Added bound option

.github/workflows/build.yml

@@ -33,6 +33,6 @@ jobs:
     - if: ${{ startsWith(matrix.os, 'macos') }}
       run: |
         brew install cpanm && cpanm IPC::Run
-        wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_4.tar.gz
-        tar xf REL_14_4.tar.gz
-        make prove_installcheck PROVE=prove PERL5LIB="postgres-REL_14_4/src/test/perl:/Users/runner/perl5/lib/perl5"
+        wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_1.tar.gz
+        tar xf REL_14_1.tar.gz
+        make prove_installcheck PROVE=prove PERL5LIB=postgres-REL_14_1/src/test/perl

CHANGELOG.md

@@ -1,11 +1,3 @@
-## 0.2.7 (2022-07-31)
-
-- Fixed `unexpected data beyond EOF` error
-
-## 0.2.6 (2022-05-22)
-
-- Improved performance of index creation for Postgres < 12
-
 ## 0.2.5 (2022-02-11)
 
 - Reduced memory usage during index creation

META.json

@@ -2,7 +2,7 @@
 	"name": "vector",
 	"abstract": "Open-source vector similarity search for Postgres",
 	"description": "Supports L2 distance, inner product, and cosine distance",
-	"version": "0.2.7",
+	"version": "0.2.5",
 	"maintainer": [
 		"Andrew Kane <andrew@ankane.org>"
 	],
@@ -20,7 +20,7 @@
 		"vector": {
 			"file": "sql/vector.sql",
 			"docfile": "README.md",
-			"version": "0.2.7",
+			"version": "0.2.5",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.2.7
+EXTVERSION = 0.2.5
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)

README.md

@@ -17,7 +17,7 @@ Supports L2 distance, inner product, and cosine distance
 Compile and install the extension (supports Postgres 9.6+)
 
 ```sh
-git clone --branch v0.2.7 https://github.com/pgvector/pgvector.git
+git clone --branch v0.2.5 https://github.com/pgvector/pgvector.git
 cd pgvector
 make
 make install # may need sudo
@@ -220,14 +220,14 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres).
 You can also build the image manually
 
 ```sh
-git clone --branch v0.2.7 https://github.com/pgvector/pgvector.git
+git clone --branch v0.2.5 https://github.com/pgvector/pgvector.git
 cd pgvector
 docker build -t pgvector .
 ```
 
 ### Homebrew
 
-With Homebrew Postgres, you can use:
+On Mac with Homebrew Postgres, you can use:
 
 ```sh
 brew install pgvector/brew/pgvector

sql/vector--0.2.5--0.2.6.sql

@@ -1,2 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "ALTER EXTENSION vector UPDATE TO '0.2.6'" to load this file. \quit

sql/vector--0.2.6--0.2.7.sql

@@ -1,2 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "ALTER EXTENSION vector UPDATE TO '0.2.7'" to load this file. \quit

src/ivfbuild.c

@@ -112,13 +112,13 @@ SampleRows(IvfflatBuildState * buildstate)
 
 #if PG_VERSION_NUM >= 120000
 		table_index_build_range_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-									 false, true, false, targblock, 1, SampleCallback, (void *) buildstate, NULL);
+									 false, true, true, targblock, 1, SampleCallback, (void *) buildstate, NULL);
 #elif PG_VERSION_NUM >= 110000
 		IndexBuildHeapRangeScan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-								false, true, targblock, 1, SampleCallback, (void *) buildstate, NULL);
+								true, true, targblock, 1, SampleCallback, (void *) buildstate, NULL);
 #else
 		IndexBuildHeapRangeScan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-								false, true, targblock, 1, SampleCallback, (void *) buildstate);
+								true, true, targblock, 1, SampleCallback, (void *) buildstate);
 #endif
 	}
 }
@@ -167,18 +167,18 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 
 #ifdef IVFFLAT_KMEANS_DEBUG
 	buildstate->inertia += minDistance;
-	buildstate->listSums[closestCenter] += minDistance;
-	buildstate->listCounts[closestCenter]++;
 #endif
 
