mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 03:57:34 +08:00
Compare commits
1 Commits
hnsw-less-
...
index-zero
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
63982fef41 |
@@ -1,9 +1,6 @@
|
||||
## 0.5.2 (unreleased)
|
||||
|
||||
- Improved performance of HNSW
|
||||
- Added support for on-disk parallel index builds for HNSW
|
||||
- Reduced WAL generation for HNSW index builds
|
||||
- Fixed `invalid memory alloc request size` error with HNSW index build
|
||||
|
||||
## 0.5.1 (2023-10-10)
|
||||
|
||||
|
||||
14
README.md
14
README.md
@@ -10,7 +10,7 @@ Store your vectors with the rest of your data. Supports:
|
||||
|
||||
Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recovery, JOINs, and all of the other [great features](https://www.postgresql.org/about/) of Postgres
|
||||
|
||||
[](https://github.com/pgvector/pgvector/actions)
|
||||
[](https://github.com/pgvector/pgvector/actions)
|
||||
|
||||
## Installation
|
||||
|
||||
@@ -379,7 +379,7 @@ Language | Libraries / Examples
|
||||
--- | ---
|
||||
C | [pgvector-c](https://github.com/pgvector/pgvector-c)
|
||||
C++ | [pgvector-cpp](https://github.com/pgvector/pgvector-cpp)
|
||||
C#, F#, Visual Basic | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
|
||||
C# | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
|
||||
Crystal | [pgvector-crystal](https://github.com/pgvector/pgvector-crystal)
|
||||
Dart | [pgvector-dart](https://github.com/pgvector/pgvector-dart)
|
||||
Elixir | [pgvector-elixir](https://github.com/pgvector/pgvector-elixir)
|
||||
@@ -388,10 +388,8 @@ Haskell | [pgvector-haskell](https://github.com/pgvector/pgvector-haskell)
|
||||
Java, Kotlin, Groovy, Scala | [pgvector-java](https://github.com/pgvector/pgvector-java)
|
||||
JavaScript, TypeScript | [pgvector-node](https://github.com/pgvector/pgvector-node)
|
||||
Julia | [pgvector-julia](https://github.com/pgvector/pgvector-julia)
|
||||
Lisp | [pgvector-lisp](https://github.com/pgvector/pgvector-lisp)
|
||||
Lua | [pgvector-lua](https://github.com/pgvector/pgvector-lua)
|
||||
Nim | [pgvector-nim](https://github.com/pgvector/pgvector-nim)
|
||||
OCaml | [pgvector-ocaml](https://github.com/pgvector/pgvector-ocaml)
|
||||
Perl | [pgvector-perl](https://github.com/pgvector/pgvector-perl)
|
||||
PHP | [pgvector-php](https://github.com/pgvector/pgvector-php)
|
||||
Python | [pgvector-python](https://github.com/pgvector/pgvector-python)
|
||||
@@ -464,14 +462,6 @@ and query with:
|
||||
SELECT * FROM items ORDER BY embedding::vector(3) <-> '[3,1,2]' LIMIT 5;
|
||||
```
|
||||
|
||||
#### Do indexes need to fit into memory?
|
||||
|
||||
No, but like other index types, you’ll likely see better performance if they do. You can get the size of an index with:
|
||||
|
||||
```sql
|
||||
SELECT pg_size_pretty(pg_relation_size('index_name'));
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
#### Why isn’t a query using an index?
|
||||
|
||||
40
src/hnsw.h
40
src/hnsw.h
@@ -104,7 +104,6 @@ typedef struct HnswElementData
|
||||
List *heaptids;
|
||||
uint8 level;
|
||||
uint8 deleted;
|
||||
uint32 hash;
|
||||
HnswNeighborArray *neighbors;
|
||||
BlockNumber blkno;
|
||||
OffsetNumber offno;
|
||||
@@ -304,7 +303,7 @@ typedef struct HnswVacuumState
|
||||
Oid collation;
|
||||
|
||||
/* Variables */
|
||||
struct tidhash_hash *deleted;
|
||||
HTAB *deleted;
|
||||
BufferAccessStrategy bas;
|
||||
HnswNeighborTuple ntup;
|
||||
HnswElementData highestPoint;
|
||||
@@ -317,9 +316,11 @@ typedef struct HnswVacuumState
|
||||
int HnswGetM(Relation index);
|
||||
int HnswGetEfConstruction(Relation index);
|
||||
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
|
||||
bool HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
|
||||
void HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
|
||||
void HnswCommitBuffer(Buffer buf, GenericXLogState *state);
|
||||
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, int m, bool inserting, HnswElement skipElement);
|
||||
HnswElement HnswGetEntryPoint(Relation index);
|
||||
@@ -330,12 +331,12 @@ HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
|
||||
void HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
|
||||
HnswElement HnswFindDuplicate(HnswElement e);
|
||||
HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
|
||||
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
|
||||
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum);
|
||||
void HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m);
|
||||
void HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
|
||||
void HnswInitNeighbors(HnswElement element, int m);
|
||||
bool HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building);
|
||||
void HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
|
||||
bool HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel);
|
||||
void HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting);
