CDATA[ Despite 5G’s Capabilities, Mobile Providers Can’t Connect With Airline Industry ]]> Want to share with others? Formatting issues in your reader? This post is available online, Despite 5G’s Capabilities, Mobile Providers Can’t Connect With Airline Industry

I spoke with Hallie Cotnam on CBC Ottawa Morning on 19-Jan-2022 about this issue and how the US ended up in this situation.

5G is here. 5G is rolling out. Just wait for 5G.

What is going on?!?

For the last few years, the mobile industry has been a buzz with 5G this and 5G that…and for good reason. The fifth generation (5G) of mobile network technologies has a lot to be excited about.

Not Just One Thing

The first thing you need to understand about 5G is that it’s not just one thing. As a term, 5G covers a range of technologies that are all aimed to take better advantage of specific areas of radio frequency.

The early cellular networks were not very efficient. They had a limited capacity to connect customers. That was ok, not many of us had cell phones back in 1970’s and 80’s.

But now, everyone has a smartphone.

For most conversations, you can think of 5G as three distinct technologies; the low, mid, and high band.

Low band is slightly faster than what we have today in 4G/LTE networks. It’s got good range and reasonable speeds. This is great for general use cases.

Mid-band is the sweet spot for big cellular networks. It’s reasonable range and has great speeds. This will be the new normal in a few years.

High band doesn’t go very far but is crazy fast. This section of 5G is best used in high density location or small spaces. Think stadiums (lots of people) or hospitals (small spaces with high bandwidth needs for those surgery robots).

But I Have 5G, Right?

Part of the problem is that in depending on the cellular network or phone provider, you may have had a “5G” phone or connection in your hand for the past few years…even though you didn’t notice anything different.

You’re not imagining that. Way too many announcements have pumped up the 5G hype train.

Which brings us around to the current issue in the United States.

In 2019, AT&T and Verizon won the auction to license the mid-band (or C-band) of the 5G spectrum in the USA. The price tag? $67 billion.

December 2021 was when this part of their 5G networks were supposed to go live. That got delayed repeatedly, eventually ending up on a 19-Jan-2022 launch date.

Why?

Catastrophic Rollout

Despite the 3 year design and rollout post-auction, it took until just recently for the aviation industry to really grasp the importance a potential issue. An issue the CEOs of United, American Airlines, Southwest, and Delta called “potentially catastrophic.”

It turns out that the frequency used for mid-band 5G (3.7—3.98 GHz) is “next” to the frequencies used by radio altimeters (4.2—4.44 GHz).

A radio altimeter is a very important piece of equipment. It helps the airplane know what altitude it’s flying at…especially critical in adverse conditions.

The altimeter is critical to several systems onboard the aircraft, including the auto landing and other systems.

With the gap between the frequencies in use, why is there an issue?

Like most technology, radio altimeters aren’t perfect. Older models could be susceptible to interference from 5G signals given their strength of those signals at lower altitudes.

Is this a problem? No one is quite sure.

The FAA (Federal Aviation Administration) issued a regulatory assessment on 23-Dec-2021 advising everyone of the potential risk and calling for collaboration in order to research the issue.

But Why?

This issue really boils down to two things. One it much easier to solve than the other.

The easier problem mitigating the potential impact of the rollout.

This has been a known issue well before the spectrum auction was held in 2019. The last minute advisories, open letters, and hyperbole should not have been needed and have muddled a reasonably simple issue.

There have been multiple opportunities since the auction to address the issue on any number of fronts…that didn’t happen. The result is the battle in the media until a reasonable compromise was reached last minute.

AT&T and Verizon will go ahead with the rollout of this section of their 5G networks as planned but will not enable any towers near airports. Effectively creating little protective bubbles around the airports until this can all be sorted out.

Don’t worry! 4G / LTE will still be available in this 5G-less bubbles.

The harder problem is how to balance the pressure new technologies are putting on the spectrum and how they can co-exist with older technologies.

Newer technologies are digital and use protocols and filters that can ignore signals that aren’t intended for them. As long as something isn’t blasting so loud on frequencies they shouldn’t be that it drowns everything else out, the filtering built into new technology is sufficient to avoid problems like this.

That leaves the multitude of other technologies that are using spectrum with assumptions that no longer hold up.

This has been managed by licensing of the spectrum that included specific limits on broadcast power. That’s why you can listen to 91.5 MHz FM radio in one city and get a completely different station on 91.5 MHz in another city.

Their broadcast licenses limit the power of their signals and reduce the chances of interference.

That system works fine as long as things are stationary and everyone respects the rules. Newer technology is far more precise and spectrum is a finite resource.

We’ll see more demand for licenses that are closer and closer to each. There won’t be as much space between uses. This issue will pop up again and again until we phase out older technologies.

But those technologies are working just fine. It’s hard to justify the replacement of a technology used in one industry for the benefit of a completely different industry.

As usual, the technology side is pretty straight forward (if still challenging) but it’s the economics and motivation that are the roadblock.

References

]]>
https://markn.ca/2022/despite-5gs-capabilities-mobile-providers-cant-connect-with-airline-industry/ 67f6bbeaaf961b0001443136 Wed, 19 Jan 2022 09:00:00 -0500
<![CDATA[ Encryption Is Good For You and Your Community ]]> Want to share with others? Formatting issues in your reader? This post is available online, Encryption Is Good For You and Your Community

With alarming regularity, the information security and privacy world has the same debate with governments around the world.

Every few years there is a push to implement back doors in encryption technology. Regardless of the government, the straw man argument is the same; back doors in encryption are the only thing that can keep everyone safe.

End-to-end Encryption

End-to-end encryption (E2E) is a technique that ensure that only the parties involved in a communication can access it’s contents.

Information about the communication is still visible to the network is travelled across. Things like source, destination, size, etc. are all required to actually get the message from one place to another.

So it’s possible to know that you and I communicated on Tuesday from 09:21 to 09:33 and that connection involved the transfer of 486 MB of information.

What did that communication entail? Only you and I can tell someone that.

Why Encrypt?

The next question asked by most people is, “Why would you want to encrypt your communications?”

I think the opposite question is more enlightening, “Why would you want any number of network providers and service providers to be able to see your communications any time they want?”

If communication is not encrypted, it’s trivial for someone in support to look at that information. Same goes for someone running one of the network providers.

Will they do that? We don’t have the hard data to properly scope this risk. But we do know that breaking encryption makes that interception trivial.

What’s The Harm?

The argument against encryption, or more specifically to include a backdoor in encryption schemes, is that governments and law enforcement should be able to monitor any communication.

In most countries, this is a capability already written into existing law for traditional technologies. However, those capabilities were granted well before the internet and haven’t been reexamined for today’s digital age.

To be clear, a backdoor that only the “good guys” can use is a fallacy. The experts agree.

A backdoor is an introduced weakness and any weakness can be exploited.

Open, transparent discussion is required to find a balanced path forward. Using the straw man of keeping you safe only sets up a conflict.

This discussion must seek to balance all concerns with data to support the highlighted risks.

]]>
https://markn.ca/2022/encryption-is-good-for-you-and-your-community/ 67f6bbeaaf961b00014432be Tue, 18 Jan 2022 09:00:00 -0500
<![CDATA[ Would You Put Your Security in the Hands of a Guess? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Would You Put Your Security in the Hands of a Guess?

If I asked you to cross the street without looking for traffic, but instead just guessing if there was an oncoming car, would you cross?

Of course not! That’s absurd. Why take such a huge risk with any data to make an informed decision.

Sadly, in the digital world, we’re crossing the street all of the time. Digital risk evaluation is often based on best guesses and not data.

Remember, risk is a combination of the impact of an event and the likelihood it will happen.

Guess What?

Say you’ve just download a new mobile game and it wants you to create an account in order to play.

That process requires you to enter your full name, email address, physical address, gender, annual household income, and phone number.

When you’re deciding to whether or not to give the game this information, what are you basing the decision on?

The look of the app? The fact that they haven’t been in the headlines? Their terms of service and privacy policy?

It usually boils down to reputation. Why?

What’s The Event?

To properly figure out the risk here, we need to understand what could happen.

This information is considered PII or personally identifiable information. Some of it is available other places (like the online shops you frequent) but it’s not something you want to give out readily.

What is the impact is this information being in the hands of the app developer? What if the information was made public?

What’s The Impact?

The information could make you a target in the real world.

After all, the household income typically correlates to the amount of goods in the home. It also indicates the earning potential if someone stole your identity.

The impact could be massive.

Data Desperately Needed

The challenge is now finding data that could indicate how likely that impact is to occur.

You could search online about the company’s reputation. Have they had breaches in the past? Do they have a clear privacy policy and terms of service?

You could look for discussions about their reputation. Information about how they use the data they collect and how they make money will help here.

But at the end of the day, it’s not enough to make an informed decision. There’s no statistic that says, “This app has a 48% of exposing your personal information.”

That’s no way to make a risk decision, but we do it every day!

For the record, when you can’t gather enough data to get an idea of the likelihood, the potential impact should sway your decision…especially with PII.
]]>
https://markn.ca/2022/would-you-put-your-security-in-the-hands-of-a-guess/ 67f6bbeaaf961b00014432bd Mon, 17 Jan 2022 09:00:00 -0500
<![CDATA[ What Is Risk? ]]> Want to share with others? Formatting issues in your reader? This post is available online, What Is Risk?

Risk is a common topic when talking about cybersecurity and digital privacy.

At some level, we all understand the idea of risk but what are we actually talking about?

Risk is way of describing exposure to danger.

Two Parts

To properly describe a risk, you need to pieces of information;

  1. The potential impact of the event
  2. The likelihood of the event occurring

You need both to make an informed decision. Unfortunately, in the digital world we rarely have both pieces of the risk puzzle.

Impact

Let’s examine the risk of someone gaining access to our crypto wallet.

If a cybercriminal gains access to our wallet they could take our cryptocurrency, transfer ownership of any NFTs, and impersonate us online if we’ve used that wallet as an identity.

The makes the impact directly related to what we’ve used that wallet for.

The value of cryptocurrency and NFTs are reasonable easy to evaluate. The impact of someone impersonating us is harder to qualify but is generally on the more serious side of things.

In the digital world, we usually have a good idea of the impact of an event.

Potential

Can we estimate the likelihood of this event occurring?

Assuming that you’re not broadcasting your wallet password, how likely is a cybercriminal or other malicious actor to try and access your wallet?

There’s not direct data to support any specific probability. That means we have to estimate…guess basically.

You could take the more secure/paranoid route and assume it’ll happen. This means you’ll take steps to reduce the potential impact because you assume you’ll lose control of your wallet at some point.

You could take the exact opposite approach and assume it’ll never happen. This utopian view rarely ends well over time.

A third possible approach is to take reasonable steps that become more strict as the value of what your wallet can access increases over time.

This is a good approach but it’s not based on any real data.

Guessing Digital Risk

The lack of probability data means that digital risks are evaluated using “best guess” numbers. There are no alternatives at the moment as the community scrambles to gather more accurate probability data.

But it’s a long way from the data-driven approach we need…

]]>
https://markn.ca/2022/what-is-risk/ 67f6bbeaaf961b00014432bc Sun, 16 Jan 2022 09:00:00 -0500
<![CDATA[ Security Challenges With NFTs ]]> Want to share with others? Formatting issues in your reader? This post is available online, Security Challenges With NFTs

A NFT or non fungible token is the representation of an asset in a smart contract. There are two immediate security challenges with NFTs that you should be aware of.

Crypto Wallet

You need an application or service called a wallet in order to prove that your own this digital token.

This program helps you interact with the blockchain. It helps you provide which assets you own, conduct transactions, and more.

Remember, the wallet doesn’t store the actual NFT, that’s on the blockchain. It does store the bits required to prove that you own the NFT though.

That makes it a security risk.

If you lose access to your wallet. You could lose all of your digital assets with no way of getting them back. That’s the downside of decentralization.

This means you need to protect your wallet diligently and any system that can access it.

Metadata Problems

As a digital object, the NFT is really a collection of metadata about an asset.

It contains an “image” field that points to the asset itself. This presents a number of challenges.

As written, the standard doesn’t present any method of validating what’s at the URI. Just the ability to add a name and description.

Who own’s that domain? Who’s running that server?

How do you know it will be up and running in a week? In a month? How about a year or two down the line?

Because the NFT is on the blockchain, there’s no method of updating it. That lack of surety around the URI is a security challenge.

The Way Forward

As part of a smart contract, NFTs have some flexibility. Their current form is a very basic implementation.

Over time, expect improvements to the format that will help address these concerns. We’re seeing the start of that work within smart contracts today.

But until it matures, make sure you understand where that asset actually lives and do you best to lock down your crypto wallet.

]]>
https://markn.ca/2022/security-challenges-with-nfts/ 67f6bbeaaf961b00014432bb Sat, 15 Jan 2022 09:00:00 -0500
<![CDATA[ You Just Bought An NFT, What Did You Actually Buy? ]]> Want to share with others? Formatting issues in your reader? This post is available online, You Just Bought An NFT, What Did You Actually Buy?

NFTs are all the rage right now. And why not?

There’s an interesting technology that has a lot of potential. Just like the early days of cryptocurrencies, there’s a bit of a gold rush happening.

Some NFT projects will succeed. A lot more will fail. Eventually things will stabilize and some community norms will emerge.

For now though, it’s important to understand what an NFT actually is. Like physically, well…digitally 😉.

Smart Contracts

Smart contracts are agreements expressed in code, instead of a mountain of legal paperwork.

This code lives on a blockchain so it’s transparent and verifiable. The blockchain will execute the contract automatically without a third party being involved when various requirements are met.

When I pay you X, I get NFT Y.

Of course, smart contracts can be much more complex but you get the idea.

NFT

An NFT is a unique record that represents an asset of some kind.

What is represents is entirely dependent on the smart contract.

Right now, we’re seeing NFTs used to represent digital artwork, membership in a group, and even as tickets to events.

When you dig into the code, an NFT is simply a name, description, and link to an image.

That’s it.

A Start

Remember, an NFT represents something. It isn’t that thing itself.

Take for example the Bored Ape Yacht Club. This funky collection provides the owner of the NFT with a digital asset (an artwork of a unique Bored Ape) and membership to the BAYC club.

Membership to the club is proven by showing you have possession of the NFT. That’s done through a standardized crypto wallet just like logging in with a username and password.

Proving you own the artwork can be done by matching the NFT to a license granted by the Bored Ape Yacht Club. Restricting usage of the artwork is a whole different matter.

If you want to make sure you are the only one using that Ape as an avatar or printing it out, you need the global copyright system and its enforcement mechanisms. That means a court of law.

NFTs may help prove ownership or licensing agreements but they don’t stop a major problem with digital assets: a complete disregard for copyright law.

It’s critical to understand any technologies goals and it’s limitations. With NFTs they are incredibly useful representations of assets but at the end of the day, they are just representations.

]]>
https://markn.ca/2022/you-just-bought-an-nft-what-did-you-actually-buy/ 67f6bbeaaf961b00014432ba Fri, 14 Jan 2022 09:00:00 -0500
<![CDATA[ What Are Blockchain, Web3, and NFTs? ]]> Want to share with others? Formatting issues in your reader? This post is available online, What Are Blockchain, Web3, and NFTs?

Web3, NFTs, and the blockchain at the apex (hopefully?) the hype cycle right now. These concepts are often talked about as a group but then are in fact distinct concepts and it’s important to recognize that.

Let’s dive in and clarify what each one is…

Web3

Web3 describes a new iteration of the web that is decentralized and allows for a common economic system in order to recognize more granular value outside of traditional structures.

This is a shift away from Web 2.0 which saw the rise of centralized data collection for ad tech and data aggregation in social media networks.

The implementation specifics of Web3 are in flux and will be for a while yet.

There is no “cut over” date or launch day. This’ll be an organic process as Web3 services gain popularity.

Blockchain

A blockchain is a linked list of records. Each record can be used to validate the previous record. This means that records can’t be changed without changing every record after it.

This allows the blockchain to maintain its integrity while distributed instead of sitting with one organization or company.

Anyone can verify each entry, ensuring that it hasn’t changed. That makes blockchains useful in any number of situations where verification of something is required. Things like voting, financial transactions, proof of ownership, etc.

NFT

An NFT is a non-fungible token (horrible name). This is an implementation of a specific contract stored on a blockchain (so it can be verified). Most commonly, an NFT is an item within an Ethereum smart contract.

The idea is to have a technological method of proving ownership of something. An NFT is a verifiable certificate of authenticity or ownership.

NFTs have been used in a number of creative ways. As tickets to events. Proving ownership for artworks. To representing ownership in a shared endeavour.

What’s Next?

Web3, blockchain, and NFTs present interesting ideas to change certain aspects of our digital world. Like any technology or approach there as strengths and weaknesses to each.

The challenge—as always—is recognizing those and making sure to use the best technology to solve the problem at hand.

]]>
https://markn.ca/2022/what-are-blockchain-web3-and-nfts/ 67f6bbeaaf961b00014432b9 Thu, 13 Jan 2022 09:00:00 -0500
<![CDATA[ Meeting Goals With Feedback Loops ]]> Want to share with others? Formatting issues in your reader? This post is available online, Meeting Goals With Feedback Loops

We use technology in almost every aspect of our lives.

The gap between the expectations of that technology and the reality of its implementation is fascinating.

The internet is held together with bubble gum and duct tape.

But it works…and we continue to see fantastic new innovations and ways of connecting to each other come to light.

Goals

When we’re building technology, we need to focus on our goals. Security and privacy are critical parts of those efforts.

Over the past few years, we’ve seen a remarkable reduction in the effort required to create technology solutions. That’s fantastic!

But it’s critical that we remember these solutions have a lifecycle and we need to set our goals to account for that.

If setting a good goal is hard, achieving that goal is even more challenging.

Spirals

Achieving your goal in tech is hard because those goals are often very ambitious. It’s easy to get swept up in the possibilities of a digital solution.

You start simple and things quickly spin out of control.

Before you know it, you’ve got from the Flintstones to the Jetsons without shipping anything to your prospective users.

One way to avoid this spiral is to use the concept of simple feedback loops.

Loops

A feedback loop has three stages; learn, build, and measure.

To be effective, a loop should be short.

The shorter the time between trying out something new (build) and learning about it, the more impactful that learning is.

This is core concept of modern solution development. When done well, feedback loops can help accelerate your work and make sure that you hits your goals.

]]>
https://markn.ca/2022/meeting-goals-with-feedback-loops/ 67f6bbeaaf961b00014432b8 Wed, 12 Jan 2022 09:00:00 -0500
<![CDATA[ Your Goal In Building Something With Technology ]]> Want to share with others? Formatting issues in your reader? This post is available online, Your Goal In Building Something With Technology

It’s exciting building solutions with the latest frameworks and technology. Especially when there’s a lot of hype and excitement behind those projects.

However, there’s a lot to be said for using technology that’s tried and true.

Sure, it isn’t as cool as the newer stuff but it’s issues are well documented and knowing that, you can design around them when necessary.

Should you use the shiny new tech or stick to the tried and true?

What’s The Goal?

As expected — hopefully — it’s never a simple this or that decision.

Before you can what a choice on what to build with, you have to figure out what the goal of what you are building is.

Most teams set their goal as to solve problem X.

That’s a start but it’s not finished.

Systems Thinking

Solutions today are dynamic systems. They have a complete lifecycle. You don’t just write the code and then forget about it.

You need to design, write, and then deploy the system. Once it’s been deployed, you need to keep it running effectively until it’s time to retire the solution.

This broader view brings a new perspective to our goal.

We no longer need to just solve problem X. We need to do so in a sustainable manner.

Updated goal: Solve problem X in a sustainable manner throughout its lifecycle.

New Goal

Operating the solution requires it to be maintainable.

How does that shiny new framework scale? How frequently is it patched? The answer to these questions will impact the choices you make through the systems lifecycle.

Shiny doesn’t always mean better.

]]>
https://markn.ca/2022/your-goal-in-building-something-with-technology/ 67f6bbeaaf961b00014432b7 Tue, 11 Jan 2022 09:00:00 -0500
<![CDATA[ Digital Privacy Is All About Choice ]]> Want to share with others? Formatting issues in your reader? This post is available online, Digital Privacy Is All About Choice

When we talk about privacy, what are we really talking about?

The formal definition of privacy is definitely outdated. Even the common understanding has failed to keep up with our digital world.

In the digital world, privacy as a human right manifests itself in very different ways. It’s not keeping to yourself. It’s about understanding your data and the data about you and how that data is used.

Focusing on the goal of digital privacy is critical to success. That goal is 👇

The assurance that the system you are using only uses the data you intend in the way that you consent.

The challenge (as always) is in the implementation.

Choices

Privacy is all about choices. Where it breaks down is the difference between an implicit and explicit choice. The complexity of the technology we use everyday amplifies this challenge, making it extremely difficult for most people to make explicit choices about their data.

A Web Page

Most users would expect that the web page they’ve asked for knows a few things about them. You could reasonably expect that the page knows what browser you’re using, whether or not you’re logged into the site, among other things.

If you’re a software engineer, you might recognize more nuance.

You know there are multiple systems that will see the request. That the browser is capable of a lot more than just showing a page. You understanding that when you ask for one page, you’re probably getting data from at least ten different locations. With a deeper understanding of the technology at play, the engineer knows there is far more data and systems involved.

Given that gap, can a user meaningfully consent to data collection and sharing? How do we even start to address this challenge given how prevalent technology is in our communities?

]]>
https://markn.ca/2022/digital-privacy-is-all-about-choice/ 67f6bbeaaf961b00014432b6 Mon, 10 Jan 2022 09:00:00 -0500
<![CDATA[ Stop Focusing on Stopping Hackers and Cybercriminals ]]> Want to share with others? Formatting issues in your reader? This post is available online, Stop Focusing on Stopping Hackers and Cybercriminals

If the goal of cybersecurity is to make sure that the system you are building works as intended and only as intended, what about stopping hackers?

What about preventing malware and ransomware? What about those ridiculous scenes we see in TV and the movies? Isn’t that security’s job?!?

Calm down, it’s ok. That’s all in there still.

But if your primary goal is to stop something from happening, you’re creating more problems than you’re solving.

Stop That

In the physical world of security, it’s easy to track and measure a stopping type goal.

Anyone can figure out how to track your performance if you goal is, “Make sure this painting doesn’t get stolen.”

As we cross over into the digital world, things get exponentially more complex. You can’t assume that you would know if something bad happened. Technology is just too complex and it changes too quickly.

The best way forward for cybersecurity is to assume a compromise at some point and try to figure out the best way to reduce any potential impacts.

Teamwork

Our updated goal encourages systems level thinking and requires teamwork.

The goal of cybersecurity is to make sure that the system you are building works as intended and only as intended.

If it sounds odd to think that security teams and people building technology should assume failure in their work. I would encourage you to try and view it as more pragmatic.

For really critical activities, it’s important to have a backup plan.

If you applied to University or College, odds are you applied to more than one school. You didn’t want to be left without an option.

More important than a backup plan, this goal forces teams to work together towards a single goal.

…and working together to build better systems has benefits well beyond just security.

]]>
https://markn.ca/2022/stop-focusing-on-stopping-hackers-and-cybercriminals/ 67f6bbeaaf961b00014432b5 Sun, 09 Jan 2022 09:00:00 -0500
<![CDATA[ Why Aren’t Security and Privacy Part of the Foundation of Technology? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Why Aren’t Security and Privacy Part of the Foundation of Technology?

Is this Secure? Does this protect my privacy?

The first question I hear regularly from people building technologies. The second, from those who use that tech. These questions are two sides of the same issue.

Security and privacy are inextricably linked.

There are formal definitions for both but their goals can be stated simply.

Cybersecurity aims to make sure that the system you are building works as intended and only as intended.

Digital privacy is the assurance that the system you are using only uses the data you intend in the way that you consent.

How do you convey intentions in a digital world?

If you searched for sneakers, it would be reasonable to expect ads for sneakers among the other results. You’ve explicitly expressed, “I’m interested in sneakers.”

There’s a clear line between the action and result.

But why do those sneaker ads follow you around throughout the day?

Reading the news, watching sport highlights, shopping for groceries; sneaker ads.

When the teams built those sites or even the browser you use to view it, did they intend for you to be tracked in this way?

Originally, no.

The technology that enables this scenario combines existing standards and stretching features into new uses.

The browser you’re using right now has a relatively unique “fingerprint.” It’s a combination of the features available, your system, where you other, and other factors.

Each of these factors has a different and understandable use.

Yet they are also being used in an unintended way to track you. And there’s a lot more data than you intend being shared about it.

This common and widely accepted workflow violates both the goals of security and privacy.

Why? Because security and privacy were never first class considerations when these systems were built.

Security and privacy were bolted on afterwards and that continues to cause major issues for all of us daily.

]]>
https://markn.ca/2022/why-arent-security-and-privacy-part-of-the-foundation-of-technology/ 67f6bbeaaf961b00014432b4 Sat, 08 Jan 2022 09:00:00 -0500
<![CDATA[ Can We Improve How IDT Stored Secrets in AWS in 2017? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Can We Improve How IDT Stored Secrets in AWS in 2017?

In late 2017, IDT did an AWS “This is My Architecture” video. The video talks about how they managed secret information in their AWS environment.

Now, a few years later, I react to that video and see what’s stood the test of time, what could be done simpler given today’s technology, and generally critique the design against the AWS Well-Architected Framework.

The AWS Well-Architected Framework

The AWS Well-Architected Framework is designed to help you and your team make informed trade offs while building in the AWS Cloud. It’s built on six pillars;

  • Operational Excellence
  • Security
  • Cost Optimization
  • Reliability
  • Performance Efficiency
  • Sustainability

There pillars cover the primary concerns of building and running any solution. And as much as we’d all love to have everything, that’s just not possible.

…enter the framework.

It’ll help you strike the right balance for your goals to make sure that your build is the best it can be now and moving forward.

Why Architecture?

I often get asked why I talk about building in the cloud and architectural choices so often…aren’t I a security person?

Yes, I do focus on security and architecture is a critical part of that.

There’s really two types of security design work. The first is when you’re handed something and need to make sure the risks of that technology matches the risk appetite of the users.

The second type is when you’re building the technology. This is where making choices informed by security early in the process can have profound effects. You’re no longer bolting security on but building it in by design.

That’s why I talk about architecture and building so much. It’s where we all can have the largest possible security impact!

This video—and the ones that will come after—looks at a specific set of design decisions and how they balance the concerns of the AWS Well-Architected Framework…where security is one of the six pillars.

IDT’s Design

At the time, IDT was using Hashicorp Consul to manage configurations in their environment. As a part of that, they had sensitive information (like API access credentials) stored with that information.

Consul allowed them to control distribution and access to that data in an effective manner. The challenge I have with the design (though understandable at the time) is the combination of sensitive and non-sensitive (or “not-as-sensitive”) information. That management approach generally leads to some challenges down the road.

A clear separation is usually a better approach. It allows for stricter permissions to be put in place for the sensitive information. This could strike a better balance between the application of least privilege and keeping operational overhead low.

Learn more in the reaction video 👆.

Btw, I’ve updated my course, “Mastering The AWS Well-Architected Framework” on A Cloud Guru. If you want a solid walk through of the ideas behind the framework and how to apply it to your work in the AWS Cloud, check it out!
]]>
https://markn.ca/2021/can-we-improve-how-idt-stored-secrets-in-aws-in-2017/ 67f6bbeaaf961b0001443186 Mon, 13 Dec 2021 09:00:00 -0500
<![CDATA[ Can We Improve How iRobot Deployed Microservices in 2017? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Can We Improve How iRobot Deployed Microservices in 2017?

In late 2017, iRobot did an AWS “This is My Architecture” video. The video talks about how they deployed their microservices in AWS.

Now, a few years later, I react to that video and see what’s stood the test of time, what could be done simpler given today’s technology, and generally critique the design against the AWS Well-Architected Framework.

The AWS Well-Architected Framework

The AWS Well-Architected Framework is designed to help you and your team make informed trade offs while building in the AWS Cloud. It’s built on six pillars;

  • Operational Excellence
  • Security
  • Cost Optimization
  • Reliability
  • Performance Efficiency
  • Sustainability

There pillars cover the primary concerns of building and running any solution. And as much as we’d all love to have everything, that’s just not possible.

…enter the framework.

It’ll help you strike the right balance for your goals to make sure that your build is the best it can be now and moving forward.

Why Architecture?

I often get asked why I talk about building in the cloud and architectural choices so often…aren’t I a security person?

Yes, I do focus on security and architecture is a critical part of that.

There’s really two types of security design work. The first is when you’re handed something and need to make sure the risks of that technology matches the risk appetite of the users.

The second type is when you’re building the technology. This is where making choices informed by security early in the process can have profound effects. You’re no longer bolting security on but building it in by design.

That’s why I talk about architecture and building so much. It’s where we all can have the largest possible security impact!

This video—and the ones that will come after—looks at a specific set of design decisions and how they balance the concerns of the AWS Well-Architected Framework…where security is one of the six pillars.

iRobot’s Design

At the time, iRobot was leveraging Amazon RDS (and still may be). They set out to build a way deploy their various microservices in a consistent manner while presenting a unified API to their mobile client and other consumers.

This system needed to provide various build artifacts throughout the process and being entirely serverless at a time when that ecosystem of tools was just beginning to develop.

Learn more in the reaction video 👆.

Btw, I’ve updated my course, “Mastering The AWS Well-Architected Framework” on A Cloud Guru. If you want a solid walk through of the ideas behind the framework and how to apply it to your work in the AWS Cloud, check it out!
]]>
https://markn.ca/2021/can-we-improve-how-irobot-deployed-microservices-in-2017/ 67f6bbeaaf961b0001443185 Mon, 06 Dec 2021 09:00:00 -0500
<![CDATA[ How To Build Streaming Media Solutions In The AWS Cloud ]]> Want to share with others? Formatting issues in your reader? This post is available online, How To Build Streaming Media Solutions In The AWS Cloud

The AWS Well-Architected Framework’s Streaming Media Lens helps you understand the challenges of building a streaming video/audio solution in the AWS cloud.

This video 👆 walks you through the highlights of the Lens and explain the key areas of concern for these types of designs.

This lesson on the Streaming Media Lens is part of my course on the entire framework. That course is over 4 hours in length and help you understand the value of the framework and how to use it to build a success cloud team.

This course is available over on the A Cloud Guru platform.

]]>
https://markn.ca/2021/how-to-build-streaming-media-solutions-in-the-aws-cloud/ 67f6bbeaaf961b00014432b3 Thu, 02 Dec 2021 09:00:00 -0500
<![CDATA[ Werner Vogel's Keynote at AWS re:Invent 2021 ]]> Want to share with others? Formatting issues in your reader? This post is available online, Werner Vogel's Keynote at AWS re:Invent 2021

AWS re:Invent is always THE event in cloud. Werner Voegls delivered the latest version of his hotly anticipated keynote on day four.

This 👇 is the Twitter thread of my coverage of the keynote…

Tweet 1/166 👇 Next tweet

. @werner takes the stage @awscloud #reinvent on day four. this is always a hotly anticipated keynote. for the past few years Werner has delivered a talk that shifts how builders view the problems they solve & changes the way they work. what does he have in store for us today?


Tweet 2/166 👇 Next tweet 👆 Start

love this intro video for @werner #reinvent

Tweet 3/166 👇 Next tweet 👆 Start

so many callbacks and shout outs! #reinvent

Tweet 4/166 👇 Next tweet 👆 Start

remember @QuinnyPig is also live tweeting this keynote. check out his take 👇 https://twitter.com/QuinnyPig/status/1466444420732133384 #reinvent

Tweet 5/166 👇 Next tweet 👆 Start

honestly, it is hard to believe that it’s already been ten years of @awscloud #reinvent

Tweet 6/166 👇 Next tweet 👆 Start

here we go! #reinvent

Tweet 7/166 👇 Next tweet 👆 Start

1st t-shirt from @werner, “The Stranglers” (music, not tech reference 😉) @awscloud #reinvent

Tweet 8/166 👇 Next tweet 👆 Start

2006: Innovation was constrained (pre-cloud) #reinvent

Tweet 9/166 👇 Next tweet 👆 Start

cloud changed the game by making everything a programmable resource, @werner #reinvent

Tweet 10/166 👇 Next tweet 👆 Start

EC2 in 2006 : super simple, 3 instance types #reinvent

Tweet 11/166 👇 Next tweet 👆 Start

let’s say it’s changed slightly since then… #reinvent

Tweet 12/166 👇 Next tweet 👆 Start

NEW FEATURE: Amazon EC2 M1 Mac instances << awesome! #reinvent

Tweet 13/166 👇 Next tweet 👆 Start

as per @apple, 60% cost improvement over Intel-based Macs #reinvent

Tweet 14/166 👇 Next tweet 👆 Start

EC2 launches 60 million instances every day! << that’s crazy. just crazy #reinvent

Tweet 15/166 👇 Next tweet 👆 Start

The cloud removed constraints, @werner << …and that opened up so many possibilities to change how we work #reinvent

Tweet 16/166 👇 Next tweet 👆 Start

. @werner seems slightly frustrated at the laws of physics. totally understand 🤣 #reinvent

Tweet 17/166 👇 Next tweet 👆 Start

remember when @awscloud was just a handful of regions? #reinvent

Tweet 18/166 👇 Next tweet 👆 Start

adding more regions made things like Alexa possible. without those regions, latency would be too high and it’s wouldn’t feel natural #reinvent

Tweet 19/166 👇 Next tweet 👆 Start

. @awscloud has become massive over the past 15 years. lots of infrastructure in place to help reduce latency and provide choice more at https://aws.amazon.com/about-aws/global-infrastructure/

Tweet 20/166 👇 Next tweet 👆 Start

Tweet 21/166 👇 Next tweet 👆 Start

NEW FEATURE: @awscloud new local zones starting in 2022 #reinvent

Tweet 22/166 👇 Next tweet 👆 Start

Tweet 23/166 👇 Next tweet 👆 Start

customer example from @werner: JackTrip, a live performance service that leverages @awscloud Local Zones to avoid latency issues << very cool more on them at https://jacktrip.org/index.html #reinvent

Tweet 24/166 👇 Next tweet 👆 Start

. @werner is continuing the latency theme. now talking about @awscloud Wavelength more at https://aws.amazon.com/wavelength/ #reinvent

Tweet 25/166 👇 Next tweet 👆 Start

networking in 2006: super simple and direct #reinvent

Tweet 26/166 👇 Next tweet 👆 Start

this led to a lot of innovation around @awscloud EC2 networking. lots of use cases required more, so they built it #reinvent

Tweet 27/166 👇 Next tweet 👆 Start

EC2 Classic eventually got deprecated…eventually…almost 🤣 15-Aug-2022 is the current target https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ec2-classic-platform.html

Tweet 28/166 👇 Next tweet 👆 Start

this is where we’re at today with network & delivery services. crazy rich set of options to build solutions with #reinvent

Tweet 29/166 👇 Next tweet 👆 Start

some @awscloud customers are running thousands of VPCs, some even 10,000+ VPCs #reinvent

Tweet 30/166 👇 Next tweet 👆 Start

NEW SERVICE: @awscloud Cloud WAN, build, manage, and monitor global wide area networks for folks with those 👆 types of challenges #reinvent

Tweet 31/166 👇 Next tweet 👆 Start

to use: 1. select regions you want to use 2. @awscloud VPN or Direct Connect to closest site 3. 🧙 …though I’m sure there’s more to it 😉


Tweet 32/166 👇 Next tweet 👆 Start

Tweet 33/166 👇 Next tweet 👆 Start

Tweet 34/166 👇 Next tweet 👆 Start

can’t wait to dig into @awscloud Cloud WAN. seems like a godsend for large scale networks. those get super complicated quickly, this could really help #reinvent

Tweet 35/166 👇 Next tweet 👆 Start

rare shot of @awscloud hardware…it does exist, btw #reinvent

Tweet 36/166 👇 Next tweet 👆 Start

more hardware shots. it’s rare to see these at an @awscloud event without someone smashing them on stage 🤣 #reinvent

Tweet 37/166 👇 Next tweet 👆 Start

a peek at what @awscloud Outposts offers from those units #reinvent

Tweet 38/166 👇 Next tweet 👆 Start

on to #IoT now… #reinvent

Tweet 39/166 👇 Next tweet 👆 Start

a bit of @awscloud Industrial now more at https://aws.amazon.com/industrial/ #reinvent

Tweet 40/166 👇 Next tweet 👆 Start

lots more hardware pics…what is happening?!? #reinvent

Tweet 41/166 👇 Next tweet 👆 Start

“Video is a data stream to be analyzed, instead of something to be watched”, @werner #reinvent

Tweet 42/166 👇 Next tweet 👆 Start

more on Monitron: https://aws.amazon.com/monitron/ more on Panorama Appliance: https://aws.amazon.com/panorama/appliance/ #reinvent

Tweet 43/166 👇 Next tweet 👆 Start

on to the Snow* family now…are we getting a new one?!? #reinvent

Tweet 44/166 👇 Next tweet 👆 Start

like Snow Globe? #reinvent

Tweet 45/166 👇 Next tweet 👆 Start

nope. off to space now. more on @awscloud Ground Station at https://aws.amazon.com/ground-station/ #reinvent

Tweet 46/166 👇 Next tweet 👆 Start

more on the Hope Probe at https://www.emiratesmarsmission.ae/ #reinvent

Tweet 47/166 👇 Next tweet 👆 Start

customer up now, @capellaspace #reinvent

Tweet 48/166 👇 Next tweet 👆 Start

talking about monitoring shipping activity in the real world. maybe through simulation? the intro was confusing and in inspire-speak #reinvent

Tweet 49/166 👇 Next tweet 👆 Start

terrestrial sensors? #reinvent

Tweet 50/166 👇 Next tweet 👆 Start

ok, that was apparently a transition into the justiciation for sensors in space #reinvent

Tweet 51/166 👇 Next tweet 👆 Start

…which I’m pretty sure we all understand the advantages of. we’ve watched enough crazy sci-fi to know https://www.youtube.com/watch?v=EuOlYPSEzSc&feature=youtu.be #reinvent

Tweet 52/166 👇 Next tweet 👆 Start

these sensors generate a massive amount of data #reinvent

Tweet 53/166 👇 Next tweet 👆 Start

now tying this data challenge back to the computer science & operational issues << for these types of stories, it’s really important to understand the audience builders understand the scale of 500PB as a stream. just dive in and use the space angle to frame the story #reinvent