 	/* Create a virtual tuple */
 	ExecClearTuple(slot);
 	slot->tts_values[0] = Int32GetDatum(closestCenter);
 	slot->tts_isnull[0] = false;
-	slot->tts_values[1] = PointerGetDatum(tid);
+	slot->tts_values[1] = Int32GetDatum(ItemPointerGetBlockNumberNoCheck(tid));
 	slot->tts_isnull[1] = false;
-	slot->tts_values[2] = value;
+	slot->tts_values[2] = Int32GetDatum(ItemPointerGetOffsetNumberNoCheck(tid));
 	slot->tts_isnull[2] = false;
+	slot->tts_values[3] = value;
+	slot->tts_isnull[3] = false;
 	ExecStoreVirtualTuple(slot);
 
 	/*
@@ -200,6 +200,8 @@ GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot,
 {
 	Datum		value;
 	bool		isnull;
+	int			tupblk;
+	int			tupoff;
 
 #if PG_VERSION_NUM >= 100000
 	if (tuplesort_gettupleslot(sortstate, true, false, slot, NULL))
@@ -208,11 +210,13 @@ GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot,
 #endif
 	{
 		*list = DatumGetInt32(slot_getattr(slot, 1, &isnull));
-		value = slot_getattr(slot, 3, &isnull);
+		tupblk = DatumGetInt32(slot_getattr(slot, 2, &isnull));
+		tupoff = DatumGetInt32(slot_getattr(slot, 3, &isnull));
+		value = slot_getattr(slot, 4, &isnull);
 
 		/* Form the index tuple */
 		*itup = index_form_tuple(tupdesc, &value, &isnull);
-		(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &isnull)));
+		ItemPointerSet(&(*itup)->t_tid, tupblk, tupoff);
 	}
 	else
 		*list = -1;
@@ -321,16 +325,17 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 
 	/* Create tuple description for sorting */
 #if PG_VERSION_NUM >= 120000
-	buildstate->tupdesc = CreateTemplateTupleDesc(3);
+	buildstate->tupdesc = CreateTemplateTupleDesc(4);
 #else
-	buildstate->tupdesc = CreateTemplateTupleDesc(3, false);
+	buildstate->tupdesc = CreateTemplateTupleDesc(4, false);
 #endif
 	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "blkno", INT4OID, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "offset", INT4OID, -1, 0);
 #if PG_VERSION_NUM >= 110000
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 4, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
 #else
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0]->atttypid, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 4, "vector", RelationGetDescr(index)->attrs[0]->atttypid, -1, 0);
 #endif
 
 #if PG_VERSION_NUM >= 120000
@@ -347,8 +352,6 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 
 #ifdef IVFFLAT_KMEANS_DEBUG
 	buildstate->inertia = 0;
-	buildstate->listSums = palloc0(sizeof(double) * buildstate->lists);
-	buildstate->listCounts = palloc0(sizeof(int) * buildstate->lists);
 #endif
 }
 
@@ -361,11 +364,6 @@ FreeBuildState(IvfflatBuildState * buildstate)
 	pfree(buildstate->centers);
 	pfree(buildstate->listInfo);
 	pfree(buildstate->normvec);
-
-#ifdef IVFFLAT_KMEANS_DEBUG
-	pfree(buildstate->listSums);
-	pfree(buildstate->listCounts);
-#endif
 }
 
 /*
@@ -473,51 +471,6 @@ CreateListPages(Relation index, VectorArray centers, int dimensions,
 	pfree(list);
 }
 