|
||||
void HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
|
||||
void HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
|
||||
void HnswSetElementTuple(HnswElementTuple etup, HnswElement element);
|
||||
@@ -359,31 +360,4 @@ void hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys,
|
||||
bool hnswgettuple(IndexScanDesc scan, ScanDirection dir);
|
||||
void hnswendscan(IndexScanDesc scan);
|
||||
|
||||
/* Hash tables */
|
||||
typedef struct TidHashEntry
|
||||
{
|
||||
ItemPointerData tid;
|
||||
char status;
|
||||
} TidHashEntry;
|
||||
|
||||
#define SH_PREFIX tidhash
|
||||
#define SH_ELEMENT_TYPE TidHashEntry
|
||||
#define SH_KEY_TYPE ItemPointerData
|
||||
#define SH_SCOPE extern
|
||||
#define SH_DECLARE
|
||||
#include "lib/simplehash.h"
|
||||
|
||||
typedef struct PointerHashEntry
|
||||
{
|
||||
uintptr_t ptr;
|
||||
char status;
|
||||
} PointerHashEntry;
|
||||
|
||||
#define SH_PREFIX pointerhash
|
||||
#define SH_ELEMENT_TYPE PointerHashEntry
|
||||
#define SH_KEY_TYPE uintptr_t
|
||||
#define SH_SCOPE extern
|
||||
#define SH_DECLARE
|
||||
#include "lib/simplehash.h"
|
||||
|
||||
#endif
|
||||
|
||||
@@ -56,8 +56,6 @@
|
||||
#define PARALLEL_KEY_HNSW_SHARED UINT64CONST(0xA000000000000001)
|
||||
#define PARALLEL_KEY_QUERY_TEXT UINT64CONST(0xA000000000000002)
|
||||
|
||||
#define LIST_MAX_LENGTH ((1 << 26) - 1)
|
||||
|
||||
/*
|
||||
* Create the metapage
|
||||
*/
|
||||
@@ -68,11 +66,11 @@ CreateMetaPage(HnswBuildState * buildstate)
|
||||
ForkNumber forkNum = buildstate->forkNum;
|
||||
Buffer buf;
|
||||
Page page;
|
||||
GenericXLogState *state;
|
||||
HnswMetaPage metap;
|
||||
|
||||
buf = HnswNewBuffer(index, forkNum);
|
||||
page = BufferGetPage(buf);
|
||||
HnswInitPage(buf, page);
|
||||
HnswInitRegisterPage(index, &buf, &page, &state);
|
||||
|
||||
/* Set metapage data */
|
||||
metap = HnswPageGetMeta(page);
|
||||
@@ -88,14 +86,14 @@ CreateMetaPage(HnswBuildState * buildstate)
|
||||
((PageHeader) page)->pd_lower =
|
||||
((char *) metap + sizeof(HnswMetaPageData)) - (char *) page;
|
||||
|
||||
UnlockReleaseBuffer(buf);
|
||||
HnswCommitBuffer(buf, state);
|
||||
}
|
||||
|
||||
/*
|
||||
* Add a new page
|
||||
*/
|
||||
static void
|
||||
HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
|
||||
HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state, ForkNumber forkNum)
|
||||
{
|
||||
/* Add a new page */
|
||||
Buffer newbuf = HnswNewBuffer(index, forkNum);
|
||||
@@ -104,6 +102,7 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
|
||||
HnswPageGetOpaque(*page)->nextblkno = BufferGetBlockNumber(newbuf);
|
||||
|
||||
/* Commit */
|
||||
GenericXLogFinish(*state);
|
||||
UnlockReleaseBuffer(*buf);
|
||||
|
||||
/* Can take a while, so ensure we can interrupt */
|
||||
@@ -114,7 +113,8 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
|
||||
|
||||
/* Prepare new page */
|
||||
*buf = newbuf;
|
||||
*page = BufferGetPage(*buf);
|
||||
*state = GenericXLogStart(index);
|
||||
*page = GenericXLogRegisterBuffer(*state, *buf, GENERIC_XLOG_FULL_IMAGE);
|
||||
HnswInitPage(*buf, *page);
|
||||
}
|
||||
|
||||
@@ -133,6 +133,7 @@ CreateElementPages(HnswBuildState * buildstate)
|
||||
BlockNumber insertPage;
|
||||
Buffer buf;
|
||||
Page page;
|
||||
GenericXLogState *state;
|
||||
ListCell *lc;
|
||||
|
||||
/* Calculate sizes */
|
||||
@@ -145,7 +146,8 @@ CreateElementPages(HnswBuildState * buildstate)
|
||||
|
||||
/* Prepare first page */
|
||||
buf = HnswNewBuffer(index, forkNum);
|
||||
page = BufferGetPage(buf);
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, GENERIC_XLOG_FULL_IMAGE);
|
||||
HnswInitPage(buf, page);
|
||||
|
||||
foreach(lc, buildstate->elements)
|
||||
@@ -171,7 +173,7 @@ CreateElementPages(HnswBuildState * buildstate)
|
||||
|
||||
/* Keep element and neighbors on the same page if possible */
|
||||
if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
|
||||
HnswBuildAppendPage(index, &buf, &page, forkNum);
|
||||
HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
|
||||
|
||||
/* Calculate offsets */
|
||||
element->blkno = BufferGetBlockNumber(buf);
|
||||
@@ -195,7 +197,7 @@ CreateElementPages(HnswBuildState * buildstate)
|
||||
|
||||
/* Add new page if needed */
|
||||
if (PageGetFreeSpace(page) < ntupSize)
|
||||
HnswBuildAppendPage(index, &buf, &page, forkNum);
|
||||
HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
|
||||
|
||||
/* Add placeholder for neighbors */
|
||||
if (PageAddItem(page, (Item) ntup, ntupSize, InvalidOffsetNumber, false, false) != element->neighborOffno)
|
||||
@@ -205,9 +207,10 @@ CreateElementPages(HnswBuildState * buildstate)
|
||||
insertPage = BufferGetBlockNumber(buf);
|
||||
|
||||
/* Commit */
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->entryPoint, insertPage, forkNum, true);
|
||||
HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->entryPoint, insertPage, forkNum);
|
||||
|
||||
pfree(etup);
|
||||
pfree(ntup);
|
||||
@@ -233,6 +236,7 @@ CreateNeighborPages(HnswBuildState * buildstate)
|
||||
HnswElement e = lfirst(lc);
|
||||
Buffer buf;
|
||||
Page page;
|
||||
GenericXLogState *state;
|
||||
Size ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
|
||||
|
||||
/* Can take a while, so ensure we can interrupt */
|
||||
@@ -241,7 +245,8 @@ CreateNeighborPages(HnswBuildState * buildstate)
|
||||
|
||||
buf = ReadBufferExtended(index, forkNum, e->neighborPage, RBM_NORMAL, NULL);
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
page = BufferGetPage(buf);
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
|
||||
HnswSetNeighborTuple(ntup, e, m);
|
||||
|
||||
@@ -249,6 +254,7 @@ CreateNeighborPages(HnswBuildState * buildstate)
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
/* Commit */
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
|
||||
@@ -301,10 +307,7 @@ InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState *
|
||||
|
||||
/* Normalize if needed */
|
||||
if (buildstate->normprocinfo != NULL)
|
||||
{
|
||||
if (!HnswNormValue(buildstate->normprocinfo, collation, &value, buildstate->normvec))
|
||||
return false;
|
||||
}
|
||||
HnswNormValue(buildstate->normprocinfo, collation, &value, buildstate->normvec);
|
||||
|
||||
/* Copy value to element so accessible outside of memory context */
|
||||
oldCtx = MemoryContextSwitchTo(outerCtx);
|
||||
@@ -375,22 +378,21 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
|
||||
if (isnull[0])
|
||||
return;
|
||||
|
||||
if (buildstate->flushed || buildstate->memoryLeft <= 0 || list_length(buildstate->elements) == LIST_MAX_LENGTH)
|
||||
if (buildstate->memoryLeft <= 0)
|
||||
{
|
||||
if (!buildstate->flushed)
|
||||
{
|
||||
if (buildstate->memoryLeft <= 0)
|
||||
ereport(NOTICE,
|
||||
(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) buildstate->indtuples),
|
||||
errdetail("Building will take significantly more time."),
|
||||
errhint("Increase maintenance_work_mem to speed up builds.")));
|
||||
ereport(NOTICE,
|
||||
(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) buildstate->indtuples),
|
||||
errdetail("Building will take significantly more time."),
|
||||
errhint("Increase maintenance_work_mem to speed up builds.")));
|
||||
|
||||
FlushPages(buildstate);
|
||||
}
|
||||
|
||||
oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
|
||||
|
||||
if (HnswInsertTuple(buildstate->index, values, isnull, tid, buildstate->heap, true))
|
||||
if (HnswInsertTuple(buildstate->index, values, isnull, tid, buildstate->heap))
|
||||
{
|
||||
if (buildstate->hnswshared)
|
||||
{
|
||||
@@ -872,22 +874,6 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
|
||||
HnswEndParallel(buildstate->hnswleader);
|
||||
}
|
||||
|
||||
#if PG_VERSION_NUM < 110008
|
||||
void
|
||||
log_newpage_range(Relation rel, ForkNumber forkNum, BlockNumber startblk, BlockNumber endblk, bool page_std)
|
||||
{
|
||||
for (BlockNumber blkno = startblk; blkno < endblk; blkno++)
|
||||
{
|
||||
Buffer buf = ReadBufferExtended(rel, forkNum, blkno, RBM_NORMAL, NULL);
|
||||
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
MarkBufferDirty(buf);
|
||||
log_newpage_buffer(buf, page_std);
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Build the index
|
||||
*/
|
||||
@@ -903,9 +889,6 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
|
||||
if (!buildstate->flushed)
|
||||
FlushPages(buildstate);
|
||||
|
||||
if (RelationNeedsWAL(index))
|
||||
log_newpage_range(index, forkNum, 0, RelationGetNumberOfBlocks(index), true);
|
||||
|
||||
FreeBuildState(buildstate);
|
||||
}
|
||||
|
||||
|
||||
118
src/hnswinsert.c
118
src/hnswinsert.c
@@ -92,7 +92,7 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
|
||||
* Add a new page
|
||||
*/
|
||||
static void
|
||||
HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page, bool building)
|
||||
HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page)
|
||||
{
|
||||
/* Add a new page */
|
||||
LockRelationForExtension(index, ExclusiveLock);
|
||||
@@ -100,11 +100,7 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
|
||||
UnlockRelationForExtension(index, ExclusiveLock);
|
||||
|
||||
/* Init new page */
|
||||
if (building)
|
||||
*npage = BufferGetPage(*nbuf);
|
||||
else
|
||||
*npage = GenericXLogRegisterBuffer(state, *nbuf, GENERIC_XLOG_FULL_IMAGE);
|
||||
|
||||
*npage = GenericXLogRegisterBuffer(state, *nbuf, GENERIC_XLOG_FULL_IMAGE);
|
||||
HnswInitPage(*nbuf, *npage);
|
||||
|
||||
/* Update previous buffer */
|
||||
@@ -115,7 +111,7 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
|
||||
* Add to element and neighbor pages
|
||||
*/
|
||||
static void
|
||||
WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
|
||||
WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage)
