Revert "Free tuple"

This reverts commit 466ec1ac46.

CHANGELOG.md

@@ -1,13 +1,13 @@
 ## 0.5.0 (2023-08-28)
 
 - Added HNSW index type
-- Added support for parallel index builds
+- Added support for parallel index builds for IVFFlat
 - Added `l1_distance` function
 - Added element-wise multiplication for vectors
 - Added `sum` aggregate
 - Improved performance of distance functions
 - Fixed out of range results for cosine distance
-- Fixed results for NULL and NaN distances
+- Fixed results for NULL and NaN distances for IVFFlat
 
 ## 0.4.4 (2023-06-12)
 

README.md

@@ -162,7 +162,7 @@ You can add an index to use approximate nearest neighbor search, which trades so
 Supported index types are:
 
 - [IVFFlat](#ivfflat)
-- [HNSW](#hnsw) - *added in 0.5.0*
+- [HNSW](#hnsw) - added in 0.5.0
 
 ## IVFFlat
 
@@ -282,8 +282,8 @@ SELECT phase, tuples_done, tuples_total FROM pg_stat_progress_create_index;
 The phases are:
 
 1. `initializing`
-2. `performing k-means` (IVFFlat only)
+2. `performing k-means` - IVFFlat only
-3. `assigning tuples` (IVFFlat only)
+3. `assigning tuples` - IVFFlat only
 4. `loading tuples`
 
 Note: `tuples_done` and `tuples_total` are only populated during the `loading tuples` phase

src/hnsw.c

@@ -155,6 +155,15 @@ hnswvalidate(Oid opclassoid)
 	return true;
 }
 
+/*
+ * Checks if index-only scan is supported
+ */
+static bool
+hnswcanreturn(Relation indexRelation, int attno)
+{
+	return attno == 1 && !OidIsValid(index_getprocid(indexRelation, 1, HNSW_NORM_PROC));
+}
+
 /*
  * Define index handler
  *
@@ -196,7 +205,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	amroutine->aminsert = hnswinsert;
 	amroutine->ambulkdelete = hnswbulkdelete;
 	amroutine->amvacuumcleanup = hnswvacuumcleanup;
-	amroutine->amcanreturn = NULL;	/* tuple not included in heapsort */
+	amroutine->amcanreturn = hnswcanreturn;
 	amroutine->amcostestimate = hnswcostestimate;
 	amroutine->amoptions = hnswoptions;
 	amroutine->amproperty = NULL;	/* TODO AMPROP_DISTANCE_ORDERABLE */

src/hnsw.h

@@ -266,7 +266,7 @@ Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
 void		HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state);
 void		HnswInit(void);
-List	   *HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, bool inserting, HnswElement skipElement);
+List	   *HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, HnswElement skipElement);
 HnswElement HnswGetEntryPoint(Relation index);
 HnswElement HnswInitElement(ItemPointer tid, int m, double ml, int maxLevel);
 void		HnswFreeElement(HnswElement element);

src/hnswscan.c

@@ -17,6 +17,7 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	Relation	index = scan->indexRelation;
 	FmgrInfo   *procinfo = so->procinfo;
 	Oid			collation = so->collation;
+	bool		loadVec = scan->xs_want_itup;
 	List	   *ep;
 	List	   *w;
 	HnswElement entryPoint = HnswGetEntryPoint(index);
@@ -24,15 +25,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, false));
+	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, loadVec));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, false, NULL);
+		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, loadVec, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, false, NULL);
+	return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, loadVec, NULL);
 }
 
 /*
@@ -83,6 +84,9 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 
 	scan->opaque = so;
 
+	/* OK to always set since cheap */
+	scan->xs_itupdesc = RelationGetDescr(index);
+
 	return scan;
 }
 
@@ -165,7 +169,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		ItemPointer tid;
 		BlockNumber indexblkno;
 
-		/* Move to next element if no valid heap tids */
+		/* Move to next element if no valid heap TIDs */
 		if (list_length(hc->element->heaptids) == 0)
 		{
 			so->w = list_delete_last(so->w);
@@ -177,6 +181,15 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 
 		hc->element->heaptids = list_delete_last(hc->element->heaptids);
 
