In Apache Druid, after ingesting some data and publishing a segment to Deep Storage, it is the Load, Drop rule a Kill process behavior that govern the caching of segments on historicals across multiple tiers. In this session we review the overall process that each segment undergoes and how to control it. We’ll talk about how to deal with hot and cold tiers and provide details on how the coordinator’s algorithm manages overall segments’ life cycle.
Keynote: Powering Event-Driven Data with Apache Druid
The distinction between OLTP and OLAP is becoming less relevant as data architectures shift toward entities and events. In this session, we’ll delve into how Apache Druid’s event-first approach synthesizes...
Watch nowClosing Keynote: Charting the Future of Druid
What lies ahead for Apache Druid? Join us as we explore the evolving landscape of Druid’s query and storage engines, and how they are positioned to address the biggest challenges in event data for the future. Speaker: Gian...
Watch nowSalesforce: Tracing Service Dependencies at Scale with Druid and Flink
At Salesforce, we manage approximately 300 million distributed spans to infer service dependencies. We have successfully utilized a combination of Druid and Flink to handle this scale with high availability....
Watch now