Tweet 54/166 👇 Next tweet 👆 Start

I want to know more about this use case. but this isn’t the format for it. need something that follows the data throughout the system, that would really hit home #reinvent

Tweet 55/166 👇 Next tweet 👆 Start

this example of making a request to the satellite sensors is way more impactful. lead with that @capellaspace! #reinvent



Tweet 56/166 👇 Next tweet 👆 Start

“One click to make a request from a space sensor” << that’s a hell of a lede #reinvent


Tweet 57/166 👇 Next tweet 👆 Start

more from @capellaspace at https://t.co/9c8JR3Hvv0 #reinvent

Tweet 58/166 👇 Next tweet 👆 Start

#reinvent

Tweet 59/166 👇 Next tweet 👆 Start

did not see this when it launched in March: https://aws.amazon.com/blogs/publicsector/announcing-aws-space-accelerator-startups/ #reinvent

Tweet 60/166 👇 Next tweet 👆 Start

Lunar 1 region “may not be that far away” << @KroonenburgRyan called in two weeks ago in our @acloudguru pre-#reinvent webinar! …he was just off a bit on the timing

Tweet 61/166 👇 Next tweet 👆 Start

‘nuff said #reinvent

Tweet 62/166 👇 Next tweet 👆 Start

Distributed but not decentralized, @werner #reinvent

Tweet 63/166 👇 Next tweet 👆 Start

on to @awscloud IAM now…I’m getting excited /cc @AWSSecurityInfo #reinvent

Tweet 64/166 👇 Next tweet 👆 Start

IAM turned 10 this year. more from the @awscloud blog at https://aws.amazon.com/blogs/aws/happy-10th-birthday-aws-identity-and-access-management/ #reinvent

Tweet 65/166 👇 Next tweet 👆 Start

IAM is part of every API call that you make. it needs to be running at scale, securely, all the time without fail #reinvent

Tweet 66/166 👇 Next tweet 👆 Start

high level overview of the IAM design #reinvent

Tweet 67/166 👇 Next tweet 👆 Start

two key #security fundamentals #reinvent

Tweet 68/166 👇 Next tweet 👆 Start

👆 we covered that in a @TwitterSpaces with @andrewbrown the other day. make sure to check out his other spaces this week. they’ve been fantastic #reinvent

Tweet 69/166 👇 Next tweet 👆 Start

. @werner giving a simplified walk through of how @awscloud IAM does authentication #reinvent



Tweet 70/166 👇 Next tweet 👆 Start

why do I ❤️ this conference? slides like this at the major keynotes #reinvent

Tweet 71/166 👇 Next tweet 👆 Start

. @werner walking through a super simplified version of the mechanics behind request validation and how your key material is kept safe #reinvent

Tweet 72/166 👇 Next tweet 👆 Start

bottom line: @awscloud IAM is an extremely well design secure system. lots of well thought out solutions to hit the required scale while meeting the #security requirements #reinvent

Tweet 73/166 👇 Next tweet 👆 Start

. @awscloud IAM processes 1/2 BILLION API calls/second #reinvent

Tweet 74/166 👇 Next tweet 👆 Start

do you ever sleep @AWSSecurityInfo? #reinvent

Tweet 75/166 👇 Next tweet 👆 Start

for more on these types of details, be sure to follow @mchancloud. he publishes a lot on @AWSIdentity (sorry for bugging you @AWSSecurityInfo, I always forget that IAM has their own account) #reinvent

Tweet 76/166 👇 Next tweet 👆 Start

. @werner talking about how simple machines can combine into more sophisticated systems #reinvent



Tweet 77/166 👇 Next tweet 👆 Start

the primitives are the critical part. they let you build what you need in the manner you need it #reinvent

Tweet 78/166 👇 Next tweet 👆 Start

this is an interesting contrast to the announcements from @aselipsky & @SwamiSivasubram who were deliver the exact opposite…because that new wave of @awscloud customers need that higher level tooling #reinvent

Tweet 79/166 👇 Next tweet 👆 Start

...but there’s still plenty of us at the nerdy core! 🤣 #reinvent

Tweet 80/166 👇 Next tweet 👆 Start

“This is your fault”, @werner << all of theses services are based on customer needs and follow @awscloud’s building philosophy of trying to keep it simple #reinvent

Tweet 81/166 👇 Next tweet 👆 Start

I “blame” @ben11kehoe for every @awscloud service that includes IoT in the name… #reinvent

Tweet 82/166 👇 Next tweet 👆 Start

#reinvent



Tweet 83/166 👇 Next tweet 👆 Start

did a complete 180 here and are talking about frontend development…builders who live in frameworks #reinvent

Tweet 84/166 👇 Next tweet 👆 Start

NEW SERVICE: AWS Amplify Studio, visual build complete feature-rich apps in hours with full control over the code #reinvent

Tweet 85/166 👇 Next tweet 👆 Start

. @ASpittel up now to talk about @AWSAmplify #reinvent

Tweet 86/166 👇 Next tweet 👆 Start

. @ASpittel showing how easy it is to build an app with the new @AWSAmplify Studio honestly, this might get me to use Amplify (finally). I could code it all but why should I? this is a great time saver #reinvent

Tweet 87/166 👇 Next tweet 👆 Start

ohh, nice link to @figmadesign from @AWSAmplify Studio #reinvent


Tweet 88/166 👇 Next tweet 👆 Start

this looks super slick #reinvent

Tweet 89/166 👇 Next tweet 👆 Start

it’s not true “copy & paste development” until you hit up @StackOverflow at least once 😉 #reinvent

Tweet 90/166 👇 Next tweet 👆 Start

“credible react code”, @ASpittel trying to start a fight from main stage @awscloud #reinvent

Tweet 91/166 👇 Next tweet 👆 Start

wow, that @figmadesign integration is nice and deep. it’ll detect the updates and let you one-click update #reinvent

Tweet 92/166 👇 Next tweet 👆 Start

Tweet 93/166 👇 Next tweet 👆 Start

some key points on @AWSAmplify in general. Studio takes advantage of these automatically #reinvent

Tweet 94/166 👇 Next tweet 👆 Start

. @werner coming back up. fantastic job @ASpittel! #reinvent

Tweet 95/166 👇 Next tweet 👆 Start

@awscloud We value innovation over coordination”, @werner #reinvent

Tweet 96/166 👇 Next tweet 👆 Start

👆 it’s all about focusing on the customers that team is working directly for. can’t wait for coordination << while frustrating sometimes in the edges, the benefits are undeniable #reinvent

Tweet 97/166 👇 Next tweet 👆 Start

. @werner cites some confusing API designs when compared to other services. in isolation they make sense but we don’t use @awscloud in isolation #reinvent

Tweet 98/166 👇 Next tweet 👆 Start

to help, they launched the @awscloud Cloud Control API https://aws.amazon.com/blogs/aws/announcing-aws-cloud-control-api/ #reinvent

Tweet 99/166 👇 Next tweet 👆 Start

👆that’s a very @awscloud solution to teams not coordinating. stand up another team (who also won’t coordinate first) to solve the problem 🤣 #reinvent

Tweet 100/166 👇 Next tweet 👆 Start

on to @werner’s 6 keys to API design #reinvent

Tweet 101/166 👇 Next tweet 👆 Start

1. APIs are forever #reinvent

Tweet 102/166 👇 Next tweet 👆 Start

2. Never break backward compatibility #reinvent

Tweet 103/166 👇 Next tweet 👆 Start

3. Work backwards from customer use cases #reinvent

Tweet 104/166 👇 Next tweet 👆 Start

4. Create APIs with explicit and well-documented failure modes #reinvent

Tweet 105/166 👇 Next tweet 👆 Start

5. Create APIs that are self-describing and have a clear, specific purpose #reinvent

Tweet 106/166 👇 Next tweet 👆 Start

6. Avoid leaking implementation details at all costs #reinvent

Tweet 107/166 👇 Next tweet 👆 Start

👆if teams followed these six simple principles, we’d all be so, so much better off #reinvent

Tweet 108/166 👇 Next tweet 👆 Start

Tweet 109/166 👇 Next tweet 👆 Start

#reinvent

Tweet 110/166 👇 Next tweet 👆 Start

NEW LAUNCH: @awscloud SDKs for Swift, Kotlin, and Rust #reinvent

Tweet 111/166 👇 Next tweet 👆 Start

#reinvent

Tweet 112/166 👇 Next tweet 👆 Start

more on the @awscloud CDK at https://aws.amazon.com/cdk/ #reinvent

Tweet 113/166 👇 Next tweet 👆 Start

NEW LAUNCH: @awscloud CDK v2 - one package for all AWS CDK libs - better handling of experimental classes, methods, & properties - CDK watch #reinvent

Tweet 114/166 👇 Next tweet 👆 Start

. @werner doesn’t like the name “CDK Watch”. he likes, “CDK hot swap” << that makes more sense. keep your apps running while you update things #reinvent

Tweet 115/166 👇 Next tweet 👆 Start

NEW LAUNCH: Construct Hub, find and use open source @awscloud CDK libraries #reinvent

Tweet 116/166 👇 Next tweet 👆 Start

. @awscloud DevTools Hero @NIDeveloper up now on main stage! #reinvent


Tweet 117/166 👇 Next tweet 👆 Start

. @NIDeveloper talking about @LibertyMutual’s journey to the cloud from the #dev point of view #reinvent

Tweet 118/166 👇 Next tweet 👆 Start

“Code is a liability”, @NIDeveloper << 100% agree #reinvent

Tweet 119/166 👇 Next tweet 👆 Start

. @NIDeveloper now onto their CDK journey #reinvent

Tweet 120/166 👇 Next tweet 👆 Start

well that’s a hell of an improvement… #reinvent

Tweet 121/166 👇 Next tweet 👆 Start

took time to get builders on board. CDK is another complete tool after all #reinvent


Tweet 122/166 👇 Next tweet 👆 Start

if you want to try @awscloud CDK yourself: https://cdkworkshop.com/ #reinvent

Tweet 123/166 👇 Next tweet 👆 Start

. @NIDeveloper showing the results of the journey. ❤️ the nod to the @awscloud Well-Architected Framework #reinvent

Tweet 124/166 👇 Next tweet 👆 Start

haven’t said it yet but @NIDeveloper is PUMPED. high energy segment for sure. love it! #reinvent

Tweet 125/166 👇 Next tweet 👆 Start

excellent goals to have... #reinvent

Tweet 126/166 👇 Next tweet 👆 Start

excellent work @NIDeveloper! #reinvent

Tweet 127/166 👇 Next tweet 👆 Start

wow. @NIDeveloper gets the “Now Go Build Award” from @werner. very well deserved! #reinvent

Tweet 128/166 👇 Next tweet 👆 Start

ohhh, should out to the @awscloud Heroes program 😊 #reinvent

Tweet 129/166 👇 Next tweet 👆 Start

now @werner is on to sustainability #reinvent

Tweet 130/166 👇 Next tweet 👆 Start

Tweet 131/166 👇 Next tweet 👆 Start

“The greenest energy is the energy you don’t use”, Peter DeSantis, @awscloud #reinvent

Tweet 132/166 👇 Next tweet 👆 Start

. @werner applying the Shared Responsibility Model to sustainability #reinvent

Tweet 133/166 👇 Next tweet 👆 Start

things like #serverless design patterns are a way to be more sustainable. it’s all about efficiency and optimizations #reinvent

Tweet 134/166 👇 Next tweet 👆 Start

. @mikegchambers really nailed this in our day one recap chat. this came up at 2x keynotes now. https://www.youtube.com/watch?v=FiJfYTqM02M&feature=youtu.be #reinvent

Tweet 135/166 👇 Next tweet 👆 Start

“Don’t forget to turn off the lights”, @Werner #reinvent

Tweet 136/166 👇 Next tweet 👆 Start

understanding the impact of your design decisions on sustainability is key to moving forward #reinvent

Tweet 137/166 👇 Next tweet 👆 Start

this would make a great @awscloud Well-Architected Framework pillar… #reinvent

Tweet 138/166 👇 Next tweet 👆 Start

…oh… #reinvent

Tweet 139/166 👇 Next tweet 👆 Start

NEW PILLAR: @awscloud Well-Architected Sustainability Pillar #reinvent

Tweet 140/166 👇 Next tweet 👆 Start

🤣🤣🤣, I did not know that was coming. super glad it’s here though #reinvent

Tweet 141/166 👇 Next tweet 👆 Start

NEW SERVICE: @awscloud re:Post, a community-driven question and answer site to help customers #reinvent

Tweet 142/166 👇 Next tweet 👆 Start

. @werner with a shout out for the AMAZING Builders Library. dive in at https://aws.amazon.com/builders-library/ #reinvent

Tweet 143/166 👇 Next tweet 👆 Start

I took a closer look at a few papers from the library a couple weeks back. more at https://markn.ca/2021/aws-reinvent/#amazon-builders-library #reinvent

Tweet 144/166 👇 Next tweet 👆 Start

#reinvent


Tweet 145/166 👇 Next tweet 👆 Start

🤖🎶 #reinvent

Tweet 146/166 👇 Next tweet 👆 Start

#reinvent

Tweet 147/166 👇 Next tweet 👆 Start

little trailer for New World. more at https://www.newworld.com/en-us/ #reinvent


Tweet 148/166 👇 Next tweet 👆 Start

if you’re interested in the game, @IGN has a review at https://t.co/9PhHCqklVU #reinvent


Tweet 149/166 👇 Next tweet 👆 Start

nice logo drop there #reinvent

Tweet 150/166 👇 Next tweet 👆 Start

. @Werner walking through some of the technical details of New World even if you’re not a gamer, the architecture behind them are fascinating #reinvent



Tweet 151/166 👇 Next tweet 👆 Start

the world is sharded in the back end in order to provide the resiliency needed #reinvent

Tweet 152/166 👇 Next tweet 👆 Start

this way, the open world stays open but doesn’t run into scaling up issues 185 world at launch. 500 quickly there after #reinvent

Tweet 153/166 👇 Next tweet 👆 Start

30/second actions for all entities in the world are processed #reinvent

Tweet 154/166 👇 Next tweet 👆 Start

the game servers are stateless. they can always be restarted. everything gets written to @awscloud DynamoDB behind the scenes #reinvent

Tweet 155/166 👇 Next tweet 👆 Start

. @werner now talking about the observability challenges of this type of system #reinvent

Tweet 156/166 👇 Next tweet 👆 Start

. @awscloud #reinvent 2012 quote, “Log everything”, @werner

Tweet 157/166 👇 Next tweet 👆 Start

this game is pumped out a massive amount of data. it’s crazy #reinvent

Tweet 158/166 👇 Next tweet 👆 Start

some of the #serverless micro services supporting the game would love to see a complete architecture diagram and walk through #reinvent

Tweet 159/166 👇 Next tweet 👆 Start

a look at the session-based modes architecture #reinvent

Tweet 160/166 👇 Next tweet 👆 Start

a higher level view of part of the architecture #reinvent

Tweet 161/166 👇 Next tweet 👆 Start

“Build systems the way you always wanted to, but never could”, @werner #reinvent

Tweet 162/166 👇 Next tweet 👆 Start

Tweet 163/166 👇 Next tweet 👆 Start

👆 2012 🤦 #reinvent

Tweet 164/166 👇 Next tweet 👆 Start

Tweet 165/166 👇 Next tweet 👆 Start

these concepts and areas of focus are just as important today as when @werner brought them up in 2012 #reinvent

Tweet 166/166 👇 Next tweet 👆 Start

“Thank you, and now go build”, @werner << thank you Werner for another fantastic keynote. lots to think about /🧵 #reinvent

]]>
https://markn.ca/2021/werner-vogels-keynote-at-aws-re-invent-2021/ 67f6bbeaaf961b000144317b Thu, 02 Dec 2021 09:00:00 -0500
<![CDATA[ Stephen Schmidt's Security Leadership Session at AWS re:Invent 2021 ]]> Want to share with others? Formatting issues in your reader? This post is available online, Stephen Schmidt's Security Leadership Session at AWS re:Invent 2021

The leadership session at AWS re:Invent provide a deeper dive into a specific area of focus. Stephen Schmidt, CISO at AWS takes the stage to talk all things security.

I missed the first 10 minutes of the session and will update this post when I watch it on demand.

The First 10 Minutes

THe session is now available on demand so I was able to watch the first ten minutes. Here are my takeaways as a list, instead of a tweet storm;

  • “If we wanted continuous improvement, we need to lower the friction of security”, Stephen Schmidt
  • “If a process is inefficient or overly taxing, people will just work around. We’ve got to make security as easy choice.”, Stephen Schmidt
  • “Getting start is simple, and you start seeing value quickly…” This was mentioned in relation to making security easier to use. 100% spot on
  • Guard Duty has added a bunch of great Amazon S3 findings
  • AWS Security Hub now allows you to designate an “aggregation region.” This makes using AWS Security Hub so much easier
  • Amazon Detective uses a bunch of techniques (machine learning, statistical analysis, and graph theory) to help accelerate your security investigations
  • AWS’s security strategy is to remain focused on tangible ways to make customers safer
  • “We need to train people on security best practices in a manner that’s engaging”, Stephen Schmidt. He segues this into highlight the newly released & free security awareness training
  • The launch of Incident Manager from AWS Systems Manager was highlighted. Lots to love in this feature set
  • Focus on making the service better through collaboration with builders. That’s critical for better security outcomes. “Let’s makes security a great experience for developers”, Stephen Schmidt

Live Tweets

This 👇 is the Twitter thread of my coverage of the keynote…

Tweet 1/44 👇 Next tweet

...ahhh, jumping in late to this one #reinvent https://twitter.com/66780587/status/1466510060784394253

Tweet 2/44 👇 Next tweet 👆 Start

Sarah from @AWSIdentity up now… #reinvent

Tweet 3/44 👇 Next tweet 👆 Start

“MFA is the best way to secure your work as you build”, Sarah from @AWSIdentity with a Yubikey on her earrings! 👇 her plates… #reinvent

Tweet 4/44 👇 Next tweet 👆 Start

ok, now I want a Yubikey on my earrings too. Sarah recommended this one, the 5c nano: https://www.yubico.com/ca/product/yubikey-5c-nano/ #reinvent

Tweet 5/44 👇 Next tweet 👆 Start

“All workloads on @awscloud should be multi-account, that’s how we’ve designed @AWSIdentity” #reinvent #security

Tweet 6/44 👇 Next tweet 👆 Start

“If you are a human, you should be logging into @awscloud through SSO”, Sarah from @AWSIdentity #reinvent #security

Tweet 7/44 👇 Next tweet 👆 Start

#reinvent

Tweet 8/44 👇 Next tweet 👆 Start

more on @AWSIdentity SSO at https://aws.amazon.com/single-sign-on/ #reinvent #security

Tweet 9/44 👇 Next tweet 👆 Start

the “data perimeter” idea is all about protecting your solutions from all angles #reinvent

Tweet 10/44 👇 Next tweet 👆 Start

Sarah covering some @AWSIdentity recent releases. top of the list: IAM Access Analyzer more at https://docs.aws.amazon.com/IAM/latest/UserGuide/what-is-access-analyzer.html #reinvent #security

Tweet 11/44 👇 Next tweet 👆 Start

…there is also Network Access Analyzer more on that new release at https://aws.amazon.com/blogs/aws/new-amazon-vpc-network-access-analyzer/ #reinvent #securtiy

Tweet 12/44 👇 Next tweet 👆 Start

another one in the list, Access Analyzer policy validation more on that at https://docs.aws.amazon.com/IAM/latest/UserGuide/access-analyzer-policy-validation.html #reinvent #security

Tweet 13/44 👇 Next tweet 👆 Start

Sarah also calls out the IAM Access Analyzer policy generation feature released by @AWSIdentity a little while back more at https://docs.aws.amazon.com/IAM/latest/UserGuide/access-analyzer-policy-generation.html #reinvent #security

Tweet 14/44 👇 Next tweet 👆 Start

👆 great list. everyone should be using these tools regularly #reinvent #security

Tweet 15/44 👇 Next tweet 👆 Start

. @StephenSchmidt back up to switch gears…updates! #reinvent #security

Tweet 16/44 👇 Next tweet 👆 Start

162 checks now in @awscloud Security Hub! + VPC endpoint support (https://docs.aws.amazon.com/securityhub/latest/userguide/security-vpc-endpoints.html) #reinvent

Tweet 17/44 👇 Next tweet 👆 Start

Amazon Detective got support S3 and DNS finding types more at https://aws.amazon.com/about-aws/whats-new/2021/09/amazon-detective-s3-dns/ #reinvent #security

Tweet 18/44 👇 Next tweet 👆 Start

. @awscloud Shield automatically does application layer DDoS mitigation more: https://aws.amazon.com/about-aws/whats-new/2021/12/aws-shield-advanced-application-layer-ddos-mitigation/ #reinvent #security

Tweet 19/44 👇 Next tweet 👆 Start

Amazon Inspector got a big update. I covered that at https://markn.ca/2021/first-look-at-the-brand-new-amazon-inspector/ lots of great stuff in this complete revamp #reinvent #security

Tweet 20/44 👇 Next tweet 👆 Start

there is a dedicated session on site for Amazon Inspector. will be on demand in a few days #reinvent #security

Tweet 21/44 👇 Next tweet 👆 Start

simple win: update the alternative security contact for your accounts. you can do this via Orgs and the CLI now more on that at https://aws.amazon.com/blogs/security/update-the-alternate-security-contact-across-your-aws-accounts-for-timely-security-notifications/ #reinvent #security

Tweet 22/44 👇 Next tweet 👆 Start

“Consider the Security Pillar of the AWS Well-Architected Framework” << …and the rest of the framework! there’s a ton of amazing stuff in there that contributes to security more https://docs.aws.amazon.com/wellarchitected/latest/security-pillar/welcome.html #reinvent #security

Tweet 23/44 👇 Next tweet 👆 Start

Thomas Avant coming up now to talk about security culture at @awscloud #reinvent #security

Tweet 24/44 👇 Next tweet 👆 Start

here’s another great talk about @awscloud #security culture from re:Inforce 2021: https://www.youtube.com/watch?v=edWC5q-enX0&feature=youtu.be be sure to bookmark this one 👇 and watch it later #reinvent

Tweet 25/44 👇 Next tweet 👆 Start

they regularly remind employees about the importance of #security to the work their doing #reinvent

Tweet 26/44 👇 Next tweet 👆 Start

🔑 @awscloud is always looking for ways to empower everyone to be a part of the #security team #reinvent #infosec

Tweet 27/44 👇 Next tweet 👆 Start

@StephenSchmidt himself gets page if it comes to that…it’s not fun, I’ve seen it”, Thomas Avant #reinvent #infosec

Tweet 28/44 👇 Next tweet 👆 Start

“We’ve got all the runbooks you would expect @awscloud but we’re also heavily reliant on employees making the best decisions possible” #reinvent #infosec

Tweet 29/44 👇 Next tweet 👆 Start

👆 that only works because they’ve built up that #security culture. it’s hard work but well worth it #reinvent

Tweet 30/44 👇 Next tweet 👆 Start

#reinvent

Tweet 31/44 👇 Next tweet 👆 Start

I ❤️ how many times I’ve heard “builders” in this #security session #reinvent

Tweet 32/44 👇 Next tweet 👆 Start

#reinvent

Tweet 33/44 👇 Next tweet 👆 Start

. @StephenSchmidt back up to talk about what sets @awscloud apart from the #security angle #reinvent

Tweet 34/44 👇 Next tweet 👆 Start

first up: containers & code #reinvent #security

Tweet 35/44 👇 Next tweet 👆 Start

“Containing risk through isolation”, pun NOT pardoned @StephenSchmidt 🤣😉 #reinvent #infosec

Tweet 36/44 👇 Next tweet 👆 Start

more on Amazon CodeGuru at https://aws.amazon.com/codeguru/ #reinvent #infosec

Tweet 37/44 👇 Next tweet 👆 Start

there’s now a nice integration with Amazon CodeGuru + @awscloud Secrets Manager. more on that at https://aws.amazon.com/about-aws/whats-new/2021/11/amazon-codeguru-reviewer-hardcoded-secrets-java-python/ #reinvent #infosec

Tweet 38/44 👇 Next tweet 👆 Start

. @awscloud GuardDuty support for #k8s audit logs coming in early 2022! #reinvent

Tweet 39/44 👇 Next tweet 👆 Start

broader container support coming to other @AWSSecurityInfo services too. no firm ETA but it’s being worked on… #reinvent #infosec

Tweet 40/44 👇 Next tweet 👆 Start

#reinvent

Tweet 41/44 👇 Next tweet 👆 Start

I remember when these slides were just a couple of names. nice to see the expansion of the #security partner community around @awscloud #reinvent


Tweet 42/44 👇 Next tweet 👆 Start

. @awscloud re:Inforce 2022 dates announced! 28 & 29-Jun-2022 in Houston, TX #reinvent #infosec

Tweet 43/44 👇 Next tweet 👆 Start

closing quote from @StephenSchmidt. this was a great leadership session (as expected), can’t wait to catch the first 10m on replay #reinvent #security

Tweet 44/44 👇 Next tweet 👆 Start

. @StephenSchmidt even gets in the “Please complete the session survey” plug at the end! 🤣 /🧵 #reinvent #security

]]>
https://markn.ca/2021/stephen-schmidts-security-leadership-session-at-aws-re-invent-2021/ 67f6bbeaaf961b000144317a Thu, 02 Dec 2021 09:00:00 -0500
<![CDATA[ Swami Sivasubramanian's Keynote at AWS re:Invent 2021 ]]> Want to share with others? Formatting issues in your reader? This post is available online, Swami Sivasubramanian's Keynote at AWS re:Invent 2021

AWS re:Invent is always THE event in cloud. Swami Sivasubramanian took the stage to deliver the machine learning focused keynote on day three.

This 👇 is the Twitter thread of my coverage of the keynote…

Tweet 1/141 👇 Next tweet

. @SwamiSivasubram up now for the #ml keynote at @awscloud #reinvent 🧵

Tweet 2/141 👇 Next tweet 👆 Start

Swami is setting the scene; data is everywhere. there’s mountains of it. that makes it hard to get value from it #reinvent

Tweet 3/141 👇 Next tweet 👆 Start

“Survival of the most informed”, @SwamiSivasubram #reinvent

Tweet 4/141 👇 Next tweet 👆 Start

quick little nod to swimming Australia. they are using @awscloud #ml services to pull insights from their training data #reinvent

Tweet 5/141 👇 Next tweet 👆 Start

name drops for @NasdaqTech, @Philips, and @carrier … all previous customer references #reinvent


Tweet 6/141 👇 Next tweet 👆 Start

now walking through an e-commerce application example #reinvent

Tweet 7/141 👇 Next tweet 👆 Start

step 1: shove things into an RDBMS #reinvent

Tweet 8/141 👇 Next tweet 👆 Start

step 2: realize that breaks at some point. time to use specific data stores that align to your data & it’s use #reinvent

Tweet 9/141 👇 Next tweet 👆 Start

step 3: snag the streaming data too #reinvent

Tweet 10/141 👇 Next tweet 👆 Start

step 4: start asking questions to draw out insights #reinvent

Tweet 11/141 👇 Next tweet 👆 Start

step 5: realize a data lake is going to help unite all of these data sources and questions #reinvent

Tweet 12/141 👇 Next tweet 👆 Start

step 6: move beyond analysis and visualization to prediction #reinvent

Tweet 13/141 👇 Next tweet 👆 Start

…that obviously isn’t that clean a process and takes time but the gist is spot on it’s a journey and it’s critical to use the right tool at the right time #reinvent

Tweet 14/141 👇 Next tweet 👆 Start

ooohhh, nice shout out to the need for #security and #privacy controls throughout this process #reinvent

Tweet 15/141 👇 Next tweet 👆 Start

good summary slide for the journey that @SwamiSivasubram’s example took us on #reinvent

Tweet 16/141 👇 Next tweet 👆 Start

tl:dr on the sales/marketing side: @awscloud has a ton to offer in this area #reinvent

Tweet 17/141 👇 Next tweet 👆 Start

lots of #ml adoption in the @awscloud community #reinvent

Tweet 18/141 👇 Next tweet 👆 Start

btw, I’m betting on/hoping for at least @mza appearance in this keynote! #reinvent

Tweet 19/141 👇 Next tweet 👆 Start

3 key elements to a modern end-to-end data strategy… #reinvent

Tweet 20/141 👇 Next tweet 👆 Start

1. modernize => move away from on-premises & the 90’s? 🤣 2. unify => take the data lake approach 3. innovate => create new experiences & draw new insights #reinvent

Tweet 21/141 👇 Next tweet 👆 Start

diving deeper into “modernize”, we have a BMW video segment #reinvent

Tweet 22/141 👇 Next tweet 👆 Start

surprising no one, @awscloud is the platform for the BMW connected car initiative (currently 15 million connected vehicles) #reinvent

Tweet 23/141 👇 Next tweet 👆 Start

. @SwamiSivasubram is cruising here. very quick moving keynote… #reinvent

Tweet 24/141 👇 Next tweet 👆 Start

this slide should’ve said: Managing infrastructure, that’s so 90’s 🤣 #reinvent

Tweet 25/141 👇 Next tweet 👆 Start

yup. 100%… #reinvent

Tweet 26/141 👇 Next tweet 👆 Start

little update on/pitch for @awscloud Aurora << if you’re in the market for an RDBMS solution, start here more on Aurora at https://t.co/8QVWyGjjjR #reinvent

Tweet 27/141 👇 Next tweet 👆 Start

as usual @QuinnyPig is also covering the keynote. his thread is up at https://twitter.com/QuinnyPig/status/1466082818056810499 #reinvent

Tweet 28/141 👇 Next tweet 👆 Start

ohhh, new feature/service coming…you can just feel it #reinvent

Tweet 29/141 👇 Next tweet 👆 Start

yup…definitely something coming around using #ml to predict data store ops issues #reinvent

Tweet 30/141 👇 Next tweet 👆 Start

NEW FEATURE/SERVICE: Amazon DevOps Guru for RDS < it’s DevOps Guru pointed at RDS GA today #reinvent

Tweet 31/141 👇 Next tweet 👆 Start

more on the launch at https://t.co/waM99vGP27 #reinvent

Tweet 32/141 👇 Next tweet 👆 Start

I ❤️ these services because they leverage the scale & insight of @awscloud to help the rest of us build better #reinvent

Tweet 33/141 👇 Next tweet 👆 Start

ohhh, are we about to get another “Get off proprietary databases” service? #reinvent

Tweet 34/141 👇 Next tweet 👆 Start

Amazon RDS Customer flew under the radar for me more on the service at https://t.co/EPCeIcH6rf << the announcement today was that it now supports SQL Server as well. GA today #reinvent

Tweet 35/141 👇 Next tweet 👆 Start

…come on @awscloud Neptune #serverless… please? #reinvent

Tweet 36/141 👇 Next tweet 👆 Start

nope (or not yet?). I think we’re going in a different direction for the moment #reinvent

Tweet 37/141 👇 Next tweet 👆 Start

EXCELLENT QUESTION …and one that not enough builders are asking (especially in legacy environments) #reinvent

Tweet 38/141 👇 Next tweet 👆 Start

. @awscloud DynamoDB might be processing a few requests at any given time 🤣 #reinvent

Tweet 39/141 👇 Next tweet 👆 Start

ok, getting the setup for a new feature/service again #reinvent

Tweet 40/141 👇 Next tweet 👆 Start

sidenote: this feels like more a @ajassy or @werner style of keynote. problem build => new feature/service #reinvent

Tweet 41/141 👇 Next tweet 👆 Start

NEW FEATURE: Amazon DynamoDB Standard-Infrequent Access table class << this should help reduce some costs for people and allow them to keep data in DynamoDB longer can’t wait to hear @alexbdebrie’s thoughts #reinvent

Tweet 42/141 👇 Next tweet 👆 Start

more on the new table class at https://t.co/wytZzcvH9D #reinvent

Tweet 43/141 👇 Next tweet 👆 Start

btw, if you’re working with @awscloud DynamoDB you NEED @alexbdebrie’s book: https://www.dynamodbbook.com/ it’s a life saver #reinvent

Tweet 44/141 👇 Next tweet 👆 Start

also, watch one of his million+ talks on DynamoDB. only person I’ve seen to get a two-part talk at @awscloud #reinvent. that one happened last year

Tweet 45/141 👇 Next tweet 👆 Start

back to the keynote, lots of purpose-built databases from @awscloud #reinvent

Tweet 46/141 👇 Next tweet 👆 Start

. @SwamiSivasubram touching on the challenges around migration of databases to @awscloud now #reinvent

Tweet 47/141 👇 Next tweet 👆 Start

more on the @awscloud Data Migration Service (DMS) at https://t.co/GBPfOnoAI6 #reinvent

Tweet 48/141 👇 Next tweet 👆 Start

NEW FEATURE: @awscloud Database Migration Service Fleet Advisor << migration your databases en masse. it routes the data through S3 and customized migration plans to align w/the right purpose-built service #reinvent

Tweet 49/141 👇 Next tweet 👆 Start

shifting to the “Unify” point now… #reinvent

Tweet 50/141 👇 Next tweet 👆 Start

. @Expedia up as the customer example #reinvent

Tweet 51/141 👇 Next tweet 👆 Start

nothing in the customer example other than they are using @awscloud 😕 #reinvent

Tweet 52/141 👇 Next tweet 👆 Start

#reinvent

Tweet 53/141 👇 Next tweet 👆 Start

key point here is that your data should be in one place and then pulled into the right tool at the right time >> data lake #reinvent

Tweet 54/141 👇 Next tweet 👆 Start

new to the whole “data lake” thing? here’s a primer from @awscloud: https://t.co/JdyiUBiO6l #reinvent

Tweet 55/141 👇 Next tweet 👆 Start

…and if you’re just getting started, use @awscloud Lake Formation and save yourself a ton of time more on that at https://t.co/MqGU3Dl0xJ #reinvent

Tweet 56/141 👇 Next tweet 👆 Start

all of these strategies start with @awscloud S3. it’s the easiest, least expensive, and most performant way to store the data at scale #reinvent

Tweet 57/141 👇 Next tweet 👆 Start

# reinvent

Tweet 58/141 👇 Next tweet 👆 Start

if you’re not using Lake Formation, your “lake” is probably going to end up more like a pit. that’s bad don’t do that #reinvent

Tweet 59/141 👇 Next tweet 👆 Start

. @awscloud Athena is my 2nd favourite service (behind QuickSight) and often overlooked more on Athena at https://t.co/mZ43E2kUxc #reinvent

Tweet 60/141 👇 Next tweet 👆 Start

ohhh, are we getting some improvements to Athena?!?! #reinvent

Tweet 61/141 👇 Next tweet 👆 Start

#reinvent

Tweet 62/141 👇 Next tweet 👆 Start

. @awscloud also takes the “purpose-built” approach when it comes to analytics interactive => Athena big data => EMR ops & logs => OpenSearch real-time => Kinesis & MSK warehouse => Redshift (roughly) #reinvent

Tweet 63/141 👇 Next tweet 👆 Start

👆 most of those are now available #serverless. which is f—king awesome, btw #reinvent

Tweet 64/141 👇 Next tweet 👆 Start

RedShift is under utilized by builders. mainly because it’s terrifying…specially when you look at cost the #serverless announcement yesterday will open it up to a whole new audience more on that at https://t.co/IhHDSxhYZS #reinvent

Tweet 65/141 👇 Next tweet 👆 Start

lots of Redshift stuff. @awscloud knows that #serverless feature will intro a new audience to it, time to catch them up #reinvent


Tweet 66/141 👇 Next tweet 👆 Start

finally an #ml tie-in! #reinvent

Tweet 67/141 👇 Next tweet 👆 Start

…for those of you just joining this keynote at @awscloud #reinvent, this IS the #ml keynote to be fair, 99% of ML is data clean up, organization, and management 😉

Tweet 68/141 👇 Next tweet 👆 Start

shifting the conversation to BI…QuickSight!!! :-) #reinvent

Tweet 69/141 👇 Next tweet 👆 Start

more on QuickSight Q at https://t.co/uGnr57F5dk #reinvent

Tweet 70/141 👇 Next tweet 👆 Start

if you’re wondering why I ❤️ QuickSight so much, it’s because it opens up a lot of analytical power to a wide audience within your business that’s amazing powerful and something we don’t consider often enough #reinvent

Tweet 71/141 👇 Next tweet 👆 Start

…also QuickSight has some very powerful sharing built in: https://docs.aws.amazon.com/quicksight/latest/user/sharing-a-dashboard.html #reinvent

Tweet 72/141 👇 Next tweet 👆 Start

. @SwamiSivasubram’s on to @awscloud Glue while I’ve been ranting about QuickSight my favourite AWS name, “AWS Glue Data Brew” << it’s true, you can use it too #reinvent

Tweet 73/141 👇 Next tweet 👆 Start

more on @awscloud Glue Data Brew: https://t.co/C5YwVftsNO #reinvent

Tweet 74/141 👇 Next tweet 👆 Start

Neeraja up now to talk about @awscloud Redshift #serverless + QuickSight #reinvent


Tweet 75/141 👇 Next tweet 👆 Start

#reinvent

Tweet 76/141 👇 Next tweet 👆 Start

walking through a use case example now… first the informercial “on-premises” view 🤦🤣 #reinvent

Tweet 77/141 👇 Next tweet 👆 Start

then right into the “don’t worry about it” #serverless approach with the new Redshift service #reinvent


Tweet 78/141 👇 Next tweet 👆 Start

Redshift’s live data sharing capabilities lets more teams access the data without having to move it anywhere more on the sharing features at https://t.co/wtTwWCuJU2 #reinvent

Tweet 79/141 👇 Next tweet 👆 Start

QuickSight comes into play now for the data analysis at the last mile. it enables ALL teams (not just BI specialists) to query the data and draw insights #reinvent

Tweet 80/141 👇 Next tweet 👆 Start

what hits home for me with this example is the low operational overhead. almost all of the work & cost is directly driving business value that’s the goal of the @awscloud Well-Architected Framework & these types of services make it way easier to strike that balance #reinvent

Tweet 81/141 👇 Next tweet 👆 Start

“You’ve got to start treating data like an organizational asset”, @SwamiSivasubram #reinvent

Tweet 82/141 👇 Next tweet 👆 Start

we’ve moved on to culture. another customer example up, this time it’s @ADP #reinvent

Tweet 83/141 👇 Next tweet 👆 Start

lots of setup in the customer story, key point so far is that @adp handles so much data it’s like it’s a major country on it’s own #reinvent

