Adjust index scan cost based on selectivity [skip ci]

src/ivfflat.c

@@ -17,8 +17,6 @@
 #endif
 
 int			ivfflat_probes;
-int			ivfflat_max_probes;
-bool		ivfflat_streaming;
 static relopt_kind ivfflat_relopt_kind;
 
 /*
@@ -35,14 +33,6 @@ IvfflatInit(void)
 							"Valid range is 1..lists.", &ivfflat_probes,
 							IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
 
-	DefineCustomIntVariable("ivfflat.max_probes", "Sets the max number of probes for iterative scans",
-							NULL, &ivfflat_max_probes,
-							-1, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
-
-	DefineCustomBoolVariable("ivfflat.streaming", "Use streaming mode",
-							 NULL, &ivfflat_streaming,
-							 IVFFLAT_DEFAULT_STREAMING, PGC_USERSET, 0, NULL, NULL, NULL);
-
 	MarkGUCPrefixReserved("ivfflat");
 }
 
@@ -68,7 +58,7 @@ ivfflatbuildphasename(int64 phasenum)
 }
 
 /*
- * Estimate the number of probes for iterative scans
+ * Estimate the number of probes needed to get requested tuples
  */
 static int
 EstimateProbes(PlannerInfo *root, IndexPath *path, int lists)
@@ -92,8 +82,12 @@ EstimateProbes(PlannerInfo *root, IndexPath *path, int lists)
 			selectivity *= rinfo->norm_selec;
 	}
 
-	tuplesPerList = path->indexinfo->tuples / (double) lists;
+	tuplesPerList = path->indexinfo->tuples * selectivity / (double) lists;
-	return root->limit_tuples / (tuplesPerList * selectivity);
+	if (tuplesPerList == 0)
+		return lists;
+
+	/* No need to cap at this point */
+	return root->limit_tuples / tuplesPerList;
 }
 
 /*
@@ -129,14 +123,7 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	IvfflatGetMetaPageInfo(index, &lists, NULL);
 	index_close(index, NoLock);
 
-	probes = ivfflat_probes;
+	probes = Max(ivfflat_probes, EstimateProbes(root, path, lists));
-	if (ivfflat_streaming)
-	{
-		probes = Max(probes, EstimateProbes(root, path, lists));
-
-		if (ivfflat_max_probes != -1)
-			probes = Min(probes, ivfflat_max_probes);
-	}
 
 	/* Get the ratio of lists that we need to visit */
 	ratio = ((double) probes) / lists;

src/ivfflat.h

@@ -43,7 +43,6 @@
 #define IVFFLAT_MIN_LISTS		1
 #define IVFFLAT_MAX_LISTS		32768
 #define IVFFLAT_DEFAULT_PROBES	1
-#define IVFFLAT_DEFAULT_STREAMING	false
 
 /* Build phases */
 /* PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE is 1 */
@@ -81,8 +80,6 @@
 
 /* Variables */
 extern int	ivfflat_probes;
-extern int	ivfflat_max_probes;
-extern bool ivfflat_streaming;
 
 typedef struct VectorArrayData
 {
@@ -250,10 +247,8 @@ typedef struct IvfflatScanOpaqueData
 {
 	const		IvfflatTypeInfo *typeInfo;
 	int			probes;
-	int			maxProbes;
 	int			dimensions;
 	bool		first;
-	Datum		value;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -270,8 +265,6 @@ typedef struct IvfflatScanOpaqueData
 
 	/* Lists */
 	pairingheap *listQueue;
-	BlockNumber *startPages;
-	int			currentIndex;
 	IvfflatScanList lists[FLEXIBLE_ARRAY_MEMBER];	/* must come last */
 }			IvfflatScanOpaqueData;
 

src/ivfscan.c

@@ -65,7 +65,7 @@ GetScanLists(IndexScanDesc scan, Datum value)
 			/* Use procinfo from the index instead of scan key for performance */
 			distance = DatumGetFloat8(so->distfunc(so->procinfo, so->collation, PointerGetDatum(&list->center), value));
 
