mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 12:07:34 +08:00
Compare commits
41 Commits
mvcc-snaps
...
hnsw-index
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
95bcda94da | ||
|
|
84c5aa14bf | ||
|
|
72e741a5a6 | ||
|
|
84ca6625a7 | ||
|
|
3f49b95f01 | ||
|
|
ef1bea7163 | ||
|
|
e630efd195 | ||
|
|
b5b912906b | ||
|
|
4b5db94307 | ||
|
|
65e70326b8 | ||
|
|
71641ed84e | ||
|
|
f3dba25036 | ||
|
|
5588ba6410 | ||
|
|
ec9fac5456 | ||
|
|
8085d3e538 | ||
|
|
cae162ffc6 | ||
|
|
62482e3760 | ||
|
|
c81302b835 | ||
|
|
a713e2acaa | ||
|
|
6e1312ddbe | ||
|
|
4ef5bca275 | ||
|
|
1ecf6ada76 | ||
|
|
564a3d45fc | ||
|
|
8d7abb6590 | ||
|
|
b247b688a8 | ||
|
|
9672446a4c | ||
|
|
334614b7f7 | ||
|
|
643eacd9dc | ||
|
|
bca50a03fa | ||
|
|
d87833cacc | ||
|
|
4c01073ac1 | ||
|
|
6fed8f1e78 | ||
|
|
611f5b1047 | ||
|
|
e367155732 | ||
|
|
466c556b1a | ||
|
|
75e09265d6 | ||
|
|
77c5070fb6 | ||
|
|
1006fdf3f2 | ||
|
|
4209c9b3af | ||
|
|
ec0bb4e4ff | ||
|
|
b164833933 |
8
.github/workflows/build.yml
vendored
8
.github/workflows/build.yml
vendored
@@ -8,6 +8,8 @@ jobs:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- postgres: 17
|
||||
os: ubuntu-22.04
|
||||
- postgres: 16
|
||||
os: ubuntu-22.04
|
||||
- postgres: 15
|
||||
@@ -21,7 +23,7 @@ jobs:
|
||||
- postgres: 11
|
||||
os: ubuntu-20.04
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ankane/setup-postgres@v1
|
||||
with:
|
||||
postgres-version: ${{ matrix.postgres }}
|
||||
@@ -43,7 +45,7 @@ jobs:
|
||||
runs-on: macos-latest
|
||||
if: ${{ !startsWith(github.ref_name, 'windows') }}
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ankane/setup-postgres@v1
|
||||
with:
|
||||
postgres-version: 14
|
||||
@@ -65,7 +67,7 @@ jobs:
|
||||
runs-on: windows-latest
|
||||
if: ${{ !startsWith(github.ref_name, 'mac') }}
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ankane/setup-postgres@v1
|
||||
with:
|
||||
postgres-version: 14
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
## 0.5.1 (unreleased)
|
||||
## 0.5.1 (2023-10-10)
|
||||
|
||||
- Fixed locking for index scans for HNSW
|
||||
- Improved performance of HNSW index builds
|
||||
- Added check for MVCC-compliant snapshot for index scans
|
||||
|
||||
## 0.5.0 (2023-08-28)
|
||||
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "vector",
|
||||
"abstract": "Open-source vector similarity search for Postgres",
|
||||
"description": "Supports L2 distance, inner product, and cosine distance",
|
||||
"version": "0.5.0",
|
||||
"version": "0.5.1",
|
||||
"maintainer": [
|
||||
"Andrew Kane <andrew@ankane.org>"
|
||||
],
|
||||
@@ -20,7 +20,7 @@
|
||||
"vector": {
|
||||
"file": "sql/vector.sql",
|
||||
"docfile": "README.md",
|
||||
"version": "0.5.0",
|
||||
"version": "0.5.1",
|
||||
"abstract": "Open-source vector similarity search for Postgres"
|
||||
}
|
||||
},
|
||||
|
||||
2
Makefile
2
Makefile
@@ -1,5 +1,5 @@
|
||||
EXTENSION = vector
|
||||
EXTVERSION = 0.5.0
|
||||
EXTVERSION = 0.5.1
|
||||
|
||||
MODULE_big = vector
|
||||
DATA = $(wildcard sql/*--*.sql)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
EXTENSION = vector
|
||||
EXTVERSION = 0.5.0
|
||||
EXTVERSION = 0.5.1
|
||||
|
||||
OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
|
||||
HEADERS = src\vector.h
|
||||
|
||||
@@ -18,7 +18,7 @@ Compile and install the extension (supports Postgres 11+)
|
||||
|
||||
```sh
|
||||
cd /tmp
|
||||
git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
|
||||
git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
|
||||
cd pgvector
|
||||
make
|
||||
make install # may need sudo
|
||||
@@ -509,7 +509,7 @@ Then use `nmake` to build:
|
||||
|
||||
```cmd
|
||||
set "PGROOT=C:\Program Files\PostgreSQL\15"
|
||||
git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
|
||||
git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
|
||||
cd pgvector
|
||||
nmake /F Makefile.win
|
||||
nmake /F Makefile.win install
|
||||
@@ -530,7 +530,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
|
||||
You can also build the image manually:
|
||||
|
||||
```sh
|
||||
git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
|
||||
git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
|
||||
cd pgvector
|
||||
docker build --build-arg PG_MAJOR=15 -t myuser/pgvector .