Tweet 84/141 👇 Next tweet 👆 Start

. @adp story was about using data at scale to drive change. no real technology aspect (beyond, "we couldn't do this without @awscloud") quick message from @slack now… #reinvent

Tweet 85/141 👇 Next tweet 👆 Start

on to innovation now... #reinvent

Tweet 86/141 👇 Next tweet 👆 Start

this slide just keeps getting bigger each year #reinvent

Tweet 87/141 👇 Next tweet 👆 Start

we’re a hop, skip, and a jump away from just a board of single pixels with just the brand’s dominant colour #reinvent

Tweet 88/141 👇 Next tweet 👆 Start

I like this stacked layer approach to explaining the @awscloud #ml service offerings basically, you want to start at the top layer & stay there as long as possible. when necessary, move to the SageMaker layer …hope you never need the bottom layer 🤣😉 #reinvent


Tweet 89/141 👇 Next tweet 👆 Start

. @SwamiSivasubram’s going to start at the bottom layer #reinvent

Tweet 90/141 👇 Next tweet 👆 Start

this is all low level stuff, that’s why I recommend staying away from it super interesting from a math/engineering perspective but also, quite a ways away from business value #reinvent

Tweet 91/141 👇 Next tweet 👆 Start

more from the low-level layer of the #ml stack on @awscloud #reinvent

Tweet 92/141 👇 Next tweet 👆 Start

more on the Trn1: https://t.co/jS08tVI7eI #reinvent

Tweet 93/141 👇 Next tweet 👆 Start

…if you stay at the top of the stack! (though SageMaker is amazing) #reinvent

Tweet 94/141 👇 Next tweet 👆 Start

it’s just that SageMaker required #ml specific knowledge. that’s ok if you have it. but the top layer requires near zero #ml knowledge just hand the service something and get a result… #reinvent

Tweet 95/141 👇 Next tweet 👆 Start

ok, back to the keynote, talking about @awscloud SageMaker now. it’s an entire suite of solutions working together #reinvent

Tweet 96/141 👇 Next tweet 👆 Start

…more of a prefix than anything, SageMaker _________ #reinvent

Tweet 97/141 👇 Next tweet 👆 Start

another customer story, this time it’s Aurora (not the database) they do self-driving vehicle tech #reinvent

Tweet 98/141 👇 Next tweet 👆 Start

this Aurora: https://aurora.tech/ #reinvent

Tweet 99/141 👇 Next tweet 👆 Start

so far the customer story is about the promise of self-driving cars #reinvent

Tweet 100/141 👇 Next tweet 👆 Start

#reinvent

Tweet 101/141 👇 Next tweet 👆 Start

this customer story is cool but I feel like it’s missing the mark. it’s not technical enough for most builders and too technical for non-builders. right in the squishy middle that leaves me wondering, “What am I supposed to take away from this?” #reinvent

Tweet 102/141 👇 Next tweet 👆 Start

I would love to get into the details of their #ml workflow or their strategy of overlaying models to deliver that self-driving vehicle this is just an ad for the fact they are working on the tech. I wanted more #reinvent

Tweet 103/141 👇 Next tweet 👆 Start

. @SwamiSivasubram is back up now. thankfully his energy will put this back on track. he’s still rolling strong… #reinvent

Tweet 104/141 👇 Next tweet 👆 Start

structured data, the “easy” data type, is about 20% of the data #ml is working with unstructured data is far more common SageMaker has features to help with both #reinvent

Tweet 105/141 👇 Next tweet 👆 Start

more on Amazon SageMaker Data Wrangler: https://t.co/bSWdnkkIVk #reinvent

Tweet 106/141 👇 Next tweet 👆 Start

more on Amazon SageMaker Ground Truth at https://t.co/TMazhaB5lq #reinvent

Tweet 107/141 👇 Next tweet 👆 Start

NEW FEATURE: Amazon SageMaker Ground Truth Plus << high quality training dataset fast, and reduce data labelling cost more at https://t.co/pNpwc746kf #reinvent

Tweet 108/141 👇 Next tweet 👆 Start

anything that helps with data labelling and clean up is very, very welcome #reinvent

Tweet 109/141 👇 Next tweet 👆 Start

NEW FEATURE: Amazon SageMaker Studio Notebook << perform data engineering, analytics, and #ML workflows in one notebook. GA today #reinvent


Tweet 110/141 👇 Next tweet 👆 Start

we’re cruising right along with the #ml keynote at @awscloud #reinvent

Tweet 111/141 👇 Next tweet 👆 Start

NEW FEATURES (under the hood): - Amazon SageMaker Training Compiler << 50% speed boost for training - …Inference Recommender << reduce time to deploy - … #Serverless Inference << f—k infrastructure 😉 #reinvent

Tweet 112/141 👇 Next tweet 👆 Start

that’s 5(?) services or features that have made a #serverless model available to users. I ❤️ it! should be the default for everything... #reinvent

Tweet 113/141 👇 Next tweet 👆 Start

if you didn’t see the announcement about SageMaker Canvas in @aselipsky’s keynote, you can read more at https://t.co/D0ggeQdxyg #reinvent

Tweet 114/141 👇 Next tweet 👆 Start

Allie up now to walk us through SageMaker Canvas #reinvent

Tweet 115/141 👇 Next tweet 👆 Start

the example is forecasting. something a lot of us do #reinvent

Tweet 116/141 👇 Next tweet 👆 Start

the example is a model that forecasts the need for new computers for your team (a/k/a onboarding new ppl) 3 steps: - access & browse the data - prepare the data - train & build the model #reinvent

Tweet 117/141 👇 Next tweet 👆 Start

so, the example is covering all computer demands, not just onboarding #reinvent

Tweet 118/141 👇 Next tweet 👆 Start

drag & drop various data sources to create one data set. SageMaker Canvas also tries to automatically clean up the data ...slick #reinvent

Tweet 119/141 👇 Next tweet 👆 Start

what, I have to click?!? ugh. 🤣🤣🤣

Tweet 120/141 👇 Next tweet 👆 Start

the platform let’s you work through “what if” scenarios as well. that’s really powerful #reinvent



Tweet 121/141 👇 Next tweet 👆 Start

the real question is how broadly applicable is this beyond forecasting. how will @awscloud SageMaker Canvas handle those other use cases? can’t wait to find out! #reinvent

Tweet 122/141 👇 Next tweet 👆 Start

. @SwamiSivasubram back up again now... #reinvent

Tweet 123/141 👇 Next tweet 👆 Start

feels like we’re in the industrial #ml solutions now https://t.co/0XhONuQnwa #reinvent

Tweet 124/141 👇 Next tweet 👆 Start

tweeted too soon, that was the intro to the high level view of #ml solutions #reinvent

Tweet 125/141 👇 Next tweet 👆 Start

quiet service callback, @awscloud Kendra, https://t.co/XIOdabtgx0 #reinvent

Tweet 126/141 👇 Next tweet 👆 Start

Kendra is one of several services that most builders forget even exists. that’s ok that’s actually kind of cool. the @awscloud has grown to the point where there’s entire categories you’ll never touch as a builder #reinvent

Tweet 127/141 👇 Next tweet 👆 Start

NEW FEATURE: Amazon Kendra Experience Builder << no code search application builder #reinvent

Tweet 128/141 👇 Next tweet 👆 Start

more on EMR cluster and Spark job management with SageMaker Studio: https://t.co/tfGu3zUU7x #reinvent

Tweet 129/141 👇 Next tweet 👆 Start

more on SageMaker’s new training compiler: https://t.co/AF3dkaYC4X #reinvent

Tweet 130/141 👇 Next tweet 👆 Start

more on @awscloud SageMaker inference recommender: https://t.co/mvsaE99b51 #reinvent

Tweet 131/141 👇 Next tweet 👆 Start

. @SwamiSivasubram’s talking about @awscloud Connect and Lex experiences #reinvent

Tweet 132/141 👇 Next tweet 👆 Start

NEW FEATURE: Amazon Lex Automated Chatbot Designer << simplifies bot design with natural language understanding #reinvent

Tweet 133/141 👇 Next tweet 👆 Start

the Chatbot Designer sounds pretty cool. hopefully it’ll reduce user frustration #reinvent

Tweet 134/141 👇 Next tweet 👆 Start

#reinvent

Tweet 135/141 👇 Next tweet 👆 Start

. @SwamiSivasubram talking about bringing more builders under the #ml umbrella. lots of work to be done in this area #reinvent

Tweet 136/141 👇 Next tweet 👆 Start

NEW SERVICE: Amazon SageMaker Studio Lab << no cost, no setup #ml learning environment sign up with an email address and start learning! #reinvent

Tweet 137/141 👇 Next tweet 👆 Start

👆 this is huge! it should make it significantly easier to learn #ml technologies goes hand-in-hand with the D2L textbook: https://d2l.ai/ #reinvent

Tweet 138/141 👇 Next tweet 👆 Start

NEW PROGRAM: @awscloud AI & ML Scholarship Program #reinvent


Tweet 139/141 👇 Next tweet 👆 Start

Tweet 140/141 👇 Next tweet 👆 Start

the lab is up at https://t.co/BgjK0AWsfZ #reinvent

Tweet 141/141 👇 Next tweet 👆 Start

on to the @awscloud DeepRacer finale now. good luck to all! #reinvent /🧵


]]>
https://markn.ca/2021/swami-sivasubramanians-keynote-at-aws-re-invent-2021/ 67f6bbeaaf961b0001443179 Wed, 01 Dec 2021 09:00:00 -0500
<![CDATA[ Peter DeSantis' Keynote at AWS re:Invent 2021 ]]> Want to share with others? Formatting issues in your reader? This post is available online, Peter DeSantis' Keynote at AWS re:Invent 2021

AWS re:Invent is always THE event in cloud. Petere DeSantis’ keynote provided a peek behind the curtain of the technology that drive AWS itself.

This 👇 is the Twitter thread of my coverage of the keynote…

Tweet 1/104 👇 Next tweet

rolling now with the keynote from Peter DeSantis, SVP Utility Computing and Apps, @awscloud #reinvent

Tweet 2/104 👇 Next tweet 👆 Start

this used to be Monday or Tuesday Night Live and is always one of my favourite talks of the week #reinvent

Tweet 3/104 👇 Next tweet 👆 Start

Peter giving his perspective on the start of the @awscloud #reinvent

Tweet 4/104 👇 Next tweet 👆 Start

big focus from the team before the launch was on the key word “Elastic” << I’m willing to be it still is! #reinvent

Tweet 5/104 👇 Next tweet 👆 Start

early memories from the original EC2 team. 7/10 of the team are still @awscloud #reinvent

Tweet 6/104 👇 Next tweet 👆 Start

email from @JeffBezos to the EC2 team in the early days. love the focus on the user experience #reinvent

Tweet 7/104 👇 Next tweet 👆 Start

key areas of focus for EVERYTHING @awscloud #reinvent

Tweet 8/104 👇 Next tweet 👆 Start

looks like we’re starting the night by looking at storage #reinvent

Tweet 9/104 👇 Next tweet 👆 Start

remember, this is (usually) not a feature/service launch keynote. it’s typically a look behind the scenes @awscloud. lots of amazing technology and engineering challenges #reinvent

Tweet 10/104 👇 Next tweet 👆 Start

remember when @awscloud looked like this? #reinvent

Tweet 11/104 👇 Next tweet 👆 Start

lots of stuff build out from S3 #reinvent

Tweet 12/104 👇 Next tweet 👆 Start

for a longer look back at @awscloud’s early days. be sure to check out @jeffbarr’s session, “15 years of AWS with Jeff Barr” https://virtual.reinvent.awsevents.com/login/ #reinvent

Tweet 13/104 👇 Next tweet 👆 Start

we’re going right down to the fundamentals. looking at old school(ish) hard drives #reinvent

Tweet 14/104 👇 Next tweet 👆 Start

lots of mechanical engineering packed into these types of drives. Peter used a crazy airplane analogy that I won’t even try to summarize lots of improvements but the mechanics are pretty steady #reinvent

Tweet 15/104 👇 Next tweet 👆 Start

“Hard drives remain the best way to store large amounts of data when you need to access it immediately”, Peter << he left out, “…even though we don’t want that to be the case” #reinvent

Tweet 16/104 👇 Next tweet 👆 Start

“Let’s do some quick math”, Peter << a key indicator as to why this is always my favourite keynote #reinvent (sorry @werner)

Tweet 17/104 👇 Next tweet 👆 Start

here’s what the math says : hard drives suck for these type of big data workloads #reinvent

Tweet 18/104 👇 Next tweet 👆 Start

the opposite view for a large but low usage workload #reinvent

Tweet 19/104 👇 Next tweet 👆 Start

basically the individual workload doesn’t align to the hard drive mechanics. you need to aggregate these workloads in order to smooth things out #reinvent

Tweet 20/104 👇 Next tweet 👆 Start

Peter’s currently walking through how @awscloud distributes customer S3 workloads across the physical backend of the service it’s the only way the math adds up #reinvent

Tweet 21/104 👇 Next tweet 👆 Start

“If you want to innovate at scale, you need to move quickly. AND you need to do it safely”, Peter DeSantis, @awscloud #reinvent

Tweet 22/104 👇 Next tweet 👆 Start

talking about how @awscloud approaches testing S3 now #reinvent

Tweet 23/104 👇 Next tweet 👆 Start

I love this type of deep dive. especially the contrast in the complexity behind the scenes of S3 for something as simple as a bucket/key #ux #reinvent

Tweet 24/104 👇 Next tweet 👆 Start

for testing, @awscloud is leveraging automated reasoning more and more. it’s the only way to truly test things out more at https://www.amazon.science/ #reinvent

Tweet 25/104 👇 Next tweet 👆 Start

excellent timing by the @AmazonScience team, “A gentle introduction to automated reasoning” << just published https://www.amazon.science/blog/a-gentle-introduction-to-automated-reasoning #reinvent

Tweet 26/104 👇 Next tweet 👆 Start

formal tools are great. they have a very high bar for correctness …but at the cost of speed and reducing the available talent pool #reinvent

Tweet 27/104 👇 Next tweet 👆 Start

this isn’t a great choice to face. at @awscloud’s scale, they deal with it all of the time …so they developed a new approach, “Lightweight Formal Methods” #reinvent

Tweet 28/104 👇 Next tweet 👆 Start

here’s a great related paper from @AmazonScience , “Using lightweight formal methods to validate a key-value storage node in Amazon S3” https://www.amazon.science/publications/using-lightweight-formal-methods-to-validate-a-key-value-storage-node-in-amazon-s3 #reinvent

Tweet 29/104 👇 Next tweet 👆 Start

lots of advantages to this approach…biggest challenge would be the initial design to allow for the application of these formal methods when required #reinvent

Tweet 30/104 👇 Next tweet 👆 Start

ohhh, I beat Peter to the punch 👊 🤣 #reinvent

Tweet 31/104 👇 Next tweet 👆 Start

first customer story up, this one’s from @Adobe #reinvent

Tweet 32/104 👇 Next tweet 👆 Start

. @adobe’s intro covered how they are massive scale in the cloud, not turning to storage #reinvent

Tweet 33/104 👇 Next tweet 👆 Start

talking about photos and how we stored physical photos #reinvent

Tweet 34/104 👇 Next tweet 👆 Start

digital is a similar challenge but at a larger scale how many photos & videos do you have? #reinvent

Tweet 35/104 👇 Next tweet 👆 Start

next year “we” (not sure who that is, all of us?), we’ll generate 1,500,000,000,000 photos #reinvent

Tweet 36/104 👇 Next tweet 👆 Start

. @adobe turning to the two primary storage use cases for storing photos and videos “I want it now" “I want it sometime, whenever really” #reinvent

Tweet 37/104 👇 Next tweet 👆 Start

the obvious questions about this story form @adobe is why do I only get 100GB of storage with Creative Cloud then? << feature request == let me use my own @awscloud account of Creative Cloud storage & sharing #reinvent

Tweet 38/104 👇 Next tweet 👆 Start

👆 s/of/for/

Tweet 39/104 👇 Next tweet 👆 Start

learn more about @adobe Sensei at https://www.adobe.com/ca/sensei.html #reinvent

Tweet 40/104 👇 Next tweet 👆 Start

. @adobe is obviously the reference customer for Amazon S3 Glacier Instance Retrieval more on the @awscloud feature at https://aws.amazon.com/about-aws/whats-new/2021/11/amazon-s3-glacier-instant-retrieval-storage-class/ #reinvent

Tweet 41/104 👇 Next tweet 👆 Start

👆 it snuck under the radar for most people but it could be quite a game changer #reinvent

Tweet 42/104 👇 Next tweet 👆 Start

Peter moving on to block storage types now #reinvent

Tweet 43/104 👇 Next tweet 👆 Start

now diving into SSD technology #reinvent

Tweet 44/104 👇 Next tweet 👆 Start

SSD remove most of the mechanical challenges but they have their own issues…like the limitations of flash storage #reinvent

Tweet 45/104 👇 Next tweet 👆 Start

primary the paging system & the lifetime of those pages #reinvent

Tweet 46/104 👇 Next tweet 👆 Start

as Peter is delivering this section of the talk, I realize I know way too much of the low level functionality of both HDD and SDD. this is the downside of nerd 🤓 life. lots of obscure knowledge …but I wouldn’t have it any other way #reinvent

Tweet 47/104 👇 Next tweet 👆 Start

of course there are different issues at hyper scale that @awscloud has discovered with low level SSD tech #reinvent

Tweet 48/104 👇 Next tweet 👆 Start

small inconsistencies add up fast at hyper scale. things we would never notice even with hundreds of systems, they see regularly #reinvent

Tweet 49/104 👇 Next tweet 👆 Start

. @awscloud Nitro smooths a lot of this out more on Nitro at https://aws.amazon.com/ec2/nitro/ #reinvent

Tweet 50/104 👇 Next tweet 👆 Start

…of course they built their own Nitro SSD #reinvent

Tweet 51/104 👇 Next tweet 👆 Start

btw, @QuinnyPig it live tweeting this keynote as well. for his take (😈) head over to https://twitter.com/QuinnyPig/status/1466181160099139586 #reinvent

Tweet 52/104 👇 Next tweet 👆 Start

Peter citing the performance delivered by the custom SSD approach via @awscloud Nitro #reinvent

Tweet 53/104 👇 Next tweet 👆 Start

Tweet 54/104 👇 Next tweet 👆 Start

on to @awscloud Graviton now... #reinvent

Tweet 55/104 👇 Next tweet 👆 Start

more on Graviton at https://aws.amazon.com/ec2/graviton/ #reinvent

Tweet 56/104 👇 Next tweet 👆 Start

. @awslcoud is pushing Graviton everywhere. and why not? more bang for your buck in most cases w/cloud native designs #reinvent


Tweet 57/104 👇 Next tweet 👆 Start

Peter touches on the Graviton3 update #reinvent

Tweet 58/104 👇 Next tweet 👆 Start

have we seen these stats for Graviton3 yet? …not that we should focus on them according to Peter (and I agree) #reinvent

Tweet 59/104 👇 Next tweet 👆 Start

I like Apple’s performance per watt approach. which @awscloud has followed as well #reinvent

Tweet 60/104 👇 Next tweet 👆 Start

more on Dennard scaling at https://en.wikipedia.org/wiki/Dennard_scaling #reinvent

Tweet 61/104 👇 Next tweet 👆 Start

Peter talking about power consumption now. it’s a critical attribute for all of us, mind boggling at @awscloud’s hyper scale #reinvent

Tweet 62/104 👇 Next tweet 👆 Start

How do we efficiently increase performance of a Graviton core? Make the core WIDER #reinvent

Tweet 63/104 👇 Next tweet 👆 Start

there have been lots of improvements in silicon design over the past decade. the easy way to think about it is for year all we worried about was the size of the engine we finally realized that the tires, chassis, fuel, and other attributes matter as well... #reinvent

Tweet 64/104 👇 Next tweet 👆 Start

…that means more cores, wider memory lanes, direct access to storage, etc. this is why we’ve seen massive boosts in performance in things like @apple’s M1 and @awscloud Graviton3 #reinvent

Tweet 65/104 👇 Next tweet 👆 Start

another customer story up now, this time it’s Fannie Mae #reinvent

Tweet 66/104 👇 Next tweet 👆 Start

Kimberly Johnson, EVP & COO of @FannieMae given the scale and scope of their operations tl:dr = it’s big #reinvent

Tweet 67/104 👇 Next tweet 👆 Start

ooohhh, @FannieMae built out an HPC solution @awscloud Lambda. would love to get a deep dive on that one… #reinvent

Tweet 68/104 👇 Next tweet 👆 Start

very interesting solution from @fanniemae. they leverage some key @awscloud data services to expand credit score analysis to include rent payments…regardless of how they were made #reinvent

Tweet 69/104 👇 Next tweet 👆 Start

now talking about evaluating risk to housing due to climate change. again another massive data problem, taking unstructured data into structure data for analysis and prediction #reinvent

Tweet 70/104 👇 Next tweet 👆 Start

good customer story from @fanniemae. I think they struck the right depth to solve solutions to unique problems at a scale that’s only really possible in the cloud #reinvent

Tweet 71/104 👇 Next tweet 👆 Start

on to #ml now. I swear this is slide is even more packed than @SwamiSivasubram from earlier today #reinvent

Tweet 72/104 👇 Next tweet 👆 Start

Peter’s breaking #ml down into two big stages: - training - inference you need different infrastructure & tools for both #reinvent



Tweet 73/104 👇 Next tweet 👆 Start

diving into inference now... #reinvent

Tweet 74/104 👇 Next tweet 👆 Start

more on @awscloud’s custom silicon, Inferentia, for #ml inference at https://aws.amazon.com/machine-learning/inferentia/ #reinvent

Tweet 75/104 👇 Next tweet 👆 Start

we’ll get there in a minute (I’m sure) but here’s more on @awscloud Trainium, the custom chip for #ml training https://aws.amazon.com/machine-learning/trainium/ #reinvent

Tweet 76/104 👇 Next tweet 👆 Start

back to inference, @awscloud is working to improve inference work on general purpose CPUs as well. sometimes you just need to run the process where the workload is w/out the custom chips #reinvent

Tweet 77/104 👇 Next tweet 👆 Start

…or at least _those_ custom chips #reinvent

Tweet 78/104 👇 Next tweet 👆 Start

sticker stats for Trainium… #reinvent

Tweet 79/104 👇 Next tweet 👆 Start

Peter says the name “Trainium” implies training #ml models. for most, it’s probably 👇 #reinvent

Tweet 80/104 👇 Next tweet 👆 Start

“..as is normal in a math party” << f--k yeah, Peter #reinvent

Tweet 81/104 👇 Next tweet 👆 Start

Peter diving into the math of #ml training runs. you need it to figure out how to scale out/up a workload to get the job done #reinvent

Tweet 82/104 👇 Next tweet 👆 Start

GPT-3 is slightly larger than BERT-Large #nlp #ml models #reinvent

Tweet 83/104 👇 Next tweet 👆 Start

these models are massive. they create their own computer science problems #reinvent

Tweet 84/104 👇 Next tweet 👆 Start

more on how to tackle these challenges the @awscloud Well-Architected Framework, Machine Learning Lens that’s available at https://docs.aws.amazon.com/wellarchitected/latest/machine-learning-lens/machine-learning-lens.html #reinvent

Tweet 85/104 👇 Next tweet 👆 Start

more math party analogy/reference! #reinvent

Tweet 86/104 👇 Next tweet 👆 Start

…lots of room left in that graph... #reinvent

Tweet 87/104 👇 Next tweet 👆 Start

Peter talking about the biggest @awscloud EC2 instance types for #ml training #reinvent

Tweet 88/104 👇 Next tweet 👆 Start

the network optimized version of the Trn1 instance type will have 1600 Gbps network bandwidth << fantastic! #reinvent

Tweet 89/104 👇 Next tweet 👆 Start

sizing your training pool is a critical decision. not only will it impact how LONG you need to wait but also how MUCH you pay read that Well-Architected Lens, please! https://docs.aws.amazon.com/wellarchitected/latest/machine-learning-lens/machine-learning-lens.html #reinvent

Tweet 90/104 👇 Next tweet 👆 Start

Tranium uses a technique called “Systolic Array Manipulation” going to have to dig into this one later on: https://en.wikipedia.org/wiki/Systolic_array #reinvent

Tweet 91/104 👇 Next tweet 👆 Start

Tranium provide 16 fully programmable inline data processors. this allows further tuning for each training workload << still doesn’t fix the name though 🤦 #reinvent

Tweet 92/104 👇 Next tweet 👆 Start

now we’re talking about how to round numbers. I ❤️ this stuff super niche but fascinating #reinvent

Tweet 93/104 👇 Next tweet 👆 Start

of course Trainium supports stochastic rounding directly in hardware. because, why not? #reinvent

Tweet 94/104 👇 Next tweet 👆 Start

more on the @awscloud Neuron SDK at https://aws.amazon.com/machine-learning/neuron/ << it abstracts a lot of what Peter just covered away, so you just get the benefits #reinvent

Tweet 95/104 👇 Next tweet 👆 Start

Peter is going to wrap up with sustainability and the climate pledge more on the pledge (now over 200 signatories) at https://sustainability.aboutamazon.com/about/the-climate-pledge #reinvent

Tweet 96/104 👇 Next tweet 👆 Start

. @awscloud is always looking to improve efficiency in every aspect of our infrastructure << we’ve heard various achievements and efforts year over year from them. it’s nice to see #reinvent

Tweet 97/104 👇 Next tweet 👆 Start

that’s a big commitment…and they are on a path to achieve it 5 years early (originally target was 2030) #reinvent

Tweet 98/104 👇 Next tweet 👆 Start

#reinvent

Tweet 99/104 👇 Next tweet 👆 Start

storage isn’t the only problem. moving that power around is a big problem as well #reinvent

Tweet 100/104 👇 Next tweet 👆 Start

here’s a great research piece from @voxdotcom https://www.youtube.com/watch?v=s3ScJ_FwaZk&feature=youtu.be #reinvent

Tweet 101/104 👇 Next tweet 👆 Start

. @mikegchambers called this the other night in our day one recap! #reinvent

Tweet 102/104 👇 Next tweet 👆 Start

you can watch that recap on @mikegchambers excellent YouTube channel at https://www.youtube.com/watch?v=FiJfYTqM02M&feature=youtu.be #reinvent

Tweet 103/104 👇 Next tweet 👆 Start

here are some other sessions at @awscloud #reinvent that focus on sustainability. be sure to check them out #reinvent

Tweet 104/104 👇 Next tweet 👆 Start

..and that’s a wrap from Peter. not nearly as broad as previous years but still a great deep dive into things like @awscloud custom silicon /🧵 #reinvent

]]>
https://markn.ca/2021/peter-desantis-keynote-at-aws-re-invent-2021/ 67f6bbeaaf961b0001443178 Wed, 01 Dec 2021 09:00:00 -0500
<![CDATA[ Opinions my own: Corey Quinn & Bill Vass ]]> Want to share with others? Formatting issues in your reader? This post is available online, Opinions my own: Corey Quinn & Bill Vass

Corey Quinn interviews key AWS leaders in a casual settings. This time he sits down with Bill Vass, VP Technology & Engineering.

This 👇 is the Twitter thread of my coverage of the keynote…

Tweet 1/20 👇 Next tweet

up now for @awscloud #reinvent: @QuinnyPig speaking with Bill Vass, VP Technology & Engineering at AWS

Tweet 2/20 👇 Next tweet 👆 Start

paraphrased: “Bill, what do you do?”, @QuinnyPig “Everything”, Bill 🤣 << Bill was very modest about it but wow, he’s got a lot of critical aspect of @awscloud rolling up into him #reinvent

Tweet 3/20 👇 Next tweet 👆 Start

Bill is also the exec sponsor for Defence & Intelligence, Automotive, & Energy << apparently Bill doesn’t sleep #reinvent

Tweet 4/20 👇 Next tweet 👆 Start

on things like quantum, @QuinnyPig asks about the challenges of getting started Bill’s highlights the efforts the team is working on to make these more approachable. Braket lets you use a Jupyter notebook to interact with the underlying system https://aws.amazon.com/braket/ #reinvent

Tweet 5/20 👇 Next tweet 👆 Start

apparently @QuinnyPig got to see pics of the quantum facilities. I’m jealous. it sounds super cool #reinvent

Tweet 6/20 👇 Next tweet 👆 Start

Tweet 7/20 👇 Next tweet 👆 Start

only things as cold as the quantum facility: Brands vs @QuinnyPig …though Bill debates this …I don’t 🤣 #reinvent

Tweet 8/20 👇 Next tweet 👆 Start

one thing Bill ❤️’s about working @awscloud is just the sheer scale. you can tell he has a passion for this work and the challenges that AWS faces at hyper scale are fascinating and motivating #reinvent

Tweet 9/20 👇 Next tweet 👆 Start

anything @quinnypig mentions as “complex” in this conversation immediately gets 10x by Bill. he’s got such a depth and breadth of knowledge on the technical side #reinvent

Tweet 10/20 👇 Next tweet 👆 Start

Bill has a fantastic way of explaining revolutionary technology as if it was all a very clear and expected step forward #reinvent

Tweet 11/20 👇 Next tweet 👆 Start

. @QuinnyPig on things like @awscloud Systems Manager extending into on-premises and other cloud. “Was that planned or an evolution?” Bill, “It was always planned that way" #reinvent

Tweet 12/20 👇 Next tweet 👆 Start

I’m glad then planned it that way. I think it’s incredibly powerful when these tools extend into other environments it reduces the operational overhead while providing a ton of flexibility #reinvent

Tweet 13/20 👇 Next tweet 👆 Start

an amazing feature Bill mentioned that doesn’t get enough attention, “Conformance Packs” in AWS Config more on those at https://docs.aws.amazon.com/config/latest/developerguide/conformance-packs.html the idea is one click conformance with various compliance standards #reinvent #security

Tweet 14/20 👇 Next tweet 👆 Start

oohhhh, Bill just mentioned “things we’re doing in the metaverse space” @QuinnyPig didn’t bite but I’m super curious… #reinvent

Tweet 15/20 👇 Next tweet 👆 Start

QLDB = is about “quanta” of data. not quantum computing Bill was not happy with the name don’t think anyone is, no idea how that one slipped through more on QLDB at https://aws.amazon.com/qldb/ #reinvent

Tweet 16/20 👇 Next tweet 👆 Start

. @quinnypig, AWS launches services as MVP (Bill says Minimum Loveable Product), customers are missing out on the changes that happen over the next year. the constant evolution is “neat" Bill mentions the high bar for #security & operational overhead at launch #reinvent

Tweet 17/20 👇 Next tweet 👆 Start

👆 that makes complete sense launch something that’s rock solid but minimally functional. then use that rock solid foundation to build out the service over time that is exactly what the principles in the @awscloud Well-Architected Framework helps you to do #reinvent

Tweet 18/20 👇 Next tweet 👆 Start

Bill’s talking about the general AWS process for new services: - find a problem (ideally one they have themselves) - generalize it - make it super easy to user - make it super easy to scale - voila #reinvent

Tweet 19/20 👇 Next tweet 👆 Start

“You’re heavily read within AWS”, Bill to @quinnypig << 🤦 🤣🤣🤣 seriously though, it’s a smart move by @awscloud. Corey is a stream of fantastic insights packaged in delightful snark #reinvent

Tweet 20/20 👇 Next tweet 👆 Start

be sure to check out the rest of the “Opinions my own” series. @QuinnyPig is an excellent interview host/conversationalist. he’s drawing out a ton of great insights from key @awscloud leaders /🧵 #reinvent

]]>
https://markn.ca/2021/opinions-my-own-corey-quinn-bill-vass/ 67f6bbeaaf961b0001443177 Wed, 01 Dec 2021 09:00:00 -0500
<![CDATA[ Adam Selipsky's Keynote at AWS re:Invent 2021 ]]> Want to share with others? Formatting issues in your reader? This post is available online, Adam Selipsky's Keynote at AWS re:Invent 2021

AWS re:Invent is always THE event in cloud. Adam Selipsky gave his first keynote as the CEO of AWS. Here’s what he covered during this two hour session.

This 👇 is the Twitter thread of my coverage of the keynote…

Tweet 1/111 👇 Next tweet

up now at @awscloud #reinvent, @aselipsky’s first major keynote. …a 🧵

Tweet 2/111 👇 Next tweet 👆 Start

a little look at the past of @awscloud and #reinvent!


Tweet 3/111 👇 Next tweet 👆 Start

some crazy innovation over the past 15 years! thank you @awscloud #reinvent



Tweet 4/111 👇 Next tweet 👆 Start

remember, @quinnypig is live tweeting the @aselipsky keynote as well 😇/ 😈 #reinvent https://twitter.com/QuinnyPig/status/1465719554957447175

Tweet 5/111 👇 Next tweet 👆 Start

. @aselipsky is up now, acknowledging the challenges of the global situation #reinvent

Tweet 6/111 👇 Next tweet 👆 Start

understatement of the year at @awscloud #reinvent

Tweet 7/111 👇 Next tweet 👆 Start

“back then IT & infrastructure just weren’t working” …still true for a lot of orgs we’ve definitely moved into the “people” side of the cloud problem #reinvent

Tweet 8/111 👇 Next tweet 👆 Start

looks like the opening of the keynote is a review of the major milestones of @awscloud. makes sense given that this is the 10th #reinvent

Tweet 9/111 👇 Next tweet 👆 Start

“What does this have to do with selling books?”, @aselipsky, “Nothing!” << …but this needs to be in place to deliver on the @amazon vision. not sure that anyone knew what @awscloud could/would become #reinvent

Tweet 10/111 👇 Next tweet 👆 Start

. “@awscloud now offers over 200 fully-featured services”, @aselipsky << I’m betting that hits 230 by Friday #reinvent

Tweet 11/111 👇 Next tweet 👆 Start

81 AZs, 25 regions, + more on the way more on @awscloud Global Infrastructure up at https://aws.amazon.com/about-aws/global-infrastructure/ #reinvent

Tweet 12/111 👇 Next tweet 👆 Start

#reinvent

Tweet 13/111 👇 Next tweet 👆 Start

“Despite what feels like massive adoption, we’re just getting started”, @aselipsky #reinvent

Tweet 14/111 👇 Next tweet 👆 Start

so far, @aselipsky’s style feels a little more pragmatic than @ajassy. both work because they’re authentic Adam is still building out the history of @awscloud at #reinvent


Tweet 15/111 👇 Next tweet 👆 Start

each of those 👆 customer examples were a bit crazy when announced. taking a chance on technical innovation to drive the business #reinvent

Tweet 16/111 👇 Next tweet 👆 Start

the storyline here is focusing on what @awscloud customers are delivering. that’s smart, it puts the technical achievements in context more impactful than just; feature X, feature Y, business result Z #reinvent

Tweet 17/111 👇 Next tweet 👆 Start

first customer speaker, @Nasdaq / @NasdaqTech, up now at #reinvent, echoing the “pathfinding” theme

Tweet 18/111 👇 Next tweet 👆 Start

. @NasdaqTech does a lot more than most people realize. not sure this story is an impactful to the broad audience because they don’t realize the extend of their technology footprint…it’s crazy big #reinvent

Tweet 19/111 👇 Next tweet 👆 Start

the speed of their processing at scale is mind boggling. 20ms end-to-end #reinvent


Tweet 20/111 👇 Next tweet 👆 Start

#reinvent

Tweet 21/111 👇 Next tweet 👆 Start

would love to see more of the mechanics of @NasdaqTech’s anti-fraud activities. it’ll never happen but would be amazing 🤣 #reinvent

Tweet 22/111 👇 Next tweet 👆 Start

“Our first bill was like $20”, @adenatfriedman << I’m assuming that’s gone up slightly. any guesses @QuinnyPig? ;-) #reinvent

Tweet 23/111 👇 Next tweet 👆 Start

the multi-year move to the @awscloud is to be expected. despite the hype and push, it takes planning and a lot of operational lifting to move everything into the ☁️. it’s worth it, but make sure you do it well #reinvent

Tweet 24/111 👇 Next tweet 👆 Start

two major, free resources will help with that move (both ppl & tech!): - @awscloud Cloud Adoption Framework, https://aws.amazon.com/professional-services/CAF/ - Well-Architected Framework, https://aws.amazon.com/architecture/well-architected/ #reinvent

Tweet 25/111 👇 Next tweet 👆 Start

ok, so @NasdaqTech ended up building their own @awscloud Private Local Zone. wow! more on local zones at: https://aws.amazon.com/about-aws/global-infrastructure/localzones/ #reinvent

Tweet 26/111 👇 Next tweet 👆 Start

that was a very cool customer story #reinvent

Tweet 27/111 👇 Next tweet 👆 Start

attributes of “pathfinding”… #reinvent


Tweet 28/111 👇 Next tweet 👆 Start

next pathfinding example is about 🏀? #reinvent

Tweet 29/111 👇 Next tweet 👆 Start

Tweet 30/111 👇 Next tweet 👆 Start

the key point of this story is that pathfinders and their innovations can truly change the game #reinvent

Tweet 31/111 👇 Next tweet 👆 Start

apparently the link is the @awscloud EC2 instance and consumption-based pricing/usage …that’s fair. maybe not as obviously revolutionary but still massively impactful #reinvent

Tweet 32/111 👇 Next tweet 👆 Start

lots of instances types…maybe time for a new innovation here as it’s hard to keep track of the over 475 instance types not sure that’s a bragging point. maybe there’s another way to look at these resources options? #reinvent

Tweet 33/111 👇 Next tweet 👆 Start

moving on to @awscloud silicon… which—objectively—are awesome #reinvent

Tweet 34/111 👇 Next tweet 👆 Start

NEW LAUNCH: Graviton 3! 25% faster for general compute of v2 #reinvent

Tweet 35/111 👇 Next tweet 👆 Start

Tweet 36/111 👇 Next tweet 👆 Start

very cool improvements with v3 for Graviton #reinvent

Tweet 37/111 👇 Next tweet 👆 Start

NEW LAUNCH: @awscloud Trainium 🧠instance type, Trn1 more on Trainium at https://aws.amazon.com/machine-learning/trainium/ #reinvent

Tweet 38/111 👇 Next tweet 👆 Start

the custom @awscloud silicon is a big boost for #ml workloads. SageMaker makes the whole thing super easy (relatively!) & these chips keep adding performance and value #reinvent

Tweet 39/111 👇 Next tweet 👆 Start

“Fewer and fewer people are learning COBOL these days”, @aselipsky << and we are worse off for it 🤣 #reinvent

Tweet 40/111 👇 Next tweet 👆 Start

wasn’t Mainframe-as-a-service announced a few years back @QuinnyPig? #reinvent

Tweet 41/111 👇 Next tweet 👆 Start

not sure how this differs from whatever was announced a couple year back, maybe just finally seeing the light of day? #reinvent

Tweet 42/111 👇 Next tweet 👆 Start

this is a clear indicator of @awscloud going after government and very large enterprise business. most builders won’t ever care about this service but it’ll help get those last critical workloads into the cloud for those target customers #reinvent

Tweet 43/111 👇 Next tweet 👆 Start

on to hybrid cloud now at @awscloud #reinvent...