-/*
- * Print k-means metrics
- */
-#ifdef IVFFLAT_KMEANS_DEBUG
-static void
-PrintKmeansMetrics(IvfflatBuildState * buildstate)
-{
-	elog(INFO, "inertia: %.3e", buildstate->inertia);
-
-	/* Calculate Davies-Bouldin index */
-	if (buildstate->lists > 1)
-	{
-		double		db = 0.0;
-
-		/* Calculate average distance */
-		for (int i = 0; i < buildstate->lists; i++)
-		{
-			if (buildstate->listCounts[i] > 0)
-				buildstate->listSums[i] /= buildstate->listCounts[i];
-		}
-
-		for (int i = 0; i < buildstate->lists; i++)
-		{
-			double		max = 0.0;
-			double		distance;
-
-			for (int j = 0; j < buildstate->lists; j++)
-			{
-				if (j == i)
-					continue;
-
-				distance = DatumGetFloat8(FunctionCall2Coll(buildstate->procinfo, buildstate->collation, PointerGetDatum(VectorArrayGet(buildstate->centers, i)), PointerGetDatum(VectorArrayGet(buildstate->centers, j))));
-				distance = (buildstate->listSums[i] + buildstate->listSums[j]) / distance;
-
-				if (distance > max)
-					max = distance;
-			}
-			db += max;
-		}
-		db /= buildstate->lists;
-		elog(INFO, "davies-bouldin: %.3f", db);
-	}
-}
-#endif
-
 /*
  * Create entry pages
  */
@@ -556,7 +509,7 @@ CreateEntryPages(IvfflatBuildState * buildstate, ForkNumber forkNum)
 	tuplesort_performsort(buildstate->sortstate);
 
 #ifdef IVFFLAT_KMEANS_DEBUG
-	PrintKmeansMetrics(buildstate);
+	elog(INFO, "inertia: %.3e", buildstate->inertia);
 #endif
 
 	/* Insert */

src/ivfflat.c

@@ -13,6 +13,7 @@
 #endif
 
 int			ivfflat_probes;
+int			ivfflat_bound;
 static relopt_kind ivfflat_relopt_kind;
 
 /*
@@ -32,6 +33,10 @@ _PG_init(void)
 	DefineCustomIntVariable("ivfflat.probes", "Sets the number of probes",
 							"Valid range is 1..lists.", &ivfflat_probes,
 							1, 1, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
+
+	DefineCustomIntVariable("ivfflat.bound", "Sets the max results from index (experimental)",
+							NULL, &ivfflat_bound,
+							0, 0, INT_MAX, PGC_USERSET, 0, NULL, NULL, NULL);
 }
 
 /*

src/ivfflat.h

@@ -62,8 +62,14 @@
 #define IvfflatBench(name, code) (code)
 #endif
 
+#if PG_VERSION_NUM < 100000
+#define ItemPointerGetBlockNumberNoCheck ItemPointerGetBlockNumber
+#define ItemPointerGetOffsetNumberNoCheck ItemPointerGetOffsetNumber
+#endif
+
 /* Variables */
 extern int	ivfflat_probes;
+extern int	ivfflat_bound;
 
 typedef struct VectorArrayData
 {
@@ -117,8 +123,6 @@ typedef struct IvfflatBuildState
 
 #ifdef IVFFLAT_KMEANS_DEBUG
 	double		inertia;
-	double	   *listSums;
-	int		   *listCounts;
 #endif
 
 	/* Sampling */
@@ -162,7 +166,6 @@ typedef IvfflatListData * IvfflatList;
 
 typedef struct IvfflatScanList
 {
-	pairingheap_node ph_node;
 	BlockNumber startPage;
 	double		distance;
 }			IvfflatScanList;
@@ -184,8 +187,6 @@ typedef struct IvfflatScanOpaqueData
 	FmgrInfo   *normprocinfo;
 	Oid			collation;
 
-	/* Lists */
-	pairingheap *listQueue;
 	IvfflatScanList lists[FLEXIBLE_ARRAY_MEMBER];	/* must come last */
 }			IvfflatScanOpaqueData;
 

src/ivfinsert.c

@@ -53,6 +53,18 @@ FindInsertPage(Relation rel, Datum *values, BlockNumber *insertPage, ListInfo *
 	}
 }
 
+/*
+ * Prepare to insert an index tuple
+ */
+static void
+LoadInsertPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state, BlockNumber insertPage)
+{
+	*buf = ReadBuffer(index, insertPage);
+	LockBuffer(*buf, BUFFER_LOCK_EXCLUSIVE);
+	*state = GenericXLogStart(index);
+	*page = GenericXLogRegisterBuffer(*state, *buf, 0);
+}
+
 /*
  * Insert a tuple into the index
  */
@@ -75,18 +87,11 @@ InsertTuple(Relation rel, IndexTuple itup, Relation heapRel, Datum *values)
 	itemsz = MAXALIGN(IndexTupleSize(itup));
 	Assert(itemsz <= BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(IvfflatPageOpaqueData)));
 
