search

qdrant / vector-db-benchmark

Framework for benchmarking vector search engines
https://qdrant.tech/benchmarks/
Apache License 2.0
270 stars 77 forks source link

Allow parallel optimizations in Qdrant after uploading #208

Open timvisee opened 5 days ago

timvisee commented 5 days ago

The max_optimization_threads parameter is currently configured incorrectly after uploading, and this does not allow parallel optimizations.

This PR sets it to a high value so that we do use parallel optimizations as it'll likely result in better results. Note that setting such high limit is fine, because in practice we're still limited by CPU budget. We cannot set it back to null through this API.

On my machine with 24 CPUs I now see 3 parallel optimizations, rather than just 1. The indexing time is more than 2 times quicker.

Am I correct that the benchmark machine we used for the public results does not have more than 8 CPU cores? If we did have more cores, we should probably redo the benchmarks.

filipecosta90 commented 4 days ago

@timvisee have you noticed: https://github.com/qdrant/vector-db-benchmark/pull/163 that solved it, plus included backoff to avoid any errors?