As a company, Datadog ingests trillions of data points per day. Kafka is the messaging persistence layer underlying many of our high-traffic services. Consequently, our Kafka usage is quite high: double-digit gigabytes per second bandwidth and the need for petabytes of high performance storage, even for relatively short retention windows.

Learn how Mercado Libre acts more quickly, strategically, and proactively thanks to Datadog’s centralized platform and context-rich alerting.Mercado Libre hosts the largest online commerce and payments ecosystem in Latin America, which means thousands of dollars can be lost if some of their critical applications stop working for even 1 minute. Senior Technical Manager Juliano Martins and software expert Marcelo Quadros share a few reasons why they chose Datadog as their observability platform of choice for their AWS environment: the power of our infrastructure monitoring solution, extensive range of integrations, strong reputation in the market, and more.

Bad planning methods can damage team morale and prevent teams from improving the systems they maintain. In this talk, Sam Handler from Shopify explains how his attempts to fix poor infrastructure planning processes through Agile methods failed. Drawing from this experience, he offers several principles that can help infrastructure teams improve the way they work.

Thiyagarajan Anandan, Uber Freight, shares how he and his team have created a center of excellence for monitoring and DevOps culture. Uber Freight, a division of Uber, delivers an end-to-end enterprise suite of Relational Logistics to advance supply chains and move the world’s goods. With more than 1,000 shippers across $18B freight under management (FUM), it’s critical for Uber Freight to provide a 99.99% uptime for its shippers and customers. Since migrating to the Datadog platform, Uber Freight for the first time has unlocked the full breadth and depth of their systems, thereby significantly decreasing MTTR/MTTD and delivering an improved customer experience.

Datadog, the observability platform used by thousands of companies, runs on dozens of self-managed Kubernetes clusters in a multi-cloud environment, adding up to tens of thousands of nodes, or hundreds of thousands of pods. This infrastructure is used by a wide variety of engineering teams at Datadog, with different feature and capacity needs.

The extended Berkeley Packet Filter, eBPF has resulted in an ecosystem of new tooling that allows running programs in the linux kernel without loading kernel modules. eBPF seeks to do this safety within a secure sandbox environment and has been a boon to observability and security.

Discover how Datadog APM & Continuous Profiler can help you identify the most resource-intensive and time-consuming lines of code. Through always-on production code profiling and thread-level visibility, you can reduce application latency, optimize your code's CPU and memory consumption, and minimize cloud costs.

Hear from a Statsig software engineer how Datadog’s platform helps them better manage their increasing data volume and improve the experiences of their global end users.

Datadog is constantly elevating the approach to cloud monitoring and security. This Month in Datadog updates you on our newest product features, announcements, resources, and events. This month, we put the Spotlight on a trio of serverless monitoring releases..

Datadog Cloud Cost Management brings fine-grained cost data that’s scoped to teams and services onto the same monitoring platform engineers already use, so costs can be understood alongside observability data and made actionable.