+		if (scan->xs_want_itup)
+		{
+			Datum		value = PointerGetDatum(hc->element->vec);
+			bool		isnull = false;
+
+			scan->xs_itup = index_form_tuple(scan->xs_itupdesc, &value, &isnull);
+			scan->xs_itup->t_tid = *tid;
+		}
+
 		MemoryContextSwitchTo(oldCtx);
 
 #if PG_VERSION_NUM >= 120000
@@ -185,6 +198,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		scan->xs_ctup.t_self = *tid;
 #endif
 
+		/* Unpin buffer */
 		if (BufferIsValid(so->buf))
 			ReleaseBuffer(so->buf);
 

src/hnswutils.c

@@ -543,7 +543,7 @@ AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, bool inserting, HnswElement skipElement)
+HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, HnswElement skipElement)
 {
 	ListCell   *lc2;
 
@@ -619,7 +619,7 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 				if (index == NULL)
 					eDistance = GetCandidateDistance(e, q, procinfo, collation);
 				else
-					HnswLoadElement(e->element, &eDistance, &q, index, procinfo, collation, inserting);
+					HnswLoadElement(e->element, &eDistance, &q, index, procinfo, collation, loadVec);
 
 				Assert(!e->element->deleted);
 

src/ivfbuild.c

@@ -10,8 +10,8 @@
 #include "ivfflat.h"
 #include "miscadmin.h"
 #include "storage/bufmgr.h"
-#include "utils/memutils.h"
 #include "tcop/tcopprot.h"
+#include "utils/memutils.h"
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_progress.h"

src/ivfscan.c

@@ -343,6 +343,7 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		scan->xs_ctup.t_self = *tid;
 #endif
 
+		/* Unpin buffer */
 		if (BufferIsValid(so->buf))
 			ReleaseBuffer(so->buf);
 

src/vector.c

@@ -695,6 +695,8 @@ vector_spherical_distance(PG_FUNCTION_ARGS)
 {
 	Vector	   *a = PG_GETARG_VECTOR_P(0);
 	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	float	   *ax = a->x;
+	float	   *bx = b->x;
 	float		dp = 0.0;
 	double		distance;
 
@@ -702,7 +704,7 @@ vector_spherical_distance(PG_FUNCTION_ARGS)
 
 	/* Auto-vectorized */
 	for (int i = 0; i < a->dim; i++)
-		dp += a->x[i] * b->x[i];
+		dp += ax[i] * bx[i];
 
 	distance = (double) dp;
 

test/expected/functions.out

@@ -106,6 +106,12 @@ SELECT cosine_distance('[1,1]', '[1,1]');
                0
 (1 row)
 
+SELECT cosine_distance('[1,0]', '[0,2]');
+ cosine_distance 
+-----------------
+               1
+(1 row)
+
 SELECT cosine_distance('[1,1]', '[-1,-1]');
  cosine_distance 
 -----------------

test/sql/functions.sql

@@ -25,6 +25,7 @@ SELECT inner_product('[3e38]', '[3e38]');
 SELECT cosine_distance('[1,2]', '[2,4]');
 SELECT cosine_distance('[1,2]', '[0,0]');
 SELECT cosine_distance('[1,1]', '[1,1]');
+SELECT cosine_distance('[1,0]', '[0,2]');
 SELECT cosine_distance('[1,1]', '[-1,-1]');
 SELECT cosine_distance('[1,2]', '[3]');
 SELECT cosine_distance('[1,1]', '[1.1,1.1]');

test/t/001_ivfflat_wal.pl

@@ -19,8 +19,6 @@ sub test_index_replay
 
 	# Wait for replica to catch up
 	my $applname = $node_replica->name;
-
-	my $server_version_num = $node_primary->safe_psql("postgres", "SHOW server_version_num");
 	my $caughtup_query = "SELECT pg_current_wal_lsn() <= replay_lsn FROM pg_stat_replication WHERE application_name = '$applname';";
 	$node_primary->poll_query_until('postgres', $caughtup_query)
 	  or die "Timed out while waiting for replica 1 to catch up";

