Here's what we've learned from making architecture changes to Meta’s event driven asynchronous computing platform.

Before jumping into the details of the migration story, we’d like to take a step back and try to explain the motivation and rationale for this migration.

Over time, the data platform has morphed into various forms as the needs of the company have grown. What was a modest data platform in the early days has grown into an exabyte-scale platform. Some systems serving a smaller scale began showing signs of being insufficient for the increased demands that were placed on them. Most notably, we’ve run into some concrete reliability and efficiency issues related to data (de)serialization, which has made us rethink the way we log data and revisit the ideas from first principles to address these pressing issues.

Logger is at the heart of the data platform. The system is used to log analytical and operational data to Scuba, Hive, and stream processing pipelines via Scribe. Every product and data platform team interacts with logging. The data format for logging was either Hive Text Delimited or JSON, for legacy reasons. The limitations of these formats are described in our previous article on Tulip.

Anonymous Credential Service (ACS) is a highly available multitenant service that allows clients to authenticate in a de-identified manner.

Nullsafe is a new static analysis tool that is used at Meta to detect NullPointerException (NPE) errors in Java code.

The journey to Precision Time Protocol (PTP) has been a long one. We're sharing a deep technical dive into our PTP migration.

Code reviews don’t have to be slow and unproductive. We’re sharing several tools and steps we’ve taken at Meta to make code reviews as fast as possible, without sacrificing quality.

How Meta developed Tulip, a serialization protocol supporting schema evolution that has enabled us to enforce schemas on data streams.

Here’s how Instagram used causal inference and ML to improve the user experience for daily digest push notifications.

At Meta, MemLab has helped make significant improvements in memory optimization. We hope it will do the same for the larger JavaScript community.

Here’s why engineers at Meta are supporting a larger community push to stop introducing any new leap seconds.

In 2020, a security researcher flagged a peculiar bug in Hermes’s Quicksort implementation. Here’s how security teams at Meta fixed the bug.

In August 2020, Instagram launched a set of dynamic and fun text styles followed by animations to give people more choices to express themselves on Stories and Reels. This was the first major update to Stories’ text tools since 2016, and we wanted to share how we approached some obstacles we encountered and what we learned along the way. With all the surprises thrown at us throughout the development of this project, we’ve included our own surprise for our users on iOS: We hid one extra text style for you. ✨ Comment if you find this Easter egg, but don’t ruin the surprise for others!

The promise of cloud gaming is a promise to democratize gaming. Anyone who loves games should be able to enjoy them and share the experience with their friends, no matter where they’re located, and even if they don’t have the latest, most expensive gaming hardware. Facebook launched its cloud gaming platform in 2020 to give anyone on Facebook instant access to native Android and Windows games across every screen and web browser.

Creating the unprecedented access offered by cloud gaming required engineers at Meta to rise to new challenges and develop a growing hardware infrastructure capable of delivering quality game experiences to people all over the world.

But gaming itself is also evolving. From new 3D experiences like AR and VR to what will eventually become the metaverse, people all over the world want to play increasingly immersive games as seamlessly and easily as possible. While it will take a massive effort across the industry to bring the metaverse to fruition, we believe creating the infrastructure and solving the challenges of cloud gaming are pointing us toward solutions for the metaverse as well.

When it comes to cache invalidation, we believe we now have an effective solution to bridge the gap between theory and practice.

Introducing Zelos, a feature- and performance-compatible implementation of ZooKeeper on Delos.

Language packs for Android and iOS enable us to provide a high-quality user experience that’s localized for people around the world.