Years ago, I worked at a large e-commerce company that was one of the biggest food delivery services in the UK. They did something very interesting - they regularly ran load tests against production using fake orders. As a partial observer, here's what I think we can learn from this practice and how it partially caused the biggest outages they ever experienced (but not from the load test itself!). Load Testing in production As a food delivery service, they experienced large traffic spikes...
8 days ago • 5 min read
Serverless is an incredible paradigm, but performance tuning sometimes feels like a black box. You have no control over the infrastructure, but that doesn’t mean you can’t optimize. In this post, let’s look at five ways to take serverless performance to the next level. 1. Right-size Lambda functions With Lambda, you have one lever to control the power and cost of your functions — its memory setting. Both CPU and network bandwidth are allocated proportionally to a function’s memory allocation....
24 days ago • 4 min read
Software systems are getting bigger and more complex. And we are constantly looking for ways to test code in production without risking user experience. Canary deployments is a popular mechanism for rolling out changes incrementally, allowing us to limit the blast radius in case something goes wrong. However, they’re not without limitations. Canary deployments essentially sacrifice a small portion of users for the greater good. But what if you want to gain insights without impacting any real...
29 days ago • 3 min read
Every software engineer should learn about the Actor Model, even if they don't work with Erlang, Elixir or Akka. It opens up your mind to a new way of thinking about computation and concurrency. And what better way to learn than to hear from its inventor, Carl Hewitt (R.I.P)? This conversation between Carl, Erik Meijer (of the Rx fame) and Clemens Szyperski is a must-see! An actor is the fundamental unit of computation which embodies the 3 things – processing, storage and communications –...
about 1 month ago • 1 min read
In security and access control, authentication and authorization are two distinct yet interconnected concepts. Authentication is the process of confirming the identity of a user or system, while authorization defines the actions that the authenticated user is permitted to perform within your system. Although API Gateway integrates directly with Cognito, it lacks built-in support for fine-grained authorization. In a previous article, we looked at implementing fine-grained authorization using a...
about 2 months ago • 4 min read
A common narrative is that one should always use access tokens to call your APIs, while ID tokens are strictly for identifying users. Some of it has come from this article by Auth0 [1], which makes a strong statement about using ID tokens: However, things are usually more nuanced. In some cases, using ID tokens instead of access tokens is both acceptable and pragmatic. Cognito User Pools might be one of these cases. Cost of using access tokens The common practice amongst Cognito users is to...
2 months ago • 3 min read
In security and access control, authentication and authorization mean two distinct but related things. Authentication verifies the identity of a user or system. Authorization determines what actions an authenticated user is allowed to perform in your system. API Gateway has built-in integration with Cognito, but it doesn’t provide any fine-grained authorization out-of-the-box. By default, a Cognito authorizer only checks if a user’s bearer token is valid and that the user belongs to the right...
2 months ago • 2 min read
Back in 2018, I shared [1] several ways to implement fan-out/fan-in with Lambda. A lot has changed since, so let’s explore the solution space in 2024. Remember, what’s “best” depends on your context. I will do my best to outline the trade-offs you should consider. Also, I will only consider AWS services in this post. But there is a wealth of OpenSource/3rd-party services that you can use too, such as Restate. If you’re not sure whether you need fan-out/fan-in or map-reduce, then you should my...
3 months ago • 5 min read
Many students and clients have asked me how to implement Map-Reduce workloads serverlessly. In most cases, they are actually asking about Fan-Out/Fan-In! At a glance, the two patterns look very similar and they are often used interchangeably in conversations. So in this post, let's compare them and see how they differ. Why? Because names matter ;-) Fan-Out/Fan-In Fan-Out and Fan-In are two patterns that are often used together to divide and conquer a large task by: Divide the task into...
4 months ago • 2 min read