Tweet 44/111 👇 Next tweet 👆 Start

quick update on @awscloud Outposts #reinvent

Tweet 45/111 👇 Next tweet 👆 Start

“Outposts isn’t like AWS, it is @awscloud”, @aselipsky #reinvent

Tweet 46/111 👇 Next tweet 👆 Start

Outposts is a smart play. it lets you update how you’re building while taking advantage of your existing investment in your data centre. those are multi-year commitments. Outposts lets you modernize without ditching those investments #reinvent

Tweet 47/111 👇 Next tweet 👆 Start

Adam now continuing the narrative introduced 2 #reinvent’s ago, expanding the idea of hybrid cloud to the edge and #5G #reinvent

Tweet 48/111 👇 Next tweet 👆 Start

some of the @awscloud services associated with this expanded idea of hybrid cloud - AWS Outposts - AWS IoT - AWS Snow Family - AWS Wavelength #reinvent

Tweet 49/111 👇 Next tweet 👆 Start

into the #iot world now…as my stream starts struggling. are the 🤖 un happy with my video yesterday? https://twitter.com/marknca/status/1465340816663142400 #reinvent

Tweet 50/111 👇 Next tweet 👆 Start

NEW SERVICE: @awscloud Private 5G, set up and scale a private mobile network in days #reinvent

Tweet 51/111 👇 Next tweet 👆 Start

I have so, so many questions… #reinvent

Tweet 52/111 👇 Next tweet 👆 Start

for the record, good questions. I would love to dive into the structure behind this new service #reinvent

Tweet 53/111 👇 Next tweet 👆 Start

if @aselipsky tells me I can also get my own private satellite next… #reinvent

Tweet 54/111 👇 Next tweet 👆 Start

. @dish up now at #reinvent. talking about #5G. it appears that they are the @awscloud Private 5G customer...maybe?

Tweet 55/111 👇 Next tweet 👆 Start

not sure where this is going… #reinvent

Tweet 56/111 👇 Next tweet 👆 Start

“that brick” ?!? that’s a classic my friend that Nokia 👆 was f—king indestructible #reinvent

Tweet 57/111 👇 Next tweet 👆 Start

how does this story link to @awcloud at all? #reinvent

Tweet 58/111 👇 Next tweet 👆 Start

given the amount of time DISH is getting here, there’s obviously an important customer with an interesting use case. what that is? no idea #reinvent

Tweet 59/111 👇 Next tweet 👆 Start

not simple: this story #reinvent

Tweet 60/111 👇 Next tweet 👆 Start

I think the take away here is that DISH has modernized their infrastructure on @awscloud and that let’s them deliver the services they want to their customers that just happens to be a 5G network. doesn’t appear related to the new AWS Private 5G service #reinvent

Tweet 61/111 👇 Next tweet 👆 Start

…and the stream is failing…again #reinvent

Tweet 62/111 👇 Next tweet 👆 Start

…and it’s skipped ahead past DISH, so I don’t know how that ended…but it obviously ended. so there’s that #reinvent

Tweet 63/111 👇 Next tweet 👆 Start

. @aselipsky on to a story about Florence Nightingale now #reinvent

Tweet 64/111 👇 Next tweet 👆 Start

the key to the story is that better data drives better decisions... #reinvent

Tweet 65/111 👇 Next tweet 👆 Start

#reinvent

Tweet 66/111 👇 Next tweet 👆 Start

so, are we transitioning to new data services or #ml ones? …I’m cool with either #reinvent

Tweet 67/111 👇 Next tweet 👆 Start

“Data goes on a journey. You need the best tools and analytics at each step of the journey”, @aselipsky #reinvent

Tweet 68/111 👇 Next tweet 👆 Start

. @awscloud continues to offer a wide variety of data stores, make sure the one you’re using matches your data and how you want to record & access your data #reinvent

Tweet 69/111 👇 Next tweet 👆 Start

🏊 into the data lake now... #reinvent

Tweet 70/111 👇 Next tweet 👆 Start

if you’re building a data lake, do yourself a favour and use @awscloud Lake Formation more on the service at https://aws.amazon.com/lake-formation/ #reinvent

Tweet 71/111 👇 Next tweet 👆 Start

ohhh, Lake Formation just got row & cell-level security. that’s awesome! #reinvent #security

Tweet 72/111 👇 Next tweet 👆 Start

Tweet 73/111 👇 Next tweet 👆 Start

more goodness for @awscloud Lake Formation, transition for governed tables << tables that support ACID transactions #reinvent

Tweet 74/111 👇 Next tweet 👆 Start

neither of these sound like game changes but they both smooth out some of the rough spots with Lake Formation. anything that improves the #ux is a win here (though it’s already pretty good!) #reinvent

Tweet 75/111 👇 Next tweet 👆 Start

…on to analytics now #reinvent

Tweet 76/111 👇 Next tweet 👆 Start

. @aselipsky’s point about the right tool for the job is a key message of the @awscloud Well-Architected Framework you balance the ops overhead, cost, etc. in meeting your goals. you need to understand what is critical to your solution and focus on that #reinvent

Tweet 77/111 👇 Next tweet 👆 Start

holy s—t! new #serverless options for Redshift, EMR, MSK, and Kinesis #reinvent

Tweet 78/111 👇 Next tweet 👆 Start

👆 that’s amazing. huge game changer for analytics in the @awscloud #reinvent

Tweet 79/111 👇 Next tweet 👆 Start

another customer up now, this time it’s @united #reinvent


Tweet 80/111 👇 Next tweet 👆 Start

this customer use case is a “get away from legacy IT” story. @united was looking to reduce costs and move IT into an enabler #reinvent

Tweet 81/111 👇 Next tweet 👆 Start

. @united shifted to “one screen” teams instead of 🍕 🍕. they made sure teams were only one screen of their video chat tool << smart #reinvent

Tweet 82/111 👇 Next tweet 👆 Start

nice data point from @united on the success of their new tooling. they’ve increased their NPS by 30pts #reinvent

Tweet 83/111 👇 Next tweet 👆 Start

Tweet 84/111 👇 Next tweet 👆 Start

Tweet 85/111 👇 Next tweet 👆 Start

. @united story over, some nice points about modernizing their approach to IT using @awscloud @aselipsky back up now #reinvent

Tweet 86/111 👇 Next tweet 👆 Start

topic is currently #ml 🧠 #reinvent

Tweet 87/111 👇 Next tweet 👆 Start

no real announcements here (yet), just a reminder that there’s an entire keynote dedicated to #ml tomorrow #reinvent

Tweet 88/111 👇 Next tweet 👆 Start

I ❤️ @awscloud’s clear statements on your control over your data the only, very small caveat is the high level #ml services. some of those will use your data to improve the models but you can opt-out as well #reinvent

Tweet 89/111 👇 Next tweet 👆 Start

…but even that usage is done well with strong #privacy controls well done @awscloud #reinvent

Tweet 90/111 👇 Next tweet 👆 Start

shout out for one of my all time favourite @awscloud services, QuickSight the first service to use the .aws domain: https://aws.amazon.com/quicksight/ #reinvent

Tweet 91/111 👇 Next tweet 👆 Start

#reinvent

Tweet 92/111 👇 Next tweet 👆 Start

NEW FEATURE: Amazon SageMaker Canvas, generate highly available #ml prediction models using a point & click interface << no code! #reinvent

Tweet 93/111 👇 Next tweet 👆 Start

#reinvent

Tweet 94/111 👇 Next tweet 👆 Start

Tweet 95/111 👇 Next tweet 👆 Start

ok, I’m super excited for this one 👆 #reinvent

Tweet 96/111 👇 Next tweet 👆 Start

#reinvent

Tweet 97/111 👇 Next tweet 👆 Start

#reinvent

Tweet 98/111 👇 Next tweet 👆 Start

. @aselipsky talking about @awscloud's efforts to train more builders #reinvent


Tweet 99/111 👇 Next tweet 👆 Start

the fact that @awscloud has launched vertical specific services is a sign of it’s growth. it’s also a sign of the gaps I see with teams regularly just because you CAN build it, doesn’t mean you will. sometimes, you need a higher touch offer…which is what AWS is doing #reinvent


Tweet 100/111 👇 Next tweet 👆 Start

huh? I know each of those words, not sure what they mean together #reinvent

Tweet 101/111 👇 Next tweet 👆 Start

ahhh, ok. so it’s tooling & data for Goldman clients delivered via @awscloud again, goes back to higher level offerings. smart #reinvent

Tweet 102/111 👇 Next tweet 👆 Start

another customer story. @3M …who make post-its. which @aselipsky proudly displays 🤣 #reinvent

Tweet 103/111 👇 Next tweet 👆 Start

let’s see what this story is all about… #reinvent


Tweet 104/111 👇 Next tweet 👆 Start

take together, the customer story this year really show how @awscloud has become accepted as “the way” questions now shift to “how” which is far more interesting. I’m glad we’re into the 2nd age of cloud #reinvent

Tweet 105/111 👇 Next tweet 👆 Start

good for 3M to go through this journey. for the rest of us, this is a “standard” digital transformation story. the big difference here is just the scale again 👆 #reinvent

Tweet 106/111 👇 Next tweet 👆 Start

. @aselipsky back up to maybe wrap? tie a bow on this whole thing? #reinvent

Tweet 107/111 👇 Next tweet 👆 Start

NEW SERVICE: AWS IoT Twin Maker, create & use digital twins of real-world systems #reinvent

Tweet 108/111 👇 Next tweet 👆 Start

the idea here 👆 is that working on a digital representation of a solution is way faster (and safer) than the real thing. this new service makes that process a lot smoother #reinvent

Tweet 109/111 👇 Next tweet 👆 Start

NEW SERVICE: AWS IoT FleetWise, collect data from vehicles & analyze it in the cloud #reinvent

Tweet 110/111 👇 Next tweet 👆 Start

#reinvent

Tweet 111/111 👇 Next tweet 👆 Start

…and that’s a wrap. nice job @aselipsky!

]]>
https://markn.ca/2021/adam-selipskys-keynote-at-aws-re-invent-2021/ 67f6bbeaaf961b0001443176 Tue, 30 Nov 2021 09:00:00 -0500
<![CDATA[ A First Look At The Brand New Amazon Inspector ]]> Want to share with others? Formatting issues in your reader? This post is available online, A First Look At The Brand New Amazon Inspector

Amazon Inspector first launched in 2015. Now in 2021, it’s re-launching with a brand new architecture and a host of new features.

The Goal

This is a vulnerability management service. What that means is that Inspector tries to find software vulnerabilities with your Amazon EC2 instances and container images stored in Amazon ECR (the Elastic Container Registry) and bring them to your attention.

Methodology

In this version 2 edition of the service, the goal appears to have been “reduce friction.” When enabled, Inspector will automatically detect new resources (instances and registries) and where possible, start to scan then continuously.

Based on my initial experiences, it delivers. It’s truly a delightful experience.

During a scan, Inspector looks for operating system and application vulnerabilities and small number of potential misconfigurations. If it detects an issue, it then issues a finding.

Findings

A finding contains a host of details to help you figure out what you want to do with this particular vulnerability.

Sometimes, you’ll simply accept that it’s there and move on. Other times, you’ll patch the software removing the issue. And sometimes, you’ll use another security control—like AWS WAF (a web application firewall)—to prevent anyone from exploiting the vulnerability.

Gotcha’s

There are only two issues with the new service.

The first is potential huge for users of Amazon Inspector Classic, The new version of the service supports a wide variety of Linux distributions but Windows support was (temporarily?) dropped.

The second issue is reasonably simple. IN order to scan an EC2 instance, that instance must be able to access AWS Systems Manager. The easier way to do this is by using the AmazonSSMManagedInstanceCore policy in AWS IAM. This policy is the simplest way to grant the required permissions.

Pricing

Amazon Inspector prices based on the number of container image scans run and average number of EC2 instances scanned.

Like any AWS service, it’s important to understand the pricing structure and how your usage will map to it. This service can be pricey at scale. But remember to evaluate that cost vs. the additional protect it offers to your builds.

Next Steps

In the video above 👆, I walk through setting the service up and scanning some resources. That demo will give you an idea of how easy the service is to use (very) and the value it can provide you and your team (a lot).

The new Amazon Inspector is generally available today in most AWS regions with a 15 day free trial. Simply visit the Amazon Inspector Management Console to get started.

]]>
https://markn.ca/2021/a-first-look-at-the-brand-new-amazon-inspector/ 67f6bbeaaf961b0001443175 Tue, 30 Nov 2021 09:00:00 -0500
<![CDATA[ The Top AWS re:Invent Announcements ]]> Want to share with others? Formatting issues in your reader? This post is available online, The Top AWS re:Invent Announcements

Here are the top AWS announcements leading up to and during AWS re:Invent 2021. I've rated these announcements Fire emojiFire emojiFire emojiFire emojiFire emojiFire emoji and for some, I've added a bit of commentary.

For the really big or impactful announcements, I'll link to more in-depth content where appropriate. I'm also tracking all of the announcements if you want the fire hose.

END-INTRO

Contents

29-Nov—05-Dec // AWS re:Invent - 40 announcements

Introducing AWS DMS Fleet Advisor for automated discovery and analysis of database and analytics workloads (Preview)

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

My take: This is a cool feature to help move your traditional databases into a data-specific data store in the AWS Cloud. It's smart move that helps teams get to a cloud native solution faster.

AWS Database Migration Service (AWS DMS) is a service that helps you migrate databases to AWS quickly and securely. AWS DMS Fleet Advisor is a new feature of AWS DMS that allows you to quickly build a database and analytics migration plan by automating the discovery and analysis of your fleet.

AWS DMS Fleet Advisor is intended for users looking to migrate a large number of database and analytic servers to AWS.

Introducing Amazon SageMaker Serverless Inference (preview)

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

Amazon SageMaker Serverless Inference is a new inference option that enables you to easily deploy machine learning models for inference without having to configure or manage the underlying infrastructure. Simply select the serverless option when deploying your machine learning model, and Amazon SageMaker automatically provisions, scales, and turns off compute capacity based on the volume of inference requests.

With SageMaker Serverless Inference, you pay only for the duration of running the inference code and the amount of data processed, not for idle time.

Introducing Amazon SageMaker Inference Recommender

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

Amazon SageMaker Inference Recommender helps you choose the best available compute instance and configuration to deploy machine learning models for optimal inference performance and cost.

Introducing Amazon SageMaker Ground Truth Plus: Create high-quality training datasets without having to build labeling applications or manage the labeling workforce on your own

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

My take: This will help reduce the time to label data at scale and speed up machine learning projects.

Today, we are excited to announce the general availability of Amazon SageMaker Ground Truth Plus, a new turnkey data labeling servicethat enables you to create high-quality training datasets quickly and reduces costs by up to 40%.

Introducing Amazon Lex Automated Chatbot Designer (Preview)

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

We are excited to announce the preview of automatic chatbot designer in Amazon Lex, enabling developers to automatically design chatbots from conversation transcripts in hours rather than weeks. Amazon Lex helps you build, test, and deploy chatbots and virtual assistants on contact center services (such as Amazon Connect), websites, and messaging channels (such as Facebook Messenger).

The automatic chatbot designer enhances the usability of Amazon Lex by automating conversational design, minimizing developer effort and reducing the time it takes to design a chatbot.

AWS Transit Gateway introduces intra-region peering for simplified cloud operations and network connectivity

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

Starting today, AWS Transit Gateway supports intra-region peering, giving you the ability to establish peering connections between multiple Transit Gateways in the same AWS Region. With this change, different units in your organization can deploy their own Transit Gateways, and easily interconnect them resulting in less administrative overhead and greater autonomy of operation.

AWS Shield Advanced introduces automatic application-layer DDoS mitigation

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

AWS Shield Advanced now automatically protects web applications by blocking application layer (Layer 7) DDoS events with no manual intervention needed by you or the AWS Shield Response Team (SRT). When you protect your resources with AWS Shield Advanced and enable automatic application layer DDoS mitigation, Shield Advanced will identify patterns associated with layer 7 DDoS events and isolate this anomalous traffic by automatically creating AWS WAF rules in your web access control lists (ACLs).

These rules can be implemented in count mode to observe how they will impact resource traffic and then deployed in block mode.

These capabilities enable you to quickly respond to and mitigate DDoS events that threaten the availability of your applications.

AWS Database Migration Service now offers a new console experience, AWS DMS Studio

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

My take: A nice user experience improvement to help get you off those proprietary databases.

AWS Database Migration Service (AWS DMS) is pleased to announce the launch of AWS DMS Studio, a new service console that makes it easy to manage database migrations from start to finish. AWS DMS Studio accelerates and simplifies migrations by integrating tools for each phase of the migration journey from assessment to conversion to migration.

AWS DMS Studio integrates AWS DMS Fleet Advisor to inventory and analyzes your database and analytics fleet, AWS Schema Conversion Tool (SCT) to convert database schema and application code, and AWS DMS to migrate your data.

At each step of the migration, AWS DMS Studio assists you by providing contextual resources such as documentation and guidance on engaging migration experts where needed.

AWS Announces the AWS AI & ML Scholarship Program in collaboration with Intel and Udacity to help bring diversity to the future of the AI and ML workforce

Wed, 01-Dec-2021Fire emojiFire emojiFire emojiFire emojiFire emoji

My take: A great move helping people get the education needed to start a career in machine learning.

The AWS Artificial Intelligence (AI) and Machine Learning (ML) Scholarship program, in collaboration with Intel and Udacity, provides students who self-identify as underserved and underrepresented in tech educational content, career mentorship programs, and 2,500 scholarships annually as part of a commitment to a more diverse future AI & ML workforce.

Announcing Amazon RDS Custom for SQL Server

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

Amazon Relational Database Service (Amazon RDS) Custom is a managed database service for legacy, custom, and packaged applications that require access to the underlying OS and DB environment. Amazon RDS Custom is now available for the SQL Server database engine. Amazon RDS Custom for SQL Server automates setup, operation, and scaling of databases in the cloud while granting access to the database and underlying operating system to configure settings, install drivers, and enable native features to meet the dependent application's requirements.

Announcing Amazon DevOps Guru for RDS, an ML-powered capability that automatically detects and diagnoses performance and operational issues within Amazon Aurora

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

My take: DevOps Guru continues to improve. This time extending into the database sphere.

Amazon DevOps Guru for RDS is a new Machine Learning (ML) powered capability for Amazon Relational Database Service (Amazon RDS) that automatically detects and diagnoses database performance and operational issues, enabling you to resolve bottlenecks in minutes rather than days. Amazon DevOps Guru for RDS is a feature of Amazon DevOps Guru, which detects operational and performance related issues for all Amazon RDS engines and dozens of other resource types.

DevOps Guru for RDS expands upon the existing capabilities of DevOps Guru to detect, diagnose, and provide remediation recommendations for a wide variety of database-related performance issues, such as resource over-utilization and misbehavior of SQL queries.

When an issue occurs, DevOps Guru for RDS immediately notifies developers and DevOps engineers and provides diagnostic information, details on the extent of the problem, and intelligent remediation recommendations to help customers quickly resolve the issue.

Amazon Virtual Private Cloud (VPC) announces Network Access Analyzer to help you easily identify unintended network access

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

My take: This expansion of access analyzer will help improve your overall network security posture within your VPC.

Amazon VPC Network Access Analyzer is a new feature that enables you to identify unintended network access to your resources on AWS. Using Network Access Analyzer, you can verify whether network access for your Virtual Private Cloud (VPC) resources meets your security and compliance guidelines.

With Network Access Analyzer, you can assess and identify improvements to your cloud security posture.

Additionally, Network Access Analyzer makes it easier for you to demonstrate that your network meets certain regulatory requirements.

Amazon Virtual Private Cloud (VPC) announces IP Address Manager (IPAM) to help simplify IP address management on AWS

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

Amazon VPC IP Address Manager (IPAM) is a new feature that makes it easier for you to plan, track, and monitor IP addresses for your AWS workloads. With IPAM's automated workflows, network administrators can more efficiently manage IP addresses.

Amazon Textract announces specialized support for automated processing of identity documents

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

Amazon Textract, a machine learning service that makes it easy to extract text and data from any document or image, now offers specialized support to extract data from identity documents, such U.S. Driver Licenses and U.S. Passports. You can extract implied fields like name and address, as well as explicit fields like Date of Birth, Date of Issue, Date of Expiry, ID #, ID Type, and more in the form of key-value pairs.

Until today, current OCR based solutions were limited, and did not offer the ability to extract all the required fields accurately due to rich background images or the ability to recognize names and addresses, as well as the fields associated with them (e.g., Washington state ID lists home address with the key "8"), or support ID designs and formats that varied by country or state.

Amazon SageMaker Studio now enables interactive data preparation and machine learning at scale within a single universal notebook through built-in integration with Amazon EMR

Wed, 01-Dec-2021Fire emojiFire emojiFire emojiFire emoji

My take: More functionality into an already jam packed tool for machine learning. Excellent.

Amazon SageMaker Studio is the first fully integrated development environment (IDE) for machine learning (ML). It provides a single, web-based visual interface where you can perform all ML development steps required to prepare data, as well as to build, train, and deploy models.

We recently introduced  the ability to visually browse and connect to Amazon EMR clusters right from the SageMaker Studio notebook.

Starting today, you can now monitor and debug your Apache Spark jobs running on EMR right from SageMaker Studio notebooks with just a click.

Additionally, you can now discover, connect to, create, terminate and manage EMR clusters directly from SageMaker Studio.

The built-in integration with EMR therefore enables you to do interactive data preparation and machine learning at peta-byte scale right within the single universal SageMaker Studio notebook.

Amazon SageMaker Studio Lab (currently in preview), a free, no-configuration ML service

Wed, 01-Dec-2021Fire emojiFire emojiFire emojiFire emojiFire emoji

My take: Sign up with your email and you can start learning machine learning tools and techniques right away. This greatly reduces the barriers to accessing this technology.

Introducing Amazon SageMaker Studio Lab is a free, no-configuration service that allows developers, academics, and data scientists to learn and experiment with machine learning.

Amazon SageMaker Pipelines now integrates with SageMaker Model Monitor and SageMaker Clarify

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

Amazon SageMaker Pipelines, a fully managed service that enables you to create, automate, and manage end-to-end machine learning (ML) workflows, now supports integration with Amazon SageMaker Model Monitor and Amazon SageMaker Clarify. With these integrations, you can easily incorporate model quality and bias detection in your ML workflow. The increased automation can help reduce your operational burden in building and managing ML models.

Amazon SageMaker now supports cross-account lineage tracking and multi-hop lineage querying

Wed, 01-Dec-2021Fire emojiFire emojiFire emoji

Amazon SageMaker now offers enhancements to the machine learning (ML) lineage tracking capability that enables customers to track and query the lineage of artifacts such as data, features, and models across an ML workflow. Now, customers can retrieve the end-to-end lineage graph spanning the entire workflow from data preparation to model deployment through a single query.

This feature eliminates undifferentiated heavy lifting needed to retrieve lineage information one workflow step at a time and manually stitch them all together.

Customers can also retrieve lineage information for segments of the workflow by defining a step as the focal point and querying the lineage of the steps that are upstream or downstream of that focal point.

For instance, customers can define a model as the focal entity and retrieve the location of the raw data set from which features were extracted to train that model.


Amazon DynamoDB announces the new Amazon DynamoDB Standard-Infrequent Access table class, which helps you reduce your DynamoDB costs by up to 60 percent

Wed, 01-Dec-2021Fire emojiFire emojiFire emojiFire emoji

My take: This new tier makes it easier to keep data in DynamoDB for longer. No more need to shuffle it out to reduce costs while increasing operational overhead.

Amazon DynamoDB announces the new Amazon DynamoDB Standard-Infrequent Access (DynamoDB Standard-IA) table class, which helps you reduce your DynamoDB costs by up to 60 percent for tables that store infrequently accessed data. The DynamoDB Standard-IA table class is ideal for use cases that require long-term storage of data that is infrequently accessed, such as application logs, old social media posts, e-commerce order history, and past gaming achievements.

Introducing AWS Mainframe Modernization

Tue, 30-Nov-2021Fire emojiFire emojiFire emoji

My take: SMart business move by AWS. This will help larger organizations (like governments) move & modernize some critical workloads...finally.

AWS Mainframe Modernization is a unique platform for mainframe migration and modernization. It allows customers to migrate and modernize their on-premises mainframe workloads to a managed and highly available runtime environment on AWS. This service currently supports two main migration patterns – replatforming and automated refactoring – allowing customers to select their best-fit migration path and associated toolchains based on their migration assessment results.

Introducing Amazon SageMaker Canvas - a visual, no-code interface to build accurate machine learning models

Tue, 30-Nov-2021Fire emojiFire emojiFire emojiFire emojiFire emoji

My take: This opens up Amazon SageMaker to a lot more audiences. This could be THE launch of AWS re:Invent 2021.

Amazon SageMaker Canvas is a new capability of Amazon SageMaker that enables business analysts to create accurate machine learning (ML) models and generate predictions using a visual, point-and-click interface, no coding required.

Introducing Amazon MSK Serverless in public preview

Tue, 30-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: This is how I want to interact with Kafka. Honestly, should've been this way from the start. Super excited about this one.

Today we announced Amazon MSK Serverless in public preview, a new type of Amazon MSK cluster that makes it easier for developers to run Apache Kafka without having to manage its capacity. MSK Serverless automatically provisions and scales compute and storage resources and offers throughput-based pricing, so you can use Apache Kafka on demand and pay for the data you stream and retain.

Introducing Amazon EMR Serverless in preview

Tue, 30-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: All the power of EMR without worrying about the infrastructure? Yes, please.

We are happy to announce the preview of Amazon EMR Serverless, a new serverless option in Amazon EMR that makes it easy and cost-effective for data engineers and analysts to run petabyte-scale data analytics in the cloud. Amazon EMR is a cloud big data platform used by customers to run large-scale distributed data processing jobs, interactive SQL queries, and machine learning applications using open-source analytics frameworks such as Apache Spark, Apache Hive, and Presto.

With EMR Serverless, customers can run applications built using these frameworks with a few clicks, without having to configure, optimize, or secure clusters.

EMR Serverless automatically provisions and scales the compute and memory resources required by the application, and customers only pay for the resources they use.

Deny services and operations for AWS Regions of your choice with AWS Control Tower

Tue, 30-Nov-2021Fire emojiFire emojiFire emoji

My take: About time, this actually solves a common problem in service sprawl.

You can now use AWS Control Tower to deny services and operations in your Control Tower environments for the AWS Region(s) of your choice. Region deny capabilities complement existing AWS Control Tower Region selection and Region deselection features, providing you with the capabilities to address compliance and regulatory requirements while improving cost efficiency of expanding into additional Regions.

AWS Outposts is Now Available in Two Smaller Form Factors

Tue, 30-Nov-2021Fire emojiFire emojiFire emoji

AWS Lake Formation support Governed Tables, storage optimization and row-level security

Tue, 30-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: Sounds super simple, it's probably a nightmare behind the scenes. Thankfully, builders don't have to worry about that and can just enjoyed the added safety & security!

AWS Lake Formation is excited to announce the general availability of three new capabilities that simplify building, securing, and managing data lakes. First, Lake Formation Governed Tables, a new type of table on Amazon S3, that simplifies building resilient data pipelines with multi-table transaction support.

As data is added or changed, Lake Formation automatically manages conflicts and errors to ensure that all users see a consistent view of the data.

This eliminates the need for customers to create custom error handling code or batch their updates.

Second, Governed Tables monitor and automatically optimize how data is stored so query times are consistent and fast.

Third, in addition to table and columns, Lake Formation now supports row and cell-level permissions, making it more easily to restrict access to sensitive information by granting users access to only the portions of the data they are allowed to see.

Governed Tables, row and cell-level permissions are now supported through Amazon Athena, Amazon Redshift Spectrum, AWS Glue, and Amazon QuickSight.

Announcing preview of AWS Private 5G

Tue, 30-Nov-2021Fire emojiFire emojiFire emojiFire emojiFire emoji

My take: This service is intriguing. It could be a revolutionary way to deploy customized 5G solutions for organizations. Time will tell...

Today, we are announcing the preview of AWS Private 5G, a new managed service that helps enterprises set up and scale private 5G mobile networks in their facilities in days instead of months. With just a few clicks in the AWS console, customers specify where they want to build a mobile network and the network capacity needed for their devices.

AWS then delivers and maintains the small cell radio units, servers, 5G core and radio access network (RAN) software, and subscriber identity modules (SIM cards) required to set up a private 5G network and connect devices.

AWS Private 5G automates the setup and deployment of the network and scales capacity on demand to support additional devices and increased network traffic.

There are no upfront fees or per-device costs with AWS Private 5G, and customers pay only for the network capacity and throughput they request.

Announcing preview of Amazon EC2 Trn1 instances

Tue, 30-Nov-2021Fire emojiFire emojiFire emoji

Today, we are announcing the preview of AWS Trainium-based Amazon EC2 Trn1 instances. AWS Trainium, is the second machine learning chip built by AWS that is optimized for high-performance deep learning training.

Announcing new Amazon EC2 Im4gn and Is4gen instances powered by AWS Graviton2 processors

Tue, 30-Nov-2021Fire emojiFire emojiFire emoji

Today, we are announcing the next generation storage optimized Amazon EC2 Im4gn and Is4gen instances. These instances are built on the AWS Nitro System and are powered by AWS Graviton2 processors. They feature up to 30TB of storage with the new AWS Nitro SSDs that are custom-designed by AWS to maximize the storage performance of I/O intensive workloads such as SQL/NoSQL databases, search engines, distributed file systems and data analytics which continuously read and write from the SSDs in a sustained manner.

AWS Nitro SSDs enable up to 60% lower latency and up to 75% reduced latency variability in Im4gn and Is4gen instances compared to the third generation of storage optimized instances.

These instances maximize the number of transactions processed per second (TPS) for I/O intensive workloads such as relational databases (e.g.

MySQL, MariaDB, PostgreSQL), and NoSQL databases (KeyDB, ScyllaDB, Cassandra) which have medium-large size data sets and can benefit from high compute performance and high network throughput.

They are also an ideal fit for search engines, and data analytics workloads that require very fast access to data sets on local storage.

Announcing new Amazon EC2 C7g instances powered by AWS Graviton3 processors

Tue, 30-Nov-2021Fire emojiFire emojiFire emoji

My take: Woohoo, Graviton 3!

Starting today, the new Amazon EC2 C7g instances powered by the latest generation custom-designed AWS Graviton3 processors are available in preview. Amazon EC2 C7g instances will provide the best price performance in Amazon EC2 for compute-intensive workloads such as high performance computing (HPC), gaming, video encoding, and CPU-based machine learning inference.

These instances are the first in the cloud to feature the cutting edge DDR5 memory technology, which provides 50% more bandwidth compared to DDR4 memory.

C7g instances provide 20% higher networking bandwidth compared to previous generation C6g instances based on AWS Graviton2 processors.

They also support Elastic Fabric Adapter (EFA) for applications such as high performance computing that require high levels of inter-node communication.

Announcing AWS IoT TwinMaker (Preview), a service that makes it easier to build digital twins

Tue, 30-Nov-2021Fire emojiFire emojiFire emoji

My take: This service has a lot of potential and could help IoT services innovate faster. However, like any new AWS service, it'll take a while to full hit it's stride.

Today, we are announcing AWS IoT TwinMaker, a new service that makes it faster and easier for developers to create and use digital twins of real-world systems to monitor and optimize operations. Digital twins are virtual representations of physical systems such as buildings, factories, production lines, and equipment that are regularly updated with real-world data to mimic the structure, state, and behavior of the systems they represent.

Although digital twin use cases are many and diverse, most customers want to get started by easily using their existing data to get a deeper understanding of their operations.

Announcing Amazon Kinesis Data Streams On-Demand

Tue, 30-Nov-2021Fire emojiFire emojiFire emojiFire emojiFire emoji

My take: Kinesis was already great, now having a serverless version make it even more flexible as a tool for builders.

Amazon Kinesis Data Streams is a serverless streaming data service that makes it easy to capture, process, and store streaming data at any scale. Kinesis Data Streams On-Demand is a new capacity mode for Kinesis Data Streams, capable of serving gigabytes of write and read throughput per minute without capacity planning.

You can create a new on-demand data stream or convert an existing data stream into the on-demand mode with a single-click and never have to provision and manage servers, storage, or throughput.

In the on-demand mode you pay for throughput consumed rather than for provisioned resources, making it easy to balance costs and performance.

Amazon Athena now supports new Lake Formation fine-grained security and reliable table features

Tue, 30-Nov-2021Fire emojiFire emojiFire emoji

Amazon Athena users can now use AWS Lake Formation to configure fine-grained access permissions and read from ACID-compliant tables. Amazon Athena makes it simple for users to analyze data in Amazon S3-based data lakes to help ensure that users only have access to data to which they're authorized and that their queries are reliable in the face of changes to the underlying data can be a complex task.

Recover from accidental deletions of your snapshots using Recycle Bin

Mon, 29-Nov-2021Fire emojiFire emojiFire emoji

Starting today, you can use Recycle Bin for EBS Snapshots to recover from accidental snapshot deletions to meet your business continuity needs. Previously, if you accidentally deleted a snapshot, you would have to roll back to a snapshot from an earlier point in time, increasing your recovery point objective.

With Recycle Bin, you can specify a retention time period and recover a deleted snapshot before the expiration of the retention period.

A recovered snapshot retains its attributes such as tags, permissions, and encryption status, which it had prior to deletion, and can be used immediately for creating volumes.

Snapshots that are not recovered from the Recycle Bin are permanently deleted upon expiration of the retention time.

Introducing Amazon CloudWatch Metrics Insights (Preview)

Mon, 29-Nov-2021Fire emojiFire emojiFire emoji

Metrics Insights is a new feature from Amazon CloudWatch that is in preview. As a fast, flexible, SQL based query engine, Metrics Insights enables developers, operators, systems engineers, and cloud solutions architects to identify trends and patterns across millions of operational metrics in real time and helps you use these insights to reduce time to resolution.

With Metrics Insights, you can gain better visibility on your infrastructure and large scale application performance with flexible querying and on-the-fly metric aggregations.

Use Metrics Insights and other CloudWatch features to monitor your AWS and hybrid environments, and to respond to operational problems promptly.

Introducing Amazon CloudWatch Evidently for feature experimentation and safer launches

Mon, 29-Nov-2021Fire emojiFire emojiFire emoji

Amazon CloudWatch Evidently is a new capability which helps application developers safely validate new features across the full application stack. Developers can use Evidently to conduct experiments on new application features and identify unintended consequences, thereby reducing risk. When launching new features, developers can expose the features to a subset of users, monitor key metrics such as page load times and conversions, then safely dial up traffic for general use.

Amazon CloudWatch Evidently is part of CloudWatch’s Digital Experience Monitoring capabilities along with Amazon CloudWatch Synthetics and Amazon CloudWatch RUM.

Customize your AWS Well-Architected Review using Custom Lenses

Mon, 29-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: The ability to add your own lens to this tool will really open up it's use. This feature allows you to define what you want your teams to be asking and investigating about their builds. A lot of power here...

The AWS Well-Architected Tool now offers the ability for customers to create their own custom lenses.

AWS announces the new Amazon Inspector for continual vulnerability management

Mon, 29-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: This functionality is enabled by a complete re-architecting of the Amazon Inspector service. The near real-time results will be a game changer for most builders.

The new Amazon Inspector is a vulnerability management service that continually scans AWS workloads for software vulnerabilities and unintended network exposure is generally available, globally. Amazon Inspector has been completely rearchitected to automate vulnerability management and deliver near real-time findings to minimize the time to discover new vulnerabilities.

Announcing AWS IoT RoboRunner, Now Available in Preview

Mon, 29-Nov-2021Fire emojiFire emojiFire emoji

My take: Is AWS trying to bring about the robot apocalypse?

AWS IoT RoboRunner is a new robotics service that makes it easier for enterprises to build and deploy applications that help fleets of robots work together seamlessly. With AWS IoT RoboRunner, it is easier to build applications that make it possible to interoperate and orchestrate robots from a single view by reducing the complex development work required to connect robots to each other and the rest of your industrial software systems.

Amazon BugBust announces the First Annual AWS BugBust re:Invent challenge

Mon, 29-Nov-2021Fire emojiFire emojiFire emoji

Today, we are excited to announce the First Annual AWS BugBust re:Invent challenge. Java and Python developers of all skill levels, can compete to fix as many software bugs as possible to earn points and climb the global leaderboard. There will be an array of prizes, from hoodies and fly swatters to Amazon Echo Dots, available to participants who meet certain milestones in the challenge.

There’s also the coveted title of “Ultimate AWS BugBuster” accompanied by a cash prize of $1500 for whomever earns the most points by squashing bugs during the event.

22-Nov—28-Nov // One Week to AWS re:Invent - 25 announcements

AWS price reduction for data transfers out to the internet

Fri, 26-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: ABOUT TIME...and sadly, still not enough of a change.

Effective December 1, 2021, AWS is making two pricing changes for data transfer out to the internet. Each month, the first terabyte of data transfer out of Amazon Cloudfront, the first 10 million HTTP/S requests, and the first 2 million CloudFront Functions invocations will be free.

Free data transfer out of CloudFront is no longer limited to the first 12 months.

In addition, the first 100 gigabytes per month of data transfer out from all AWS Regions (except China and GovCoud) will be free.

Free data transfer out from AWS Regions is also no longer limited to the first 12 months.

These changes will replace the existing data transfer and CloudFront AWS Free Tier offerings, and AWS customers will see these changes automatically reflected in their AWS bills going forward.

All AWS customers will benefit from these pricing changes, and millions of customers will see no data transfer charges as a result.

AWS Lambda now supports event filtering for Amazon SQS, Amazon DynamoDB, and Amazon Kinesis as event sources

Fri, 26-Nov-2021Fire emojiFire emojiFire emoji

AWS Lambda now provides content filtering options for SQS, DynamoDB and Kinesis as event sources. With event pattern content filtering, customers can write complex rules so that their Lambda function is only triggered by SQS, DynamoDB, or Kinesis under filtering criteria you specify.

