This lecture discusses speculative query execution for complex queries, focusing on bottlenecks and dependencies. It explores the use of oracles to resolve dependencies, parallel processing of speculated results, and minimizing stalls. The instructor presents a proof-of-concept in Spark, addressing the resource allocation problem and performance prediction. The lecture concludes with an overview of modern analytics involving complex workloads and the implementation of speculative execution over a Distributed SQL Engine.
This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.
Watch on Mediaspace