|
||||
{
|
||||
Buffer buf;
|
||||
Page page;
|
||||
@@ -155,16 +151,8 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
|
||||
buf = ReadBuffer(index, currentPage);
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
|
||||
if (building)
|
||||
{
|
||||
state = NULL;
|
||||
page = BufferGetPage(buf);
|
||||
}
|
||||
else
|
||||
{
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
}
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
|
||||
/* Keep track of first page where element at level 0 can fit */
|
||||
if (!BlockNumberIsValid(newInsertPage) && PageGetFreeSpace(page) >= minCombinedSize)
|
||||
@@ -184,12 +172,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
|
||||
if (HnswFreeOffset(index, buf, page, e, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
|
||||
{
|
||||
if (nbuf != buf)
|
||||
{
|
||||
if (building)
|
||||
npage = BufferGetPage(nbuf);
|
||||
else
|
||||
npage = GenericXLogRegisterBuffer(state, nbuf, 0);
|
||||
}
|
||||
npage = GenericXLogRegisterBuffer(state, nbuf, 0);
|
||||
|
||||
break;
|
||||
}
|
||||
@@ -198,7 +181,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
|
||||
/* Skip if both tuples can fit on the same page */
|
||||
if (combinedSize > maxSize && PageGetFreeSpace(page) >= etupSize && !BlockNumberIsValid(HnswPageGetOpaque(page)->nextblkno))
|
||||
{
|
||||
HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
|
||||
HnswInsertAppendPage(index, &nbuf, &npage, state, page);
|
||||
break;
|
||||
}
|
||||
|
||||
@@ -207,8 +190,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
|
||||
if (BlockNumberIsValid(currentPage))
|
||||
{
|
||||
/* Move to next page */
|
||||
if (!building)
|
||||
GenericXLogAbort(state);
|
||||
GenericXLogAbort(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
else
|
||||
@@ -216,31 +198,22 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
|
||||
Buffer newbuf;
|
||||
Page newpage;
|
||||
|
||||
HnswInsertAppendPage(index, &newbuf, &newpage, state, page, building);
|
||||
HnswInsertAppendPage(index, &newbuf, &newpage, state, page);
|
||||
|
||||
/* Commit */
|
||||
if (!building)
|
||||
GenericXLogFinish(state);
|
||||
GenericXLogFinish(state);
|
||||
|
||||
/* Unlock previous buffer */
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
/* Prepare new buffer */
|
||||
state = GenericXLogStart(index);
|
||||
buf = newbuf;
|
||||
if (building)
|
||||
{
|
||||
state = NULL;
|
||||
page = BufferGetPage(buf);
|
||||
}
|
||||
else
|
||||
{
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
}
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
|
||||
/* Create new page for neighbors if needed */
|
||||
if (PageGetFreeSpace(page) < combinedSize)
|
||||
HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
|
||||
HnswInsertAppendPage(index, &nbuf, &npage, state, page);
|
||||
else
|
||||
{
|
||||
nbuf = buf;
|
||||
@@ -294,8 +267,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
|
||||
}
|
||||
|
||||
/* Commit */
|
||||
if (!building)
|
||||
GenericXLogFinish(state);
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
if (nbuf != buf)
|
||||
UnlockReleaseBuffer(nbuf);
|
||||
@@ -329,7 +301,7 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
|
||||
* Update neighbors
|
||||
*/
|
||||
void
|
||||
HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
|
||||
HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting)
|
||||
{
|
||||
for (int lc = e->level; lc >= 0; lc--)
|
||||
{
|
||||
@@ -370,16 +342,8 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
|
||||
/* Register page */
|
||||
buf = ReadBuffer(index, hc->element->neighborPage);
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
if (building)
|
||||
{
|
||||
state = NULL;
|
||||
page = BufferGetPage(buf);
|
||||
}
|
||||
else
|
||||
{
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
}
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
|
||||
/* Get tuple */
|
||||
itemid = PageGetItemId(page, offno);
|
||||
@@ -421,10 +385,9 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
/* Commit */
|
||||
if (!building)
|
||||
GenericXLogFinish(state);
|
||||
GenericXLogFinish(state);
|
||||
}
|
||||
else if (!building)
|
||||
else
|
||||
GenericXLogAbort(state);
|
||||
|
||||
UnlockReleaseBuffer(buf);
|
||||
@@ -436,7 +399,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
|
||||
* Add a heap TID to an existing element
|
||||
*/
|
||||
static bool
|
||||
HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool building)
|
||||
HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
|
||||
{
|
||||
Buffer buf;
|
||||
Page page;
|
||||
@@ -449,16 +412,8 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
|
||||
/* Read page */
|
||||
buf = ReadBuffer(index, dup->blkno);
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
if (building)
|
||||
{
|
||||
state = NULL;
|
||||
page = BufferGetPage(buf);
|
||||
