Skip to content
Merged
Changes from 4 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -122,3 +122,13 @@ You can check the current value in `KiB` using `lsblk -o NAME,RA,MOUNTPOINT,TYPE
::::


## Use Direct IO when the vector data does not fit in RAM
```{applies_to}
stack: preview 9.1
serverless: unavailable
```
If your indices are of type `bbq_hnsw` and your nodes don't have enough off-heap RAM to store all vector data in memory, you may see very high search latencies. Vector data includes the HNSW graph, quantized vectors, and raw float32 vectors.

In these scenarios, direct IO can significantly improve query latency. Enable it by setting `vector.rescoring.directio=true` JVM option on all vector search nodes in your cluster.

Only use this option if you're experiencing significant query latencies. Otherwise, enabling direct IO may increase your query latencies.
Loading