This helps reduce traffic to customers’ Lambda functions, simplifies code, and reduces overall cost.

EC2 Image Builder enables sharing Amazon Machine Images (AMIs) with AWS Organizations and Organization Units

Wed, 24-Nov-2021Fire emojiFire emojiFire emoji

Now on EC2 Image Builder, customers can share their Amazon Machine Images (AMIs) with AWS Organizations and Organizational Units (OUs) in the image distribution phase of their build process. As their organization structure changes, customers no longer have to manually update AMI permissions for individual AWS accounts in their organization.

Customers can create OUs within AWS Organizations and manage AMI permissions for AWS accounts within those OUs.

AWS WAF adds support for Captcha

Wed, 24-Nov-2021Fire emojiFire emojiFire emoji

AWS today announced AWS WAF Captcha to help block unwanted bot traffic by requiring users to successfully complete challenges before their web request are allowed to reach AWS WAF protected resources. Captcha is an acronym for Completely Automated Public Turing test to tell Computers and Humans Apart and is commonly used to distinguish between robotic and human visitors to prevent activity like web scraping, credential stuffing, and spam.

You can configure AWS WAF rules to require WAF Captcha challenges to be solved for specific resources that are frequently targeted by bots such as login, search, and form submissions.

You can also require WAF Captcha challenges for suspicious requests based on the rate, attributes, or labels generated from AWS Managed Rules, such as AWS WAF Bot Control or the Amazon IP Reputation list.

WAF Captcha challenges are simple for humans while remaining effective against bots.

WAF Captcha includes an audio version and is designed to meet WCAG accessibility requirements.

AWS Single Sign-On is now in scope for AWS SOC reporting

Wed, 24-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: A smart expansion of SOC coverage.

AWS Single Sign-On (AWS SSO) is now in scope for AWS SOC 1 , SOC 2, and SOC 3 reports. You can now use AWS SSO in applications requiring audited evidence of the controls in our System and Organization Controls (SOC) reporting. For example, if you use AWS to manage access to accounts and applications, you can use the SOC reports to help meet your compliance requirements for those use cases.  AWS SOC reports are independent third-party examination reports that demonstrate how AWS achieves key compliance controls and objectives.

AWS Proton now supports Terraform Open Source for infrastructure provisioning

Wed, 24-Nov-2021Fire emojiFire emojiFire emoji

AWS Proton now supports the definition of infrastructure in HashiCorp Configuration Language (HCL) and the provisioning of infrastructure using Terraform Open Source through a git-based workflow. Platform teams define AWS Proton templates using Terraform modules, and AWS Proton leverages the customer-managed Terraform automation to provision or update the infrastructure.

Customers can use Terraform as their infrastructure definition and provisioning tool, and AWS Proton will ensure that modules are used consistently and kept up to date.

AWS Proton introduces Git management of infrastructure as code templates

Wed, 24-Nov-2021Fire emojiFire emojiFire emoji

AWS Proton now allows customers to sync their Proton templates from a git repository. Platform teams can create AWS Proton templates based on AWS CloudFormation and Terraform templates uploaded to a git repository. AWS Proton is designed to automatically sync and create a new version when changes are made and committed to the git repository.

With this new feature, platform and development teams can eliminate manual steps and and reduce the chance for human error.

Announcing General Availability of Enterprise On-Ramp

Wed, 24-Nov-2021Fire emojiFire emojiFire emoji

Amazon Web Services (AWS) has announced the general availability of Enterprise On-Ramp, a new Support tier designed for production and business-critical needs to help customers that are starting their cloud journey and need expert guidance to grow and optimize on cloud. With Enterprise On-Ramp, customers can solve cloud-related challenges with 24/7 access to AWS experts whether by phone or live chat, share their screen, and get support to improve issue resolution and eliminate the frustration of back-and-forth emails.

Announcing AWS PrivateLink Support for Amazon Translate

Wed, 24-Nov-2021Fire emojiFire emojiFire emoji

Amazon Translate is a neural machine translation service that delivers fast, high-quality, and affordable language translation. Amazon Translate now supports Amazon Virtual Private Cloud (VPC) endpoints via AWS PrivateLink so you can securely initiate API calls to Amazon Translate from within your VPC and without using public IPs.

AWS PrivateLink provides private connectivity between VPCs and AWS services, without ever leaving the Amazon network, significantly simplifying your internal network architecture.

You no longer need to use an Internet Gateway, Network Address Translation (NAT) devices or firewall proxies to connect to Amazon Translate.

Amazon QuickSight launches versioning in datasets

Wed, 24-Nov-2021Fire emojiFire emojiFire emoji

Amazon QuickSight now supports dataset versioning, which allows dataset owners to understand historical changes within a dataset, preview a specific version, or revert back to a previous version if needed. Dataset versions can be viewed and tracked via the UI, allowing dataset owners to view versions and switch to a specific version via UI. Dataset Versions gives dataset authors the confidence to experiment with their content, knowing that their older versions are available and that they easily can revert back to it when required.

Amazon Managed Grafana adds support for Amazon Athena and Amazon Redshift data sources and Geomap visualization

Wed, 24-Nov-2021Fire emojiFire emojiFire emoji

Amazon Managed Grafana announces new data source plugins for Amazon Athena and Amazon Redshift, enabling customers to query, visualize, and alert on their Athena and Redshift data from Amazon Managed Grafana workspaces. Amazon Managed Grafana now also supports CloudFlare, Zabbix, and Splunk Infrastructure Monitoring data sources as well as the Geomap panel visualization and open source Grafana version 8.2.

AWS Systems Manager Fleet Manager now provides console based access to Windows instances with enhanced security protocols

Tue, 23-Nov-2021Fire emojiFire emojiFire emoji

Fleet Manager, a feature in AWS Systems Manager (SSM) that helps IT Admins streamline and scale their remote server management processes, now enables a console-based management experience for Windows instances. This new feature provides customers a full graphical interface to setup secure connections to and manage Windows instances. You no longer need to install additional software, set up additional servers, or open direct inbound access to ports on the instance.

Announcing usability improvements in the navigation bar of the AWS Management Console

Tue, 23-Nov-2021Fire emojiFire emojiFire emoji

My take: This should be rated lower but it also should've shipped a long time ago. Good upgrade, makes things easier for sure.

Today, we launched usability improvements for the navigation bar in the AWS Management Console. The improvements include a customizable favorites bar, updates to the services menu, and visual updates for consistency and accessibility. The new favorites bar appears when you have selected at least one service as a favorite in the services menu. It also supports an unlimited number of favorites that can be organized with drag and drop.

The updated services menu groups services by category and provides an A to Z listing of all services. 

Amazon ECS announces a new integration with AWS Distro for OpenTelemetry

Tue, 23-Nov-2021Fire emojiFire emojiFire emoji

My take: I like to see the expansion of OpenTelemetry. It's a great project and much easier to ingest data when it's all in the same format.

Amazon Elastic Container Service (Amazon ECS) now enables customers to quickly get started to monitor and debug their applications with traces and custom metrics using AWS Distro for OpenTelemetry (ADOT). This feature allows Amazon ECS customers to use the console to enable metrics and traces collection, and then export to Amazon CloudWatch, Amazon Managed Service for Prometheus, and AWS X-Ray with just few clicks. This experience simplifies a multi-step manual process of configuring ADOT in task definitions, and enables customers to solve application availability and performance issues.

You can now import your AWS CloudFormation stacks into a CloudFormation stack set

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

Today, AWS CloudFormation StackSets announces the capability to import existing CloudFormation stacks into a stack set. StackSets extend the functionality of stacks letting you create, update, or delete stacks across multiple AWS accounts and regions with a single operation.

You can now bring your existing CloudFormation stacks into the management purview of a new or an existing stack set.

This will let you create resources, applications or environments across your AWS Organization and AWS Regions efficiently.

You can subsequently avoid the process of manually replicating and managing the infrastructure in each account and region individually.

Announcing preview of Amazon Linux 2022

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

Today, we are announcing the public preview of Amazon Linux 2022 (AL2022), Amazon's new general purpose Linux for AWS that is designed to provide a secure, stable, and high-performance execution environment to develop and run your cloud applications. Starting with AL2022, a new Amazon Linux major version will be available every two years and each version will be supported for five years. Customers will also be able to take advantage of quarterly updates via minor releases and use the latest software for their applications.

Finally, AL2022 provides the ability to lock to a specific version of the Amazon Linux package repository giving customers control over how and when they absorb updates.

Announcing AWS Graviton2-based instances for Amazon Neptune

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

Starting today, Amazon Neptune announced the general availability of general-purpose T4g and memory-optimized R6g database instances powered by the AWS Graviton2 processor. AWS Graviton2-based instances deliver up to 40% better price performance over comparable current generation x86-based instances for a variety of workloads. Customers running graph workloads using Apache TinkerPop Gremlin, openCypher, or W3C SPARQL 1.1 query languages can expect to see significant improvements in query latency at a lower cost in comparison to x86-based instances of equivalent instance size.

Amazon RDS on AWS Outposts now supports backups on AWS Outposts

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

Amazon Relational Database Service (Amazon RDS) on AWS Outposts now supports creating backups locally on AWS Outposts with Amazon S3 support. You can create backups of your Amazon RDS databases running on AWS Outposts to the same Outpost or to the AWS Region of your Outpost, allowing you to maintain your data residency requirements while giving you flexibility for maintaining your data recovery solutions.

CloudFormation support will be coming soon.

Amazon MemoryDB for Redis now supports AWS Graviton2-based T4g instances and a 2-month Free Trial

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

Amazon MemoryDB for Redis now supports AWS Graviton2-based T4 instances. T4g is the next generation burstable general-purpose DB instance type that provides a baseline level of CPU performance, with the ability to burst CPU usage at any time for as long as required.

This instance type offers a balance of compute, memory, and network resources for a broad spectrum of general purpose workloads.

Amazon EventBridge cross-Region support now expands to more Regions

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

Amazon EventBridge expands support to all Regions, except for AWS GovCloud (US) and China, as a destination for its cross-Region event bus as a target functionality launched in April’2021 (initially launched with 3 destination Regions - US East (N. Virgina), US West (Oregon) and Europe(Ireland)). This will allow customers to consolidate events in one central Region from any Region. This makes it easier for customers to centralize their events for auditing and monitoring purposes or replicate events from source to destinations Regions to help synchronize data across Regions. 

Amazon ECS-optimized AMI is now available as an open-source project

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

Amazon Elastic Container Service (Amazon ECS) today open-sourced the build scripts that Amazon ECS uses to build the Amazon ECS-optimized Amazon Machine Image (AMI). These build scripts are now available on GitHub as an open-source project under the Apache license 2.0.

Customers can use these build scripts to build custom AMIs with security, monitoring, and compliance controls based on their organization’s requirements while using the same components as the Amazon ECS-optimized AMI.

Amazon EC2 Mac Instances now support macOS Monterey

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

Starting today, customers can run macOS Monterey (12.0.1) as Amazon Machine Images (AMIs) on Amazon EC2 Mac instances. Apple macOS Monterey is the current major macOS release from Apple, and introduces multiple new capabilities and performance improvements over prior macOS versions.

macOS Monterey supports running Xcode versions 13.0 and later, which include the latest SDKs for iOS, iPadOS, macOS, tvOS, and watchOS.

Amazon EC2 Mac Instances now support hot attach and detach of EBS volumes

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

Starting today, customers can dynamically attach and detach Amazon Elastic Block Storage (EBS) volumes on their running Amazon EC2 Mac instances. Prior to today, customers attaching or detaching EBS volumes on EC2 Mac instances needed to reboot their instances for revised EBS configuration to be reflected within their macOS guest environments.

Now with this capability, customers do not need to trigger an instance reboot and wait for it to complete when attaching or detaching EBS volumes on EC2 Mac instances.

Amazon CloudWatch Lambda Insights now supports AWS Lambda functions powered by AWS Graviton2 Processor (General Availability)

Mon, 22-Nov-2021Fire emojiFire emojiFire emoji

You can now use Amazon CloudWatch Lambda Insights to monitor, troubleshoot, and optimize the performance of AWS Lambda functions powered by AWS Graviton2 processor. With CloudWatch Lambda Insights you have access to automated dashboards summarizing the performance and health of your Lambda functions.

Amazon Athena adds console support for visualizing AWS Step Functions workflows

Mon, 22-Nov-2021Fire emojiFire emojiFire emojiFire emojiFire emoji

My take: Super handy if you're using Athena...and you are, right?

You can now manage AWS Step Functions workflows from the Amazon Athena console, making it easier to build scalable data processing pipelines, execute queries based on custom business logic, automate administrative and alerting tasks, and more.

15-Nov—21-Nov // Two Weeks to AWS re:Invent - 16 announcements

You can now submit multiple operations for simultaneous execution with AWS CloudFormation StackSets

Fri, 19-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: Finally, a speed increase for CloudFormation!

Today, AWS CloudFormation StackSets announces the capability to execute multiple operations for simultaneous execution. StackSets extends the functionality of CloudFormation stacks by letting you create, update, or delete stacks across multiple AWS accounts and Regions with a single operation.

You can now submit more than one operation per stack set to be executed concurrently.

This capability will enable you to reduce overall processing times with StackSets.

Additionally, you can avoid the overhead of building logic to batch and queue operations submitted to StackSets.

AWS Amplify UI launches new Authenticator component for React, Angular, and Vue

Fri, 19-Nov-2021Fire emojiFire emojiFire emoji

With today’s release, AWS Amplify offers a new Authenticator UI component for web apps built with React, Angular, and Vue, giving developers the easiest way to add login experiences to their app with a single line of code. The new Authenticator UI component not only gives developers the quickest way to add user login and registration workflows to their apps, but also also gives developers complete control over modifying the layout and behavior to match any designs.

Amazon CloudWatch now supports anomaly detection on metric math expressions

Fri, 19-Nov-2021Fire emojiFire emojiFire emoji

Amazon CloudWatch now supports anomaly detection based on metric math expressions. Amazon CloudWatch anomaly detection allows you to apply machine-learning algorithms to continuously analyze system and application metrics, determine a normal baseline, and surface anomalies with minimal user intervention.

CloudWatch metric math allows you to aggregate and transform metrics to create custom visualizations of your health and performance metrics.

Metric math supports basic arithmetic functions such as +,-,/,*, comparison and logical operators such as AND & OR, and a number of additional functions such as RATE and INSIGHT_RULE_METRIC.

For example, with AWS Lambda metrics you can divide the Errors metric by the Invocations metric to get an error rate, use anomaly detection to visualize expected values on a metric graph, and create an anomaly detection alarm to dynamically alert you when the value falls outside of the expected range.

Amazon Athena accelerates queries with AWS Glue Data Catalog partition indexes

Fri, 19-Nov-2021Fire emojiFire emojiFire emoji

Today, we're excited to announce that Amazon Athena supports AWS Glue Data Catalog partition indexes to optimize query planning and reduce query runtime. When you query a table containing a large number of partitions, Athena retrieves the available partitions from the AWS Glue Data Catalog and determines which are required by your query.

As new partitions are added, the time needed to retrieve the partitions increases and can cause query runtime to increase.

AWS Glue Data Catalog allows customers to create partition indexes which reduce the time required to retrieve and filter partition metadata on tables with tens and hundreds of thousands of partitions.

The dashboard feature is now generally available in AWS Audit Manager

Thu, 18-Nov-2021Fire emojiFire emojiFire emoji

AWS Audit Manager now offers a dashboard to simplify your audit preparations with at-a-glance views of your evidence collection status per control. You can instantly track the progress of your audit assessments relative to common control domains. These control domains are general categories of controls, not specific to any one framework that allow customers to quickly assess status on common themes (E.g.- track overall issues in Identity and Compliance control domain).

AWS Identity and Access Management now makes it more efficient to troubleshoot access denied errors in AWS

Thu, 18-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: Yes please!

To help you quickly troubleshoot your permissions in Amazon Web Services (AWS), AWS Identity and Access Management (IAM) now includes the policy type that’s responsible for the denied permissions in access denied error messages. Amazon Sagemaker, AWS CodeCommit and AWS Secrets Manager are among the first AWS services that now offer this additional context, with other services following in the next few months. When you troubleshoot access-related challenges, the identified policy type in the access denied error message helps you to quickly identify the root cause and unblock your developers by updating relevant policies.

Amazon Rekognition reduces pricing of all Image APIs by up to 38%

Thu, 18-Nov-2021Fire emojiFire emojiFire emoji

My take: I'm always a fan of price drops!

Starting November 9, 2021, Amazon Rekognition Image APIs pricing has been reduced by up to 38% in all 14 supported regions. This price reduction will automatically reflect in customer bills starting from November 2021.

Amazon OpenSearch Service (successor to Amazon Elasticsearch Service) now offers - M6g - instances for Asia Pacific (Mumbai) and US West (N. California) Regions

Thu, 18-Nov-2021Fire emojiFire emojiFire emoji

Amazon OpenSearch Service (successor to Amazon Elasticsearch Service) now offers AWS Graviton2 general purpose - M6g instance family. Customers can enjoy up to 38% improvement in indexing throughput, 50% reduction in indexing latency, and 30% improvement in query performance when compared to the corresponding x86-based instances from the current generation M5.

Visualize all your Kubernetes clusters in one place with Amazon EKS Connector, now generally available

Wed, 17-Nov-2021Fire emojiFire emojiFire emoji

My take: I'm all for anything that helps you get a handle on what's happening in your k8s environments.

Today, we are excited to announce the general availability of Amazon Elastic Kubernetes Service (EKS) Connector. With EKS Connector, you can now extend the EKS console to view your Kubernetes clusters outside of AWS. You can use the EKS console to visualize Kubernetes clusters including your on-premises Kubernetes clusters, self-managed clusters running on Amazon Elastic Compute Cloud (EC2), and clusters from other cloud providers.

Once connected, you can see all of your clusters’ statuses, configurations, and workloads in one place on the EKS console.

AWS Network Firewall achieves ISO compliance

Wed, 17-Nov-2021Fire emojiFire emojiFire emoji

Starting today, AWS Network Firewall is compliant with the ISO 9001, ISO 27001, ISO 27017, ISO 27018 and ISO 27701 standards. AWS maintains certifications through extensive audits of its controls to ensure that information security risks that affect the confidentiality, integrity, and availability of company and customer information are appropriately managed.

AWS Glue FindMatches now provides match scores

Wed, 17-Nov-2021Fire emojiFire emojiFire emoji

The FindMatches ML transform in AWS Glue now includes an option to output match scores, which indicate how closely each grouping of records match each other. The FindMatches transform allows you to identify duplicate or matching records in your dataset, even when the records do not have a common unique identifier and no fields match exactly.

FindMatches helps automate complex data cleaning and deduplication tasks.

Amazon CloudWatch Container Insights adds console support for visualizing workload issues and problems via Amazon CloudWatch Application Insights problems

Wed, 17-Nov-2021Fire emojiFire emojiFire emoji

You can now easily setup workload specific monitoring and view the health of these workloads via Amazon CloudWatch Application Insights problems directly from the Amazon CloudWatch Container Insights console, making it easier to dive deep into issues, troubleshoot problems and reduce mean time to resolution.

New and improved Amazon Athena console is now generally available

Tue, 16-Nov-2021Fire emojiFire emojiFire emoji

My take: Woohoo!

Amazon Athena’s redesigned console is now generally available in all AWS commercial and GovCloud regions where Athena is available. The new and improved console brings a modern, more personalized experience to all of the features you enjoy in the current console and includes several new features which make analyzing data with Athena more powerful and productive.

AWS Amplify announces the ability to add custom AWS resources to Amplify-created backends using CDK and CloudFormation

Tue, 16-Nov-2021Fire emojiFire emojiFire emoji

Today, AWS Amplify announces a new “amplify add custom” command to add any of the 175+ AWS services to an Amplify-created backend using the AWS Cloud Development Kit (CDK) or AWS CloudFormation. The AWS Amplify CLI is a command line toolchain that helps frontend developers create app backends in the cloud. The new ability to add custom resources enables developers to add additional resources beyond Amplify’s built-in use cases with a single command.

AWS releases open source JDBC driver to connect to Amazon Neptune

Mon, 15-Nov-2021Fire emojiFire emojiFire emoji

My take: This will help with graph database adoption...not as much as a true serverless version would though.

AWS released an open source Java (JDBC) driver to connect to Amazon Neptune. This makes it easy for customers to connect to Neptune with tools and libraries that support JDBC, such as popular Business Intelligence (BI) tools.

AWS IoT Device Management is now supported on AWS CloudFormation

Mon, 15-Nov-2021Fire emojiFire emojiFire emoji

My take: I gave this is a three because it's solid functionality. It should get a zero because it should have been there at launch.

We are excited to announce that AWS IoT Device Management resources are now supported on AWS CloudFormation. With a few clicks, you can now use a CloudFormation template to pre-configure and deploy IoT fleet management infrastructure like Job Templates, Fleet Metrics, and IoT Logging settings in a standardized and repeatable way across multiple regions and accounts.

08-Nov—14-Nov // Three Weeks to AWS re:Invent - 9 announcements

Unified Search in the AWS Management Console now includes blogs, knowledge articles, events, and tutorials

Fri, 12-Nov-2021Fire emojiFire emojiFire emoji

My take: This makes the AWS Management Console search experience a lot more useful...still a ways to go though

We are excited to announce that blogs, knowledge articles, events, and tutorials are available in Unified Search to enable users to easily search and discover information in the AWS Management Console. AWS users can now search for blogs (e.g., Implementing Auto Scaling for EC2 Mac Instances), knowledge articles (e.g., Set Your Preferences for AWS Emails), tutorials (e.g., Remotely Run Commands on an EC2 Instance), and events (e.g., AWS Container Day) without leaving the AWS Management Console.

Amazon Athena announces cross-account federated query

Fri, 12-Nov-2021Fire emojiFire emojiFire emoji

My take: This will make it easier to leverage Amazon Athena at scale.

If you have data in sources other than Amazon S3, you can use Amazon Athena federated query to analyze the data in-place or build pipelines that extract and store data in Amazon S3. Until today, querying this data required the data source and its connector to use the same AWS account as the user querying the data. Athena now supports cross-account federated query to enable teams of analysts, data scientists, and data engineers to query data stored in other AWS accounts.

AWS Security Hub adds three new FSBP controls and three new partners

Thu, 11-Nov-2021Fire emojiFire emojiFire emoji

My take: We all win when more things get added to AWS Security Hub.

AWS Security Hub has released three new controls for its Foundational Security Best Practice standard (FSBP) to enhance customers’ Cloud Security Posture Management (CSPM). These controls conduct fully-automatic checks against security best practices for Elastic Load Balancing and AWS Systems Manager. If you have Security Hub set to automatically enable new controls and are already using AWS Foundational Security Best Practices, these controls are enabled by default.

Security Hub now supports 162 security controls to automatically check your security posture in AWS.

AWS CloudTrail announces ErrorRate Insights

Thu, 11-Nov-2021Fire emojiFire emojiFire emoji

My take: Very handy to spot operational and security issues.

AWS CloudTrail announces CloudTrail error rate Insights, a new feature of CloudTrail Insights that enables customers to identify unusual activity in their AWS account based on API error codes and their rate.

Amazon EC2 M6gd and C6gd instances powered by AWS Graviton2 now available in additional regions

Thu, 11-Nov-2021Fire emojiFire emojiFire emoji

My take: Nice to see more and more instance types powered by AWS Graviton2. These CPUs are fantastic.

Starting today, general-purpose Amazon EC2 M6gd instances are now available in Asia Pacific (Mumbai), and Europe (London). The compute-optimized Amazon EC2 C6gd instances are now available in Asia Pacific (Mumbai), Canada (Central), and Europe (London). 

AWS Control Tower now supports concurrent operations for detective guardrails

Wed, 10-Nov-2021Fire emojiFire emojiFire emoji

AWS Control Tower now supports concurrent operations for detective guardrails to help expedite guardrail management. You can now enable multiple detective guardrails without needing to wait for individual guardrail operations to complete. AWS Control Tower provides customers with out-of-the-box preventive and detective guardrails that you can deploy to increase your security, operational, and compliance posture.

Announcing general availability of AWS Resilience Hub

Wed, 10-Nov-2021Fire emojiFire emojiFire emojiFire emoji

My take: A new service with a lot of promise. This one aims to gather all of the health metrics in one place and trigger actions based on the overview of your systems.

Amazon Web Services (AWS) has announced the general availability of AWS Resilience Hub, a new service that provides you with a single place to define, validate, and track the resilience of your applications so that you can avoid unnecessary downtime caused by software, infrastructure, or operational disruptions.

Amazon ECS now adds container instance health information

Wed, 10-Nov-2021Fire emojiFire emojiFire emoji

Amazon Elastic Container Service (Amazon ECS) now provides customers enhanced visibility into the health of their compute infrastructure. Customers running containerized workloads using Amazon ECS on Amazon Elastic Compute Cloud  (Amazon EC2) or on-premises with Amazon ECS Anywhere can now query the health status of the container runtime (i.e Docker) for their container instances directly from the Amazon ECS API.

This helps customers improve application resiliency.

AWS Fault Injection Simulator now supports Amazon CloudWatch Alarms and AWS Systems Manager Automation Runbooks.

Mon, 08-Nov-2021Fire emojiFire emojiFire emoji

My take: A very cool service gets a little bit better with this update.

You can now create and run AWS Fault Injection Simulator (FIS) experiments that check the state of Amazon CloudWatch alarms and run AWS Systems Manager (SSM) Automations. You can also now run new FIS experiment actions that inject I/O, network black hole, and packet loss faults into your Amazon EC2 instanes using pre-configured SSM Agent documents.

Because it can be difficult to predict how applications will respond to stress under real world conditions whether in testing or production environments, integrating alarm checks and automated runbooks into your FIS experiments can help you gain more confidence when injecting disruptive events such as network problems, instance termination, API throttling, or other failure conditions.

01-Nov—07-Nov // Four Weeks to AWS re:Invent - 5 announcements

AWS Toolkits for Cloud9, JetBrains and VS Code now support interaction with over 200 new resource types

Fri, 05-Nov-2021Fire emojiFire emojiFire emoji

AWS Toolkits for JetBrains, VS Code and Cloud9 now provide customers with the ability to select and view from a list of 245 resource types across 94 services without leaving their IDEs. With this release, in addition to accessing AWS services that are listed by default in the AWS Explorer pane, customers can choose from hundreds of resources to interact with.

This feature uses the AWS Cloud Control API enabling the Toolkit to continually and rapidly add new resource types in the future. 

Amazon Athena adds cost details to query execution plans

Fri, 05-Nov-2021Fire emojiFire emojiFire emoji

My take: Fantastic update. Athena queries pricing can be tricky. This'll help shine a light on it when you're doing it...that's key.

Amazon Athena now displays the computational cost of your queries alongside their execution plans. With the release of the EXPLAIN ANALYZE statement, Athena can now execute your specified query and return a detailed breakdown of its execution plan along with the CPU usage of each stage and the number of rows processed.

AWS Security Hub adds support for AWS PrivateLink for private access to Security Hub APIs

Wed, 03-Nov-2021Fire emojiFire emojiFire emoji

My take: The more data points we can get into AWS Security Hub, the better.

AWS Security Hub now supports Amazon Virtual Private Cloud (VPC) endpoints via AWS PrivateLink so that you can securely initiate API calls to Security Hub from within your VPC without requiring those calls to traverse across the Internet. AWS PrivateLink support for Security Hub is now available in all AWS Regions where Security Hub is available. To try the new feature, you can go to the VPC console, API, or SDK to create a VPC endpoint for Security Hub in your VPC.

This creates an elastic network interface in your specified subnets.

The interface has a private IP address that serves as an entry point for traffic that is destined for Security Hub.

You can read more about Security Hub’s integration with PrivateLink here.

AWS Lake Formation now supports AWS PrivateLink

Wed, 03-Nov-2021Fire emojiFire emojiFire emoji

AWS Lake Formation now support managed VPC endpoints (powered by AWS PrivateLink) to access a data lake in a Virtual Private Cloud (VPC).  With AWS Lake Formation-managed endpoints, you can now authorize access to the data lake for client applications and services inside of your VPC and on-premises using private IP connectivity. You can also configure VPC endpoint policies to have finer grained control over how services access AWS Lake Formation.

Amazon CloudFront now supports configurable CORS, security, and custom HTTP response headers

Tue, 02-Nov-2021Fire emojiFire emojiFire emoji

My take: Awesome! This is a critical security feature for CloudFront distributions.

Today, Amazon CloudFront is launching support for response headers policies. You can now add cross-origin resource sharing (CORS), security, and custom headers to HTTP responses returned by your CloudFront distributions. You no longer need to configure your origins or use custom Lambda@Edge or CloudFront functions to insert these headers. 

]]>
https://markn.ca/2021/the-top-aws-re-invent-announcements/ 67f6bbeaaf961b0001443174 Mon, 29 Nov 2021 09:00:00 -0500
<![CDATA[ AWS Re-launches Amazon Inspector To Find Software Vulnerabilities ]]> Want to share with others? Formatting issues in your reader? This post is available online, AWS Re-launches Amazon Inspector To Find Software Vulnerabilities

AWS re-launches a dramatically improved Amazon Inspector, a software vulnerability discovery/management service.

The idea behind these types of services is to scan your servers and containers before they reach production to identify known vulnerabilities so that you are aware of them and can mitigate them appropriately.

Notice I said “mitigate” not “patch”. Patching is just one of many possible mitigations.

Amazon Inspector launched in 2015 and a lot has changed since then. This is a much needed upgrade to the service that should help builders identify these issues with the minimal amount of effort possible.

This 👇 Twitter thread highlights some of the details of the launch…

Tweet 1/11 👇 Next tweet

at #reinvent, @awscloud has just re-launched Amazon Inspector this is HUGE! https://www.youtube.com/watch?v=wi1PDr9n67Y&feature=youtu.be 🧵☁️ #cloud #security

Tweet 2/11 👇 Next tweet 👆 Start

re-launches are hard. @awscloud Macie is way, way better now but still doesn't have the traction it should (a/k/a everyone using it) because of a few years of brutal costs & #ux Inspector has always been better, but now it's a lot more user friendly 🧵☁️ #cloud #security

Tweet 3/11 👇 Next tweet 👆 Start

1: assessments are now continual & automated << no more set time period assessments & super delayed results...if you remembered to scan at all the service now just bubbles up findings == awesome 🧵☁️ #cloud #security

Tweet 4/11 👇 Next tweet 👆 Start

2: Inspector uses "the" @awscloud agent (I think there's only one now) which means it's already there on AWS managed AMIs the service leverages that to find EC2 instances as well as ECR repos 🧵☁️ #cloud #security

Tweet 5/11 👇 Next tweet 👆 Start

3: containers! 🧵☁️ #cloud #security

Tweet 6/11 👇 Next tweet 👆 Start

4: @awscloud Organizations support << about f--king time! enabling Inspector was a pain. I ❤️ to be able to say that, "was" critical improvement for adoption 🧵☁️ #cloud #security

Tweet 7/11 👇 Next tweet 👆 Start

5: see no. 2 ... the custom Inspector agent is out the door. the @awscloud Systems Manager agent—the one agent to rule them all—is now used << again, that greatly simplifies adoption 🧵☁️ #cloud #security

Tweet 8/11 👇 Next tweet 👆 Start

6: better risk scoring << we'll see about this one. assigning risk scores is tricky as there are layers involved most vulnerability discovery/management services use the CVE/CVSS score to assess risk but that lacks context it's a start...but only a start 🧵☁️ #cloud #security

Tweet 9/11 👇 Next tweet 👆 Start

7: integrates directly with @awscloud EventBridge << no more routing events through another service. I mean, it still happens behind the scenes but if it's behind the scenes, I can safely ignore 🧵☁️ #cloud #security

Tweet 10/11 👇 Next tweet 👆 Start

8: AWS Security Hub integration << need to dive into this one more. it's unclear what's changed here as there was some level of integration...at least if you consider dumping findings in the Hub "integrating" 🧵☁️ #cloud #security

Tweet 11/11 👇 Next tweet 👆 Start

overall, this is a huge improvement to @awscloud Inspector. I'll take some time next week to dive in but so far, this is a big win for #cloud #security this is GA now the launch blog is up at https://aws.amazon.com/blogs/aws/improved-automated-vulnerability-management-for-cloud-workloads-with-a-new-amazon-inspector/ / 🧵☁️

]]>
https://markn.ca/2021/aws-re-launches-amazon-inspector-to-find-software-vulnerabilities/ 67f6bbeaaf961b0001443173 Mon, 29 Nov 2021 09:00:00 -0500
<![CDATA[ The Ultimate Guide to AWS re:Invent 2021 ]]> Want to share with others? Formatting issues in your reader? This post is available online, The Ultimate Guide to AWS re:Invent 2021

This guide will grow as we get closer to the show. Please check back regularly for updates! Ping me, if you spot a problem or if something is missing @marknca.

As always, the event site is the ultimate source of truth (though I try to provide more context here). The site is available at https://reinvent.awsevents.com
Heads up, AWS has made a change to the campus. Please read the updated “Hotels” section so you’re aware.

Index

A Little Bit of History

I’ve written this guide year after year and it’s an interesting way to track how AWS re:Invent has evolved over the years.

Here are the guides of AWS re:Invent past:

As you would expect, the show has grown in scale and ambition every year as a reflection of the growth of the AWS Cloud and the larger community.

Last Year

Last year’s event was the outlier. With the global pandemic and widespread shutdowns, the event moved to a completely virtual format.

It was…different.

The session content was amazing but a lot of the things we all love about the event simply weren’t possible in a virtual version. That’s understandable, everyone has struggled with what a virtual event looks like compared to an in-person one.

The conflicted news? AWS re:Invent 2021 will be an in-person event with limited virtual aspects.

That means a very different feel to the show. Not only in size but also the demographics. Will there be a strong international attendance? What safety measures will be in place? What will be the requirements to attend?

The short and simple answer: no one is sure.

The show is months away and if you look back to even a month ago, things were very, very different. There are a lot of questions about this year’s AWS re:Invent.

I have a strong feeling that this guide will change even more than previous years…and that’s saying a lot.

Code of Conduct

AWS re:Invent is all about learning and having a shared experience. The key to that is making sure that environment is inviting, safe, and supportive.

The AWS Community Codes of Conduct applies to both the physical and digital space surrounding AWS re:Invent…and to all other AWS events.

I would say that it’s all common sense and following the golden rule but with tens of thousands of people from around the world sharing the experience for the week, it’s best to call this out explicitly.

READ THE CODE OF CONDUCT AND LIVE BY IT.

If you encounter an issue or problem that runs counter to the code or if you in any way feel unsafe, please reach out for help. Amazon Security can be reached at [email protected] for live events. In addition, any one of the on-site staff or security can help resolve any issues.

No system is perfect but this is a great start at creating a safe, inclusive community at this fantastic event.

Who Am I?

I’m an AWS Community Hero, a long time AWS re:Invent attendee (all of them!) and a big fan of the show.

I teach a few courses here on the A Cloud Guru platform (AWS Business Essentials, Introduction to the AWS Marketplace, and Mastering the AWS Well-Architected Framework), tweet regularly, and generally nerd out about all things cloud and security.

I write this guide every year to help the community get the most out of the show. Also, if I’m being 💯 honest, it helps me keep track of everything that’s going on so I can get the most out of the show. 😉

Health Measures

AWS has updated the health measures they are taking to help reduce the overall risk to everyone attending AWS re:Invent 2021.

As with everything, these measures may change as we get closer to the show.

Please read the entire page on the official re:Invent site, but the key aspects are:

  • All badge holders at the event must be fully vaccinated (2 weeks after final shot in the protocol) and provide a record of vaccination in order to receive your badge
  • Masks will be required for everyone at the event
  • Hotels have a different health policy called “Vegas Smart”, please verify the specific measures with your hotel
  • Physical distancing will not be enforced during the event
  • In the event of a positive test being disclosed to AWS, contact tracing will be conducted in partnership with the relevant health authorities

Registration

AWS re:Invent 2021 is now sold out. The cost was $1,799 USD and virtual access remains free.

If you were curious, registration officially opened on Tuesday, 15-Jun-2021.

Hotels

In keeping with the process over the past couple of in-person shows, hotel rooms at discounted will be available as part of the registration flow and after you’re registered.

These rates are always very good and the blocks of rooms are at properties hosting the show. In past years, these room blocks went very, very quickly.

So quickly in fact, that AWS expanded the “campus” to include a number of hotels that weren’t hosting any of the event, just ones where discounts were made available.

This year’s campus is again spread out across a number of venues;

  • Venetian / Palazzo remains the center fo AWS re:Invent. This year it’ll host breakouts, AWS Certification exams, the lounge(s), Content Hub, the Expo, keynotes, leadership sessions, registration, self-paced labs, and SWAG
  • Caesars Forum for breakout content, Content Hub, and meals
  • Encore for breakout content and bookable meeting space
  • Wynn has breakout content, meals, Bootcamps, and will host the Jams

Some of the originally listed properties are no longer part of the campus. There will be no events hosted at these properties and they are no longer listed as a “sleeping room hotel”:

  • The MGM Grand
  • Signature at MGM Grand
  • Mandalay Bay
  • Delano

Venues included in campus but not hosting events;

We’ll get more information closer to the event (as always!) but it looks like most of the content is going to take place at the Venetian/Palazzo, Wynn/Encore, and Caesars Forum.

That’s a bit of a shift from previous years.

The ARIA has dropped its activities in favour of Caesars Forum. That actually makes a lot of sense. Now that AWS has adjusted and dropped the MGM Grand from the campus, most activities will be taking place near each other. The Venetian/Palazzo, Wynn/Encore, and Caesars Forum are the epicentre of AWS re:Invent 2021.

This should make moving between venues a lot easier during the day and give you more flexibility in where you decide to actually stay.

It looks like you’re going to be heading to one of these three hotels (and maybe all three) every day of the show.

Virtual Attendance

As you can probably tell, I’m a big fan of this show. This year will be great but it won’t be the same. The world has changed.

If you aren’t comfortable or cannot attend in person, there is a limited virtual component. I’ll be honest, as an international attendee, I’m disappointed in this aspect of the show.

As it currently stands, the keynotes and leadership sessions will be live streamed. Breakout sessions will be available on-demand after the event.

Given the virtual infrastructure in place for AWS re:Invent 2020, I’m assuming that will all take place on that platform (vs. say, YouTube).