|
||||
```
|
||||
|
||||
2
sql/vector--0.5.0--0.5.1.sql
Normal file
2
sql/vector--0.5.0--0.5.1.sql
Normal file
@@ -0,0 +1,2 @@
|
||||
-- complain if script is sourced in psql, rather than via CREATE EXTENSION
|
||||
\echo Use "ALTER EXTENSION vector UPDATE TO '0.5.1'" to load this file. \quit
|
||||
11
src/hnsw.c
11
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;
|
||||
amroutine->amcanreturn = hnswcanreturn;
|
||||
amroutine->amcostestimate = hnswcostestimate;
|
||||
amroutine->amoptions = hnswoptions;
|
||||
amroutine->amproperty = NULL; /* TODO AMPROP_DISTANCE_ORDERABLE */
|
||||
|
||||
@@ -57,6 +57,8 @@
|
||||
/* PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE is 1 */
|
||||
#define PROGRESS_HNSW_PHASE_LOAD 2
|
||||
|
||||
#define HNSW_MAX_SIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - sizeof(ItemIdData))
|
||||
|
||||
#define HNSW_ELEMENT_TUPLE_SIZE(_dim) MAXALIGN(offsetof(HnswElementTupleData, vec) + VECTOR_SIZE(_dim))
|
||||
#define HNSW_NEIGHBOR_TUPLE_SIZE(level, m) MAXALIGN(offsetof(HnswNeighborTupleData, indextids) + ((level) + 2) * (m) * sizeof(ItemPointerData))
|
||||
|
||||
@@ -110,11 +112,13 @@ typedef struct HnswCandidate
|
||||
{
|
||||
HnswElement element;
|
||||
float distance;
|
||||
bool closer;
|
||||
} HnswCandidate;
|
||||
|
||||
typedef struct HnswNeighborArray
|
||||
{
|
||||
int length;
|
||||
bool closerSet;
|
||||
HnswCandidate *items;
|
||||
} HnswNeighborArray;
|
||||
|
||||
@@ -218,7 +222,6 @@ typedef HnswNeighborTupleData * HnswNeighborTuple;
|
||||
typedef struct HnswScanOpaqueData
|
||||
{
|
||||
bool first;
|
||||
Buffer buf;
|
||||
List *w;
|
||||
MemoryContext tmpCtx;
|
||||
|
||||
@@ -259,14 +262,14 @@ typedef struct HnswVacuumState
|
||||
/* Methods */
|
||||
int HnswGetM(Relation index);
|
||||
int HnswGetEfConstruction(Relation index);
|
||||
FmgrInfo *HnswOptionalProcInfo(Relation rel, uint16 procnum);
|
||||
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
|
||||
bool 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);
|
||||
List *HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool loadVec, HnswElement skipElement);
|
||||
HnswElement HnswGetEntryPoint(Relation index);
|
||||
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
|
||||
HnswElement HnswInitElement(ItemPointer tid, int m, double ml, int maxLevel);
|
||||
|
||||
@@ -81,7 +81,6 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **
|
||||
HnswPageGetOpaque(*page)->nextblkno = BufferGetBlockNumber(newbuf);
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(*buf);
|
||||
GenericXLogFinish(*state);
|
||||
UnlockReleaseBuffer(*buf);
|
||||
|
||||
@@ -118,12 +117,12 @@ CreateElementPages(HnswBuildState * buildstate)
|
||||
ListCell *lc;
|
||||
|
||||
/* Calculate sizes */
|
||||
maxSize = BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData));
|
||||
maxSize = HNSW_MAX_SIZE;
|
||||
etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
|
||||
|
||||
/* Allocate once */
|
||||
etup = palloc0(etupSize);
|
||||
ntup = palloc0(maxSize);
|
||||
ntup = palloc0(BLCKSZ);
|
||||
|
||||
/* Prepare first page */
|
||||
buf = HnswNewBuffer(index, forkNum);
|
||||
@@ -179,7 +178,6 @@ CreateElementPages(HnswBuildState * buildstate)
|
||||
insertPage = BufferGetBlockNumber(buf);
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
@@ -227,7 +225,6 @@ CreateNeighborPages(HnswBuildState * buildstate)
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
|
||||
@@ -135,7 +135,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
|
||||
etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
|
||||
ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
|
||||
combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
|
||||
maxSize = BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData));
|
||||
maxSize = HNSW_MAX_SIZE;
|
||||
minCombinedSize = etupSize + HNSW_NEIGHBOR_TUPLE_SIZE(0, m) + sizeof(ItemIdData);
|
||||
|
||||
/* Prepare element tuple */
|
||||
@@ -202,8 +202,6 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
|
||||
HnswInsertAppendPage(index, &newbuf, &newpage, state, page);
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(newbuf);
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
|
||||
/* Unlock previous buffer */
|
||||
@@ -270,9 +268,6 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
|
||||
}
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(buf);
|
||||
if (nbuf != buf)
|
||||
MarkBufferDirty(nbuf);
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
if (nbuf != buf)
|
||||
@@ -391,7 +386,6 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
}
|
||||
else
|
||||
@@ -445,7 +439,6 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
|
||||
@@ -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;
|
||||
int m;
|
||||
@@ -28,15 +29,15 @@ 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, m, false, NULL);
|
||||
w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, loadVec, NULL);
|
||||
ep = w;
|
||||
}
|
||||
|
||||
return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
|
||||
return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, loadVec, NULL);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -101,7 +102,6 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
|
||||
scan = RelationGetIndexScan(index, nkeys, norderbys);
|
||||
|
||||
so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
|
||||
so->buf = InvalidBuffer;
|
||||
so->first = true;
|
||||
so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
|
||||
"Hnsw scan temporary context",
|
||||
@@ -114,11 +114,8 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
|
||||
|
||||
scan->opaque = so;
|
||||
|
||||
/*
|
||||
* Get a shared lock. This allows vacuum to ensure no in-flight scans
|
||||
* before marking tuples as deleted.