+	LoadInsertPage(rel, &buf, &page, &state, insertPage);
+
 	/* Find a page to insert the item */
-	for (;;)
+	while (PageGetFreeSpace(page) < itemsz)
 	{
-		buf = ReadBuffer(rel, insertPage);
-		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-
-		state = GenericXLogStart(rel);
-		page = GenericXLogRegisterBuffer(state, buf, 0);
-
-		if (PageGetFreeSpace(page) >= itemsz)
-			break;
-
 		insertPage = IvfflatPageGetOpaque(page)->nextblkno;
 
 		if (BlockNumberIsValid(insertPage))
@@ -94,31 +99,15 @@ InsertTuple(Relation rel, IndexTuple itup, Relation heapRel, Datum *values)
 			/* Move to next page */
 			GenericXLogAbort(state);
 			UnlockReleaseBuffer(buf);
+
+			LoadInsertPage(rel, &buf, &page, &state, insertPage);
 		}
 		else
 		{
 			/* Add a new page */
-			Buffer		newbuf = IvfflatNewBuffer(rel, MAIN_FORKNUM);
-			Page		newpage = GenericXLogRegisterBuffer(state, buf, GENERIC_XLOG_FULL_IMAGE);
+			IvfflatAppendPage(rel, &buf, &page, &state, MAIN_FORKNUM);
 
-			insertPage = BufferGetBlockNumber(newbuf);
-
-			/* Update previous buffer */
-			IvfflatPageGetOpaque(page)->nextblkno = insertPage;
-
-			/* Init page */
-			PageInit(newpage, BufferGetPageSize(newbuf), sizeof(IvfflatPageOpaqueData));
-			IvfflatPageGetOpaque(newpage)->nextblkno = InvalidBlockNumber;
-			IvfflatPageGetOpaque(newpage)->page_id = IVFFLAT_PAGE_ID;
-
-			/* Commit */
-			MarkBufferDirty(buf);
-			MarkBufferDirty(newbuf);
-			GenericXLogFinish(state);
-
-			/* Unlock */
-			UnlockReleaseBuffer(buf);
-			UnlockReleaseBuffer(newbuf);
+			insertPage = BufferGetBlockNumber(buf);
 		}
 	}
 

src/ivfscan.c

@@ -1,7 +1,5 @@
 #include "postgres.h"
 
-#include <float.h>
-
 #include "access/relscan.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
@@ -19,12 +17,14 @@
  * Compare list distances
  */
 static int
-CompareLists(const pairingheap_node *a, const pairingheap_node *b, void *arg)
+CompareLists(const void *a, const void *b)
 {
-	if (((const IvfflatScanList *) a)->distance > ((const IvfflatScanList *) b)->distance)
+	double		diff = (((IvfflatScanList *) a)->distance - ((IvfflatScanList *) b)->distance);
+
+	if (diff > 0)
 		return 1;
 
-	if (((const IvfflatScanList *) a)->distance < ((const IvfflatScanList *) b)->distance)
+	if (diff < 0)
 		return -1;
 
 	return 0;
@@ -45,8 +45,6 @@ GetScanLists(IndexScanDesc scan, Datum value)
 	int			listCount = 0;
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 	double		distance;
-	IvfflatScanList *scanlist;
-	double		maxDistance = DBL_MAX;
 
 	/* Search all list pages */
 	while (BlockNumberIsValid(nextblkno))
@@ -64,39 +62,22 @@ GetScanLists(IndexScanDesc scan, Datum value)
 			/* Use procinfo from the index instead of scan key for performance */
 			distance = DatumGetFloat8(FunctionCall2Coll(so->procinfo, so->collation, PointerGetDatum(&list->center), value));
 
