[
https://issues.apache.org/jira/browse/LUCENE-10318?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17581016#comment-17581016
]
Julie Tibshirani edited comment on LUCENE-10318 at 8/17/22 8:51 PM:
--------------------------------------------------------------------
[~jmazanec15] it's great you're interested in looking into this! I don't have
any prototype or experiments, you're welcome to pick it up.
Removing nodes and repairing the graph could be a nice direction. But for now
we can keep things simple and assume there's a segment without deletes. If
that's looking good and shows a nice improvement in index/ merge benchmarks,
then we can handle deletes in a follow-up.
Edit: Oops, I didn't refresh the page so I missed Mayya's comment. It looks
like we're in agreement!
was (Author: julietibs):
[~jmazanec15] it's great you're interested in looking into this! I don't have
any prototype or experiments, you're welcome to pick it up.
Removing nodes and repairing the graph could be a nice direction. But for now
we can keep things simple and assume there's a segment without deletes. If
that's looking good and shows a nice improvement in index/ merge benchmarks,
then we can handle deletes in a follow-up.
> Reuse HNSW graphs when merging segments?
> ----------------------------------------
>
> Key: LUCENE-10318
> URL: https://issues.apache.org/jira/browse/LUCENE-10318
> Project: Lucene - Core
> Issue Type: Improvement
> Reporter: Julie Tibshirani
> Priority: Major
>
> Currently when merging segments, the HNSW vectors format rebuilds the entire
> graph from scratch. In general, building these graphs is very expensive, and
> it'd be nice to optimize it in any way we can. I was wondering if during
> merge, we could choose the largest segment with no deletes, and load its HNSW
> graph into heap. Then we'd add vectors from the other segments to this graph,
> through the normal build process. This could cut down on the number of
> operations we need to perform when building the graph.
> This is just an early idea, I haven't run experiments to see if it would
> help. I'd guess that whether it helps would also depend on details of the
> MergePolicy.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