|
||||
*/
|
||||
LockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
|
||||
/* OK to always set since cheap */
|
||||
scan->xs_itupdesc = RelationGetDescr(index);
|
||||
|
||||
return scan;
|
||||
}
|
||||
@@ -167,11 +164,25 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
if (scan->orderByData == NULL)
|
||||
elog(ERROR, "cannot scan hnsw index without order");
|
||||
|
||||
/* Requires MVCC-compliant snapshot as not able to maintain a pin */
|
||||
/* https://www.postgresql.org/docs/current/index-locking.html */
|
||||
if (!IsMVCCSnapshot(scan->xs_snapshot))
|
||||
elog(ERROR, "non-MVCC snapshots are not supported with hnsw");
|
||||
|
||||
/* Get scan value */
|
||||
value = GetScanValue(scan);
|
||||
|
||||
/*
|
||||
* Get a shared lock. This allows vacuum to ensure no in-flight scans
|
||||
* before marking tuples as deleted.
|
||||
*/
|
||||
LockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
|
||||
|
||||
so->w = GetScanItems(scan, value);
|
||||
|
||||
/* Release shared lock */
|
||||
UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
|
||||
|
||||
so->first = false;
|
||||
}
|
||||
|
||||
@@ -179,7 +190,6 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
{
|
||||
HnswCandidate *hc = llast(so->w);
|
||||
ItemPointer heaptid;
|
||||
BlockNumber indexblkno;
|
||||
|
||||
/* Move to next element if no valid heap TIDs */
|
||||
if (list_length(hc->element->heaptids) == 0)
|
||||
@@ -189,10 +199,18 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
}
|
||||
|
||||
heaptid = llast(hc->element->heaptids);
|
||||
indexblkno = hc->element->blkno;
|
||||
|
||||
hc->element->heaptids = list_delete_last(hc->element->heaptids);
|
||||
|
||||
if (scan->xs_want_itup)
|
||||
{
|
||||
Datum value = PointerGetDatum(hc->element->vec);
|
||||
bool isnull = false;
|
||||
|
||||
/* Allocate in temporary context, so no need to free */
|
||||
scan->xs_itup = index_form_tuple(scan->xs_itupdesc, &value, &isnull);
|
||||
}
|
||||
|
||||
MemoryContextSwitchTo(oldCtx);
|
||||
|
||||
#if PG_VERSION_NUM >= 120000
|
||||
@@ -201,18 +219,6 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
scan->xs_ctup.t_self = *heaptid;
|
||||
#endif
|
||||
|
||||
/* Unpin buffer */
|
||||
if (BufferIsValid(so->buf))
|
||||
ReleaseBuffer(so->buf);
|
||||
|
||||
/*
|
||||
* An index scan must maintain a pin on the index page holding the
|
||||
* item last returned by amgettuple
|
||||
*
|
||||
* https://www.postgresql.org/docs/current/index-locking.html
|
||||
*/
|
||||
so->buf = ReadBuffer(scan->indexRelation, indexblkno);
|
||||
|
||||
scan->xs_recheckorderby = false;
|
||||
return true;
|
||||
}
|
||||
@@ -229,13 +235,6 @@ hnswendscan(IndexScanDesc scan)
|
||||
{
|
||||
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
|
||||
|
||||
/* Release pin */
|
||||
if (BufferIsValid(so->buf))
|
||||
ReleaseBuffer(so->buf);
|
||||
|
||||
/* Release shared lock */
|
||||
UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
|
||||
|
||||
MemoryContextDelete(so->tmpCtx);
|
||||
|
||||
pfree(so);
|
||||
|
||||
141
src/hnswutils.c
141
src/hnswutils.c
@@ -38,12 +38,12 @@ HnswGetEfConstruction(Relation index)
|
||||
* Get proc
|
||||
*/
|
||||
FmgrInfo *
|
||||
HnswOptionalProcInfo(Relation rel, uint16 procnum)
|
||||
HnswOptionalProcInfo(Relation index, uint16 procnum)
|
||||
{
|
||||
if (!OidIsValid(index_getprocid(rel, 1, procnum)))
|
||||
if (!OidIsValid(index_getprocid(index, 1, procnum)))
|
||||
return NULL;
|
||||
|
||||
return index_getprocinfo(rel, 1, procnum);
|
||||
return index_getprocinfo(index, 1, procnum);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -117,7 +117,6 @@ HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState *
|
||||
void
|
||||
HnswCommitBuffer(Buffer buf, GenericXLogState *state)
|
||||
{
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
@@ -140,9 +139,21 @@ HnswInitNeighbors(HnswElement element, int m)
|
||||
a = &element->neighbors[lc];
|
||||
a->length = 0;
|
||||
a->items = palloc(sizeof(HnswCandidate) * lm);
|
||||
a->closerSet = false;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Free neighbors
|
||||
*/
|
||||
static void
|
||||
HnswFreeNeighbors(HnswElement element)
|
||||
{
|
||||
for (int lc = 0; lc <= element->level; lc++)
|
||||
pfree(element->neighbors[lc].items);
|
||||
pfree(element->neighbors);
|
||||
}
|
||||
|
||||
/*
|
||||
* Allocate an element
|
||||
*/
|
||||
@@ -174,10 +185,8 @@ HnswInitElement(ItemPointer heaptid, int m, double ml, int maxLevel)
|
||||
void
|
||||
HnswFreeElement(HnswElement element)
|
||||
{
|
||||
HnswFreeNeighbors(element);
|
||||
list_free_deep(element->heaptids);
|
||||
for (int lc = 0; lc <= element->level; lc++)
|
||||
pfree(element->neighbors[lc].items);
|
||||
pfree(element->neighbors);
|
||||
pfree(element->vec);
|
||||
pfree(element);
|
||||
}
|
||||
@@ -560,7 +569,7 @@ 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, int m, bool inserting, HnswElement skipElement)
|
||||
HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool loadVec, HnswElement skipElement)
|
||||
{
|
||||
ListCell *lc2;
|
||||
|
||||
@@ -636,7 +645,7 @@ 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);
|
||||
|
||||