}
|
||||
else
|
||||
{
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
}
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
|
||||
/* Find space */
|
||||
itemid = PageGetItemId(page, dup->offno);
|
||||
@@ -473,8 +428,7 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
|
||||
/* Either being deleted or we lost our chance to another backend */
|
||||
if (i == 0 || i == HNSW_HEAPTIDS)
|
||||
{
|
||||
if (!building)
|
||||
GenericXLogAbort(state);
|
||||
GenericXLogAbort(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
return false;
|
||||
}
|
||||
@@ -487,8 +441,7 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
/* Commit */
|
||||
if (!building)
|
||||
GenericXLogFinish(state);
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
return true;
|
||||
@@ -498,37 +451,37 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
|
||||
* Write changes to disk
|
||||
*/
|
||||
static void
|
||||
WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint, bool building)
|
||||
WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
|
||||
{
|
||||
BlockNumber newInsertPage = InvalidBlockNumber;
|
||||
|
||||
/* Try to add to existing page */
|
||||
if (dup != NULL)
|
||||
{
|
||||
if (HnswAddDuplicate(index, element, dup, building))
|
||||
if (HnswAddDuplicate(index, element, dup))
|
||||
return;
|
||||
}
|
||||
|
||||
/* Write element and neighbor tuples */
|
||||
WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage, building);
|
||||
WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage);
|
||||
|
||||
/* Update insert page if needed */
|
||||
if (BlockNumberIsValid(newInsertPage))
|
||||
HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
|
||||
HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM);
|
||||
|
||||
/* Update neighbors */
|
||||
HnswUpdateNeighborPages(index, procinfo, collation, element, m, false, building);
|
||||
HnswUpdateNeighborPages(index, procinfo, collation, element, m, false);
|
||||
|
||||
/* Update metapage if needed */
|
||||
if (entryPoint == NULL || element->level > entryPoint->level)
|
||||
HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, building);
|
||||
HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
|
||||
}
|
||||
|
||||
/*
|
||||
* Insert a tuple into the index
|
||||
*/
|
||||
bool
|
||||
HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building)
|
||||
HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
|
||||
{
|
||||
Datum value;
|
||||
FmgrInfo *normprocinfo;
|
||||
@@ -547,10 +500,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
|
||||
/* Normalize if needed */
|
||||
normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||
if (normprocinfo != NULL)
|
||||
{
|
||||
if (!HnswNormValue(normprocinfo, collation, &value, NULL))
|
||||
return false;
|
||||
}
|
||||
HnswNormValue(normprocinfo, collation, &value, NULL);
|
||||
|
||||
/*
|
||||
* Get a shared lock. This allows vacuum to ensure no in-flight inserts
|
||||
@@ -587,7 +537,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
|
||||
dup = HnswFindDuplicate(element);
|
||||
|
||||
/* Write to disk */
|
||||
WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint, building);
|
||||
WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint);
|
||||
|
||||
/* Release lock */
|
||||
UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
|
||||
@@ -621,7 +571,7 @@ hnswinsert(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid,
|
||||
oldCtx = MemoryContextSwitchTo(insertCtx);
|
||||
|
||||
/* Insert tuple */
|
||||
HnswInsertTuple(index, values, isnull, heap_tid, heap, false);
|
||||
HnswInsertTuple(index, values, isnull, heap_tid, heap);
|
||||
|
||||
/* Delete memory context */
|
||||
MemoryContextSwitchTo(oldCtx);
|
||||
|
||||
165
src/hnswutils.c
165
src/hnswutils.c
@@ -7,89 +7,6 @@
|
||||
#include "utils/datum.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 130000
|
||||
#include "common/hashfn.h"
|
||||
#else
|
||||
#include "utils/hashutils.h"
|
||||
#endif
|
||||
|
||||
#if PG_VERSION_NUM < 170000
|
||||
static inline uint64
|
||||
murmurhash64(uint64 data)
|
||||
{
|
||||
uint64 h = data;
|
||||
|
||||
h ^= h >> 33;
|
||||
h *= 0xff51afd7ed558ccd;
|
||||
h ^= h >> 33;
|
||||
h *= 0xc4ceb9fe1a85ec53;
|
||||
h ^= h >> 33;
|
||||
|
||||
return h;
|
||||
}
|
||||
#endif
|
||||
|
||||
/* TID hash table */
|
||||
static uint32
|
||||
hash_tid(ItemPointerData tid)
|
||||
{
|
||||
union
|
||||
{
|
||||
uint64 i;
|
||||
ItemPointerData tid;
|
||||
} x;
|
||||
|
||||
/* Initialize unused bytes */
|
||||
x.i = 0;
|
||||
x.tid = tid;
|
||||
|
||||
return murmurhash64(x.i);
|
||||
}
|
||||
|
||||
#define SH_PREFIX tidhash
|
||||
#define SH_ELEMENT_TYPE TidHashEntry
|
||||
#define SH_KEY_TYPE ItemPointerData
|
||||
#define SH_KEY tid
|
||||
#define SH_HASH_KEY(tb, key) hash_tid(key)
|
||||
#define SH_EQUAL(tb, a, b) ItemPointerEquals(&a, &b)
