In this session you will learn about what it takes to process joins in distributed databases and then we’ll take a deep dive into how Apache Druid does joins in each of its processing engines. Druid’s native query engine is designed for fast queries and it can do joins, we’ll talk about query design to take advantage of how it works. You will also learn its limits and when a use case is better resolved by the Multi-Stage Query engine (MSQ). We’ll review the current state of MSQ-based joins and when to use broadcast vs sortMerge join algorithms based on how each works and how they use resources.
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