This approach isn’t really any different than previous in-person years. 😔

I’ve created a separate guide to attending AWS re:Invent virtually that might help if you’re going remote.

How to re:Invent

Season four of the show, “How to re:Invent” has already kicked off!

This year, Annie Hancock returns with a new co-host, Kelley Schultz.

This show brings you tips and tricks about the conference and gives you an inside look as we get closer to the show.

Stay tuned for each episode as they are always chock full of great info.

The episodes published so far;

  1. Why attend re:Invent 2021
  2. Reserved seating
  3. AWS Partners at re:Invent

Reserved Seating

AWS has again put a reserved seating system in place. That’s probably even more important this year with the health and safety measures put in place.

You can view the session catalog and reserve your seat by logging in.

As always, the earlier you do this the better. Reserved seating is open now, so don’t delay.

The good news is that this process—while sometimes frustrating—generally makes the week go much smoother. Also, keep checking back as AWS often added repeats for the most popular sessions.

…and keep in mind that all breakout sessions will be available on YouTube shortly after re:Invent. However, chalk talks, workshops, and some other session types won’t be recorded.

Keep that in mind as you build out your week.

Agenda

The official agenda has been published. This gives us a glimpse at the structure of the show.

Things kick off on Sunday with the Midnight Madness party. Other than that, Sunday is just a day to get oriented, check-in to get your badge, and pick up your swag!

Monday is when things really start to roll. The certification exams start, labs open up, bootcamps kick off, and some of the breakout sessions start.

We also have the first keynote of the week. This one is at 3:00—5:00pm pacific time. After that keynote, the expo hall will host the now traditional Welcome Reception.

Tuesday is the first “standard” day of the show. Most activities are open and we have a keynote from 8:00—10:00am pacific.

In the evening, there are several restaurant receptions hosted by sponsors and a few “quirky activities” which promise to be a lot of fun.

Wednesday is almost a cookie cutter of Tuesday with the one exception being a second keynote that runs from 3:00—5:00pm pacific.

On Thursday, we’re back to the Tuesday schedule during the day. Only the one, morning keynote. We have the AWS Certification Reception in the early evening and the night caps off with the legendary re:Play party.

No idea how that’s going to feel this year given the circumstances but every other year, it’s been an absolutely blast.

re:Invent is still going strong on Friday. Maybe “strong” is not the right word, that always depends on how your re:Play party experience was. No keynotes on Friday but breakout sessions (often with repeats to the best of the week) run until 12:30pm when the conference officially ends.

Leadership Sessions

AWS has also announced an expanded “leadership sessions” series. These were introduced a couple years back to serve as “mini-keynotes”.

I like the idea as the sessions are typically delivered by a senior AWS leader in that area.

Here are the 2021 leadership sessions;

  • AWS Executive Panel hosted by Francessca Vasquez, Vice President, Technology
  • AWS Public Sector with Max Peterson, Vice President, Worldwide Public Sector
  • AWS Public Sector Partners by Sandy Carter, Vice President, Worldwide Public Sector Partners and Programs
  • AWS Storage with Mai-Lan Tomsen-Bukovec who is the Vice President of Block and Object Storage
  • Rahul Pathak (Vice President, Analytics) is back with the leadership session for Analytics
  • The Cloud Operations session will be delivered by Bill Vass, Vice President, Engineering — Storage, Automation, Streaming & Management
  • David Brown, the Vice President of Amazon EC2, will deliver the session focusing on Compute
  • Containers gets covered by Deepak Singh, Vice President of Compute Services
  • The Developer session is brought to your by Ken Exner, Director of AWS Developer Tools
  • Bill Vass gets the double call this year, delivering the Edge session as well as the already mentioned Cloud Operations one
  • Enterprise/Migration will be covered by Todd Weatherby, Vice President of Professional Services
  • Mayumi Hiramatsu (Vice President, Amazon EC2 Networking) will deliver the session one Networking and Content Delivery
  • Stephen Schmidt (Vice President and Chief Information Security Officer) is back with another leadership session on Security, Compliance and Identity
  • David Richardson, Vice President of Serverless, has us covered for Serverless
  • Maureen Lonergan, Director of AWS Training and Certification, will deliver the final leadership session with a focus on Training & Certification

These sessions all follow the same general format. They review the biggest announcements from the past year for the theme. Then make a few announcements of either new services or features either launching immediately or coming soon.

These announcements are ones that are not quite main keynote level but still deserving more attention than just a blog post or documentation update.

Hero Guides

Navigating all of the different sessions can be overwhelming. This year, a few of the AWS Heroes have again come together to present various guides aligned with specific interests.

The guides are downloadable PDFs which is a bit of a change from previous years where they were built into the registration system and available as HTML.

The following guides are available;

In addition to the Hero guides, AWS has also pulled together guides for specific industries and a few tailored to APN Partner interests.

The Quad

For now, it appears the The Quad has been removed from AWS re:Invent 2021. It’s still early (mid-September) but the following events are currently up in the air:

No word yet if they’ll find a new home as the AWS re:Invent 2021 campus has been reduced in size.

I’ll leave the description of these events here in case they do find a new home and come back to the schedule…

The DeepRacer league has grown year after year. It’s always a blast to watch or race in. You can get started by reviewing the documentation online or watching some of the great content here on the A Cloud Guru platform.

The Builder’s Fair is basically a big science fair. Groups from schools, companies, and other organizations show off their projects with hands-on demos and interactive discussions. It’s a very cool way to see some different use cases for AWS technologies and their real world applications.

AWS Connected World is new to AWS re:Invent. This space provides an area to highlight IoT, AI/ML, AR/VR, robotics, and more. AWS experts and partners will be on hand to show how they’ve applied these technologies to solve interesting problems.

The Demo Theatre in The Quad is where AWS Partners and experts can showcase short (usually 15m) demos of various services and solutions. The casual nature of the theatre makes it easy to ask questions and learn more about specific solutions.

Again, 👆 these events and the entire Quad have been removed from the official site alongside the reduction in campus size. Stay tuned for more.

Midnight Madness

For the past few years, re:Invent has kicked off with this great event. Styled after a US college sports pep rally, the party always hosts the first product launch of the week along with fun activities, food, music…and maybe, just maybe, another world record!

re:Play

The legendary conference party is back again for its 10th iteration. Every year makes the last seem small. Expect more dodgeball, office chair races, and of course amazing musical performances.

Other Social Activities

With most of AWS re:Invent 2021 taking place physically, there are going to be a host of other social activities.

AWS has updated the “Quirky” page with some of the available activities.

This year there will be;

  • A ping pong tournament in the Venetian, Tuesday to Thursday
  • Amazon’s World Famous Chicken Wing Eating Contest taking place a Midnight Madness
  • Amazon Fishbowl, a glimpse into Amazon’s culture
  • Choir!Choir!Choir!
  • Bingo night
  • Board Game Night + Lego Competition

AWS does a great job of filling the calendar making sure that you can find something to suit. You definitely won’t be bored during the week!

Please check back regularly for updates! Ping me, if you spot a problem or if something is missing @marknca.

]]>
https://markn.ca/2021/the-ultimate-guide-to-aws-re-invent-2021/ 67f6bbeaaf961b000144326e Fri, 26 Nov 2021 09:00:00 -0500
<![CDATA[ Performance Efficiency in the AWS Well-Architected Framework ]]> Want to share with others? Formatting issues in your reader? This post is available online, Performance Efficiency in the AWS Well-Architected Framework

Performance Efficiency is one of the five pillars of the AWS Well-Architected Framework. The framework describes the principles and techniques required to make informed trade-offs when you’re building in the AWS Cloud.

I’ve taught thousands of builders how to build better using the framework on the A Cloud Guru platform. Be sure to check out my course, “Mastering The Well-Architected Framework

This 👇 Twitter thread dives deeper into the Performance Efficiency pillar of the framework…

Tweet 1/8 👇 Next tweet

time to dive into the Performance Efficiency Pillar of the @awscloud Well-Architected Framework this one is all about removing bottlenecks and reducing waste...and making things go fast! 🤣 🧵☁️ #cloud #devops

Tweet 2/8 👇 Next tweet 👆 Start

you can view this thread unrolled at https://markn.ca/2021/performance-efficiency-in-the-aws-well-architected-framework/ yesterday's, I had a thread on the Reliability Pillar of the Framework. that's up at https://markn.ca/2021/reliability-in-the-aws-well-architected-framework/ 🧵☁️ #cloud #devops

Tweet 3/8 👇 Next tweet 👆 Start

the "official" definition from the Framework for Performance Efficiency is, "…the ability to use computing resources efficiently to meet system requirements, and to maintain that efficiency as demand changes and technologies evolve." meh. super formal 🧵☁️ #cloud #devops

Tweet 4/8 👇 Next tweet 👆 Start

I think it's really as simple as; - meet user experience goals - reduce waste - remove bottlenecks simple definition-wise. it's tricky to accomplish these things. but, like the rest of the framework, it's part of a larger practice 🧵☁️ #cloud #devops

Tweet 5/8 👇 Next tweet 👆 Start

the principles for this pillar are; - let @awscloud do the work whenever possible - reduce latency through regions & the edge - #serverless first - experience as new services GA - think about the user, not your tech stack 🧵☁️ #cloud #devops

Tweet 6/8 👇 Next tweet 👆 Start

...and honestly, if you only do one thing under "performance efficiency", switching your thinking to the user first will move the needle the most tackling the system from the #ux, really shines a light on what's important 🧵☁️ #cloud #devops

Tweet 7/8 👇 Next tweet 👆 Start

the pillar breaks it's activities into four phases. they are; - selection - review - monitoring - trade-offs that's a solid feedback loop that will help guide your choices 🧵☁️ #cloud #devops

Tweet 8/8 👇 Next tweet 👆 Start

I think this pillar has the most variation. what performance means for your solution is probably completely different than another team's solution read the full pillar at https://docs.aws.amazon.com/wellarchitected/latest/performance-efficiency-pillar/welcome.html /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/performance-efficiency-in-the-aws-well-architected-framework/ 67f6bbeaaf961b0001443172 Fri, 26 Nov 2021 09:00:00 -0500
<![CDATA[ Getting The Most Out of AWS re:Invent Remotely ]]> Want to share with others? Formatting issues in your reader? This post is available online, Getting The Most Out of AWS re:Invent Remotely

AWS re:Invent is always THE event in cloud. This year a lot of people can’t attend in person. This post tells you how to get the most out of the virtual side of the event.

I’ve got a lot of content up around AWS re:Invent 2021. Be sure to browse the full list. If you’re attending in person, you want, “[The Ultimate Guide to AWS re:Invent 2021](/2021/the-ultimate-guide-to-aws-reinvent-2021”

Index

Registration

Attending AWS re:Invent 2021 virtually is free. You just need to sign up and that will give you access to the event system.

…and yes, we now know that AWS is using a slightly modified version of their new event platform from AWS re:Invent 2020. That was a mixed bag last year but with the vast majority of the event happening in person, it should be a better experience this year.

If you haven’t already registered, make sure you take care of that soon. Remember that in-person attendance is now sold out.

The Platform

The main focus of the platform is your agenda. This is essentially your event calendar.

There are two major problems with it;

  1. It’s locked into the platform. There’s no simple way to export or sync with your actual calendar 😔
  2. The search feature is very weak. It will only show results for the selected day 😔

It’s hard to find sessions and then to remember to attend them. Not a great start but it’s what we have to work with.

No matter, the content is divided into two main areas; live and on-demand.

It’s not mentioned but I suspect that the in-person sessions will be published here but I hope they end up on the AWS Events YouTube channel as it’s a lot easier to share content from there.

On Demand

At the moment, there are currently 554 unique sessions listed as “on demand.” This sounds close total number of breakout sessions. The other session types; Chalk talks, workshops, and Builder’s Sessions aren’t typically recorded.

I’ve dumped the session catalog to make it a bit easier to search. You can use your browser’s find function to locate a session you’re interested in and then click through to that session on the re:Invent platform.

Not ideal, but simple and easy to work with…well easier than the platform itself.

The question that I can’t seem to find an answer to is when will the sessions become available on demand? When I find out, I’ll update this post.

Live

The live schedule is as expected. The five keynotes and the leadership sessions will all be broadcast live based on Pacific Time. They will then be rebroadcast twice, once for Europe and again for Asia.

Additionally, we’ll get regular content on Twitch via the AWSonAir program. That’s going to be running 24/7 and will include these shows (with some repeats for the time zones);

  • Launch Sessions
  • Game Day
  • Community
  • Industry Live
  • This is My Architecture
  • Get Started
  • Daily Recaps
  • Voice of the Customer
  • BugBust Hackathon
  • IoT All The Things
  • All in the Field
  • All Things Automotive

More about these shows in the description on the event platform.

If you like “This is My Architecture”, I’ve been doing reaction videos of old episodes over on my YouTube channel.

I’ve added all of the live events to an accessible calendar. To make it easier to overlay the broadcasts with your actual calendar. Not perfect but better than having that data locked in the platform.

As is reasonable, things may change and the AWS re:Invent platform is the ultimate source of truth here. Make sure to double check the timing & schedule.

My Strategy

This is the first time that I’m not on site for a physical re:Invent. I have very mixed feelings about it. In order to get the most out of the virtual side of the event, I’m planning on the following;

  • Watching (and live tweeting!) the keynotes (…but will probably skip the Global Partner Keynote)
  • Watching the “Opinions my own” series where Corey Quinn sits down with various AWS leaders…which I’m sure they immediately regret
  • Catching a few of the leadership sessions. Specifically, Stephen Schmidt’s security session, Deepak Singh’s session on containers, and Francessca Vasquez panel, “Leading through Uncertainty: Resilience, Grit, and Courage”
  • Watching on demand sessions as they are published on the platform. I’ll be following a bunch of the sessions I recommended in my Hero Guide (which you can add to your agenda with one click on the platform)
  • Actually taking time to use the new features/services and provide some analysis here on my site and via Twitter, where I’m @marknca
  • Joining Andrew Brown for at least one Twitter space to talk about everything

What I’m missing out on is all of the personal connections. It’s been too long and sadly, it’ll be a little bit longer for me. I’m happy to connect virtually throughout the show, I’m sure there’s going to be a lot to talk about.

]]>
https://markn.ca/2021/getting-the-most-out-of-aws-re-invent-remotely/ 67f6bbeaaf961b0001443171 Fri, 26 Nov 2021 09:00:00 -0500
<![CDATA[ Reliability in the AWS Well-Architected Framework ]]> Want to share with others? Formatting issues in your reader? This post is available online, Reliability in the AWS Well-Architected Framework

Reliability is one of the five pillars of the AWS Well-Architected Framework. The framework describes the principles and techniques required to make informed trade-offs when you’re building in the AWS Cloud.

I’ve taught thousands of builders how to build better using the framework on the A Cloud Guru platform. Be sure to check out my course, “Mastering The Well-Architected Framework

This 👇 Twitter thread dives deeper into the Reliability pillar of the framework…

Tweet 1/8 👇 Next tweet

the Reliability Pillar is on tap today. this is one of the five pillars of the @awscloud Well-Architected Framework this pillar is all about making sure that your systems work CONSISTENTLY and RECOVER quickly 🧵☁️ #cloud #devops

Tweet 2/8 👇 Next tweet 👆 Start

this thread is available unrolled at https://markn.ca/2021/reliability-in-the-aws-well-architected-framework/ yesterday's thread on the Cost Optimization Pillar is up at https://markn.ca/2021/cost-optimization-in-the-aws-well-architected-framework/ 🧵☁️ #cloud #devops

Tweet 3/8 👇 Next tweet 👆 Start

. @awscloud defines reliability as, "…the ability of a workload to recover from infrastructure or service disruptions, dynamically…meet demand, and mitigate disruptions." simply: systems shouldn't fail & if they do, recover quickly & automatically 🧵☁️ #cloud #devops

Tweet 4/8 👇 Next tweet 👆 Start

three areas of focus for the Reliability Pillar: - limits == know them, stay within them - networking == topology, bandiwdth, & latency will impact a lot of things - availability == your solution should be ready for business use almost all of the time 🧵☁️ #cloud #devops

Tweet 5/8 👇 Next tweet 👆 Start

. @werner's keynote from @awscloud #reinvent last year centered around the ideas that are core to this pillar. if you haven't already, watch it at https://www.youtube.com/watch?v=jt-gV1YwmnI&feature=youtu.be (even if you have, it's worth a re-watch) 🧵☁️ #cloud #devops

Tweet 6/8 👇 Next tweet 👆 Start

the pillar principles here are: - recover from issues automatically - scale horizontally first for resiliency - redule idle resources - manage change through automation - recover from issues automatically 😉 🧵☁️ #cloud #devops

Tweet 7/8 👇 Next tweet 👆 Start

biggest mistake I see with this pillar is that builders put too much focus on things never failing that would be great but 💩 happens. being able to recover automatically will do a lot more for your customers than trying to make everything 100% available 🧵☁️ #cloud #devops

Tweet 8/8 👇 Next tweet 👆 Start

you can read the entire Reliability Pillar at https://docs.aws.amazon.com/wellarchitected/latest/reliability-pillar/welcome.html remember, the Framework teaches you to balance the concerns of the five pillars to find the right fit for your solution...and that balance will change regularly /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/reliability-in-the-aws-well-architected-framework/ 67f6bbeaaf961b0001443170 Thu, 25 Nov 2021 09:00:00 -0500
<![CDATA[ How (not)? to move a security practice to the cloud ]]> For posts that explain one of my talks, you'll probably want to view them directly online at, How (not)? to move a security practice to the cloud

This talk was presented at SPIE on 25-Nov-2021.

Abstract

When a business moves to the cloud, there are six major strategies they use for each IT service. Whether they move a system “as-is” or do a complete re-architecture, each approach has specific advantages and disadvantages.

When a security practice moves to the cloud, it’s almost always using the same “as-is” strategy. Why?

In this talk, we’ll examine that predominant strategy and explore its impact. We’ll also take a look at what we could—and should—be doing in cloud environments to move our cloud security practices forward.

Can security get the same benefits from the cloud as the rest of the business? Let’s discuss the challenge together!

Slides

Business use any combination of these six strategies to migrate to the cloud.

  • Retire
  • Retain / revisit
  • Repurchase
  • Re-platform
  • Re-host
  • Refactor / re-architect

...but security typically only uses one, "Retain / revist"

Why?

Security really should be focusing on improving their practice by leveraging the three options that lead to a cloud native practice; re-platform, re-host, refactor/re-architect.

Remember, throughout this process the principles of security don't change. But we do need to change the way we—the security community—work.

Your Current Reality

Let's accept for a minute our current reality in the security community.

We're constantly fighting fires. There's no time to work on anything forward looking.

Even if we did have the time, we're not involved in the rest of the business at the levels we should be.

...and we simply don't have the resources to do the job we're tasked with.

😔

How (Not)? To Move

Stop saying no. Stop moving slow. Stop adding weighty processed to everything.

It should be obvious, but don't fork lift you're current practice into the cloud.

That way madness lies...

Instead, we need to focus on the Shared Responsibility Model, automating everything, and delegating security responsibilities to other teams who are better positioned to meet our goals.

This model dictates how all operational and security activities work. It shows whether you—the builder—or the Cloud Service Provider (CSP) is responsible for a specific area of the system.

We start with on-premises, where you are responsible for everything. This is the traditional working model but it still lines up with this concept. You were sharing responsibilities. Just with different teams, not external partners.

Moving into the cloud, you immediate delegate 1/2 of the work to the CSP. That only increases as you move towards SaaS-type services.

No matter what, you are responsible for your data and configuring the CSPs service. Those are always your responsibilities.

The business advantages are clear. The more your delegate to your CSP, the more you can focus on providing direct business value.

This means that you should bias towards SaaS-type or managed services whenever possible.

The good news? Security responsibilities follow suit.

People often remark that it's hard to figure out where your responsibilities lie. It turns out, it's actually pretty simple.

You need to verify if you're expected to manage the operating system and the application layers. That's it.

This means your areas of security focus should be...

  • Your data (access, risk tolerance)
  • Service configuration (features, settings)
  • Operating system (harden, maintain, monitor)
  • Applications (harden, maintain, monitor)
  • Boundaries (input sanitization, observe)
  • Identity (who, when, where)

Identity

We make a lot of assumptions on-premises about our security practice. In fairness, they're usually true.

  • Permissions align with teams
  • Systems are long lived
  • IP addresses used as identifiers
  • Environment is predictable

...these don't hold up anymore.

Permissions change significantly in the cloud. Some key areas;

  • IAM fabric is built in to each cloud
  • Easy to verify which permissions used
  • Permissions should align to tasks
  • Manage at the group/role level

The lifecycle of systems in the cloud is unrecognizable compared to on-premises. You should be looking in to...

  • Capacity management no longer being an issue
  • Resource becoming ephemeral
  • Fixing/remediating issues in templates and then re-rolling production

The IP is the gold standard for system identity on-premises. That's out the window in the cloud.

  • IPs are re-assignable
  • IPs might not be controllable
  • CSP assigns immutable identifier for each resource...use that!

If you haven't figured it out yet, the overall environment in the cloud is drastically different from on-premises...and that's a good thing.

  • Teams are constantly experimenting
  • Resources have wildly different lifecycles
  • CSPs constantly roll out new features

Speed

Again, we deal with a set of assumptions from our on-premises environments.

  • Strong, manual change management
  • Systems are long lived
  • Slow rate of change

Gone are the days of manual change process. Automation is key to success here.

  • Automated system, ideally CI/CD
  • Significant increase in volume of changes
  • Can validate the environment programmatically

Resource lifecycle is very dynamic in the cloud. The effort to get something in production is so low, that it happens all of the time.

  • Capacity management no longer an issue
  • Most resources are ephemeral
  • Fix/remediate in template, re-roll production

We've touched on this a few times already, the rate of change is exponentially faster than on-premises.

  • One API call can build almost anything
  • Feedback loops in DevOps philosophy
  • Push for digital transformation

Collaboration

The assumptions built up on-premises have helped security operate. Again, these were made through a series of logical steps but the result doesn't make sense in today's reality.

  • Security as a gating function
  • Common infrastructure
  • Accepting of "cost" of dealing with security

Gating is a useful tool for security teams. It doesn't go away in the cloud but it does change significant. Gates should now be full automated and transparent to other teams involved with the systems.

  • Automated, not manual, verification
  • Guardrails used in "maybe" situations
  • Approval tied to automated risk evaluation

As with everything else, the infrastructure is very different in the cloud.

  • Environments are separated at the CSP level
  • Workloads are logically isolated by the CSP
  • Common standards and configurations set structure for the organization

No security team wants to work in isolation. However, the lack of time, constant firefighting, and other constants make it really hard to work together effectively.

  • Digital transformation is accept at the board level
  • Builders moving fast under DevOps philosophy
  • Systems over people and feedback loops drive internal change

👆 all of these things make it clear that if the security community doesn't change, it'll be passed by. No one wants that.

Next Steps

Step 1.

  • Understand cloud as an environment
  • Integrate with cloud strategy for the business
  • Read "Cloud Adoption Framework" and "Well-Architected Framework"

This step is all about coming up to speed on what the is and what it means for the business. Take off your security hat and just learn.

Step 2.

  • Accept "Systems over people"
  • Build feedback loops for security
  • Automate everything

This step gets you "cloud-y". Becoming comfortable with the core drivers of cloud is critical to security success.

Step 3.

  • Build strong relationships with other teams
  • Teach the why of security decisions
  • Iterate...a lot

With a strong foundation underneath you, it's time to branch out. Working in a modern way with other teams throughout the business.

Remember the key is small steps over and over again. With each one, make sure you are learning and getting a little bit better!

Thank you!

References

]]>
https://markn.ca/2021/how-not-to-move-a-security-practice-to-the-cloud/ 67f6bbeaaf961b00014432ea Thu, 25 Nov 2021 03:00:00 -0500
<![CDATA[ Cost Optimization in the AWS Well-Architected Framework ]]> Want to share with others? Formatting issues in your reader? This post is available online, Cost Optimization in the AWS Well-Architected Framework

Cost Optimization is one of the five pillars of the AWS Well-Architected Framework. The framework describes the principles and techniques required to make informed trade-offs when you’re building in the AWS Cloud.

I’ve taught thousands of builders how to build better using the framework on the A Cloud Guru platform. Be sure to check out my course, “Mastering The Well-Architected Framework

This 👇 Twitter thread dives deeper into the Cost Optimization pillar of the framework…

Tweet 1/8 👇 Next tweet

it's time to take a look at the Cost Optimization Pillar of the @awscloud Well-Architected Framework this one is all about making sure that you're getting the most value out of the services you use in the cloud 🧵☁️ #cloud #devops

Tweet 2/8 👇 Next tweet 👆 Start

you can view this thread unrolled at https://markn.ca/2021/cost-optimization-in-the-aws-well-architected-framework/ yesterday's thread on the #security pillar is up at https://markn.ca/2021/security-in-the-aws-well-architected-framework/ 🧵☁️ #cloud #devops

Tweet 3/8 👇 Next tweet 👆 Start

you'll notice in the goal of this pillar isn't "spend the least amount of money possible" it's called "Cost Optimization" for a reason. you're trying to maximize business value for the lowest price point 🧵☁️ #cloud #devops

Tweet 4/8 👇 Next tweet 👆 Start

officially, @awscloud states that cost optimization is, "...a continual process of refinement and improvement over the space of a workload’s lifecycle." that's not bad. basically, do the research, try things out, adjust as needed, repeat 🧵☁️ #cloud #devops

Tweet 5/8 👇 Next tweet 👆 Start

that's illustrated in the four phases that the pillar is divided into: - cost effective resources - match supply & demand - awareness of spend - optimize 👆 that's a solid feedback loop 🧵☁️ #cloud #devops

Tweet 6/8 👇 Next tweet 👆 Start

the principles driving this pillar: - consumption based pricing - measure efficiency constantly - let @awscloud do the work whenever possible if you just follow these principles, you'll actually do a decent job of aligning busines value to cost 🧵☁️ #cloud #devops

Tweet 7/8 👇 Next tweet 👆 Start

now, there's a lot more here and the pillar does a good job touching on it there's an art to cloud spending but the one key takeaway that everyone should have is that this—like security—is just one concern it needs to be balanced 🧵☁️ #cloud #devops

Tweet 8/8 👇 Next tweet 👆 Start

the full details on the Cost Optimization Pillar are up at https://docs.aws.amazon.com/wellarchitected/latest/cost-optimization-pillar/welcome.html I strongly encourage you to check it out /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/cost-optimization-in-the-aws-well-architected-framework/ 67f6bbeaaf961b000144316f Wed, 24 Nov 2021 09:00:00 -0500
<![CDATA[ Updating your security practice for the cloud, step-by-step ]]> For posts that explain one of my talks, you'll probably want to view them directly online at, Updating your security practice for the cloud, step-by-step

This talk was presented at TASK on 24-Nov-2021.

Abstract

While the rest of the business has jumped into the push towards cloud, how should your security practice adjust? Architectures, visibility requirements, and data protection needs, among others, are different in the cloud.

It can be hard to know where to focus. How can you identify and manage different risks and exposures? There are so many changes, what steps should you take?

In this session, we’ll look at different areas of your security practice, how they shift, and how to prioritize them as your organization moves to the cloud.

The goal is to provide a map of your next steps and to highlight what resources can help you not just move your practice to the cloud but improve it at the same time.

Slides

We're beyond this now, right?

Let's talk about how we should be working in the cloud.

We—the security community—haven't advanced our work methodology as much as we should because it's a pain in the you-know-what on-premises.

On prem, there are just too many different ways of interfacing with systems. This drives up the cost of automation.

In the cloud, this is simplified greatly. The CSP provides a unified interface through which you can interact with almost all of your stack. That opens up a lot of new possibilities.

Let's take a look at the...

  • ...opportunities
  • ...challenges
  • ...risks

...and come up with a plan.

The Shared Responsibility Model

This model dictates how all operational and security activities work. It shows whether you—the builder—or the Cloud Service Provider (CSP) is responsible for a specific area of the system.

We start with on-premises, where you are responsible for everything. This is the traditional working model but it still lines up with this concept. You were sharing responsibilities. Just with different teams, not external partners.

Moving into the cloud, you immediate delegate 1/2 of the work to the CSP. That only increases as you move towards SaaS-type services.

No matter what, you are responsible for your data and configuring the CSPs service. Those are always your responsibilities.

The business advantages are clear. The more your delegate to your CSP, the more you can focus on providing direct business value.

This means that you should bias towards SaaS-type or managed services whenever possible.

The good news? Security responsibilities follow suit.

People often remark that it's hard to figure out where your responsibilities lie. It turns out, it's actually pretty simple.

You need to verify if you're expected to manage the operating system and the application layers. That's it.

This provides clear areas of security focus...

  • Your data (access, risk tolerance)
  • Service configuration (features, settings)
  • Operating system (harden, maintain, monitor)
  • Applications (harden, maintain, monitor)
  • Boundaries (input sanitization, observe)
  • Identity (who, when, where)

You are already familiar with securing your data, operating systems, and applications. Nothing changes at these layers in the cloud.

So, for this talk, we'll focus on the other areas...

Guiding Tenets

Remember the principles of security don't change...but the way we work needs to.

There are four main tenets...

  • Feedback loops
  • Being part of a larger team
  • Everything-as-Code
  • Automation

A feedback loop is simply following these steps;

  1. Idea
  2. Experiement
  3. Analyze
  4. Improve
  5. Iterate

Being part of a larger team is hard.

Security teams are typically firefighting constantly. That makes it very difficult to coordinate and collaborate with the rest of the business.

Add to that the chronic challenge of finding enough resources and it's completely understandable why security teams operate the way they do.

But change need to start somewhere. This is a big one and a perfect example of the cliche, short term pain for long term gain.

"as-Code" is a popular buzzword. Thankfully, there's real value behind the hype.

Everything should be code in the cloud. From infrastructure definitions, to security controls, to automations, to...um...code.

Having source or a template or a script that can (re)create whatever is needed is an amazing ability.

It also means we can track changes over time, analyze before running, and programmatically interact with everything in our environment.

DevOps is successful because of their constant put for automation. Security needs to be the same.

Automation is more reliable, faster, and helps take the pressure off of your team.

Service Configuration


Opportunities;

  • Offload work & responsibility to CSP
  • Added functionality with minimal effort

This new feature from AWS was just released and it lets you remove a Windows Server remote access tool from your stack.

Instead of exposing RDP access in your design. This feature automatically manages the access securely for you.

Challenges;

  • Keeping up with CSP release cadence
  • Builder service adoption

This same AWS remote access featureonly received a couple of paragraphs in the "What's New" stream and a documentation update.

...and this is just one of hundreds of features that get released every year.

Leading up to AWS re:Invent 2021, AWS has already release 215 new features

Misconfiguration of CSP services is the #1 security issue in the cloud right now.

All of the cloud-specific breaches in the past few years have been a result of misconfigurations.

In fact, the few security issues reported by the CSPs themselves have also been misconfigurations!

Plan;

  • Regularly follow CSP releases
  • Strong communications with builders
  • Monitor usage & configurations

Boundaries

Opportunities;

  • Simplify application of controls
  • Minimize operational overhead

Google Cloud Armor is a good example of a boundary control.

It provides DDoS, WAF, and IP access control capabilities for any workload behind it. Whether that's virtual machines, containers, functions or something else.


Challenges;

  • May not have access to the boundary
  • Transition coverage may not be 100%
  • Monitoring & options may not fit risk tolerance

...back to Google Cloud Armor. This service can protect Cloud Functions but if a user or actor knows the direct URL for the function, the request won't pass through Google Cloud Armor.

While still incredibly useful, this control doesn't completely cover the service boundary.

Risk;

  • Misconfiguration in the CSP offering
  • Lack of flexibility in control
  • Only options could be insufficient

Plan;

  • Test, test, test
  • ...continue to test
  • Mitigate gaps with defence in depth

Identity


Opportunities;

  • Full traceability within your systems
  • Actual least privilege environment
  • Reduce operational overhead


Challenges;

  • AWS links identity to account
  • Legacy structure don't align to tasks
  • Sheer scale of the problem

Risk;

  • Users have incorrect permissions
  • Systems have incorrect permissions
  • Things don't work

Plan;

  • Use federated identity system
  • Align groups/roles with tasks
  • Monitor and assess regularly

Step-by-step

Step 1;

  • Read Cloud Adoption Framework
  • Read Well-Architected Framework
  • Align with overall business cloud strategy


Step 2;

  • Start with a simple feedback loop
  • Iterate...a lot
  • Map out other feedback loops in your practice

Step 3;

  • Make sure all controls are in a template
  • Test, test, test some more
  • Verify that all CSP services, applications, and deployments are observable

Step 4;

  • Start & contribute to security code repo
  • Automate a simple task
  • Rinse & repeat...everything should be automated


Step 5;

  • Work in the open
  • Collaborate constantly
  • Teach other the WHY behind security decisions

Step 6;

  • Create a culture of constant learning
  • Question & test everything
  • Share the security work with other teams

Thank you!

References

]]>
https://markn.ca/2021/updating-your-security-practice-for-the-cloud-step-by-step-2/ 67f6bbeaaf961b00014432e9 Wed, 24 Nov 2021 03:00:00 -0500
<![CDATA[ Security in the AWS Well-Architected Framework ]]> Want to share with others? Formatting issues in your reader? This post is available online, Security in the AWS Well-Architected Framework

Security is one of the five pillars of the AWS Well-Architected Framework. The framework describes the principles and techniques required to make informed trade-offs when you’re building in the AWS Cloud.

I’ve taught thousands of builders how to build better using the framework on the A Cloud Guru platform. Be sure to check out my course, “Mastering The Well-Architected Framework

This 👇 Twitter thread dives deeper into the Security pillar of the framework…

Tweet 1/12 👇 Next tweet

yesterday, we took a look at the Operational Excellence pillar of the @awscloud Well-Architected Framework today, my personal favourite, the Security Pillar 🧵☁️ #cloud #devops

Tweet 2/12 👇 Next tweet 👆 Start

Tweet 3/12 👇 Next tweet 👆 Start

one of the reasons I ❤️ the Well-Architected Framework so much is that it presents #security in CONTEXT it's not an isolated activity but one that must be considers next to the other four pillars. you need to find a balance here...the framework helps 🧵☁️ #cloud #devops

Tweet 4/12 👇 Next tweet 👆 Start

there are formal definitions of the various types of security (cyber, information, physical, & operational) but I like the catch all: To make sure that your systems work as intended and ONLY as intended 🧵☁️ #cloud #devops

Tweet 5/12 👇 Next tweet 👆 Start

... it's 👆 simple to understand in that context. all of these processes and controls we put in place are there to make sure that things work the way to expect and ONLY that way that covers everything from attacks to mistakes. also, it's more positive 🧵☁️ #cloud #devops

Tweet 6/12 👇 Next tweet 👆 Start

...I cannot stand the conflict/FUD oriented view of security. yes there are malicious actors out there but security is so much more than that besides, if you're only ever trying to STOP things, you won't see the other advantages, like building reslience 🧵☁️ #cloud #devops

Tweet 7/12 👇 Next tweet 👆 Start

so, the Framework does use a formal definition (my rant aside). it states that security is, "the ability to protect data, systems, and assets to take advantage of cloud technologies." yawn 😴 🧵☁️ #cloud #devops

Tweet 8/12 👇 Next tweet 👆 Start

this pillar is broken down into five areas: - identity & access - detective controls - infrastructure protection - data protection - incident response 🧵☁️ #cloud #devops

Tweet 9/12 👇 Next tweet 👆 Start

in simple terms, those areas end up being: - identity & access == who can do what, when? - detective controls == is this normal? - infrastructure protection == boundaries & chokepoints 🧵☁️ #cloud #devops

Tweet 10/12 👇 Next tweet 👆 Start

... - data protection == classification, management, & encryption - incident response == 💩+fan, time to contain & restore 🧵☁️ #cloud #devops

Tweet 11/12 👇 Next tweet 👆 Start

like every pillar, this one has some key principles: - identities have the least amount of privileges required - know who did what, when - security is a part of everything - automate all tasks - encrypt at rest & in transit - prepare for the worst 🧵☁️ #cloud #devops

Tweet 12/12 👇 Next tweet 👆 Start

you can read the whole Security pillar here: https://docs.aws.amazon.com/wellarchitected/latest/security-pillar/welcome.html there's a lot more in that document and in the references. but, like anything in the framework, Gamedays and practice will help you understand these concepts the best /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/security-in-the-aws-well-architected-framework/ 67f6bbeaaf961b000144316e Tue, 23 Nov 2021 09:00:00 -0500
<![CDATA[ Can We Improve How Airbnb Tested Their Amazon RDS Databases in 2017? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Can We Improve How Airbnb Tested Their Amazon RDS Databases in 2017?

In late 2017, Airbnb did an AWS “This is My Architecture” video. The video talks about how they built a system to test their Amazon RDS databases.

Now, a few years later, I react to that video and see what’s stood the test of time, what could be done simpler given today’s technology, and generally critique the design against the AWS Well-Architected Framework.

The AWS Well-Architected Framework

The AWS Well-Architected Framework is designed to help you and your team make informed trade offs while building in the AWS Cloud. It’s built on five pillars;

  • Operational Excellence
  • Security
  • Cost Optimization
  • Reliability
  • Performance Efficiency

There pillars cover the primary concerns of building and running any solution. And as much as we’d all love to have everything, that’s just not possible.

…enter the framework.

It’ll help you strike the right balance for your goals to make sure that your build is the best it can be now and moving forward.

Why Architecture?

I often get asked why I talk about building in the cloud and architectural choices so often…aren’t I a security person?

Yes, I do focus on security and architecture is a critical part of that.

There’s really two types of security design work. The first is when you’re handed something and need to make sure the risks of that technology matches the risk appetite of the users.

The second type is when you’re building the technology. This is where making choices informed by security early in the process can have profound effects. You’re no longer bolting security on but building it in by design.

That’s why I talk about architecture and building so much. It’s where we all can have the largest possible security impact!

This video—and the ones that will come after—looks at a specific set of design decisions and how they balance the concerns of the AWS Well-Architected Framework…where security is one of the five pillars.

Airbnb’s Design

At the time, Airbnb was leveraging Amazon RDS (and still may be). They set out to build a way to test their databases but not just with the queries and load they were currently seeing, but with what could happen as well.

Simply replaying the logs wouldn’t work. They designed a simple system to capture and protect production queries and data. This system allowed them to replay and expand on those queries to simulate what would happen if these new types of loads hit their production systems.

Learn more in the reaction video 👆.

