msokolov commented on PR #14097: URL: https://github.com/apache/lucene/pull/14097#issuecomment-2568337179
One interesting detail that came out while testing with the merge policy is that indexing actually becomes *faster* with this change since the additional work we do in the BP reordering is outweighed by the savings we have performing HNSW searches during merging. Indeed the savings can be dramatic: |condition| recall| latency (ms)| nDoc| topK| fanout| maxConn| beamWidth| quantized| index s| index docs/s| force merge s| num segments| index size (MB)| vec disk (MB)| vec RAM (MB)| |---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---| |no BP| 0.794 | 0.996 | 2000000 | 10 | 64 | 64 | 250 | 7 bits | 1073.04 | 1863.87 | 271.95 | 1 | 2607.89 | 2441.406 | 488.281 |with BP|0.797 | 0.887 | 2000000 | 10 | 64 | 64 | 250 | 7 bits | 987.76 | 2024.78 | 143.48 | 1 | 2558.39 | 2441.406 | 488.281 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