-			if (listCount < so->probes)
-			{
-				scanlist = &so->lists[listCount];
-				scanlist->startPage = list->startPage;
-				scanlist->distance = distance;
-				listCount++;
-
-				/* Add to heap */
-				pairingheap_add(so->listQueue, &scanlist->ph_node);
-
-				/* Calculate max distance */
-				if (listCount == so->probes)
-					maxDistance = ((IvfflatScanList *) pairingheap_first(so->listQueue))->distance;
-			}
-			else if (distance < maxDistance)
-			{
-				/* Remove */
-				scanlist = (IvfflatScanList *) pairingheap_remove_first(so->listQueue);
-
-				/* Reuse */
-				scanlist->startPage = list->startPage;
-				scanlist->distance = distance;
-				pairingheap_add(so->listQueue, &scanlist->ph_node);
-
-				/* Update max distance */
-				maxDistance = ((IvfflatScanList *) pairingheap_first(so->listQueue))->distance;
-			}
+			so->lists[listCount].startPage = list->startPage;
+			so->lists[listCount].distance = distance;
+			listCount++;
 		}
 
 		nextblkno = IvfflatPageGetOpaque(cpage)->nextblkno;
 
 		UnlockReleaseBuffer(cbuf);
 	}
+
+	/* Sort by distance */
+	/* TODO Use heap for performance */
+	qsort(so->lists, listCount, sizeof(IvfflatScanList), CompareLists);
+
+	if (so->probes > listCount)
+		so->probes = listCount;
 }
 
 /*
@@ -114,6 +95,7 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	OffsetNumber maxoffno;
 	Datum		datum;
 	bool		isnull;
+	int			i;
 	TupleDesc	tupdesc = RelationGetDescr(scan->indexRelation);
 
 #if PG_VERSION_NUM >= 120000
@@ -129,10 +111,14 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	 */
 	BufferAccessStrategy bas = GetAccessStrategy(BAS_BULKREAD);
 
+	/* Set the max number of results */
+	if (ivfflat_bound > 0)
+		tuplesort_set_bound(so->sortstate, ivfflat_bound);
+
 	/* Search closest probes lists */
-	while (!pairingheap_is_empty(so->listQueue))
+	for (i = 0; i < so->probes; i++)
 	{
-		searchPage = ((IvfflatScanList *) pairingheap_remove_first(so->listQueue))->startPage;
+		searchPage = so->lists[i].startPage;
 
 		/* Search all entry pages for list */
 		while (BlockNumberIsValid(searchPage))
@@ -156,10 +142,12 @@ GetScanItems(IndexScanDesc scan, Datum value)
 				ExecClearTuple(slot);
 				slot->tts_values[0] = FunctionCall2Coll(so->procinfo, so->collation, datum, value);
 				slot->tts_isnull[0] = false;
-				slot->tts_values[1] = PointerGetDatum(&itup->t_tid);
+				slot->tts_values[1] = Int32GetDatum((int) ItemPointerGetBlockNumberNoCheck(&itup->t_tid));
 				slot->tts_isnull[1] = false;
-				slot->tts_values[2] = Int32GetDatum((int) searchPage);
+				slot->tts_values[2] = Int32GetDatum((int) ItemPointerGetOffsetNumberNoCheck(&itup->t_tid));
 				slot->tts_isnull[2] = false;
+				slot->tts_values[3] = Int32GetDatum((int) searchPage);
+				slot->tts_isnull[3] = false;
 				ExecStoreVirtualTuple(slot);
 
 				tuplesort_puttupleslot(so->sortstate, slot);
@@ -187,18 +175,13 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	Oid			sortOperators[] = {Float8LessOperator};
 	Oid			sortCollations[] = {InvalidOid};
 	bool		nullsFirstFlags[] = {false};
-	int			probes = ivfflat_probes;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
 	lists = IvfflatGetLists(scan->indexRelation);
 
-	if (probes > lists)
-		probes = lists;
-
-	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
+	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + lists * sizeof(IvfflatScanList));
 	so->buf = InvalidBuffer;
 	so->first = true;
-	so->probes = probes;
 
