Realtime data analytics at Datadog
You are tasked with building a platform to monitor the performance of 500,000 servers in real-time. How would you design it? What tools would you choose? (Cassandra? Storm? Spark? HBase? ...) What technical challenges would you expect?
As a monitoring company, Datadog receives tens of billions of telemetry data points every day and changes the way operations teams understand and troubleshoot their infrastructure and applications.
Come to this talk to find out how Datadog built its (python-based) low-latency, real-time analytics pipeline.
About the speaker
Alexis Lê-Quôc (@alq) is one of the founding engineers of Datadog, and frequently talks at performance and operations conferences on metrics, monitoring and operations.