After updating to a new Redis version the Cache team saw a regression. This goes over the investigation and our conclusions.

Recently, Twitter Engineering embarked on an effort to migrate elements of the Twitter stack to the cloud. This article is the first in a series describing that journey.

Pattern to keep code clean and to the point for the success path

A Manhattan cluster can contain one or more datasets. Manhattan provides a data model where each record contains a partition key (PKey) and a local key (LKey) mapping to a value.

See why Twitter decided to adopt Kafka as its PubSub system and the challenges we faced during adoption.

Learn about the infrastructure that enables developers at Twitter to manage application configurations, perform experiments, and release changes safely and efficiently.

Apache ZooKeeper is a system for distributed coordination. ZooKeeper is used at Twitter as the source of truth for storing critical metadata. I

Silhouette, a new technique for discovering the identity of logged-in users to online platforms, was recently published. This is an account of the action we took to address this.

The blog details how Cortex is working toward developing models, related tooling, and infrastructure with the objective of making embeddings a first-class citizen within Twitter's ML platform

Load Testing at Twitter Scale with Iago V2