-			if (listCount < so->maxProbes)
+			if (listCount < so->probes)
 			{
 				IvfflatScanList *scanlist;
 
@@ -102,11 +102,6 @@ GetScanLists(IndexScanDesc scan, Datum value)
 
 		UnlockReleaseBuffer(cbuf);
 	}
-
-	for (int i = listCount - 1; i >= 0; i--)
-		so->startPages[i] = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
-
-	Assert(pairingheap_is_empty(so->listQueue));
 }
 
 /*
@@ -119,14 +114,11 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	TupleDesc	tupdesc = RelationGetDescr(scan->indexRelation);
 	double		tuples = 0;
 	TupleTableSlot *slot = so->vslot;
-	int			batchProbes = 0;
-
-	tuplesort_reset(so->sortstate);
 
 	/* Search closest probes lists */
-	while (so->currentIndex < so->maxProbes && (++batchProbes) <= so->probes)
+	while (!pairingheap_is_empty(so->listQueue))
 	{
-		BlockNumber searchPage = so->startPages[so->currentIndex++];
+		BlockNumber searchPage = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
 
 		/* Search all entry pages for list */
 		while (BlockNumberIsValid(searchPage))
@@ -174,17 +166,13 @@ GetScanItems(IndexScanDesc scan, Datum value)
 		}
 	}
 
-	if (tuples < 100 && !ivfflat_streaming)
+	if (tuples < 100)
 		ereport(DEBUG1,
 				(errmsg("index scan found few tuples"),
 				 errdetail("Index may have been created with little data."),
 				 errhint("Recreate the index and possibly decrease lists.")));
 
 	tuplesort_performsort(so->sortstate);
-
-#if defined(IVFFLAT_MEMORY)
-	elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
-#endif
 }
 
 /*
@@ -252,7 +240,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	int			lists;
 	int			dimensions;
 	int			probes = ivfflat_probes;
-	int			maxProbes;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
 
@@ -262,21 +249,10 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	if (probes > lists)
 		probes = lists;
 
-	if (ivfflat_streaming)
+	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
-	{
-		if (ivfflat_max_probes == -1)
-			maxProbes = lists;
-		else
-			maxProbes = Min(ivfflat_max_probes, lists);
-	}
-	else
-		maxProbes = probes;
-
-	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + maxProbes * sizeof(IvfflatScanList));
 	so->typeInfo = IvfflatGetTypeInfo(index);
 	so->first = true;
 	so->probes = probes;
-	so->maxProbes = maxProbes;
 	so->dimensions = dimensions;
 
 	/* Set support functions */
@@ -304,8 +280,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->bas = GetAccessStrategy(BAS_BULKREAD);
 
 	so->listQueue = pairingheap_allocate(CompareLists, scan);
-	so->startPages = palloc(maxProbes * sizeof(BlockNumber));
-	so->currentIndex = 0;
 
 	scan->opaque = so;
 
@@ -320,9 +294,11 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
+	if (!so->first)
+		tuplesort_reset(so->sortstate);
+
 	so->first = true;
 	pairingheap_reset(so->listQueue);
-	so->currentIndex = 0;
 
 	if (keys && scan->numberOfKeys > 0)
 		memmove(scan->keyData, keys, scan->numberOfKeys * sizeof(ScanKeyData));
@@ -338,8 +314,6 @@ bool
 ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
-	ItemPointer heaptid;
-	bool		isnull;
 
 	/*
 	 * Index can be used to scan backward, but Postgres doesn't support
@@ -367,25 +341,28 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		IvfflatBench("GetScanLists", GetScanLists(scan, value));
 		IvfflatBench("GetScanItems", GetScanItems(scan, value));
 		so->first = false;
-		so->value = value;
 
-		/* TODO clean up if we allocated a new value */
+#if defined(IVFFLAT_MEMORY)
+		elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
+#endif
+
+		/* Clean up if we allocated a new value */
+		if (value != scan->orderByData->sk_argument)
+			pfree(DatumGetPointer(value));
 	}
 
