liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-14 08:36:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Moved logic for calculating number of samples [skip ci]

Browse Source
This commit is contained in:
Andrew Kane
2026-07-01 12:27:03 -07:00
parent 971b7d7fd6
commit f15a50387f
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/ivfbuild.c
View File

@@ -438,12 +438,6 @@ ComputeCenters(IvfflatBuildState * buildstate)
pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_KMEANS); pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_KMEANS);
/* Target 50 samples per list, with at least 10000 samples */
/* The number of samples has a large effect on index build time */
numSamples = buildstate->lists * 50;
if (numSamples < 10000)
numSamples = 10000;
/* Skip samples for unlogged table */ /* Skip samples for unlogged table */
if (buildstate->heap == NULL) if (buildstate->heap == NULL)
numSamples = 1; numSamples = 1;
@@ -451,6 +445,12 @@ ComputeCenters(IvfflatBuildState * buildstate)
{ {
int64 maxTuples = (int64) RelationGetNumberOfBlocks(buildstate->heap) * MaxHeapTuplesPerPage; int64 maxTuples = (int64) RelationGetNumberOfBlocks(buildstate->heap) * MaxHeapTuplesPerPage;
/* Target 50 samples per list, with at least 10000 samples */
/* The number of samples has a large effect on index build time */
numSamples = buildstate->lists * 50;
if (numSamples < 10000)
numSamples = 10000;
/* Save memory since will not have more than max tuples */ /* Save memory since will not have more than max tuples */
numSamples = Max(Min(numSamples, maxTuples), 1); numSamples = Max(Min(numSamples, maxTuples), 1);
} }