Btw, I’ve updated my course, “Mastering The AWS Well-Architected Framework” on A Cloud Guru. If you want a solid walk through of the ideas behind the framework and how to apply it to your work in the AWS Cloud, check it out!
]]>
https://markn.ca/2021/can-we-improve-how-airbnb-tested-their-amazon-rds-databases-in-2017/ 67f6bbeaaf961b0001443184 Mon, 22 Nov 2021 09:00:00 -0500
<![CDATA[ Operational Excellence in the AWS Well-Architected Framework ]]> Want to share with others? Formatting issues in your reader? This post is available online, Operational Excellence in the AWS Well-Architected Framework

Operational Excellence is one of the five pillars of the AWS Well-Architected Framework. The framework describes the principles and techniques required to make informed trade-offs when you’re building in the AWS Cloud.

I’ve taught thousands of builders how to build better using the framework on the A Cloud Guru platform. Be sure to check out my course, “Mastering The Well-Architected Framework

This 👇 Twitter thread dives deeper into the Operational Excellence pillar of the framework…

Tweet 1/13 👇 Next tweet

leading up to @awscloud #reinvent, I've been diving into AWS resources & sharing what I find first it was whitepapers, then AWS Labs code projects. this week, it's the AWS Well-Architected Framework everything (and more) up at https://markn.ca/2021/aws-reinvent/ 🧵☁️ #cloud #devops

Tweet 2/13 👇 Next tweet 👆 Start

there are 5 pillars in the framework, today, let's look at the Operational Excellence pillar of the AWS Well-Architected Framework this thread is available unrolled at https://t.co/WcNfjEXkPV 🧵☁️ #cloud #devops

Tweet 3/13 👇 Next tweet 👆 Start

this pillar is all about making sure that your architecture works and continues to work, regardless of what happens yes, things happen, and yes, your system should continue to work when they do 😉 🧵☁️ #cloud #devops

Tweet 4/13 👇 Next tweet 👆 Start

the AWS def. of this pillar is, "the ability to support development and run workloads effectively, gain insight into their operations, and to continuously improve supporting processes and procedures to deliver business value" I prefer mine, less adjectives 🧵☁️ #cloud #devops

Tweet 5/13 👇 Next tweet 👆 Start

this pillar really works in three phases: 1. organize and prepare 2. operate 3. evolve ideally, this is a strong feedback loop & with each iteration, your team is getting better & your design is improving 🧵☁️ #cloud #devops

Tweet 6/13 👇 Next tweet 👆 Start

six principles guide this pillar. the first is All operations are code - type it somewhere => script - clicked on something => add it to a script/template - make any change => find that line in code be ruthless here... 🧵☁️ #cloud #devops

Tweet 7/13 👇 Next tweet 👆 Start

...having every op as code (in addition to your infrastructure, security, and code) will save you a ton of headaches later "code" is a catch-all here. it can be a script (bash + awscli), CDK, 3rd party tool, CFN template, Terraform, something repeatable 🧵☁️ #cloud #devops

Tweet 8/13 👇 Next tweet 👆 Start

this leads to the next principles; update your documentation automatically a lot of the "how" and "what" docs should be auto generated. that saves the people effort for the "why" docs remember, writing this stuff is 1% of work, 99% is reading. docs are 🔑 🧵☁️ #cloud #devops

Tweet 9/13 👇 Next tweet 👆 Start

3rd principle: small frequent changes despite an initial concern, this actually reduces risk. you get used to making changes (and build tooling to support) but small changes are easier to troubleshoot, evaluate, and rollback if necessary 🧵☁️ #cloud #devops

Tweet 10/13 👇 Next tweet 👆 Start

4th principle: iterate ...a lot ...like all the time ...feedback loops => small improvements => big changes over time! 🧵☁️ #cloud #devops

Tweet 11/13 👇 Next tweet 👆 Start

💩 happens. no matter how much you plan & prepare. accept that. plan for that understanding that recovery & adjustments are a key part of ops will lead to smarter decisions (#security too) 🧵☁️ #cloud #devops

Tweet 12/13 👇 Next tweet 👆 Start

last principle: always learn. failure, sucess, complete disaster << they are all learning opportunities the only failure is the failure to learn...or some other such cliche just try not to make the same mistake twice. you can do that by learning 😉 🧵☁️ #cloud #devops

Tweet 13/13 👇 Next tweet 👆 Start

there's a lot more in the operational excellence pillar of the AWS Well-Architected Framework you can read through the pillar at https://docs.aws.amazon.com/wellarchitected/latest/operational-excellence-pillar/welcome.html /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/operational-excellence-in-the-aws-well-architected-framework/ 67f6bbeaaf961b000144316d Mon, 22 Nov 2021 09:00:00 -0500
<![CDATA[ Smithy ]]> Want to share with others? Formatting issues in your reader? This post is available online, Smithy

AWS Labs has a lot of open source code up on GitHub. In this post, we’re taking a look at AWS Data Wrangler. This project provides a smoother interface between pandas DataFrames and various AWS Cloud data services.

I call out a few more details in the Twitter thread below…

Tweet 1/11 👇 Next tweet

to wrap up the week, let's look a Smithy, https://github.com/awslabs/smithy from @awscloud Labs this project "defines and generates clients, services, and documentation for any protocol" which is a big claim let's see what's actually here... 🧵☁️ #cloud #devops

Tweet 2/11 👇 Next tweet 👆 Start

read this thread unrolled at https://t.co/FICk4Hpn4p the previous thread is up at https://markn.ca/2021/aws-data-wrangler/ 🧵☁️ #cloud #devops

Tweet 3/11 👇 Next tweet 👆 Start

the full docs site (https://awslabs.github.io/smithy/), clarifies the goal, "A language for defining services and SDKs" ok, so this is DSL-type project. the 4 main features: - protocol-agnostic - codify & enforce API governance - designed to evolve - resource based 🧵☁️ #cloud #devops

Tweet 4/11 👇 Next tweet 👆 Start

the FAQ calls out that this project has been used inside Amazon & @awscloud for over a decade (that's a good sign) the project uses the term IDL or interface description language...so not quite a DSL 🧵☁️ #cloud #devops

Tweet 5/11 👇 Next tweet 👆 Start

this is not a project that you are going to implement (most likely). but it is a fascinating project to learn from AWS uses Smithy to describe their services, metadata, and capabilities in a programmatic way 🧵☁️ #cloud #devops

Tweet 6/11 👇 Next tweet 👆 Start

describing these systems in a machine reading format opens up a host of new possibilities like automated policy enforcement, service validate, compatibility checking, and a lot more 🧵☁️ #cloud #devops

Tweet 7/11 👇 Next tweet 👆 Start

this example description from the docs really drives the point home. look 👇 at how much clearer the Smithy description is vs. a more common JSON structure 🧵☁️ #cloud #devops

Tweet 8/11 👇 Next tweet 👆 Start

in Smithy, services have: - resources - operations - shapes resources & operations are straightforward but the "shape" concept deserves a closer look 🧵☁️ #cloud #devops

Tweet 9/11 👇 Next tweet 👆 Start

according to the docs, a "shape" is an instance of a type and it has "traits" shapes can be simple, aggregate, or a service https://awslabs.github.io/smithy/1.0/spec/core/model.html#shapes 🧵☁️ #cloud #devops

Tweet 10/11 👇 Next tweet 👆 Start

using these constructs together, you can accurately describe your service in a clear and simple manner here's a complete example from the docs: https://awslabs.github.io/smithy/quickstart.html#complete-example 🧵☁️ #cloud #devops

Tweet 11/11 👇 Next tweet 👆 Start

if you're building out a distributed system, the Smithy project is worth exploring. there's a lot of great ideas here and you might be able to leverage the project for your work at the very least, you'll learn a lot about IDLs from @awscloud's experience /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/smithy/ 67f6bbeaaf961b000144316c Fri, 19 Nov 2021 09:00:00 -0500
<![CDATA[ AWS Data Wrangler ]]> Want to share with others? Formatting issues in your reader? This post is available online, AWS Data Wrangler

AWS Labs has a lot of open source code up on GitHub. In this post, we’re taking a look at AWS Data Wrangler. This project provides a smoother interface between python pandas DataFrames and various AWS Cloud data services.

I call out a few more details in the Twitter thread below…

Tweet 1/8 👇 Next tweet

AWS Data Wrangler, https://github.com/awslabs/aws-data-wrangler, is an interesting project from the @awscloud ProServe team it aims to connect python pandas data frames to various AWS services 🧵☁️ #cloud #devops

Tweet 2/8 👇 Next tweet 👆 Start

this thread (unrolled) is up at https://t.co/v1ZIBgC6W3 the last thread is up at https://markn.ca/2021/amazon-api-gateway-serverless-developer-portal/ 🧵☁️ #cloud #devops

Tweet 3/8 👇 Next tweet 👆 Start

if you've been anywhere near a data science project, you've probably seen either the scipy, numpy, or pandas projects in python...or all three they are awesome one of the fundamental units of these projects is the DataFrame, https://pandas.pydata.org/pandas-docs/stable/user_guide/dsintro.html 🧵☁️ #cloud #devops

Tweet 4/8 👇 Next tweet 👆 Start

the AWS Data Wrangler project lets you save DataFrames to various @awscloud data services this could save a ton of time for your python projects 👇 🧵☁️ #cloud #devops

Tweet 5/8 👇 Next tweet 👆 Start

the repo has a broad spectrum of samples, all in @ProjectJupyter notebooks. I ❤️ that because it makes it easier to play with the code find the tutorials at https://github.com/awslabs/aws-data-wrangler/tree/main/tutorials 🧵☁️ #cloud #devops

Tweet 6/8 👇 Next tweet 👆 Start

this project installs via standard pip but is also available as a Lambda layer, in the AWS Glue shell, in @awscloud SageMaker Notebooks, and more that flexibility is much appreciated 🧵☁️ #cloud #devops

Tweet 7/8 👇 Next tweet 👆 Start

this library does more than just save and load data, the full API for it is up at https://aws-data-wrangler.readthedocs.io/en/2.12.1/api.html there's a lot of very useful data manipulation functions here 🧵☁️ #cloud #devops

Tweet 8/8 👇 Next tweet 👆 Start

all-in-all if you're using pandas, scipy, or numpy in your python project and your data is on @awscloud, you'll want to—at the very least—check out the AWS Data Wrangler at https://github.com/awslabs/aws-data-wrangler /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/aws-data-wrangler/ 67f6bbeaaf961b000144316b Fri, 19 Nov 2021 09:00:00 -0500
<![CDATA[ Amazon S3 Glacier Re:Freezer ]]> Want to share with others? Formatting issues in your reader? This post is available online, Amazon S3 Glacier Re:Freezer

AWS Labs has a lot of open source code up on GitHub. Amazon S3 Glacier Re:Freezer is one of those projects.

It’s got a simple premise: get the data out of Amazon S3 Glacier and back into Amazon S3.

That sounds simple but the solution is surprisingly nuanced. I call out a few more details in the Twitter thread below…

Tweet 1/10 👇 Next tweet

let's take a look at the Amazon S3 Glacier Re:Freezer project from @awscloud Labs the project is available at https://github.com/awslabs/amazon-s3-glacier-refreezer 🧵☁️ #cloud #devops

Tweet 2/10 👇 Next tweet 👆 Start

this thread can be see unrolled at https://t.co/4d3MidmVDs the previous thread about AWS Perspective is up at https://markn.ca/2021/aws-perspective/ 🧵☁️ #cloud #devops

Tweet 3/10 👇 Next tweet 👆 Start

the goal of this project is simple: get data out of @awscloud S3 Glacier and back into an Amazon S3 bucket that shouldn't be too hard... 🤣🤣🤣 🧵☁️ #cloud #devops

Tweet 4/10 👇 Next tweet 👆 Start

I laugh because this is the solution architecture 👇 🧵☁️ #cloud #devops

Tweet 5/10 👇 Next tweet 👆 Start

think about that for a minute. it builds out resources in SEVEN different @awscloud services just to move data from one service to another worse, those two services are intertwined already! if there was ever a solution crying out to be in product, it's this 🧵☁️ #cloud #devops

Tweet 6/10 👇 Next tweet 👆 Start

ok, rant aside (for now), this is a very useful solution. Glacier is the long term, cold storage (https://aws.amazon.com/s3/glacier/) where writing is easy and reading is slow and expensive Glacier is the "just in case" place for storage. 🧵☁️ #cloud #devop

Tweet 7/10 👇 Next tweet 👆 Start

Glacier is a great service because it's super low storage costs (https://aws.amazon.com/s3/pricing/) make it easy to keep things "available" you're charge to get data out and for those times you actually need that data, it's usually worth it 🧵☁️ #cloud #devop

Tweet 8/10 👇 Next tweet 👆 Start

you would think that restoration process is automation in a slick manner. it isn't natively this solution does a nice job of smoothing out this process simply: - point at the Glacier Vault - pick your retrieval tier - target bucket - target storage class 🧵☁️ #cloud #devop

Tweet 9/10 👇 Next tweet 👆 Start

the complexity in the architecture 👆 is because the data retrieval from @awscloud Glacier is glacially slow like a herd of 🐢🐢🐢 who aren't sure which way they are supposed to be going type of slow 🧵☁️ #cloud #devop

Tweet 10/10 👇 Next tweet 👆 Start

all of the different components in the design make sure that the data gets to the target bucket with a high level of reliability should this be part of the core service offering ? yes but it's not, so use this code /🧵☁️ #cloud #devop

]]>
https://markn.ca/2021/amazon-s3-glacier-re-freezer/ 67f6bbeaaf961b000144316a Thu, 18 Nov 2021 09:00:00 -0500
<![CDATA[ Amazon API Gateway Serverless Developer Portal ]]> Want to share with others? Formatting issues in your reader? This post is available online, Amazon API Gateway Serverless Developer Portal

AWS Labs has a lot of open source code up on GitHub. This project, “Amazon API Gateway Serverless Developer Portal” builds a slick web interface for your Amazon API Gateway APIs.

Think of it like automatic documentation. It’s a great way to help developers get up to speed with your APIs.

I call out a few more details in the Twitter thread below…

Tweet 1/9 👇 Next tweet

this thread is going to look at "Amazon API Gateway Serverless Developer Portal" by @awscloud Labs on GitHub at https://github.com/awslabs/aws-api-gateway-developer-portal this project delivers a web portal for developer engagement with your APIs 🧵☁️ #cloud #devops

Tweet 2/9 👇 Next tweet 👆 Start

this thread is unrolled at https://t.co/4d3MidmVDs the last thread is at https://markn.ca/2021/amazon-s3-glacier-refreezer/ 🧵☁️ #cloud #devops

Tweet 3/9 👇 Next tweet 👆 Start

this is what this project builds out for you 👇 it's like fancy automated documentation + self-serve provisioning 🧵☁️ #cloud #devops

Tweet 4/9 👇 Next tweet 👆 Start

the project has spent a lot of time on deployment. you can roll it out via SAM, SAR, or script like good docs, that's very much appreciated more on SAM at https://aws.amazon.com/serverless/sam/ more on SAR at https://aws.amazon.com/serverless/serverlessrepo/ 🧵☁️ #cloud #devops

Tweet 5/9 👇 Next tweet 👆 Start

this project addresses a big gap for most teams. they might build out a solid API but how do you get the word out to developers? having clear documentation & a way to get an API key/token yourself is really important for the developer experience (#dx) 🧵☁️ #cloud #devops

Tweet 6/9 👇 Next tweet 👆 Start

this project doesn't go beyond the basic endpoint/parameters documentation. YOU need to add in the "here's how to get the most out of this API" and other, more in-depth documentation 🧵☁️ #cloud #devops

Tweet 7/9 👇 Next tweet 👆 Start

there's a fair bit of customization built into the project as well. you can adjust the branding and add your own content, like 👆 more on customization at https://github.com/awslabs/aws-api-gateway-developer-portal/wiki/Customization 🧵☁️ #cloud #devops

Tweet 8/9 👇 Next tweet 👆 Start

under the covers, here's what the project builds 👇 it's a pretty lightweight, #serverless build. that will keep operations light and the costs low 🧵☁️ #cloud #devops

Tweet 9/9 👇 Next tweet 👆 Start

if you're building out APIs using @awscloud API Gateway (even if they are internal-only), this project should help you document those APIs & provision access check it out at https://github.com/awslabs/aws-api-gateway-developer-portal /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/amazon-api-gateway-serverless-developer-portal/ 67f6bbeaaf961b0001443169 Thu, 18 Nov 2021 09:00:00 -0500
<![CDATA[ AWS Perspective ]]> Want to share with others? Formatting issues in your reader? This post is available online, AWS Perspective

AWS Labs has a lot of open source code up on GitHub. This repo helps you visualize your AWS workloads and highlight areas of cost.

AWS Perspective builds out a simple-ish solution that creates architecture diagrams of your current workloads.

I call out a few more details in the Twitter thread below…

Tweet 1/9 👇 Next tweet

AWS Perspective sounds like a real service. sadly, it's not. it is however another @awscloud Labs repo we're taking a look at this one is up at https://github.com/awslabs/aws-perspective 🧵☁️ #cloud #devops

Tweet 2/9 👇 Next tweet 👆 Start

this thread is unrolled at https://t.co/4d3MidmVDs you can read the last thread (on Amazon QuickSight embedding) at https://markn.ca/2021/amazon-quicksight-embedding-sdk/ 🧵☁️ #cloud #devops

Tweet 3/9 👇 Next tweet 👆 Start

so, AWS CloudFormation designer does something similar (https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/working-with-templates-cfn-designer.html) but only for CFN templates this solution just looks at the actual @awscloud resources running/created and visualizes theme, regardless of CFN status/linkage 🧵☁️ #cloud #devops

Tweet 4/9 👇 Next tweet 👆 Start

it builds diagrams like this 👇 🧵☁️ #cloud #devops

Tweet 5/9 👇 Next tweet 👆 Start

as you can imagine, that's very handy. getting a visual layout of what's running makes it a lot easier to; - understand your solutions - spot issues (potential & actual) - understand where costs are - talk about your workloads 🧵☁️ #cloud #devops

Tweet 6/9 👇 Next tweet 👆 Start

honestly, the ability to show teams what you're talking about might be THE top advantage of this project that clear shared understanding of what's out there and how they are connected is very valuable 🧵☁️ #cloud #devops

Tweet 7/9 👇 Next tweet 👆 Start

this solution is quite mature and has a formal implementation guide up at https://docs.aws.amazon.com/solutions/latest/aws-perspective/welcome.html this guide walks you through the step-by-step to get up and running and how to get the most from this project 🧵☁️ #cloud #devops

Tweet 8/9 👇 Next tweet 👆 Start

one word of warning though, there's a lot running in this solution. this is the default build 👇 🧵☁️ #cloud #devops

Tweet 9/9 👇 Next tweet 👆 Start

that's pretty heavy. but if you're building a lot in @awscloud, it could be worth it. these aren't theoretical diagrams. they represent the reality of your environment that's a worthwhile investment! /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/aws-perspective/ 67f6bbeaaf961b0001443168 Wed, 17 Nov 2021 09:00:00 -0500
<![CDATA[ Amazon QuickSight Embedding SDK ]]> Want to share with others? Formatting issues in your reader? This post is available online, Amazon QuickSight Embedding SDK

AWS Labs has a lot of open source code up on GitHub. The code in this repo lets your embed Amazon QuickSight dashboards in your HTML.

I’m a big fan of Amazon QuickSight. I think it solves a lot of business problems quickly and easily for customers. The service’s biggest weakness is that no one really knows about it or it’s functionality.

This repo, Amazon QuickSight Embedding SDK, lets you embed QuickSight dashboards in your HTML. I think that goes a long way to help make the insights this service can generate a lot more accessible.

I call out a few more details in the Twitter thread below…

Tweet 1/8 👇 Next tweet

next up in my walk through @awscloud Labs repos of note: the Amazon QuickSight Embedding SDK it's up at https://github.com/awslabs/amazon-quicksight-embedding-sdk#example 🧵☁️ #cloud #devops

Tweet 2/8 👇 Next tweet 👆 Start

you can view this thread unrolled at https://t.co/zjVFFiSwmP the previous thread on AWS WAF Security Automations is at https://markn.ca/2021/aws-waf-security-automations/ 🧵☁️ #cloud #devops

Tweet 3/8 👇 Next tweet 👆 Start

Amazon QuickSight is one of my favourite services. it was also one of the first, if not the first to be hosted at the .aws TLD (fun fact-ish!) https://aws.amazon.com/quicksight/ 🧵☁️ #cloud #devops

Tweet 4/8 👇 Next tweet 👆 Start

this service is billed as "scalable, serverless, embeddable, ML-powered BI service for the cloud", which is a little to marketing-y for my tastes but is a reasonable description basically point it at your data and you can click to view/explore your data... 🧵☁️ #cloud #devops

Tweet 5/8 👇 Next tweet 👆 Start

...while it stays (ideally) in your @awscloud S3 buckets. it's a super low effort, low cost analytical engine for your data more on pricing at https://aws.amazon.com/quicksight/pricing/ 🧵☁️ #cloud #devops

Tweet 6/8 👇 Next tweet 👆 Start

ok, back to the project at hand, this one (AGAIN, come on @awscloud) fills in a product gap. in this case, embedding your QuickSight dashboards in HTML...somewhere you can embed; - dashboards - authoring portals - the Q search bar (natural language) 🧵☁️ #cloud #devops

Tweet 7/8 👇 Next tweet 👆 Start

that's super powerful, and this project make it easy-ish to do. as long as you following the steps closely, you'll get things up and running. it's a reasonably smooth ux but could be slicker in product (think YouTube's "embed" option) 🧵☁️ #cloud #devops

Tweet 8/8 👇 Next tweet 👆 Start

simple and to the point, if you want to embed Amazon QuickSight in HTML somewhere, start here it'll save you a ton of headache /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/amazon-quicksight-embedding-sdk/ 67f6bbeaaf961b0001443167 Wed, 17 Nov 2021 09:00:00 -0500
<![CDATA[ Gluon TS (Time Series) ]]> Want to share with others? Formatting issues in your reader? This post is available online, Gluon TS (Time Series)

AWS Labs has a lot of open source code up on GitHub. Gluon TS helps you build and train models for forecasting time series data. It’s built on the Apache MXNet project and is can help with a lot of the heavy lifting for this use case.

I call out a few more details in the Twitter thread below…

Tweet 1/1 👇 Next tweet

let's look at the Gluon Time Series code repo from @awscloud it's up at https://github.com/awslabs/gluon-ts 🧵☁️ #cloud #devops

That thread broke on Twitter for some reason (probably me, I'm probably the reason 🤣). Here's the rest of it...

Tweet 1/6 👇 Next tweet

this thread is available unrolled at https://t.co/DXLQOJxSHn yesterday's threads up at: - Lambda power tools for python, https://markn.ca/2021/aws-lambda-powertools-python/ - AWS Deployment Framework, https://markn.ca/2021/aws-deployment-framework/ 🧵☁️ #cloud #devops

Tweet 2/6 👇 Next tweet 👆 Start

Gluon is build around Apache MXNet, https://mxnet.incubator.apache.org/versions/1.8.0/, which is now an incubator project original announced in 2017, this one has flown under the radar for most folks...that's ok, it's pretty low level but still worth a look 🧵☁️ #cloud #devops

Tweet 3/6 👇 Next tweet 👆 Start

this project focuses on "probabilistic time series modelling" which sounds super cool...and is time series data is everywhere. being able to easily build & train models around this type of data is extremely useful to a lot of businesses 🧵☁️ #cloud #devops

Tweet 4/6 👇 Next tweet 👆 Start

we're talking about output like this 👇 to help you model predictions or actions over time 🧵☁️ #cloud #devops

Tweet 5/6 👇 Next tweet 👆 Start

included in the library are some very handy synthetic data generation tools. if you're testing to ensure that your model is trained on a well rounded data set, these are invaluable more on them at https://ts.gluon.ai/tutorials/data_manipulation/synthetic_data_generation.html 🧵☁️ #cloud #devops

Tweet 6/6 👇 Next tweet 👆 Start

most ppl won't dive into the level of #ml 🧠 where you'd need Gluon-TS. the Deeper forecasting algorithm in @awscloud SageMaker usually does the trick: https://docs.aws.amazon.com/sagemaker/latest/dg/deepar.html ...but if you do need it, this is a very handy repo for time series forecasting! /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/gluon-ts-time-series/ 67f6bbeaaf961b0001443166 Tue, 16 Nov 2021 09:00:00 -0500
<![CDATA[ AWS WAF Security Automations ]]> Want to share with others? Formatting issues in your reader? This post is available online, AWS WAF Security Automations

AWS Labs has a lot of open source code up on GitHub. This repo contains a solid set of AWS WAF rules for common web-based attacks.

AWS WAF Security Automations creates some simple rules for common attacks that really should be part of the default offering for AWS WAF. But they aren’t, which makes this repo extremely useful.

I call out a few more details in the Twitter thread below…

Tweet 1/9 👇 Next tweet

let's look at this repo full of @awscloud WAF #security automations the repo is up at https://github.com/awslabs/aws-waf-security-automations and it contains a set of WAF rules to filter out common web-based attacks 🧵☁️ #cloud #devops

Tweet 2/9 👇 Next tweet 👆 Start

this thread is available unrolled at https://t.co/Za14IqWUud my last thread on Gluon Time Series 🧠 models is spat https://markn.ca/2021/gluon-ts/ 🧵☁️ #cloud #devops

Tweet 3/9 👇 Next tweet 👆 Start

AWS WAF, https://aws.amazon.com/waf/, is a bit controversial. it's more of a skeleton than other @awscloud services. basically providing you with a framework that you have to build out before it's useful 🧵☁️ #cloud #devops

Tweet 4/9 👇 Next tweet 👆 Start

you create a web access control list or WACL (awesome name), then add rules and resources that are a target (a/k/a where the traffic goes) so it'll go: internet > WAF > [ CloudFront | API Gateway | ALB | AppSync ] 🧵☁️ #cloud #devops

Tweet 5/9 👇 Next tweet 👆 Start

the idea is that WAF drops the bad stuff. but there are no rules in place by default this is the biggest failing of the service. now, you can buy a set of managed rules from APN partners or load up your own this repo, has a set that you can load 🧵☁️ #cloud #devops

Tweet 6/9 👇 Next tweet 👆 Start

....honestly, they should be available in the services as a one-click option. that would reduce customer friction and provide some protection out of the box (though WAF does have other features like IP access control and Bot Control) 🧵☁️ #cloud #devops

Tweet 7/9 👇 Next tweet 👆 Start

back to the repo, the rules in the repo provide some basic protections again SQL injection attacks, scanning/probing, cross-site scripting, flood attacks, and other attack techniques it's not fool proof but they are solid rules 🧵☁️ #cloud #devops

Tweet 8/9 👇 Next tweet 👆 Start

now, usually I'd go easy here and say that repos like this are a FANTASTIC way to test new functionality and customer demand before rolling it into the product however, this repo launched in 2016 and was last updated here in Sep/2021 🧵☁️ #cloud #devops

Tweet 9/9 👇 Next tweet 👆 Start

so, these are obviously useful and well used. that's why I wanted to highlight this repo if you think WAF might help improve your security posture and you don't want to go the managed rule route, this will help get your started /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/aws-waf-security-automations/ 67f6bbeaaf961b0001443165 Tue, 16 Nov 2021 09:00:00 -0500
<![CDATA[ The Infinite Loop of Lost Potential ]]> Want to share with others? Formatting issues in your reader? This post is available online, The Infinite Loop of Lost Potential

In the past few days, we’ve seen two great essays around the topic of serverless. Both written by people that I respect and admire, these essays got me thinking.

The first, “The Unfulfilled Promise of Serverless” by Corey Quinn. The second is a rebuttal from Jeremy Daly, “The Unfulfilled Potential of Serverless".

You should read both essays in full, but I’ll give you the gist here.

Corey’s argument is that serverless compute was supposed to drive change in how we build solutions. It’s failed to live up to that. He cites the lack of portability and the low cost leading to a perception of low value as reasons. He calls out the lack of widespread adoption. That makes it harder to find talent comfortable with these solutions.

These are all great points and I agree with Corey.

Jeremy’s point is that it is early for serverless as concept. If we get out of the weeds, there’s a lot of value here. The tooling and ecosystem around the concept isn’t where it needs. That’s what is driving Corey’s argument. As things progress, we should see these issues recede, realizing the potential of serverless.

These are great points and I also agree with Jeremy.

But I think both essays only touch on a little of what’s going on here.

That’s New, What Is It?

Fifteen years into this “cloud” thing and AWS itself provides a good example of what’s happening.

When AWS expanded beyond just a couple of services, it reached a point where it’s potential was revealed. This wasn’t just an easier to use data centre. Building in the cloud let businesses shift away from a mountain of undifferentiated IT work.

The hardware and software upgrades. Provisioning new capacity. Operating lower level systems that users never see. And more. IT is very much an iceberg. The cloud teased that you could hand that work off and focus on solving business problems.

Some of that potential has been realized. However, a lot of business saw the cloud as better outsourcing. That was their existing mental model. They wanted to put the new technology into the old model. It was comfortable to do so.

The APIs and clear(ish) pricing from AWS was a smoother way of doing business vs. the traditional outsourcing contracts that plagued IT of the 1990s. That’s what was driving a lot of “the cloud is cheaper” myths.

It took years to break from that mental model. Eventually we realized that the cloud was different. It wasn’t about a better outsourcing model.

Building The New Way

It was—and is—about a cloud service provider operating at a scale where the economics are different. This economy of scale allows them to create new services and technologies. Most important, 99.9% of businesses will never reach that scale.

That scale provides an opportunity for the builders using the cloud.

Builders have access to technologies that would’ve taken years of steady growth to reach. Who would’ve been able to build out a storage service that had 11 9’s of durability? A queuing service handling millions of messages per minute?

Now, it is a simple API call and only costs pennies per hour.

This created new opportunities. The AWS Cloud was an exciting place to build for first few years of mainstream cloud acceptance.

It struck the right balance between power and simplicity. The tooling was mature enough. New features and services came out at a steady pace. With minimal effort, you could create very innovative solutions.

That’s still possible today. But builders are now dealing with overwhelming complexity. Just look at the list of AWS Cloud services in the AWS Management Console. How does anyone know where to get started?

In this confusion, builders default back to what they know.

It’s Always The People

This is why containers have skyrocketed in popularity. Especially compared to serverless designs over the past three years.

I see a lot of container-based solutions that would be better as serverless designs. Better in that they would be more efficient, less costly, and scale easier.

Why do these container-based solutions keep popping up?

Containers hit the sweet spot. They are familiar enough but push the envelope in interesting ways. They allow builders to be more productive using modern development methods. At the same time, they don’t require a new mental model.

What both Jeremy and Corey hint at is the people problem. The technology and concept around serverless designs makes more sense for most problems. People just aren’t ready for it yet.

Corey is right, serverless is an unfulfilled promise. Jeremy is also right, hang tight…it’ll happen.

Kubernetes Is The Stop Gap

The critical question is when? I don’t think it will happen for a while yet. Businesses will have to start to feel the pain of running Kubernetes before serverless comes to the forefront.

Before you fire up the Twitter cannon. Let’s take an objective look at Kubernetes. You cannot deny that it is a massive piece of critical infrastructure. It’s a burden for organizations adopting it. Despite the push away from running undifferentiated systems, k8s continues to rise.

Why? It lets team maximize the value their containers. Kubernetes allows containers to behave in modern ways. Solutions built on top of k8s are far closer to a serverless design than a traditional server-based ones.

That’s a good thing.

Yes, there’s a significant complexity cost associated with k8s. But it’s one that teams are used to paying. After all, is running k8s all that different than running your own application servers? Or mail servers? Or any of the other underlying infrastructure that we’ve been running for decades.

They are all critical to making other things run but your customers don’t get exposed to them. Conceptually, they operate at the same level. You teams and organization are ready for this effort. Doing this work is easier than changing the way everyone thinks.

Don’t get me wrong, this isn’t bad. This is normal. And it’s a good thing. Overall, these efforts move everyone closer to the ideas inherent in serverless designs.

Infinite Loops

This is a pattern that plays out time and time again. Gartner covers the technical side of it with their hype cycle approach. But, at it’s core this problem is a people challenge.

For the cutting edge, the devotees, the benefits of the new technology are clear. The shift to a new mental model is an easy one. But that’s a small percentage of the overall IT community.

The majority of the IT community is pushing towards a container driven landscape. And they will be there for a few years. Over time that will become too complex and burdensome. Then the mental model of serverless will become the dominant model.

It’ll take some time, but be patient. We’ve seen the pattern time and time again.

While the serverless community waits, innovation will continue. The ecosystem will mature. And when the rest of the IT community is ready, the technology will be too.

…and then we can start the loop all over again with whatever is next.

]]>
https://markn.ca/2021/the-infinite-loop-of-lost-potential/ 67f6bbeaaf961b00014432b2 Mon, 15 Nov 2021 09:00:00 -0500
<![CDATA[ Can We Improve How Station X Processed Genomics Data on AWS in 2017? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Can We Improve How Station X Processed Genomics Data on AWS in 2017?

In late 2017, Station X did an AWS “This is My Architecture” video. The video talks about how they built out a genomics processing pipeline on AWS.

Now, a few years later, I react to that video and see what’s stood the test of time, what could be done simpler given today’s technology, and generally critique the design against the AWS Well-Architected Framework.

The AWS Well-Architected Framework

The AWS Well-Architected Framework is designed to help you and your team make informed trade offs while building in the AWS Cloud. It’s built on five pillars;

  • Operational Excellence
  • Security
  • Cost Optimization
  • Reliability
  • Performance Efficiency

There pillars cover the primary concerns of building and running any solution. And as much as we’d all love to have everything, that’s just not possible.

…enter the framework.

It’ll help you strike the right balance for your goals to make sure that your build is the best it can be now and moving forward.

Why Architecture?

I often get asked why I talk about building in the cloud and architectural choices so often…aren’t I a security person?

Yes, I do focus on security and architecture is a critical part of that.

There’s really two types of security design work. The first is when you’re handed something and need to make sure the risks of that technology matches the risk appetite of the users.

The second type is when you’re building the technology. This is where making choices informed by security early in the process can have profound effects. You’re no longer bolting security on but building it in by design.

That’s why I talk about architecture and building so much. It’s where we all can have the largest possible security impact!

This video—and the ones that will come after—looks at a specific set of design decisions and how they balance the concerns of the AWS Well-Architected Framework…where security is one of the five pillars.

Station X’s Design

Station X (now defunct) built out a very simple (in concept) data pipeline to process genomics data. The customer’s sequencing equipment uploads the data directly to S3. A fleet of EC2 instances then cleans and enriches that data and re-formats it to optimize for analysis.

That analysis happens via a managed service for Hadoop. Station X then built a custom analysis front end running in another fleet of EC2 instances.

Learn more in the reaction video 👆.

Btw, I’ve updated my course, “Mastering The AWS Well-Architected Framework” on A Cloud Guru. If you want a solid walk through of the ideas behind the framework and how to apply it to your work in the AWS Cloud, check it out!
]]>
https://markn.ca/2021/can-we-improve-how-station-x-processed-genomics-data-on-aws-in-2017/ 67f6bbeaaf961b0001443183 Mon, 15 Nov 2021 09:00:00 -0500
<![CDATA[ AWS Lambda Powertools (Python) ]]> Want to share with others? Formatting issues in your reader? This post is available online, AWS Lambda Powertools (Python)

AWS Labs has a lot of open source code up on GitHub. This post looks at the AWS Lambda Powertools for Python. This project aims to help you get the most out of your AWS Lambda functions.

I call out a few more details in the Twitter thread below…

Tweet 1/7 👇 Next tweet

too many cool repos from @awscloud Labs, so we're 2x the 🧵's this week let's look at AWS Lambda Powertools (Python). it's available at https://github.com/awslabs/aws-lambda-powertools-python 🧵☁️ #cloud #devops

Tweet 2/7 👇 Next tweet 👆 Start

this thread is up unrolled at https://t.co/ACLd1UfFgv the last thread on the @awscloud Deployment Framework is up at https://markn.ca/2021/aws-deployment-framework/ 🧵☁️ #cloud #devops

Tweet 3/7 👇 Next tweet 👆 Start

this project follows a set of tenets: - AWS Lambda only - ease the adoption of best practice - keep it lean - strive for backwards compatibility - work backwards from the community - be idiomatic 👆 those are solid 🧵☁️ #cloud #devops

Tweet 4/7 👇 Next tweet 👆 Start

the goal of this project is really to help you get the most out of your Lambdas this project deploys as a layer (https://docs.aws.amazon.com/lambda/latest/dg/configuration-layers.html), making it super simple to use the main areas of help: - tracing - logging - metrics - event handling 🧵☁️ #cloud #devops

Tweet 5/7 👇 Next tweet 👆 Start

these are areas that come up time & time again when you're dealing with #serverless functions. this project does the heavy lifting here, so that you don't need to re-invent the wheel << very handy 🧵☁️ #cloud #devops

Tweet 6/7 👇 Next tweet 👆 Start

there's also some there utilities that are starting to make their way towards release. the feature flag utility is of particular interest, keep your eye on it 🧵☁️ #cloud #devops

Tweet 7/7 👇 Next tweet 👆 Start

all-in-all, if you're using AWS Lambda (& who isn't?), the power tools can really help. this repo is for Python but there's a project for Java too full docs at https://awslabs.github.io/aws-lambda-powertools-python/latest/ /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/aws-lambda-powertools-python/ 67f6bbeaaf961b0001443164 Mon, 15 Nov 2021 09:00:00 -0500
<![CDATA[ AWS Deployment Framework ]]> Want to share with others? Formatting issues in your reader? This post is available online, AWS Deployment Framework

AWS Labs has a lot of open source code up on GitHub. This post looks at the AWS Deployment Framework, a project designed to help you deploy across accounts in an AWS Organizations environment.