 	/* Set support functions */
 	so->procinfo = index_getprocinfo(index, 1, IVFFLAT_DISTANCE_PROC);
@@ -207,13 +190,14 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 
 	/* Create tuple description for sorting */
 #if PG_VERSION_NUM >= 120000
-	so->tupdesc = CreateTemplateTupleDesc(3);
+	so->tupdesc = CreateTemplateTupleDesc(4);
 #else
-	so->tupdesc = CreateTemplateTupleDesc(3, false);
+	so->tupdesc = CreateTemplateTupleDesc(4, false);
 #endif
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
-	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
-	TupleDescInitEntry(so->tupdesc, (AttrNumber) 3, "indexblkno", INT4OID, -1, 0);
+	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "blkno", INT4OID, -1, 0);
+	TupleDescInitEntry(so->tupdesc, (AttrNumber) 3, "offset", INT4OID, -1, 0);
+	TupleDescInitEntry(so->tupdesc, (AttrNumber) 4, "indexblkno", INT4OID, -1, 0);
 
 	/* Prep sort */
 #if PG_VERSION_NUM >= 110000
@@ -228,8 +212,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->slot = MakeSingleTupleTableSlot(so->tupdesc);
 #endif
 
-	so->listQueue = pairingheap_allocate(CompareLists, scan);
-
 	scan->opaque = so;
 
 	return scan;
@@ -249,7 +231,7 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 #endif
 
 	so->first = true;
-	pairingheap_reset(so->listQueue);
+	so->probes = ivfflat_probes;
 
 	if (keys && scan->numberOfKeys > 0)
 		memmove(scan->keyData, keys, scan->numberOfKeys * sizeof(ScanKeyData));
@@ -308,13 +290,14 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 	if (tuplesort_gettupleslot(so->sortstate, true, so->slot, NULL))
 #endif
 	{
-		ItemPointer tid = (ItemPointer) DatumGetPointer(slot_getattr(so->slot, 2, &so->isnull));
-		BlockNumber indexblkno = DatumGetInt32(slot_getattr(so->slot, 3, &so->isnull));
+		BlockNumber blkno = DatumGetInt32(slot_getattr(so->slot, 2, &so->isnull));
+		OffsetNumber offset = DatumGetInt32(slot_getattr(so->slot, 3, &so->isnull));
+		BlockNumber indexblkno = DatumGetInt32(slot_getattr(so->slot, 4, &so->isnull));
 
 #if PG_VERSION_NUM >= 120000
-		scan->xs_heaptid = *tid;
+		ItemPointerSet(&scan->xs_heaptid, blkno, offset);
 #else
-		scan->xs_ctup.t_self = *tid;
+		ItemPointerSet(&scan->xs_ctup.t_self, blkno, offset);
 #endif
 
 		if (BufferIsValid(so->buf))
@@ -347,7 +330,6 @@ ivfflatendscan(IndexScanDesc scan)
 	if (BufferIsValid(so->buf))
 		ReleaseBuffer(so->buf);
 
-	pairingheap_free(so->listQueue);
 	tuplesort_end(so->sortstate);
 
 	pfree(so);

src/ivfutils.c

@@ -135,29 +135,17 @@ IvfflatCommitBuffer(Buffer buf, GenericXLogState *state)
 void
 IvfflatAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state, ForkNumber forkNum)
 {
-	/* Get new buffer */
-	Buffer		newbuf = IvfflatNewBuffer(index, forkNum);
-	Page		newpage = GenericXLogRegisterBuffer(*state, newbuf, GENERIC_XLOG_FULL_IMAGE);
+	Buffer		prevbuf = *buf;
 
-	/* Update the previous buffer */
-	IvfflatPageGetOpaque(*page)->nextblkno = BufferGetBlockNumber(newbuf);
+	/* Get new buffer */
+	*buf = IvfflatNewBuffer(index, forkNum);
+
+	/* Update and commit previous buffer */
+	IvfflatPageGetOpaque(*page)->nextblkno = BufferGetBlockNumber(*buf);
+	IvfflatCommitBuffer(prevbuf, *state);
 
 	/* Init new page */
-	PageInit(newpage, BufferGetPageSize(newbuf), sizeof(IvfflatPageOpaqueData));
-	IvfflatPageGetOpaque(newpage)->nextblkno = InvalidBlockNumber;
-	IvfflatPageGetOpaque(newpage)->page_id = IVFFLAT_PAGE_ID;
-
-	/* Commit */
-	MarkBufferDirty(*buf);
-	MarkBufferDirty(newbuf);
-	GenericXLogFinish(*state);
-
-	/* Unlock */
-	UnlockReleaseBuffer(*buf);
-
-	*state = GenericXLogStart(index);
-	*page = GenericXLogRegisterBuffer(*state, newbuf, GENERIC_XLOG_FULL_IMAGE);
-	*buf = newbuf;
+	IvfflatInitPage(index, buf, page, state);
 }
 