@@ -684,6 +693,34 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
|
||||
return w;
|
||||
}
|
||||
|
||||
/*
|
||||
* Compare candidate distances
|
||||
*/
|
||||
static int
|
||||
#if PG_VERSION_NUM >= 130000
|
||||
CompareCandidateDistances(const ListCell *a, const ListCell *b)
|
||||
#else
|
||||
CompareCandidateDistances(const void *a, const void *b)
|
||||
#endif
|
||||
{
|
||||
HnswCandidate *hca = lfirst((ListCell *) a);
|
||||
HnswCandidate *hcb = lfirst((ListCell *) b);
|
||||
|
||||
if (hca->distance < hcb->distance)
|
||||
return 1;
|
||||
|
||||
if (hca->distance > hcb->distance)
|
||||
return -1;
|
||||
|
||||
if (hca->element < hcb->element)
|
||||
return 1;
|
||||
|
||||
if (hca->element > hcb->element)
|
||||
return -1;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Calculate the distance between elements
|
||||
*/
|
||||
@@ -740,33 +777,77 @@ CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid c
|
||||
* Algorithm 4 from paper
|
||||
*/
|
||||
static List *
|
||||
SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswCandidate * *pruned)
|
||||
SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
|
||||
{
|
||||
List *r = NIL;
|
||||
List *w = list_copy(c);
|
||||
pairingheap *wd;
|
||||
bool mustCalculate = !e2->neighbors[lc].closerSet;
|
||||
List *added = NIL;
|
||||
bool removedAny = false;
|
||||
|
||||
if (list_length(w) <= m)
|
||||
return w;
|
||||
|
||||
wd = pairingheap_allocate(CompareNearestCandidates, NULL);
|
||||
|
||||
/* Ensure order of candidates is deterministic for closer caching */
|
||||
if (sortCandidates)
|
||||
list_sort(w, CompareCandidateDistances);
|
||||
|
||||
while (list_length(w) > 0 && list_length(r) < m)
|
||||
{
|
||||
/* Assumes w is already ordered desc */
|
||||
HnswCandidate *e = llast(w);
|
||||
bool closer;
|
||||
|
||||
w = list_delete_last(w);
|
||||
|
||||
closer = CheckElementCloser(e, r, lc, procinfo, collation);
|
||||
/* Use previous state of r and wd to skip work when possible */
|
||||
if (mustCalculate)
|
||||
e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
|
||||
else if (list_length(added) > 0)
|
||||
{
|
||||
/*
|
||||
* If the current candidate was closer, we only need to compare it
|
||||
* with the other candidates that we have added.
|
||||
*/
|
||||
if (e->closer)
|
||||
{
|
||||
e->closer = CheckElementCloser(e, added, lc, procinfo, collation);
|
||||
|
||||
if (closer)
|
||||
if (!e->closer)
|
||||
removedAny = true;
|
||||
}
|
||||
else
|
||||
{
|
||||
/*
|
||||
* If we have removed any candidates from closer, a candidate
|
||||
* that was not closer earlier might now be.
|
||||
*/
|
||||
if (removedAny)
|
||||
{
|
||||
e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
|
||||
if (e->closer)
|
||||
added = lappend(added, e);
|
||||
}
|
||||
}
|
||||
}
|
||||
else if (e == newCandidate)
|
||||
{
|
||||
e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
|
||||
if (e->closer)
|
||||
added = lappend(added, e);
|
||||
}
|
||||
|
||||
if (e->closer)
|
||||
r = lappend(r, e);
|
||||
else
|
||||
pairingheap_add(wd, &(CreatePairingHeapNode(e)->ph_node));
|
||||
}
|
||||
|
||||
/* Cached value can only be used in future if sorted deterministically */
|
||||
e2->neighbors[lc].closerSet = sortCandidates;
|
||||
|
||||
/* Keep pruned connections */
|
||||
while (!pairingheap_is_empty(wd) && list_length(r) < m)
|
||||
r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
|
||||
@@ -820,28 +901,6 @@ AddConnections(HnswElement element, List *neighbors, int m, int lc)
|
||||
a->items[a->length++] = *((HnswCandidate *) lfirst(lc2));
|
||||
}
|
||||
|
||||
/*
|
||||
* Compare candidate distances
|
||||
*/
|
||||
static int
|
||||
#if PG_VERSION_NUM >= 130000
|
||||
CompareCandidateDistances(const ListCell *a, const ListCell *b)
|
||||
#else
|
||||
CompareCandidateDistances(const void *a, const void *b)
|
||||
#endif
|
||||
{
|
||||
HnswCandidate *hca = lfirst((ListCell *) a);
|
||||
HnswCandidate *hcb = lfirst((ListCell *) b);
|
||||
|
||||
if (hca->distance < hcb->distance)
|
||||
return 1;
|
||||
|
||||
if (hca->distance > hcb->distance)
|
||||
return -1;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Update connections
|
||||
*/
|
||||
@@ -895,13 +954,12 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
|
||||
{
|
||||
List *c = NIL;
|
||||
|
||||
/* Add and sort candidates */
|
||||
/* Add candidates */
|
||||
for (int i = 0; i < currentNeighbors->length; i++)
|
||||
c = lappend(c, ¤tNeighbors->items[i]);
|
||||
c = lappend(c, &hc2);
|
||||
list_sort(c, CompareCandidateDistances);
|
||||
|
||||
SelectNeighbors(c, m, lc, procinfo, collation, &pruned);
|
||||
SelectNeighbors(c, m, lc, procinfo, collation, hc->element, &hc2, &pruned, true);
|
||||
|
||||
/* Should not happen */
|
||||
if (pruned == NULL)
|
||||
@@ -1000,7 +1058,12 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
|
||||
else
|
||||
lw = w;
|
||||
|
||||
neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, NULL);
|
||||
/*
|
||||
* Candidates are sorted, but not deterministically. Could set
|
||||
* sortCandidates to true for in-memory builds to enable closer
|
||||
* caching, but there does not seem to be a difference in performance.