|
||||
#define SH_SCOPE extern
|
||||
#define SH_DEFINE
|
||||
#include "lib/simplehash.h"
|
||||
|
||||
/* Needed to include simplehash.h twice */
|
||||
#if PG_VERSION_NUM < 120000
|
||||
#undef SH_EQUAL
|
||||
#define sh_log2 pointerhash_sh_log2
|
||||
#define sh_pow2 pointerhash_sh_pow2
|
||||
#endif
|
||||
|
||||
/* Pointer hash table */
|
||||
static uint32
|
||||
hash_pointer(uintptr_t ptr)
|
||||
{
|
||||
#if SIZEOF_VOID_P == 8
|
||||
return murmurhash64((uint64) ptr);
|
||||
#else
|
||||
return murmurhash32((uint32) ptr);
|
||||
#endif
|
||||
}
|
||||
|
||||
#define SH_PREFIX pointerhash
|
||||
#define SH_ELEMENT_TYPE PointerHashEntry
|
||||
#define SH_KEY_TYPE uintptr_t
|
||||
#define SH_KEY ptr
|
||||
#define SH_HASH_KEY(tb, key) hash_pointer(key)
|
||||
#define SH_EQUAL(tb, a, b) (a == b)
|
||||
#define SH_SCOPE extern
|
||||
#define SH_DEFINE
|
||||
#include "lib/simplehash.h"
|
||||
|
||||
typedef union
|
||||
{
|
||||
pointerhash_hash *pointers;
|
||||
tidhash_hash *tids;
|
||||
} visited_hash;
|
||||
|
||||
/*
|
||||
* Get the max number of connections in an upper layer for each element in the index
|
||||
*/
|
||||
@@ -138,7 +55,7 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
|
||||
* The caller needs to free the pointer stored in value
|
||||
* if it's different than the original value
|
||||
*/
|
||||
bool
|
||||
void
|
||||
HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result)
|
||||
{
|
||||
double norm = DatumGetFloat8(FunctionCall1Coll(procinfo, collation, *value));
|
||||
@@ -154,11 +71,7 @@ HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result)
|
||||
result->x[i] = v->x[i] / norm;
|
||||
|
||||
*value = PointerGetDatum(result);
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -184,6 +97,27 @@ HnswInitPage(Buffer buf, Page page)
|
||||
HnswPageGetOpaque(page)->page_id = HNSW_PAGE_ID;
|
||||
}
|
||||
|
||||
/*
|
||||
* Init and register page
|
||||
*/
|
||||
void
|
||||
HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state)
|
||||
{
|
||||
*state = GenericXLogStart(index);
|
||||
*page = GenericXLogRegisterBuffer(*state, *buf, GENERIC_XLOG_FULL_IMAGE);
|
||||
HnswInitPage(*buf, *page);
|
||||
}
|
||||
|
||||
/*
|
||||
* Commit buffer
|
||||
*/
|
||||
void
|
||||
HnswCommitBuffer(Buffer buf, GenericXLogState *state)
|
||||
{
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
|
||||
/*
|
||||
* Allocate neighbors
|
||||
*/
|
||||
@@ -358,7 +292,7 @@ HnswUpdateMetaPageInfo(Page page, int updateEntry, HnswElement entryPoint, Block
|
||||
* Update the metapage
|
||||
*/
|
||||
void
|
||||
HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building)
|
||||
HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum)
|
||||
{
|
||||
Buffer buf;
|
||||
Page page;
|
||||
@@ -366,22 +300,12 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
|
||||
|
||||
buf = ReadBufferExtended(index, forkNum, HNSW_METAPAGE_BLKNO, RBM_NORMAL, NULL);
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
if (building)
|
||||
{
|
||||
state = NULL;
|
||||
page = BufferGetPage(buf);
|
||||
}
|
||||
else
|
||||
{
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
}
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
|
||||
HnswUpdateMetaPageInfo(page, updateEntry, entryPoint, insertPage);
|
||||
|
||||
if (!building)
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
HnswCommitBuffer(buf, state);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -625,22 +549,16 @@ CreatePairingHeapNode(HnswCandidate * c)
|
||||
* Add to visited
|
||||
*/
|
||||
static inline void
|
||||
AddToVisited(visited_hash v, HnswCandidate * hc, Relation index, bool *found)
|
||||
AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
|
||||
{
|
||||
if (index == NULL)
|
||||
{
|
||||
#if PG_VERSION_NUM >= 130000
|
||||
pointerhash_insert_hash(v.pointers, (uintptr_t) hc->element, hc->element->hash, found);
|
||||
#else
|
||||
pointerhash_insert(v.pointers, (uintptr_t) hc->element, found);
|
||||
#endif
|
||||
}
|
||||
hash_search(v, &hc->element, HASH_ENTER, found);
|
||||
else
|
||||
{
|
||||
ItemPointerData indextid;
|
||||
|
||||
ItemPointerSet(&indextid, hc->element->blkno, hc->element->offno);
|
||||
tidhash_insert(v.tids, indextid, found);
|
||||
hash_search(v, &indextid, HASH_ENTER, found);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -656,21 +574,30 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
|
||||
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
|
||||
pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
|
||||
int wlen = 0;
|
||||
visited_hash v;
|
||||
HASHCTL hash_ctl;
|
||||
HTAB *v;
|
||||
|
||||
/* Create hash table */
|
||||
if (index == NULL)
|
||||
v.pointers = pointerhash_create(CurrentMemoryContext, ef * m * 2, NULL);
|
||||
{
|
||||
hash_ctl.keysize = sizeof(HnswElement *);
|
||||
hash_ctl.entrysize = sizeof(HnswElement *);
|
||||
}
|
||||