-	while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
+	if (tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
 	{
-		if (so->currentIndex == so->maxProbes)
+		bool		isnull;
-			return false;
+		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
 
-		IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
+		scan->xs_heaptid = *heaptid;
+		scan->xs_recheck = false;
+		scan->xs_recheckorderby = false;
+		return true;
 	}
 
-	heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
+	return false;
-
-	scan->xs_heaptid = *heaptid;
-	scan->xs_recheck = false;
-	scan->xs_recheckorderby = false;
-	return true;
 }
 
 /*
@@ -397,7 +374,6 @@ ivfflatendscan(IndexScanDesc scan)
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
 	pairingheap_free(so->listQueue);
-	pfree(so->startPages);
 	tuplesort_end(so->sortstate);
 	FreeAccessStrategy(so->bas);
 	FreeTupleDesc(so->tupdesc);

test/t/009_ivfflat_filtering.pl

@@ -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 on attribute_idx/);
-like($explain, qr/Index Scan using 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 partial_idx/);
-like($explain, qr/Index Scan using idx/);
 
 done_testing();

test/t/039_ivfflat_streaming.pl

@@ -1,31 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $dim = 3;
-my $array_sql = join(",", ('random()') x $dim);
-
-# Initialize node
-my $node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
-);
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
-
-my $count = $node->safe_psql("postgres", qq(
-	SET enable_seqscan = off;
-	SET ivfflat.probes = 10;
-	SET ivfflat.streaming = on;
-	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
-));
-is($count, 10);
-
-done_testing();

test/t/040_ivfflat_streaming_recall.pl

@@ -1,125 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @expected;
-my $limit = 20;
-my @cs = (100, 1000);
-
-sub test_recall
-{
-	my ($c, $probes, $min, $operator) = @_;
-	my $correct = 0;
-	my $total = 0;
-
-	my $explain = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		SET ivfflat.probes = $probes;
-		SET ivfflat.streaming = on;
-		EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Scan using idx on tst/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SET ivfflat.probes = $probes;
-			SET ivfflat.streaming = on;
-			SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-
-		my @expected_ids = split("\n", $expected[$i]);
-		my %expected_set = map { $_ => 1 } @expected_ids;
-
-		foreach (@actual_ids)
-		{
-			if (exists($expected_set{$_}))
-			{
-				$correct++;
-			}
-		}
-
-		$total += $limit;
-	}
-
-	cmp_ok($correct / $total, ">=", $min, $operator);
-}
-
-# Initialize node
-$node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector(3));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 100000) i;"
-);
-
-# Generate queries
-for (1 .. 20)
-{
-	my $r1 = rand();
-	my $r2 = rand();
-	my $r3 = rand();
-	push(@queries, "[$r1,$r2,$r3]");
-}
-
-# Check each index type
-my @operators = ("<->", "<=>");
-my @opclasses = ("vector_l2_ops", "vector_cosine_ops");
-
-for my $i (0 .. $#operators)
-{
-	my $operator = $operators[$i];
-	my $opclass = $opclasses[$i];
-
-	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v $opclass);");
-
-	foreach (@cs)
-	{
-		my $c = $_;
-
-		# Get exact results
-		@expected = ();
-		foreach (@queries)
-		{
-			my $res = $node->safe_psql("postgres", qq(
-				SET enable_indexscan = off;
-				WITH top AS (
-					SELECT v $operator '$_' AS distance FROM tst WHERE i % $c = 0 ORDER BY distance LIMIT $limit
-				)
-				SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
-			));
-			push(@expected, $res);
-		}
-
-		if ($c == 100)
-		{
-			test_recall($c, 1, 0.58, $operator);
-			test_recall($c, 10, 0.98, $operator);
-		}
-		else
-		{
-			if ($operator eq "<->")
-			{
-				test_recall($c, 1, 0.80, $operator);
-			}
-			else
-			{
-				test_recall($c, 1, 0.88, $operator);
-			}
-		}
-	}
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-}
-
-done_testing();