 /*

test/t/001_wal.pl

@@ -7,8 +7,6 @@ use PostgresNode;
 use TestLib;
 use Test::More tests => 31;
 
-my $dim = 32;
-
 my $node_primary;
 my $node_replica;
 
@@ -32,15 +30,13 @@ sub test_index_replay
 	$node_primary->poll_query_until('postgres', $caughtup_query)
 	  or die "Timed out while waiting for replica 1 to catch up";
 
-	my @r = ();
-	for (1 .. $dim) {
-		push(@r, rand());
-	}
-	my $sql = join(",", @r);
+	my $r1 = rand();
+	my $r2 = rand();
+	my $r3 = rand();
 
 	my $queries = qq(
 		SET enable_seqscan = off;
-		SELECT * FROM tst ORDER BY v <-> '[$sql]' LIMIT 10;
+		SELECT * FROM tst ORDER BY v <-> '[$r1,$r2,$r3]' LIMIT 10;
 	);
 
 	# Run test queries and compare their result
@@ -54,10 +50,6 @@ sub test_index_replay
 # Initialize primary node
 $node_primary = get_new_node('primary');
 $node_primary->init(allows_streaming => 1);
-if ($dim > 32) {
-	# TODO use wal_keep_segments for Postgres < 13
-	$node_primary->append_conf('postgresql.conf', qq(wal_keep_size = 1GB));
-}
 $node_primary->start;
 my $backup_name = 'my_backup';
 
@@ -72,9 +64,9 @@ $node_replica->start;
 
 # Create ivfflat index on primary
 $node_primary->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node_primary->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
+$node_primary->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector(3));");
 $node_primary->safe_psql("postgres",
-	"INSERT INTO tst SELECT i % 10, (SELECT array_agg(random()) FROM generate_series(1, $dim)) FROM generate_series(1, 100000) i;"
+	"INSERT INTO tst SELECT i % 10, ARRAY[random(), random(), random()] FROM generate_series(1, 100000) i;"
 );
 $node_primary->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v);");
 
@@ -90,7 +82,7 @@ for my $i (1 .. 10)
 	test_index_replay("vacuum $i");
 	my ($start, $end) = (100001 + ($i - 1) * 10000, 100000 + $i * 10000);
 	$node_primary->safe_psql("postgres",
-		"INSERT INTO tst SELECT i % 10, (SELECT array_agg(random()) FROM generate_series(1, $dim)) FROM generate_series($start, $end) i;"
+		"INSERT INTO tst SELECT i % 10, ARRAY[random(), random(), random()] FROM generate_series($start, $end) i;"
 	);
 	test_index_replay("insert $i");
 }

test/t/003_recall.pl

@@ -2,16 +2,15 @@ use strict;
 use warnings;
 use PostgresNode;
 use TestLib;
-use Test::More tests => 9;
+use Test::More tests => 2;
 
 my $node;
 my @queries = ();
-my @expected;
-my $limit = 20;
+my @expected = ();
 
 sub test_recall
 {
-	my ($probes, $min, $operator) = @_;
+	my ($probes, $min) = @_;
 	my $correct = 0;
 	my $total = 0;
 
@@ -19,7 +18,7 @@ sub test_recall
 		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 $limit;
+			SELECT i FROM tst ORDER BY v <-> '$queries[$i]' LIMIT 10;
 		));
 		my @actual_ids = split("\n", $actual);
 		my %actual_set = map { $_ => 1 } @actual_ids;
@@ -34,7 +33,7 @@ sub test_recall
 		}
 	}
 
-	cmp_ok($correct / $total, ">=", $min, $operator);
+	cmp_ok($correct / $total, ">=", $min);
 }
 