|
||||
*/
|
||||
neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, element, NULL, NULL, false);
|
||||
|
||||
AddConnections(element, neighbors, lm, lc);
|
||||
|
||||
|
||||
@@ -128,10 +128,7 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
|
||||
blkno = HnswPageGetOpaque(page)->nextblkno;
|
||||
|
||||
if (updated)
|
||||
{
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
}
|
||||
else
|
||||
GenericXLogAbort(state);
|
||||
|
||||
@@ -229,7 +226,6 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
@@ -547,9 +543,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(buf);
|
||||
if (nbuf != buf)
|
||||
MarkBufferDirty(nbuf);
|
||||
GenericXLogFinish(state);
|
||||
if (nbuf != buf)
|
||||
UnlockReleaseBuffer(nbuf);
|
||||
|
||||
@@ -506,29 +506,30 @@ CreateListPages(Relation index, VectorArray centers, int dimensions,
|
||||
Buffer buf;
|
||||
Page page;
|
||||
GenericXLogState *state;
|
||||
OffsetNumber offno;
|
||||
Size itemsz;
|
||||
Size listSize;
|
||||
IvfflatList list;
|
||||
|
||||
itemsz = MAXALIGN(IVFFLAT_LIST_SIZE(dimensions));
|
||||
list = palloc(itemsz);
|
||||
listSize = MAXALIGN(IVFFLAT_LIST_SIZE(dimensions));
|
||||
list = palloc(listSize);
|
||||
|
||||
buf = IvfflatNewBuffer(index, forkNum);
|
||||
IvfflatInitRegisterPage(index, &buf, &page, &state);
|
||||
|
||||
for (int i = 0; i < lists; i++)
|
||||
{
|
||||
OffsetNumber offno;
|
||||
|
||||
/* Load list */
|
||||
list->startPage = InvalidBlockNumber;
|
||||
list->insertPage = InvalidBlockNumber;
|
||||
memcpy(&list->center, VectorArrayGet(centers, i), VECTOR_SIZE(dimensions));
|
||||
|
||||
/* Ensure free space */
|
||||
if (PageGetFreeSpace(page) < itemsz)
|
||||
if (PageGetFreeSpace(page) < listSize)
|
||||
IvfflatAppendPage(index, &buf, &page, &state, forkNum);
|
||||
|
||||
/* Add the item */
|
||||
offno = PageAddItem(page, (Item) list, itemsz, InvalidOffsetNumber, false, false);
|
||||
offno = PageAddItem(page, (Item) list, listSize, InvalidOffsetNumber, false, false);
|
||||
if (offno == InvalidOffsetNumber)
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
|
||||
@@ -275,7 +275,7 @@ VectorArray VectorArrayInit(int maxlen, int dimensions);
|
||||
void VectorArrayFree(VectorArray arr);
|
||||
void PrintVectorArray(char *msg, VectorArray arr);
|
||||
void IvfflatKmeans(Relation index, VectorArray samples, VectorArray centers);
|
||||
FmgrInfo *IvfflatOptionalProcInfo(Relation rel, uint16 procnum);
|
||||
FmgrInfo *IvfflatOptionalProcInfo(Relation index, uint16 procnum);
|
||||
bool IvfflatNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
|
||||
int IvfflatGetLists(Relation index);
|
||||
void IvfflatGetMetaPageInfo(Relation index, int *lists, int *dimensions);
|
||||
|
||||
@@ -11,36 +11,37 @@
|
||||
* Find the list that minimizes the distance function
|
||||
*/
|
||||
static void
|
||||
FindInsertPage(Relation rel, Datum *values, BlockNumber *insertPage, ListInfo * listInfo)
|
||||
FindInsertPage(Relation index, Datum *values, BlockNumber *insertPage, ListInfo * listInfo)
|
||||
{
|
||||
Buffer cbuf;
|
||||
Page cpage;
|
||||
IvfflatList list;
|
||||
double distance;
|
||||
double minDistance = DBL_MAX;
|
||||
BlockNumber nextblkno = IVFFLAT_HEAD_BLKNO;
|
||||
FmgrInfo *procinfo;
|
||||
Oid collation;
|
||||
OffsetNumber offno;
|
||||
OffsetNumber maxoffno;
|
||||
|
||||
/* Avoid compiler warning */
|
||||
listInfo->blkno = nextblkno;
|
||||
listInfo->offno = FirstOffsetNumber;
|
||||
|
||||
procinfo = index_getprocinfo(rel, 1, IVFFLAT_DISTANCE_PROC);
|
||||
collation = rel->rd_indcollation[0];
|
||||
procinfo = index_getprocinfo(index, 1, IVFFLAT_DISTANCE_PROC);
|
||||
collation = index->rd_indcollation[0];
|
||||
|
||||
/* Search all list pages */
|
||||
while (BlockNumberIsValid(nextblkno))
|
||||
{
|
||||
cbuf = ReadBuffer(rel, nextblkno);
|
||||
Buffer cbuf;
|
||||
Page cpage;
|
||||
OffsetNumber maxoffno;
|
||||
|
||||
cbuf = ReadBuffer(index, nextblkno);
|
||||
LockBuffer(cbuf, BUFFER_LOCK_SHARE);
|
||||
cpage = BufferGetPage(cbuf);
|
||||
maxoffno = PageGetMaxOffsetNumber(cpage);
|
||||
|
||||
for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
|
||||
for (OffsetNumber offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
|
||||
{
|
||||
IvfflatList list;
|
||||
double distance;
|
||||
|
||||
list = (IvfflatList) PageGetItem(cpage, PageGetItemId(cpage, offno));
|
||||
distance = DatumGetFloat8(FunctionCall2Coll(procinfo, collation, values[0], PointerGetDatum(&list->center)));
|
||||
|
||||
@@ -63,7 +64,7 @@ FindInsertPage(Relation rel, Datum *values, BlockNumber *insertPage, ListInfo *