test/t/003_ivfflat_build_recall.pl

@@ -94,7 +94,7 @@ for my $i (0 .. $#operators)
 	# Test approximate results
 	if ($operator ne "<#>")
 	{
-		# TODO fix test
+		# TODO Fix test (uniform random vectors all have similar inner product)
 		test_recall(1, 0.71, $operator);
 		test_recall(10, 0.95, $operator);
 	}
@@ -115,7 +115,7 @@ for my $i (0 .. $#operators)
 	# Test approximate results
 	if ($operator ne "<#>")
 	{
-		# TODO fix test
+		# TODO Fix test (uniform random vectors all have similar inner product)
 		test_recall(1, 0.71, $operator);
 		test_recall(10, 0.95, $operator);
 	}

test/t/010_hnsw_wal.pl

@@ -19,8 +19,6 @@ sub test_index_replay
 
 	# Wait for replica to catch up
 	my $applname = $node_replica->name;
-
-	my $server_version_num = $node_primary->safe_psql("postgres", "SHOW server_version_num");
 	my $caughtup_query = "SELECT pg_current_wal_lsn() <= replay_lsn FROM pg_stat_replication WHERE application_name = '$applname';";
 	$node_primary->poll_query_until('postgres', $caughtup_query)
 	  or die "Timed out while waiting for replica 1 to catch up";

test/t/016_hnsw_vacuum_recall.pl

@@ -89,7 +89,7 @@ foreach (@queries)
 test_recall(0.20, $limit, "before vacuum");
 test_recall(0.95, 100, "before vacuum");
 
-# TODO test concurrent inserts with vacuum
+# TODO Test concurrent inserts with vacuum
 $node->safe_psql("postgres", "VACUUM tst;");
 
 test_recall(0.95, $limit, "after vacuum");

test/t/017_ivfflat_insert_recall.pl

@@ -0,0 +1,117 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $node;
+my @queries = ();
+my @expected;
+my $limit = 20;
+
+sub test_recall
+{
+	my ($probes, $min, $operator) = @_;
+	my $correct = 0;
+	my $total = 0;
+
+	my $explain = $node->safe_psql("postgres", qq(
+		SET enable_seqscan = off;
+		SET ivfflat.probes = $probes;
+		EXPLAIN ANALYZE SELECT i FROM tst 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;
+			SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
+		));
+		my @actual_ids = split("\n", $actual);
+		my %actual_set = map { $_ => 1 } @actual_ids;
+
+		my @expected_ids = split("\n", $expected[$i]);
+
+		foreach (@expected_ids)
+		{
+			if (exists($actual_set{$_}))
+			{
+				$correct++;
+			}
+			$total++;
+		}
+	}
+
+	cmp_ok($correct / $total, ">=", $min, $operator);
+}
+
+# Initialize node
+$node = get_new_node('node');
+$node->init;
+$node->start;
+
+# Create table
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i serial, v vector(3));");
+
+# 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_ip_ops", "vector_cosine_ops");
+
+for my $i (0 .. $#operators)
+{
+	my $operator = $operators[$i];
+	my $opclass = $opclasses[$i];
+
+	# Add index
+	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v $opclass);");
+
+	# Use concurrent inserts
+	$node->pgbench(
+		"--no-vacuum --client=10 --transactions=1000",
+		0,
+		[qr{actually processed}],
+		[qr{^$}],
+		"concurrent INSERTs",
+		{
+			"017_ivfflat_insert_recall_$opclass" => "INSERT INTO tst (v) SELECT ARRAY[random(), random(), random()] FROM generate_series(1, 10) i;"
+		}
+	);
+
+	# Get exact results
+	@expected = ();
+	foreach (@queries)
+	{
+		my $res = $node->safe_psql("postgres", qq(
+			SET enable_indexscan = off;
+			SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;
+		));
+		push(@expected, $res);
+	}
+
+	# Test approximate results
+	if ($operator ne "<#>")
+	{
+		# TODO Fix test (uniform random vectors all have similar inner product)
+		test_recall(1, 0.71, $operator);
+		test_recall(10, 0.95, $operator);
+	}
+	# Account for equal distances
+	test_recall(100, 0.9925, $operator);
+
+	$node->safe_psql("postgres", "DROP INDEX idx;");
+	$node->safe_psql("postgres", "TRUNCATE tst;");
+}
+
+done_testing();