lance
lance copied to clipboard
implement deletion vector handling in index scan
closes #916
Implement deletion vector handling in PQIndex
, where all vector index are stored.
TODO:
- [ ] add tests
- [ ] add TODO comments in places we could have potential performance gains
TL;DR:
- Seems to have very little latency impact
- We should also test query throughput than just latency.
after picking in #960 the difference of index scan performance pre/post this PR is negligible. Any perf impact introduced is smaller in magnitude than noise.
The impact maybe become more pronunciated in a environment where IO latency is high, say, EC2 instance with EBS, which is a remote disk.
Since this change introduces more IO, I'd hypothesis that there could be a hit to the query throughput
Seems to have very little latency impact
is this for scanning or the ANN search?
is this for scanning or the ANN search? ann search. The bench mark uses
nearest
.