|
||||
* Insert a tuple into the index
|
||||
*/
|
||||
static void
|
||||
InsertTuple(Relation rel, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
|
||||
InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
|
||||
{
|
||||
IndexTuple itup;
|
||||
Datum value;
|
||||
@@ -80,33 +81,33 @@ InsertTuple(Relation rel, Datum *values, bool *isnull, ItemPointer heap_tid, Rel
|
||||
value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
|
||||
|
||||
/* Normalize if needed */
|
||||
normprocinfo = IvfflatOptionalProcInfo(rel, IVFFLAT_NORM_PROC);
|
||||
normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
|
||||
if (normprocinfo != NULL)
|
||||
{
|
||||
if (!IvfflatNormValue(normprocinfo, rel->rd_indcollation[0], &value, NULL))
|
||||
if (!IvfflatNormValue(normprocinfo, index->rd_indcollation[0], &value, NULL))
|
||||
return;
|
||||
}
|
||||
|
||||
/* Find the insert page - sets the page and list info */
|
||||
FindInsertPage(rel, values, &insertPage, &listInfo);
|
||||
FindInsertPage(index, values, &insertPage, &listInfo);
|
||||
Assert(BlockNumberIsValid(insertPage));
|
||||
originalInsertPage = insertPage;
|
||||
|
||||
/* Form tuple */
|
||||
itup = index_form_tuple(RelationGetDescr(rel), &value, isnull);
|
||||
itup = index_form_tuple(RelationGetDescr(index), &value, isnull);
|
||||
itup->t_tid = *heap_tid;
|
||||
|
||||
/* Get tuple size */
|
||||
itemsz = MAXALIGN(IndexTupleSize(itup));
|
||||
Assert(itemsz <= BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(IvfflatPageOpaqueData)));
|
||||
Assert(itemsz <= BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(IvfflatPageOpaqueData)) - sizeof(ItemIdData));
|
||||
|
||||
/* Find a page to insert the item */
|
||||
for (;;)
|
||||
{
|
||||
buf = ReadBuffer(rel, insertPage);
|
||||
buf = ReadBuffer(index, insertPage);
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
|
||||
state = GenericXLogStart(rel);
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
|
||||
if (PageGetFreeSpace(page) >= itemsz)
|
||||
@@ -126,9 +127,9 @@ InsertTuple(Relation rel, Datum *values, bool *isnull, ItemPointer heap_tid, Rel
|
||||
Page newpage;
|
||||
|
||||
/* Add a new page */
|
||||
LockRelationForExtension(rel, ExclusiveLock);
|
||||
newbuf = IvfflatNewBuffer(rel, MAIN_FORKNUM);
|
||||
UnlockRelationForExtension(rel, ExclusiveLock);
|
||||
LockRelationForExtension(index, ExclusiveLock);
|
||||
newbuf = IvfflatNewBuffer(index, MAIN_FORKNUM);
|
||||
UnlockRelationForExtension(index, ExclusiveLock);
|
||||
|
||||
/* Init new page */
|
||||
newpage = GenericXLogRegisterBuffer(state, newbuf, GENERIC_XLOG_FULL_IMAGE);
|
||||
@@ -141,15 +142,13 @@ InsertTuple(Relation rel, Datum *values, bool *isnull, ItemPointer heap_tid, Rel
|
||||
IvfflatPageGetOpaque(page)->nextblkno = insertPage;
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(newbuf);
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
|
||||
/* Unlock previous buffer */
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
/* Prepare new buffer */
|
||||
state = GenericXLogStart(rel);
|
||||
state = GenericXLogStart(index);
|
||||
buf = newbuf;
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
break;
|
||||
@@ -158,13 +157,13 @@ InsertTuple(Relation rel, Datum *values, bool *isnull, ItemPointer heap_tid, Rel
|
||||
|
||||
/* Add to next offset */
|
||||
if (PageAddItem(page, (Item) itup, itemsz, InvalidOffsetNumber, false, false) == InvalidOffsetNumber)
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(rel));
|
||||
elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
|
||||
|
||||
IvfflatCommitBuffer(buf, state);
|
||||
|
||||
/* Update the insert page */
|
||||
if (insertPage != originalInsertPage)
|
||||
IvfflatUpdateList(rel, listInfo, insertPage, originalInsertPage, InvalidBlockNumber, MAIN_FORKNUM);
|
||||
IvfflatUpdateList(index, listInfo, insertPage, originalInsertPage, InvalidBlockNumber, MAIN_FORKNUM);
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
@@ -17,10 +17,6 @@ InitCenters(Relation index, VectorArray samples, VectorArray centers, float *low
|
||||
FmgrInfo *procinfo;
|
||||
Oid collation;
|
||||
int64 j;
|
||||
double distance;
|
||||
double sum;
|
||||
double choice;
|
||||
Vector *vec;
|
||||
float *weight = palloc(samples->length * sizeof(float));
|
||||
int numCenters = centers->maxlen;
|
||||
int numSamples = samples->length;
|
||||
@@ -33,17 +29,21 @@ InitCenters(Relation index, VectorArray samples, VectorArray centers, float *low
|
||||
centers->length++;
|
||||
|
||||
for (j = 0; j < numSamples; j++)
|
||||
weight[j] = DBL_MAX;
|
||||