else
|
||||
v.tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
|
||||
{
|
||||
hash_ctl.keysize = sizeof(ItemPointerData);
|
||||
hash_ctl.entrysize = sizeof(ItemPointerData);
|
||||
}
|
||||
|
||||
hash_ctl.hcxt = CurrentMemoryContext;
|
||||
v = hash_create("hnsw visited", 256, &hash_ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
|
||||
|
||||
/* Add entry points to v, C, and W */
|
||||
foreach(lc2, ep)
|
||||
{
|
||||
HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
|
||||
bool found;
|
||||
|
||||
AddToVisited(v, hc, index, &found);
|
||||
AddToVisited(v, hc, index, NULL);
|
||||
|
||||
pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
|
||||
pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
|
||||
@@ -1090,12 +1017,6 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
|
||||
Datum q = element->value;
|
||||
HnswElement skipElement = existing ? element : NULL;
|
||||
|
||||
#if PG_VERSION_NUM >= 130000
|
||||
/* Precompute hash */
|
||||
if (index == NULL)
|
||||
element->hash = hash_pointer((uintptr_t) element);
|
||||
#endif
|
||||
|
||||
/* No neighbors if no entry point */
|
||||
if (entryPoint == NULL)
|
||||
return;
|
||||
|
||||
@@ -12,9 +12,12 @@
|
||||
* Check if deleted list contains an index TID
|
||||
*/
|
||||
static bool
|
||||
DeletedContains(tidhash_hash * deleted, ItemPointer indextid)
|
||||
DeletedContains(HTAB *deleted, ItemPointer indextid)
|
||||
{
|
||||
return tidhash_lookup(deleted, *indextid) != NULL;
|
||||
bool found;
|
||||
|
||||
hash_search(deleted, indextid, HASH_FIND, &found);
|
||||
return found;
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -107,13 +110,11 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
|
||||
if (!ItemPointerIsValid(&etup->heaptids[0]))
|
||||
{
|
||||
ItemPointerData ip;
|
||||
bool found;
|
||||
|
||||
/* Add to deleted list */
|
||||
ItemPointerSet(&ip, blkno, offno);
|
||||
|
||||
tidhash_insert(vacuumstate->deleted, ip, &found);
|
||||
Assert(!found);
|
||||
(void) hash_search(vacuumstate->deleted, &ip, HASH_ENTER, NULL);
|
||||
}
|
||||
else if (etup->level > highestLevel && !(entryPoint != NULL && blkno == entryPoint->blkno && offno == entryPoint->offno))
|
||||
{
|
||||
@@ -230,7 +231,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
/* Update neighbors */
|
||||
HnswUpdateNeighborPages(index, procinfo, collation, element, m, true, false);
|
||||
HnswUpdateNeighborPages(index, procinfo, collation, element, m, true);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -286,7 +287,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
|
||||
* point is outdated and empty, the entry point will be empty
|
||||
* until an element is repaired.
|
||||
*/
|
||||
HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM, false);
|
||||
HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM);
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -419,7 +420,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
|
||||
* was replaced and highest point was outdated.
|
||||
*/
|
||||
if (entryPoint == NULL || element->level > entryPoint->level)
|
||||
HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, false);
|
||||
HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
|
||||
|
||||
/* Release lock */
|
||||
UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
|
||||
@@ -564,7 +565,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
|
||||
}
|
||||
|
||||
/* Update insert page last, after everything has been marked as deleted */
|
||||
HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM, false);
|
||||
HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -574,6 +575,7 @@ static void
|
||||
InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state)
|
||||
{
|
||||
Relation index = info->index;
|
||||
HASHCTL hash_ctl;
|
||||
|
||||
if (stats == NULL)
|
||||
stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
|
||||
@@ -595,7 +597,10 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
|
||||
HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);
|
||||
|
||||
/* Create hash table */
|
||||
vacuumstate->deleted = tidhash_create(CurrentMemoryContext, 256, NULL);
|
||||
hash_ctl.keysize = sizeof(ItemPointerData);
|
||||
hash_ctl.entrysize = sizeof(ItemPointerData);
|
||||
hash_ctl.hcxt = CurrentMemoryContext;
|
||||
vacuumstate->deleted = hash_create("hnswbulkdelete indextids", 256, &hash_ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -604,7 +609,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
|
||||
static void
|
||||
FreeVacuumState(HnswVacuumState * vacuumstate)
|
||||
{
|
||||
tidhash_destroy(vacuumstate->deleted);
|
||||
hash_destroy(vacuumstate->deleted);
|
||||
FreeAccessStrategy(vacuumstate->bas);
|
||||
pfree(vacuumstate->ntup);
|
||||
MemoryContextDelete(vacuumstate->tmpCtx);
|
||||
|
||||
@@ -177,10 +177,7 @@ AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState
|
||||
|
||||
/* Normalize if needed */
|
||||
if (buildstate->normprocinfo != NULL)
|
||||
{
|
||||
if (!IvfflatNormValue(buildstate->normprocinfo, buildstate->collation, &value, buildstate->normvec))
|
||||
return;
|
||||
}
|
||||
IvfflatNormValue(buildstate->normprocinfo, buildstate->collation, &value, buildstate->normvec);
|
||||
|
||||
/* Find the list that minimizes the distance */
|
||||
for (int i = 0; i < centers->length; i++)
|
||||
|
||||
@@ -83,10 +83,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
|
||||
/* Normalize if needed */
|
||||
normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
|
||||
if (normprocinfo != NULL)
|
||||
{
|
||||
if (!IvfflatNormValue(normprocinfo, index->rd_indcollation[0], &value, NULL))
|
||||
return;
|
||||
}
|
||||
IvfflatNormValue(normprocinfo, index->rd_indcollation[0], &value, NULL);
|
||||
|
||||
/* Find the insert page - sets the page and list info */
|
||||
FindInsertPage(index, values, &insertPage, &listInfo);
|
||||
|
||||
30
src/vector.c
30
src/vector.c
@@ -724,7 +724,7 @@ vector_spherical_distance(PG_FUNCTION_ARGS)
|
||||
}
|
||||
|
||||
/*
|
||||
* Get the L1 distance between two vectors
|
||||
* Get the L1 distance between vectors
|
||||
*/
|
||||
PGDLLEXPORT PG_FUNCTION_INFO_V1(l1_distance);
|
||||
Datum
|
||||
@@ -903,8 +903,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_lt);
|
||||
Datum
|
||||
vector_lt(PG_FUNCTION_ARGS)
|
||||
{
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
Vector *a = (Vector *) PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = (Vector *) PG_GETARG_VECTOR_P(1);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) < 0);
|
||||
}
|
||||
@@ -916,8 +916,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_le);
|
||||
Datum
|
||||
vector_le(PG_FUNCTION_ARGS)
|
||||
{
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
Vector *a = (Vector *) PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = (Vector *) PG_GETARG_VECTOR_P(1);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) <= 0);
|
||||
}
|
||||
@@ -929,8 +929,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_eq);
|
||||
Datum
|
||||
vector_eq(PG_FUNCTION_ARGS)
|
||||
{
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
Vector *a = (Vector *) PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = (Vector *) PG_GETARG_VECTOR_P(1);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) == 0);
|
||||
}
|
||||
@@ -942,8 +942,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ne);
|
||||
Datum
|
||||
vector_ne(PG_FUNCTION_ARGS)
|
||||
{
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
Vector *a = (Vector *) PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = (Vector *) PG_GETARG_VECTOR_P(1);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) != 0);
|
||||
}
|
||||
@@ -955,8 +955,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ge);
|
||||
Datum
|
||||
vector_ge(PG_FUNCTION_ARGS)
|
||||
{
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
Vector *a = (Vector *) PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = (Vector *) PG_GETARG_VECTOR_P(1);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) >= 0);
|
||||
}
|
||||
@@ -968,8 +968,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_gt);
|
||||
Datum
|
||||
vector_gt(PG_FUNCTION_ARGS)
|
||||
{
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
Vector *a = (Vector *) PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = (Vector *) PG_GETARG_VECTOR_P(1);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) > 0);
|
||||
}
|
||||
@@ -981,8 +981,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_cmp);
|
||||
Datum
|
||||
vector_cmp(PG_FUNCTION_ARGS)
|
||||
{
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
Vector *a = (Vector *) PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = (Vector *) PG_GETARG_VECTOR_P(1);
|
||||
|
||||
PG_RETURN_INT32(vector_cmp_internal(a, b));
|
||||
}
|
||||
|
||||
@@ -9,18 +9,19 @@ SELECT * FROM t ORDER BY val <=> '[3,3,3]';
|
||||
[1,1,1]
|
||||
[1,2,3]
|
||||
[1,2,4]
|
||||
(3 rows)
|
||||
[0,0,0]
|
||||
(4 rows)
|
||||
|
||||
SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
|
||||
count
|
||||
-------
|
||||
3
|
||||
4
|
||||
(1 row)
|
||||
|
||||
SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2;
|
||||
count
|
||||
-------
|
||||
3
|
||||
4
|
||||
(1 row)
|
||||
|
||||
DROP TABLE t;
|
||||
|
||||
@@ -9,18 +9,19 @@ SELECT * FROM t ORDER BY val <=> '[3,3,3]';
|
||||
[1,1,1]
|
||||
[1,2,3]
|
||||
[1,2,4]
|
||||
(3 rows)
|
||||
[0,0,0]
|
||||
(4 rows)
|
||||
|
||||
SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
|
||||
count
|
||||
-------
|
||||
3
|
||||
4
|
||||
(1 row)
|
||||
|
||||
SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2;
|
||||
count
|
||||
-------
|
||||
3
|
||||
4
|
||||
(1 row)
|
||||
|
||||
DROP TABLE t;
|
||||
|
||||
Reference in New Issue
Block a user