liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-06-06 05:51:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Adjust index scan cost based on selectivity [skip ci]

Browse Source
This commit is contained in:
Andrew Kane
2024-09-22 20:23:56 -07:00
parent 97cf990e0f
commit 61b2ddeb86
2 changed files with 40 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
src/ivfflat.c
View File

@@ -57,6 +57,39 @@ ivfflatbuildphasename(int64 phasenum)
}
}
/*
* Estimate the number of probes needed to get requested tuples
*/
static int
EstimateProbes(PlannerInfo *root, IndexPath *path, int lists)
{
double selectivity = 1;
ListCell *lc;
double tuplesPerList;
/* Cannot estimate without limit */
/* limit_tuples includes offset */
if (root->limit_tuples < 0)
return 0;
/* Get the selectivity of non-index conditions */
foreach(lc, path->indexinfo->indrestrictinfo)
{
RestrictInfo *rinfo = lfirst(lc);
/* Skip DEFAULT_INEQ_SEL since it may be a distance filter */
if (rinfo->norm_selec >= 0 && rinfo->norm_selec <= 1 && rinfo->norm_selec != (Selectivity) DEFAULT_INEQ_SEL)
selectivity *= rinfo->norm_selec;
}
tuplesPerList = path->indexinfo->tuples * selectivity / (double) lists;
if (tuplesPerList == 0)
return lists;
/* No need to cap at this point */
return root->limit_tuples / tuplesPerList;
}
/*
* Estimate the cost of an index scan
*/
@@ -68,6 +101,7 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
{
GenericCosts costs;
int lists;
int probes;
double ratio;
double spc_seq_page_cost;
Relation index;
@@ -89,8 +123,10 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
IvfflatGetMetaPageInfo(index, &lists, NULL);
index_close(index, NoLock);
probes = Max(ivfflat_probes, EstimateProbes(root, path, lists));
/* Get the ratio of lists that we need to visit */
ratio = ((double) ivfflat_probes) / lists;
ratio = ((double) probes) / lists;
if (ratio > 1.0)
ratio = 1.0;

8
test/t/009_ivfflat_filtering.pl
View File

@@ -5,7 +5,7 @@ use PostgreSQL::Test::Utils;
use Test::More;
my $dim = 3;
my $nc = 50;
my $nc = 100;
my $limit = 20;
my $array_sql = join(",", ('random()') x $dim);
@@ -102,15 +102,13 @@ $node->safe_psql("postgres", "CREATE INDEX attribute_idx ON tst (c);");
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Use attribute index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Index Scan on attribute_idx/);
# Test partial index
$node->safe_psql("postgres", "CREATE INDEX partial_idx ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 5) WHERE (c = $c);");
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Use partial index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Index Scan using partial_idx/);
done_testing();