weight[j] = FLT_MAX;
|
||||
|
||||
for (int i = 0; i < numCenters; i++)
|
||||
{
|
||||
double sum;
|
||||
double choice;
|
||||
|
||||
CHECK_FOR_INTERRUPTS();
|
||||
|
||||
sum = 0.0;
|
||||
|
||||
for (j = 0; j < numSamples; j++)
|
||||
{
|
||||
vec = VectorArrayGet(samples, j);
|
||||
Vector *vec = VectorArrayGet(samples, j);
|
||||
double distance;
|
||||
|
||||
/* Only need to compute distance for new center */
|
||||
/* TODO Use triangle inequality to reduce distance calculations */
|
||||
@@ -112,7 +112,6 @@ CompareVectors(const void *a, const void *b)
|
||||
static void
|
||||
QuickCenters(Relation index, VectorArray samples, VectorArray centers)
|
||||
{
|
||||
Vector *vec;
|
||||
int dimensions = centers->dim;
|
||||
Oid collation = index->rd_indcollation[0];
|
||||
FmgrInfo *normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_KMEANS_NORM_PROC);
|
||||
@@ -123,7 +122,7 @@ QuickCenters(Relation index, VectorArray samples, VectorArray centers)
|
||||
qsort(samples->items, samples->length, VECTOR_SIZE(samples->dim), CompareVectors);
|
||||
for (int i = 0; i < samples->length; i++)
|
||||
{
|
||||
vec = VectorArrayGet(samples, i);
|
||||
Vector *vec = VectorArrayGet(samples, i);
|
||||
|
||||
if (i == 0 || CompareVectors(vec, VectorArrayGet(samples, i - 1)) != 0)
|
||||
{
|
||||
@@ -136,7 +135,7 @@ QuickCenters(Relation index, VectorArray samples, VectorArray centers)
|
||||
/* Fill remaining with random data */
|
||||
while (centers->length < centers->maxlen)
|
||||
{
|
||||
vec = VectorArrayGet(centers, centers->length);
|
||||
Vector *vec = VectorArrayGet(centers, centers->length);
|
||||
|
||||
SET_VARSIZE(vec, VECTOR_SIZE(dimensions));
|
||||
vec->dim = dimensions;
|
||||
@@ -168,7 +167,6 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
Oid collation;
|
||||
Vector *vec;
|
||||
Vector *newCenter;
|
||||
int iteration;
|
||||
int64 j;
|
||||
int64 k;
|
||||
int dimensions = centers->dim;
|
||||
@@ -182,14 +180,6 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
float *s;
|
||||
float *halfcdist;
|
||||
float *newcdist;
|
||||
int changes;
|
||||
double minDistance;
|
||||
int closestCenter;
|
||||
double distance;
|
||||
bool rj;
|
||||
bool rjreset;
|
||||
double dxcx;
|
||||
double dxc;
|
||||
|
||||
/* Calculate allocation sizes */
|
||||
Size samplesSize = VECTOR_ARRAY_SIZE(samples->maxlen, samples->dim);
|
||||
@@ -247,14 +237,14 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
/* Assign each x to its closest initial center c(x) = argmin d(x,c) */
|
||||
for (j = 0; j < numSamples; j++)
|
||||
{
|
||||
minDistance = DBL_MAX;
|
||||
closestCenter = 0;
|
||||
float minDistance = FLT_MAX;
|
||||
int closestCenter = 0;
|
||||
|
||||
/* Find closest center */
|
||||
for (k = 0; k < numCenters; k++)
|
||||
{
|
||||
/* TODO Use Lemma 1 in k-means++ initialization */
|
||||
distance = lowerBound[j * numCenters + k];
|
||||
float distance = lowerBound[j * numCenters + k];
|
||||
|
||||
if (distance < minDistance)
|
||||
{
|
||||
@@ -268,13 +258,14 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
}
|
||||
|
||||
/* Give 500 iterations to converge */
|
||||
for (iteration = 0; iteration < 500; iteration++)
|
||||
for (int iteration = 0; iteration < 500; iteration++)
|
||||
{
|
||||
int changes = 0;
|
||||
bool rjreset;
|
||||
|
||||
/* Can take a while, so ensure we can interrupt */
|
||||
CHECK_FOR_INTERRUPTS();
|
||||
|
||||
changes = 0;
|
||||
|
||||
/* Step 1: For all centers, compute distance */
|
||||
for (j = 0; j < numCenters; j++)
|
||||
{
|
||||
@@ -282,7 +273,8 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
|
||||
for (k = j + 1; k < numCenters; k++)
|
||||
{
|
||||
distance = 0.5 * DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(vec), PointerGetDatum(VectorArrayGet(centers, k))));
|
||||
float distance = 0.5 * DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(vec), PointerGetDatum(VectorArrayGet(centers, k))));
|
||||
|
||||
halfcdist[j * numCenters + k] = distance;
|
||||
halfcdist[k * numCenters + j] = distance;
|
||||
}
|
||||
@@ -291,10 +283,12 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
/* For all centers c, compute s(c) */
|
||||
for (j = 0; j < numCenters; j++)
|
||||
{
|
||||
minDistance = DBL_MAX;
|
||||
float minDistance = FLT_MAX;
|
||||
|
||||
for (k = 0; k < numCenters; k++)
|
||||
{
|
||||
float distance;
|
||||
|
||||
if (j == k)
|
||||
continue;
|
||||
|
||||
@@ -310,6 +304,8 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
|
||||
for (j = 0; j < numSamples; j++)
|
||||
{
|
||||
bool rj;
|
||||
|
||||
