IMPORTANT NOTE: Timing of sessions and room locations are subject to change.
The Sched app allows you to build your schedule but is not a substitute for your event registration. In order to attend OpenSearchCon Europe 2026, please visit our website to register.
This schedule is automatically displayed in Central European Summer Time (UTC+02:00). To see the schedule in your preferred timezone, please select from the drop-down located at the bottom of the menu to the right.
Sign up or log in to add sessions to your schedule and sync them to your phone or calendar.
Aggregation performance in OpenSearch is often limited by JVM execution overhead rather than aggregation logic itself. Most queries process documents at a time (DAAT) through Lucene collectors and rely on deep virtual call chains, which restrict JIT optimizations and waste CPU resources at scale.
This talk explores how Lucene-aware, bulk-oriented execution can significantly speed up aggregation processing. We will show how batching document processing, simplifying collector and doc values access patterns, and reducing virtual method dispatch lead to more JVM-friendly execution paths. We will also touch on how Lucene skip indexes built on sorted doc values can be used to skip or bulk-process ranges of documents during aggregation, reducing unnecessary work when data can be summarized at a higher level.
Using real OpenSearch aggregation pipelines as examples, the session presents early performance results and discusses practical trade-offs when moving from fine-grained per-document logic to bulk processing. The talk is aimed at engineers working on search engines, Lucene-based systems, or JVM performance.
Ankit Jain is a Software Engineer on the Amazon OpenSearch Service team, leading performance and scalability initiatives for search infrastructure. He is an active maintainer and committer for the Apache Lucene and OpenSearch projects, with hands-on experience operating large-scale... Read More →