I call out a few more details in the Twitter thread below…

Tweet 1/9 👇 Next tweet

ok, leading up to @awsreinvent I've been busy . last week I featured a number of papers from the Amazon Builder's Library, the week before that, @awscloud white papers you can catch up at https://markn.ca/2021/aws-reinvent/ this week: AWS Labs projects! 🧵☁️ #cloud #devops

Tweet 2/9 👇 Next tweet 👆 Start

you may or may not know that @awscloud is quite active on @github. you can find a lot of work up at https://github.com/awslabs you can find this thread unrolled at https://t.co/dEPr3d9EJ5 🧵☁️ #cloud #devops

Tweet 3/9 👇 Next tweet 👆 Start

let's look at the "AWS Deployment Framework" available at https://github.com/awslabs/aws-deployment-framework this project tries to manage deployments across accounts within the same AWS Organization 🧵☁️ #cloud #devops

Tweet 4/9 👇 Next tweet 👆 Start

this one is billed as, "an extensive and flexible framework to manage and deploy resources across multiple AWS accounts and regions within an AWS Organization" hmmm, that sounds like it might solve some real challenges for teams 🧵☁️ #cloud #devops

Tweet 5/9 👇 Next tweet 👆 Start

installation is pretty straight forward and well documented up at https://github.com/awslabs/aws-deployment-framework/blob/master/docs/installation-guide.md it launches from the Serverless Application Repository which is an excellent resource if you haven't already checked it out 🧵☁️ #cloud #devops

Tweet 6/9 👇 Next tweet 👆 Start

the repo includes a "Sample Guide" that walks you through deploying a couple different resources types https://github.com/awslabs/aws-deployment-framework/blob/master/docs/samples-guide.md these types of practical examples are critical for user success. show me the steps! (which they do here 😉) 🧵☁️ #cloud #devops

Tweet 7/9 👇 Next tweet 👆 Start

while this framework uses a bunch of the @awscloud Code* services (which aren't as popular as something like @github), you could adapt it to use something else the principles it shows are widely applicable 🧵☁️ #cloud #devops

Tweet 8/9 👇 Next tweet 👆 Start

I've got mixed feelings on this repo. it's super useful but also feels like this should be simple within a native @awscloud experience however, xp shows us that AWS' weak point is cross-service delivery, this project steps in to fill that gap for deployment 🧵☁️ #cloud #devops

Tweet 9/9 👇 Next tweet 👆 Start

if you're in an AWS Organization (& you probably should be), this is useful framework if only to illustrate a robust approach to deploying assets across accounts check it out at https://github.com/awslabs/aws-deployment-framework /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/aws-deployment-framework/ 67f6bbeaaf961b0001443163 Mon, 15 Nov 2021 09:00:00 -0500
<![CDATA[ Avoiding overload in distributed systems by putting the smaller service in control ]]> Want to share with others? Formatting issues in your reader? This post is available online, Avoiding overload in distributed systems by putting the smaller service in control

The Amazon Builder’s Library is a great set of deep dive papers into the challenges with modern systems. This post looks at how Amazon balances system stability between control and data plane requests.

Avoiding overload in distributed systems by putting the smaller service in control, looks at

I call out a few more details in the Twitter thread below…

Tweet 1/10 👇 Next tweet

wrapping up my Amazon Builder's Library week, I'm looking at "Avoiding overload in distributed systems by putting the smaller service in control" today. this paper is by @_joemag_ from @awscloud 🧵☁️ #cloud #devops

Tweet 2/10 👇 Next tweet 👆 Start

you can view this thread unrolled at https://t.co/b3S6hIfSAB yesterday's thread on "Automating safe, hands-off deployments" by @clare_liguori is up at https://markn.ca/2021/automating-safe-hands-off-deployments/ 🧵☁️ #cloud #devops

Tweet 3/10 👇 Next tweet 👆 Start

this is a shorter, straight to the ➡ paper. it discusses an uncommon pattern between the two planes of most services: - data plane, "responsible for executing customer requests" - control plane, "responsible for managing and vending customer configuration" 🧵☁️ #cloud #devops

Tweet 4/10 👇 Next tweet 👆 Start

the paper mentions a number of interactions but focuses in on the pattern when the smaller control plane fleet is in control of making sure the service doesn't get overloaded (which is the opposite of most designs) 🧵☁️ #cloud #devops

Tweet 5/10 👇 Next tweet 👆 Start

data plane is typically 100x (or more) the size of the control plane. that makes sense given that it's doing most of the work the author uses EC2 as an example. a lot more systems run compute/storage vs. vending those configurations 🧵☁️ #cloud #devops

Tweet 6/10 👇 Next tweet 👆 Start

it's natural to assume that it would be best for the bigger service to manage the overall health. after all, it's already doing way more work to keep itself running the 📑 provides more details here 🧵☁️ #cloud #devops

Tweet 7/10 👇 Next tweet 👆 Start

in some cases, when the volume is high & predictability low of control plane requests, the author makes the case that it's more sensible for the small plane (control) to be in the drivers seat 🧵☁️ #cloud #devops

Tweet 8/10 👇 Next tweet 👆 Start

having the control plane responsible for stability needs some specific plumbing and design patterns in place but the overall benefit is worth it (when merited) this is a really fascinating write up on a pattern that probably comes up more than we realize 🧵☁️ #cloud #devops

Tweet 9/10 👇 Next tweet 👆 Start

the paper doesn't provide a complete roadmap here but it does a good job of providing the key points that signal this reverse pattern could be the solution you're looking for this paper is exactly what the Builders Library was made for. 🧵☁️ #cloud #devops

Tweet 10/10 👇 Next tweet 👆 Start

it helps others learn from some hard won lessons @awscloud. take a few minutes to read this one all the way through, it's excellent thanks for sharing this @_joemag_ /🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/avoiding-overload-in-distributed-systems-by-putting-the-smaller-service-in-control/ 67f6bbeaaf961b0001443162 Fri, 12 Nov 2021 09:00:00 -0500
<![CDATA[ Automating safe, hands-off deployments ]]> Want to share with others? Formatting issues in your reader? This post is available online, Automating safe, hands-off deployments

The Amazon Builder’s Library is a great set of deep dive papers into the challenges with modern systems. This post looks at how Amazon conducts hands-off deployments.

Automating safe, hands-off deployments, takes a look at how Amazon does continuous deployment. Amazon has been doing this practice for a long while and has automated each process to the point where it’s hands-off.

I call out a few more details in the Twitter thread below…

Tweet 1/10 👇 Next tweet

in today's review, I'm looking at "Automating safe, hands-off deployments" by @clare_liguori at @awscloud

https://aws.amazon.com/builders-library/automating-safe-hands-off-deployments/

this one is all about getting your work out to your customers

🧵☁️ #cloud #devops

Tweet 2/10 👇 Next tweet 👆 Start

this thread is available unrolled at https://t.co/PIavI51500

yesterday's thread on "Fairness in multi-tenant systems" is up at https://markn.ca/2021/fairness-in-multi-tenant-systems/

🧵☁️ #cloud #devops

Tweet 3/10 👇 Next tweet 👆 Start

right out of the gate, I love @clare_liguori's callout, "continuous deployment pipelines to help us deploy quickly and safely"

two keys there: - quickly - safely

🧵☁️ #cloud #devops

Tweet 4/10 👇 Next tweet 👆 Start

another key quote from early on in the paper, "We identified deployment risks and found ways to mitigate those risks through new safety automation in pipelines" ❤️❤️❤️

spot on! modern deployment reduces risk when done well. keep that in mind #infosec folks

🧵☁️ #cloud #devops

Tweet 5/10 👇 Next tweet 👆 Start

the paper is roughly broken down in the parts of a pipeline:

- source - build - test - prod

...and of course how they all fit together

🧵☁️ #cloud #devops

Tweet 6/10 👇 Next tweet 👆 Start

one key point is that _everything_ in production at Amazon gets there via a pipeline. static assets, code, infrastructure, everything

these pipelines make it easier to keep track of the history of changes & to ensure a high bar for quality

🧵☁️ #cloud #devops

Tweet 7/10 👇 Next tweet 👆 Start

👆this also make it easier to do code reviews, as they are all going through the pipelines. a nice example of a code review checklist in presented in the 📑

🧵☁️ #cloud #devops

Tweet 8/10 👇 Next tweet 👆 Start

testing is discussed in depth & honestly there is a lot more testing than I expected. it's an example of how Amazon's approach has matured & takes advantage of the @awscloud environment

🧵☁️ #cloud #devops

Tweet 9/10 👇 Next tweet 👆 Start

deployments themselves are a bit crazy. that, I did expect.

the pipelines need to ensure that they don't negatively impact production...especially at scale.

@clare_liguori does a great job of breaking down the concerns & techniques used here

🧵☁️ #cloud #devops

Tweet 10/10 👇 Next tweet 👆 Start

📑 finishes off w/idea of pipelines as code. very meta but it makes sense given the number of pipelines in use

if you're deploying to production, you should check out this paper. that's a nice way of saying you should go read this paper ASAP 🤣

/🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/automating-safe-hands-off-deployments/ 67f6bbeaaf961b0001443161 Thu, 11 Nov 2021 09:00:00 -0500
<![CDATA[ This One Mistake Will Stop a DevSecOps Shift Left Strategy Dead in Its Tracks ]]> Want to share with others? Formatting issues in your reader? This post is available online, This One Mistake Will Stop a DevSecOps Shift Left Strategy Dead in Its Tracks

DevOps has taken the development world by storm. And why not? It’s a fantastic way of working and the cloud has taken that to an 11.

Now DevSecOps is a thing…isn’t it? Security is a huge concern of everyone. No one really debates that. The debate is how to improve security overall.

In this video, we look at the biggest mistake security teams make when trying to get involved in modern development with DevSecOps.

Feel free to join the discussion on LinkedIn or in the YouTube comments.

Transcript

I see security teams making the same mistake over and over again when it comes to “shifting left.” It’s frustrating from afar and infuriating when you have to deal with it day-to-day.

Let’s dig in to the disaster that is DevSecOps…

[00:15]

Imagine for a minute, you’re in your kitchen preparing dinner. You’re a reasonably good home cook. More often than not, what you put on the table is enjoyed by those you’re sharing with it.

Sure, every once and a while you miss. But that’s the rare case, so when it does happen everyone smiles, you laugh, and then place an order for take out. Mistakes happen.

Not too bad, right?

[00:29]

Now, let’s say while you’re getting ready to sit down for a wonderful home cooked meal, you neighbour invites themselves in. They immediate start hammering you with questions like, “How sharp is that knife?”, “Do you know who grew that broccoli?”, “Are there too many ovens in this neighbourhood?”

Taken aback, you politely ask, “Um, are you a professional chef? Do you have a lot of experience cooking?”

They reply, “Oh no, I don’t even have a kitchen in my place. I just order food every once and a while.”

That’s basically the scenario I see play out in organizations around the world.

The development teams and builders are working to solve business problems and address customer needs.

Then the security team shows up out of no where and starts asking seemingly irrelevant questions and demanding that priorities change in the name “reducing risk” and “improving the overall security posture” without understanding what you’re working on or how you work.

[01:37]

This is why even the name DevSecOps frustrates me to no end. The DevOps philosophy already assumes that you want to build a resilient, reliable system. There’s no need to jam another acronym in there.

Teams know that security is important, they just need the information and support to make smart decisions at the right time.

So is this whole “shift left” thing doomed?

No.

Not if you do it well.

[02:06]

If you’re on the security team, the first thing you need to understand is that you probably don’t understand how the builders are working.

You can fix that.

Spend some time with them. Ask lots of questions to better understand their workflow and concerns.

Most important of all, make sure that the information from security tools that shift left provide information with the proper context and enough data for teams to make an informed decision.

[02:34]

Just because it’s a security priority, doesn’t mean it’s a business priority.

For developers and builders, understand that security controls can provide real value to you. The whole goal of these controls is to make sure things work as intended.

Network security tools look for malicious activity and malformed traffic. You don’t want that anywhere near your app.

Threat detection on your servers and containers is looking for errant processes and other indicators of compromise. This makes sure that your resources are only working for you instead of doing things like mining cryptocurrency for cybercriminals.

Posture management—ugh, horrible name—looks at the cloud services you’re using to make sure that you have configured them in a way that matches your risk appetite.

Vulnerability scanners look at your tech stack trying to find known issue before so they don’t bite you in the you-know-what.

[03:26]

Everything on this list and most of the other security controls out there can dramatic HELP you meet your goals.

With that understanding, you need to make sure that you have access to the outputs of these tools. You need to know that they are in place and doing their job, so that you can focus on other parts of yours.

By now, you’ve figured out that the number one mistake I see security teams making when they “shift left” is IGNORING the developers and builders.

For some reason, security teams assume that to “shift left” means doing their isolated security work earlier in the development process. That’s an archaic way of thinking.

[04:05]

To truly shift left, you need to leverage the capability of security tools and processes to help developers and builders identify risks with their systems earlier in THEIR processes.

This data will help the teams make informed decisions about what actions should be taken to meet the business goals.

Shifting security left can help reduce the risks to the business while improving the quality of the systems your build.

Who wouldn’t want that?

]]>
https://markn.ca/2021/this-one-mistake-will-stop-a-devsecops-shift-left-strategy-dead-in-its-tracks/ 67f6bbeaaf961b00014432d4 Wed, 10 Nov 2021 09:00:00 -0500
<![CDATA[ Fairness in multi-tenant systems ]]> Want to share with others? Formatting issues in your reader? This post is available online, Fairness in multi-tenant systems

The Amazon Builder’s Library is a great set of deep dive papers into the challenges with modern systems. This post highlights some of the challenges in dealing with mult-tenant systems.

Fairness in multi-tenant systems, looks at the challenges of balancing loads within multi-tenant systesm. Specifically, issues around handling API requests to these systems.

I call out a few more details in the Twitter thread below…

Tweet 1/16 👇 Next tweet

today we’re looking at “Fairness in multi-tenant systems” by @dyanacek from the Amazon Builder’s library

it’s available at https://aws.amazon.com/builders-library/fairness-in-multi-tenant-systems/

🧵☁️ cloud devops @awscloud

Tweet 2/16 👇 Next tweet 👆 Start

you can find this thread unrolled at https://t.co/henuJwkAKm

…and yesterday’s thread on “Making retries safe with idempotent APIs” at https://markn.ca/2021/making-retries-safe-with-idempotent-apis/

🧵☁️ cloud devops

Tweet 3/16 👇 Next tweet 👆 Start

I’ve helped a lot of teams build out multi-tenant systems. it’s a fascinating problem space. you’re trying to find the right balance between isolation & economy of scale

it’s not easy

🧵☁️ cloud devops

Tweet 4/16 👇 Next tweet 👆 Start

before we dive into this 📑, let me just add the “SaaS Lens” from the Well-Architected Framework to your reading list as well

this Lens explains a few different multi-tenancy models

it’s at https://docs.aws.amazon.com/wellarchitected/latest/saas-lens/saas-lens.html

🧵☁️ cloud devops

Tweet 5/16 👇 Next tweet 👆 Start

ok, back on track, this paper from @dyanacek looks at how Amazon manages APIs requests in order to avoid overload

what does that have to do with multi-tenancy? you ask (you did ask, right?)

well…

🧵☁️ cloud devops

Tweet 6/16 👇 Next tweet 👆 Start

it's economy of scale bit. you optimize resource usage (& thus spend) by making sure that you’re streamlining the use of your service

@dyanacek takes it a step further in this 📑 & shows how you can use this to reduce pressures on your systems as well

🧵☁️ cloud devops

Tweet 7/16 👇 Next tweet 👆 Start

first up, is the case for multitenancy. there’s a few well structured arguments in the paper, but basically it’s all about resource optimization

idle = bad (generally)

🧵☁️ cloud devops

Tweet 8/16 👇 Next tweet 👆 Start

one of the biggest downfalls is rightfully called out by @dyanacek as well; tenants impacting each other

if we’re each sharing a resource, what if I grab more than my fair share?

this is something we need to solve for…

🧵☁️ cloud devops

Tweet 9/16 👇 Next tweet 👆 Start

which is why this 📑 is a great one, it transitions out of the example highlighting the +/- and into “fairness”

summed up as, “every client in a multi-tenant system is provided with a single-tenant experience” << or at least they SHOULD be

🧵☁️ cloud devops

Tweet 10/16 👇 Next tweet 👆 Start

one area that gets more attention is the case when demand is outpacing supply (which should increasing as scaling catches up). what do you then?

the author introduces the concept of “load shedding”

🧵☁️ cloud devops

Tweet 11/16 👇 Next tweet 👆 Start

…a/k/a saying 🚫 quickly with little resource cost. this can relieve the pressure on the backend & clients can easily retry using the techniques we highlighted in previous threads 👆

🧵☁️ cloud devops

Tweet 12/16 👇 Next tweet 👆 Start

load shedding isn’t enough to solve the issue of fairness, that’s where “rate limiting” comes into play. you can use this technique to “shape unplanned increases in traffic”

the paper details how & what to look out for when adding this pattern to your design

🧵☁️ cloud devops

Tweet 13/16 👇 Next tweet 👆 Start

quotas go hand-in-hand with rate limited & the author spends quite a bit of time of them as well (rightfully so!)

there’s a fine art to implementing a quota system & the 📑 does a good job of providing a sold overview

🧵☁️ cloud devops

Tweet 14/16 👇 Next tweet 👆 Start

all of these techniques are known as “admission control systems”

the paper highlights how Amazon uses these (and why, and when), showing a few different models and patterns that could help you out

🧵☁️ cloud devops

Tweet 15/16 👇 Next tweet 👆 Start

finally the paper dives into architecture design patterns that can help reduce your need for these techniques.

nothing is every perfect, so knowing all of the tools ⚒️ at your disposal is critical

🧵☁️ cloud devops

Tweet 16/16 👇 Next tweet 👆 Start

all-in-all, this is a FANTASTIC paper by @dyanacek highlight years of hard won learning.

it builds nicely on the other two papers I’ve mini-reviewed this week. I really think you should add this one to your reading list!

/🧵☁️ cloud devops

]]>
https://markn.ca/2021/fairness-in-multi-tenant-systems/ 67f6bbeaaf961b0001443160 Wed, 10 Nov 2021 09:00:00 -0500
<![CDATA[ Making retries safe with idempotent APIs ]]> Want to share with others? Formatting issues in your reader? This post is available online, Making retries safe with idempotent APIs

The Amazon Builder’s Library is a great set of deep dive papers into the challenges with modern systems. This post highlights some of the challenges that the retry pattern presents.

The paper, “Making retries safe with idempotent APIs, follows-up yesterday’s thread on the, “Timeouts, retries, and backoff with jitter” paper.

This one takes a much deeper dive into the challenges that a simple retry poses to an API. It’s all about balancing the customer experience with the systems’ stability & performance.

I call out a few more details in the Twitter thread below…

Tweet 1/9 👇 Next tweet

diving into the Amazon Builder's Library again today. this time with, "Making retries safe with idempotent APIs", by @mfeatonby

📑: https://aws.amazon.com/builders-library/making-retries-safe-with-idempotent-APIs/

this is a level 300 paper, digging a bit deeper than yesterday's' level 200

🧵☁️ #cloud #devops @awscloud

Tweet 2/9 👇 Next tweet 👆 Start

this thread is available unrolled at https://t.co/nEPvsF8Awt

yesterday's thread is up at https://markn.ca/2021/timeouts-retries-and-backoff-with-jitter/

🧵☁️ #cloud #devops

Tweet 3/9 👇 Next tweet 👆 Start

idempotent is one of my all time favourite words, especially in tech.

if you're unfamiliar, in this context it means that you can run operations more than once and the results won't change

more at https://en.wikipedia.org/wiki/Idempotence

🧵☁️ #cloud #devops

Tweet 4/9 👇 Next tweet 👆 Start

for this paper, the author explores the concept of idempotency (see, awesome word) within the "retry" pattern

basically, how can the backend service make sure that retry doesn't end up being a duplicate or something worse

🧵☁️ #cloud #devops

Tweet 5/9 👇 Next tweet 👆 Start

excellent quote to build by, "We’ve found that in many cases the simplest solution is the best solution", @mfeatonby, @awscloud

followed by, "a surprisingly large number of transient or random faults can be overcome by simply retrying the call"

🧵☁️ #cloud #devops

Tweet 6/9 👇 Next tweet 👆 Start

the 📑 walks through some of the potential downsides of the retry pattern

it then moves on to a topic that isn't discussed enough; reducing complexity

the author discusses API design & how @awscloud uses an identifier handled by the SDKs to manage retries

🧵☁️ #cloud #devops

Tweet 7/9 👇 Next tweet 👆 Start

this approach avoids lots of problems on the service side, but issues remain. that brings up to the various strategies that can be used to implement a retry pattern

📑 uses @awscloud EC2 as an example & this really helps drive some of these key points home

🧵☁️ #cloud #devops

Tweet 8/9 👇 Next tweet 👆 Start

one fascinating edge case is that of late arriving requests. in any distributed system (especially one over the internet) this is a distinct possibility

📑 explores these challenges & explains how @awscloud looks at making reasonable trade offs to handle

🧵☁️ #cloud #devops

Tweet 9/9 👇 Next tweet 👆 Start

overall, this is a fantastic paper. it dives deep into an area that most assume is simple. at scale, nothing is

however, these patterns & tips can help you replicate this pattern in your services to deliver a better customer experience

worth the 🕙 to read

/🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/making-retries-safe-with-idempotent-apis/ 67f6bbeaaf961b000144315f Tue, 09 Nov 2021 09:00:00 -0500
<![CDATA[ Can We Improve How Capital One Enforced Policies in AWS with Cloud Custodian in 2017? ]]> Want to share with others? Formatting issues in your reader? This post is available online, Can We Improve How Capital One Enforced Policies in AWS with Cloud Custodian in 2017?

In late 2017, Capital One did an AWS “This is My Architecture” video. The video talks about how they built Cloud Custodian and how that tool helps them enforce policies in the AWS Cloud.

Now, a few years later, I react to that video and see what’s stood the test of time, what could be done simpler given today’s technology, and generally critique the design against the AWS Well-Architected Framework.

The AWS Well-Architected Framework

The AWS Well-Architected Framework is designed to help you and your team make informed trade offs while building in the AWS Cloud. It’s built on five pillars;

  • Operational Excellence
  • Security
  • Cost Optimization
  • Reliability
  • Performance Efficiency

There pillars cover the primary concerns of building and running any solution. And as much as we’d all love to have everything, that’s just not possible.

…enter the framework.

It’ll help you strike the right balance for your goals to make sure that your build is the best it can be now and moving forward.

Why Architecture?

I often get asked why I talk about building in the cloud and architectural choices so often…aren’t I a security person?

Yes, I do focus on security and architecture is a critical part of that.

There’s really two types of security design work. The first is when you’re handed something and need to make sure the risks of that technology matches the risk appetite of the users.

The second type is when you’re building the technology. This is where making choices informed by security early in the process can have profound effects. You’re no longer bolting security on but building it in by design.

That’s why I talk about architecture and building so much. It’s where we all can have the largest possible security impact!

This video—and the ones that will come after—looks at a specific set of design decisions and how they balance the concerns of the AWS Well-Architected Framework…where security is one of the five pillars.

Capital One’s Design

Capital One was an early leader in cloud. They quickly realized that it was hard to enforce various security and compliance policies in the AWS Cloud.

In order to solve that problem, they built Cloud Custodian.

This open source tool allows you to write policies in a simple domain specific language (DSL) and then enforce them entire on a schedule or as a serverless design pattern.

Capital One open sourced the tool and since then, it’s taken on a life of it’s own. It’s wildly popular and with good reason. It’s simple to use and addresses a key pain point for teams who want to build well in the cloud.

Learn more in the reaction video 👆.

Btw, I’ve updated my course, “Mastering The AWS Well-Architected Framework” on A Cloud Guru. If you want a solid walk through of the ideas behind the framework and how to apply it to your work in the AWS Cloud, check it out!
]]>
https://markn.ca/2021/can-we-improve-how-capital-one-enforced-policies-in-aws-with-cloud-custodian-in-2017/ 67f6bbeaaf961b0001443182 Mon, 08 Nov 2021 09:00:00 -0500
<![CDATA[ Timeouts, retries, and backoff with jitter ]]> Want to share with others? Formatting issues in your reader? This post is available online, Timeouts, retries, and backoff with jitter

The Amazon Builder’s Library is a great set of deep dive papers into the challenges with modern systems. This post highlights some of the challenges in dealing with failure at scale.

Timeouts, retries, and backoff with jitter, looks at various types of failures and their potential impact on both your service and it’s consumers.

I call out a few more details in the Twitter thread below…

Tweet 1/6 👇 Next tweet

last week, I looked at a number of @awscloud white papers. this week, I'll be diving into the Amazon Builder's LIbrary

first up: "Timeouts, retries, and backoff with jitter", by @MarcJBrooker, https://aws.amazon.com/builders-library/timeouts-retries-and-backoff-with-jitter/

🧵☁️ #cloud #devops

Tweet 2/6 👇 Next tweet 👆 Start

this 🧵 is available unrolled at https://t.co/dqEcUqffGB

Friday's thread is up at https://markn.ca/2021/machine-learning-best-practices-for-public-sector-organizations/

🧵☁️ #cloud #devops

Tweet 3/6 👇 Next tweet 👆 Start

tldr: 💩 happens. plan for it. make sure to keep your customers perspective in mind

more 👇

🤣

🧵☁️ #cloud #devops

Tweet 4/6 👇 Next tweet 👆 Start

. @MarcJBrooker calls out the 3 primary techniques that Amazon uses for handling failures:

1. timeouts 2. retries 3. backoff

the rest of the 📑 details the how, why, & when or each of these techniques

🧵☁️ #cloud #devops

Tweet 5/6 👇 Next tweet 👆 Start

the discussion of timeouts is of particular note. looking at the impacts of server vs. client timeouts & how to manage both without causing a flood of retries is really interesting

🧵☁️ #cloud #devops

Tweet 6/6 👇 Next tweet 👆 Start

retries is where the paper goes next. the author calls out that retries as "selfish" & cause failures to amplify. this is why Amazon combines them with the backoff technique to avoid a flood of requests

🧵☁️ #cloud #devops

]]>
https://markn.ca/2021/timeouts-retries-and-backoff-with-jitter/ 67f6bbeaaf961b000144315e Mon, 08 Nov 2021 09:00:00 -0500
<![CDATA[ Machine Learning Best Practices for Public Sector Organizations ]]> Want to share with others? Formatting issues in your reader? This post is available online, Machine Learning Best Practices for Public Sector Organizations

AWS has a huge library of fantastic resources. This post highlights the recently released whitepaper walking public sector organizations through machine learning best practices.

Machine Learning Best Practices for Public Sector Organizations, walks you through the ups and downs of a machine learning practice.

While the title and positioning calls out the US Public Sector, this paper is really broadly applicable. There’s a few specific resources for the US Public Sector—like The National Artificial Intelligence Research and Development Strategic Plan: 2019 Update—but really, only about 1% of the paper is specific to that audience.

I call out a few more details in the Twitter thread below…

Tweet 1/15 👇 Next tweet

today I'm taking a look at the @awscloud paper 📑, "Machine Learning Best Practices for Public Sector Organizations"

it's available as a PDF from https://d1.awsstatic.com/whitepapers/machine-learning-best-practices-for-public-sector-organizations.pdf

🧵☁️ #cloud #ml

Tweet 2/15 👇 Next tweet 👆 Start

this thread is unrolled at https://t.co/t4UCZEUxNA

you can read yesterday's thread at https://markn.ca/2021/aws-serverless-multi-tier-architectures/

🧵☁️ #cloud #ml

Tweet 3/15 👇 Next tweet 👆 Start

the intro lays out the specific challenges & reqs for US public sector organizations heading down the path of leveraging machine learning

...that's good but the paper is really broadly applicable! don't ignore it just because you're not in the public sector

🧵☁️ #cloud #ml

Tweet 4/15 👇 Next tweet 👆 Start

to that point, the section "Challenges for public sector" should be read as "Challenges for everyone" as the only public sector-specific point is that there are draft guidelines for the use of AI within the US government

more at https://www.nitrd.gov/pubs/National-AI-RD-Strategy-2019.pdf

🧵☁️ #cloud #ml

Tweet 5/15 👇 Next tweet 👆 Start

the majority of the paper is the "best practices" section. for each of the subsections, it calls out the biggest challenges you'll face building out your ML practice

🧵☁️ #cloud #ml

Tweet 6/15 👇 Next tweet 👆 Start

on data ingestion & preparation: there are some practical suggestions and use cases for various @awscloud services

what this section should've said is, "Get ready to plow through a bunch of 💩. Data is always messy and there's a lot of clean up to be done" 🤣

🧵☁️ #cloud #ml

Tweet 7/15 👇 Next tweet 👆 Start

on model training & tuning: the paper provides a really great overview of the practical aspects of this part of the ML pipeline.

it's really well written and consistently links out to other resources so you can learn more

🧵☁️ #cloud #ml

Tweet 8/15 👇 Next tweet 👆 Start

MLOps is a little light but I think that's understandable

ops is a very big rabbit hole

this section does well to explain the issues and links out to references and key services like @awscloud SageMaker Pipelines

🧵☁️ #cloud #ml

Tweet 9/15 👇 Next tweet 👆 Start

management & governance is always a 😴 but it's also critical

if you don't pay attention, you're not going to build a reliable practice

you're not going to understand where the data came from, the restrictions on it, how to get the most from it, etc.

🧵☁️ #cloud #ml

Tweet 10/15 👇 Next tweet 👆 Start

security & compliance is near and dear to my ❤️. the paper does a good job of covering this area.

if you're using mainly managed services, a lot of your focus will be on service configuration & data access...read on for more (of course!)

🧵☁️ #cloud #ml

Tweet 11/15 👇 Next tweet 👆 Start

on cost, the paper highlights the areas where costs may bubble up

I would've liked some more concrete tips about how to cut down on costs

of course, what trade offs you can make will depend on your situation so it does make sense they didn't dive in too deep

🧵☁️ #cloud #ml

Tweet 12/15 👇 Next tweet 👆 Start

the last best practice area is bias and explainability

this is THE critical topic when it comes to ML, especially in the public sector

we need more resources on this topic. not just about bias in the model but also understanding where the data comes from...

🧵☁️ #cloud #ml

Tweet 13/15 👇 Next tweet 👆 Start

...honestly, I can't overemphasize how critical it is to focus on this in any ML practice. when it comes to public sector projects, where policy could be influenced or set based on results, the risks are even higher

🧵☁️ #cloud #ml

Tweet 14/15 👇 Next tweet 👆 Start

overall, this is a great paper. it's biggest weakness is that it's labeled as a public sector paper. that's going to turn a lot of ppl away that should read it

there are other papers on ML from the @awscloud team

like, MLOps, https://d1.awsstatic.com/whitepapers/mlops-continuous-delivery-machine-learning-on-aws.pdf

🧵☁️ #cloud #ml

Tweet 15/15 👇 Next tweet 👆 Start

...Model Explainability with AWS Artificial Intelligence and Machine Learning Solutions at https://d1.awsstatic.com/whitepapers/leveraging-model-explainability-with-AWS.pdf

...and of course the ML lens of the @awscloud Well-Architected Framework at https://docs.aws.amazon.com/wellarchitected/latest/machine-learning-lens/machine-learning-lens.html

/🧵☁️ #cloud #ml

]]>
https://markn.ca/2021/machine-learning-best-practices-for-public-sector-organizations/ 67f6bbeaaf961b000144315d Fri, 05 Nov 2021 10:00:00 -0400
<![CDATA[ AWS Serverless Multi-Tier Architectures with Amazon API Gateway and AWS Lambda ]]> Want to share with others? Formatting issues in your reader? This post is available online, AWS Serverless Multi-Tier Architectures with Amazon API Gateway and AWS Lambda

AWS has a huge library of fantastic resources. This post highlights the recently released whitepaper talking about serverless multi-tier architectures.

AWS Serverless Multi-Tier Architectures with Amazon API Gateway and AWS Lambda”, walks through how the class 3-tier—presentation, logic, data—design pattern works in a serverless world.

I call out a few more details in the Twitter thread below…

Tweet 1/16 👇 Next tweet

next up in the @awscloud white paper 🧵 series, "AWS Serverless Multi-Tier Architectures with Amazon API Gateway and AWS Lambda"

yes, horrible title. thankfully, a good paper

available at : https://docs.aws.amazon.com/whitepapers/latest/serverless-multi-tier-architectures-api-gateway-lambda/welcome.html

🧵☁️ #cloud #serverless

Tweet 2/16 👇 Next tweet 👆 Start

you can read this unrolled at https://t.co/4GKVQwcume

yesterday's thread on @nistcyber & @awscloud is unrolled at https://markn.ca/2021/nist-cybersecurity-framework/

🧵☁️ #cloud #serverless

Tweet 3/16 👇 Next tweet 👆 Start

ok, first things first. yikes. what a title.

it's a marketing/SEO title that probably hinder the paper more than help it. could've easily stopped at, "AWS Serverless Multi-Tier Architectures"

that would've gotten the point across

🧵☁️ #cloud #serverless

Tweet 4/16 👇 Next tweet 👆 Start

multi-tier or n-tier architectures are pretty standard. you have three-ish layers with a specific intention:

1. presentation 2. logic 3. data

the aim is keep the bits required the goal of each layer in that layer. more at https://en.wikipedia.org/wiki/Multitier_architecture

🧵☁️ #cloud #serverless

Tweet 5/16 👇 Next tweet 👆 Start

the goal of this paper is to show you how to adapt those designs into a #serverless design. so no idle resources in an event-driven system

lots of @awscloud serverless resources are up at https://aws.amazon.com/serverless/

🧵☁️ #cloud #serverless

Tweet 6/16 👇 Next tweet 👆 Start

right in the intro, the paper calls out a big reason to move these designs to #serverless ones: there's a lot of "boilerplate" components required in n-tier apps to make the connections between layers

that transitions to API calls in a serverless world

🧵☁️ #cloud #serverless

Tweet 7/16 👇 Next tweet 👆 Start

right out of the gate:

- CloudFront + S3 for presentation - @awscloud API Gateway + Lambda for logic - DynamoDB for data

is a very sweet #serverless toolkit for n-tier apps. if you're migrating an existing app, sub Lambda for Fargate

🧵☁️ #cloud #serverless

Tweet 8/16 👇 Next tweet 👆 Start

the paper itself focuses on the classic 3-tier app. mainly because n != 3 is pretty rare and a stretch most of the time 🤣

🧵☁️ #cloud #serverless

Tweet 9/16 👇 Next tweet 👆 Start

they start w/the logic layer and the paper does a good job at highlighting the advantages of that @awscloud API Gateway + Lambda combo

summed up nicely as, "Your business logic goes here, no servers necessary"

🧵☁️ #cloud #serverless

Tweet 10/16 👇 Next tweet 👆 Start

the 📑 has a nice, quick call out for security, performance, and deployment for this layer. it links out to some handy resources to help you dig deeper in these areas

🧵☁️ #cloud #serverless

Tweet 11/16 👇 Next tweet 👆 Start

. @awscloud API Gateway section does a nice job of heading off most of the questions that builders ask when using the service. where appropriate, it links out to other resources

...though more links to examples & documentation would be appreciated here

🧵☁️ #cloud #serverless

Tweet 12/16 👇 Next tweet 👆 Start

the data tier is a bit of a dodge, though that's ok. it's basically a list of @awscloud data services and whether or not they are "serverless"

not much to add here because service choice depends entirely on the data & it's use...but default DynamoDB 😉

🧵☁️ #cloud #serverless

Tweet 13/16 👇 Next tweet 👆 Start

the presentation is a bit thin. it calls out Cognito (identity & data sync), CloudFront (serving up content), & Amplify (a middle glue-y framework)

Amplify deserves more attention. learn more at https://aws.amazon.com/amplify/

🧵☁️ #cloud #serverless

Tweet 14/16 👇 Next tweet 👆 Start

...but I would've liked to see more description about the challenges at the presentation layer and some of the potential solutions. if they authors didn't want to go deeper, linking out to some blog posts or public code repos would've helped readers

🧵☁️ #cloud #serverless

Tweet 15/16 👇 Next tweet 👆 Start

the 📑 wraps with some sample architectures. this is excellent and more papers need this. it really drives the key points home

mobile backend, single-page apps, web apps, & microservices are all discussed

🧵☁️ #cloud #serverless

Tweet 16/16 👇 Next tweet 👆 Start

all-in-all, this is a solid paper with—again—a terrible name. look past that and take a few minutes to read this one through. it'll give you a great overview of how to adapt these classic designs to a serverless world

/🧵☁️ #cloud #serverless

]]>
https://markn.ca/2021/aws-serverless-multi-tier-architectures-with-amazon-api-gateway-and-aws-lambda/ 67f6bbeaaf961b000144315c Thu, 04 Nov 2021 10:00:00 -0400
<![CDATA[ NIST Cybersecurity Framework ]]> Want to share with others? Formatting issues in your reader? This post is available online, NIST Cybersecurity Framework

AWS has a huge library of fantastic resources. This post highlights the recently updated whitepaper aligning the NIST Cybersecurity Framework to AWS.

NIST Cybersecurity Framework, Aligning to the NIST CSF in the AWS Cloud”, does exactly what the subtitle promises.

This paper aligns the NIST CSF to the AWS Cloud.

I call out a few more details in the Twitter thread below…

Tweet 1/5 👇 Next tweet

today I'm taking a look at "NIST Cybersecurity Framework, Aligning to the NIST CSF in the AWS Cloud" which...um...aligns @NISTcyber's framework with @awscloud designs

PDF 📁: https://d1.awsstatic.com/whitepapers/compliance/NIST_Cybersecurity_Framework_CSF.pdf?did=wp_card&trk=wp_card

🧵☁️ #cloud #infosec

Tweet 2/5 👇 Next tweet 👆 Start

read the thread unrolled at https://t.co/LKnrxH9Sp0

yesterday's thread is up at https://markn.ca/2021/reactive-systems-on-aws/

🧵☁️ #cloud #infosec #devops

Tweet 3/5 👇 Next tweet 👆 Start

the structure of the paper 📑 is simple. a few use cases and then best practices by @nistcyber CSF core function:

- identify - protect - detect - respond - recover

...and finally an alignment of @awscloud services with the framework

🧵☁️ #cloud #infosec

Tweet 4/5 👇 Next tweet 👆 Start

the use cases are handy, but really ANYONE can benefit from looking at the framework. it's right on pg 3, @nistcyber CSF is "a simple-yet-effective construct" for your security efforts

it looks at practice, outcomes, and controls

🧵☁️ #cloud #infosec

Tweet 5/5 👇 Next tweet 👆 Start

as an aside, @nistcyber has documented the framework thoroughly. you can check it out at https://www.nist.gov/cyberframework

at that site, you'll find the framework, a "new to framework" guide, and material for learning specific aspects of the CSF

🧵☁️ #cloud #infosec

]]>
https://markn.ca/2021/nist-cybersecurity-framework/ 67f6bbeaaf961b000144315b Wed, 03 Nov 2021 10:00:00 -0400