liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-10 06:40:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Improved HNSW vacuuming

Browse Source
This commit is contained in:
Andrew Kane
2023-08-13 15:53:07 -07:00
parent 304e262a41
commit 6fc7d06313
2 changed files with 20 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/hnswutils.c
View File

@@ -566,7 +566,13 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node)); pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node)); pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
wlen++; /*
* Do not count elements being deleted towards ef when vacuuming. It
* would be ideal to do this for inserts as well, but this could
* affect insert performance.
*/
if (skipElement == NULL || list_length(hc->element->heaptids) != 0)
wlen++;
} }
while (!pairingheap_is_empty(C)) while (!pairingheap_is_empty(C))
@@ -625,12 +631,19 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
pairingheap_add(C, &(CreatePairingHeapNode(ec)->ph_node)); pairingheap_add(C, &(CreatePairingHeapNode(ec)->ph_node));
pairingheap_add(W, &(CreatePairingHeapNode(ec)->ph_node)); pairingheap_add(W, &(CreatePairingHeapNode(ec)->ph_node));
/* TODO Possibly don't count elements being deleted in wlen */ /*
wlen++; * Do not count elements being deleted towards ef when
* vacuuming. It would be ideal to do this for inserts as
* well, but this could affect insert performance.
*/
if (skipElement == NULL || list_length(e->element->heaptids) != 0)
{
wlen++;
/* No need to decrement wlen */ /* No need to decrement wlen */
if (wlen > ef) if (wlen > ef)
pairingheap_remove_first(W); pairingheap_remove_first(W);
}
} }
} }
} }

2
test/t/016_hnsw_vacuum_recall.pl
View File

@@ -61,7 +61,7 @@ $node->safe_psql("postgres",
); );
# Add index # Add index
$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops) WITH (m = 4);"); $node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops) WITH (m = 4, ef_construction = 8);");
# Delete data # Delete data
$node->safe_psql("postgres", "DELETE FROM tst WHERE i > 2500;"); $node->safe_psql("postgres", "DELETE FROM tst WHERE i > 2500;");