 # Initialize node
@@ -57,32 +56,17 @@ for (1..20) {
 	push(@queries, "[$r1,$r2,$r3]");
 }
 
-# Check each index type
-my @operators = ("<->", "<#>", "<=>");
-
-foreach (@operators) {
-	my $operator = $_;
-
-	# Get exact results
-	@expected = ();
-	foreach (@queries) {
-		my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;");
-		push(@expected, $res);
-	}
-
-	# Add index
-	my $opclass;
-	if ($operator == "<->") {
-		$opclass = "vector_l2_ops";
-	} elsif ($operator == "<#>") {
-		$opclass = "vector_ip_ops";
-	} else {
-		$opclass = "vector_cosine_ops";
-	}
-	$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v $opclass);");
-
-	# Test approximate results
-	test_recall(1, 0.75, $operator);
-	test_recall(10, 0.95, $operator);
-	test_recall(100, 1.0, $operator);
+# Get exact results
+foreach (@queries) {
+	my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v <-> '$_' LIMIT 10;");
+	push(@expected, $res);
 }
+
+# Add index
+$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v);");
+
+# Test approximate results
+test_recall(1, 0.8);
+
+# Test probes
+test_recall(100, 1.0);

test/t/005_query_recall.pl

@@ -1,45 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More tests => 60;
-
-# Initialize node
-my $node = get_new_node('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4 primary key, v vector(3));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 100000) i;"
-);
-
-# Check each index type
-my @operators = ("<->", "<#>", "<=>");
-foreach (@operators) {
-	my $operator = $_;
-
-	# Add index
-	my $opclass;
-	if ($operator == "<->") {
-		$opclass = "vector_l2_ops";
-	} elsif ($operator == "<#>") {
-		$opclass = "vector_ip_ops";
-	} else {
-		$opclass = "vector_cosine_ops";
-	}
-	$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v $opclass);");
-
-	# Test 100% recall
-	for (1..20) {
-		my $i = int(rand() * 100000);
-		my $query = $node->safe_psql("postgres", "SELECT v FROM tst WHERE i = $i;");
-		my $res = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SELECT v FROM tst ORDER BY v <-> '$query' LIMIT 1;
-		));
-		is($res, $query);
-	}
-}

test/t/006_lists.pl

@@ -1,31 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More tests => 3;
-
-# Initialize node
-my $node = get_new_node('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (v vector(3));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT ARRAY[random(), random(), random()] FROM generate_series(1, 100000) i;"
-);
-
-$node->safe_psql("postgres", "CREATE INDEX lists50 ON tst USING ivfflat (v) WITH (lists = 50);");
-$node->safe_psql("postgres", "CREATE INDEX lists100 ON tst USING ivfflat (v) WITH (lists = 100);");
-
-# Test prefers more lists
-my $res = $node->safe_psql("postgres", "EXPLAIN SELECT v FROM tst ORDER BY v <-> '[0.5,0.5,0.5]' LIMIT 10;");
-like($res, qr/lists100/);
-unlike($res, qr/lists50/);
-
-# Test errors with too much memory
-my ($ret, $stdout, $stderr) = $node->psql("postgres",
-	"CREATE INDEX lists10000 ON tst USING ivfflat (v) WITH (lists = 10000);"
-);
-like($stderr, qr/memory required is/);

test/t/007_inserts.pl

@@ -1,33 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More tests => 3;
-
-# Initialize node
-my $node = get_new_node('node');
-$node->init;
-$node->start;
-
-# Create table and index
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (v vector(768));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT (SELECT array_agg(random()) FROM generate_series(1, 768)) FROM generate_series(1, 10000) i;"
-);
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v);");
-
-$node->pgbench(
-	"--no-vacuum --client=5 --transactions=100",
-	0,
-	[qr{actually processed}],
-	[qr{^$}],
-	"concurrent INSERTs",
-	{
-		"007_concurrent" => q(
-			BEGIN;
-			INSERT INTO tst SELECT (SELECT array_agg(random()) FROM generate_series(1, 768)) FROM generate_series(1, 10) i;
-			COMMIT;
-		),
-	}
-);

vector.control

@@ -1,4 +1,4 @@
 comment = 'vector data type and ivfflat access method'
-default_version = '0.2.7'
+default_version = '0.2.5'
 module_pathname = '$libdir/vector'
 relocatable = true