/* Step 2: Identify all points x such that u(x) <= s(c(x)) */
|
||||
if (upperBound[j] <= s[closestCenters[j]])
|
||||
continue;
|
||||
@@ -318,6 +314,8 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
|
||||
for (k = 0; k < numCenters; k++)
|
||||
{
|
||||
float dxcx;
|
||||
|
||||
/* Step 3: For all remaining points x and centers c */
|
||||
if (k == closestCenters[j])
|
||||
continue;
|
||||
@@ -347,7 +345,7 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
/* Step 3b */
|
||||
if (dxcx > lowerBound[j * numCenters + k] || dxcx > halfcdist[closestCenters[j] * numCenters + k])
|
||||
{
|
||||
dxc = DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(vec), PointerGetDatum(VectorArrayGet(centers, k))));
|
||||
float dxc = DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(vec), PointerGetDatum(VectorArrayGet(centers, k))));
|
||||
|
||||
/* d(x,c) calculated */
|
||||
lowerBound[j * numCenters + k] = dxc;
|
||||
@@ -361,7 +359,6 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
|
||||
changes++;
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -378,6 +375,8 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
|
||||
for (j = 0; j < numSamples; j++)
|
||||
{
|
||||
int closestCenter;
|
||||
|
||||
vec = VectorArrayGet(samples, j);
|
||||
closestCenter = closestCenters[j];
|
||||
|
||||
@@ -426,7 +425,7 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
{
|
||||
for (k = 0; k < numCenters; k++)
|
||||
{
|
||||
distance = lowerBound[j * numCenters + k] - newcdist[k];
|
||||
float distance = lowerBound[j * numCenters + k] - newcdist[k];
|
||||
|
||||
if (distance < 0)
|
||||
distance = 0;
|
||||
@@ -442,7 +441,7 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
|
||||
|
||||
/* Step 7 */
|
||||
for (j = 0; j < numCenters; j++)
|
||||
memcpy(VectorArrayGet(centers, j), VectorArrayGet(newCenters, j), VECTOR_SIZE(dimensions));
|
||||
VectorArraySet(centers, j, VectorArrayGet(newCenters, j));
|
||||
|
||||
if (changes == 0 && iteration != 0)
|
||||
break;
|
||||
@@ -465,9 +464,6 @@ static void
|
||||
CheckCenters(Relation index, VectorArray centers)
|
||||
{
|
||||
FmgrInfo *normprocinfo;
|
||||
Oid collation;
|
||||
Vector *vec;
|
||||
double norm;
|
||||
|
||||
if (centers->length != centers->maxlen)
|
||||
elog(ERROR, "Not enough centers. Please report a bug.");
|
||||
@@ -475,7 +471,7 @@ CheckCenters(Relation index, VectorArray centers)
|
||||
/* Ensure no NaN or infinite values */
|
||||
for (int i = 0; i < centers->length; i++)
|
||||
{
|
||||
vec = VectorArrayGet(centers, i);
|
||||
Vector *vec = VectorArrayGet(centers, i);
|
||||
|
||||
for (int j = 0; j < vec->dim; j++)
|
||||
{
|
||||
@@ -501,11 +497,12 @@ CheckCenters(Relation index, VectorArray centers)
|
||||
normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
|
||||
if (normprocinfo != NULL)
|
||||
{
|
||||
collation = index->rd_indcollation[0];
|
||||
Oid collation = index->rd_indcollation[0];
|
||||
|
||||
for (int i = 0; i < centers->length; i++)
|
||||
{
|
||||
norm = DatumGetFloat8(FunctionCall1Coll(normprocinfo, collation, PointerGetDatum(VectorArrayGet(centers, i))));
|
||||
double norm = DatumGetFloat8(FunctionCall1Coll(normprocinfo, collation, PointerGetDatum(VectorArrayGet(centers, i))));
|
||||
|
||||
if (norm == 0)
|
||||
elog(ERROR, "Zero norm detected. Please report a bug.");
|
||||
}
|
||||
|
||||
@@ -288,7 +288,8 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
if (scan->orderByData == NULL)
|
||||
elog(ERROR, "cannot scan ivfflat index without order");
|
||||
|
||||
/* Safety check */
|
||||
/* Requires MVCC-compliant snapshot as not able to pin during sorting */
|
||||
/* https://www.postgresql.org/docs/current/index-locking.html */
|
||||
if (!IsMVCCSnapshot(scan->xs_snapshot))
|
||||
elog(ERROR, "non-MVCC snapshots are not supported with ivfflat");
|
||||
|
||||
@@ -326,12 +327,6 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
scan->xs_ctup.t_self = *heaptid;
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Since no pinning during sorting, requires MVCC-compliant snapshot.
|
||||
* Also, cannot kill prior tuples, since heap TID may be recycled.
|
||||
* https://www.postgresql.org/docs/current/index-locking.html
|
||||
*/
|
||||
|
||||
scan->xs_recheckorderby = false;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -57,12 +57,12 @@ IvfflatGetLists(Relation index)
|
||||
* Get proc
|
||||
*/
|
||||
FmgrInfo *
|
||||
IvfflatOptionalProcInfo(Relation rel, uint16 procnum)
|
||||
IvfflatOptionalProcInfo(Relation index, uint16 procnum)
|
||||
{
|
||||
if (!OidIsValid(index_getprocid(rel, 1, procnum)))
|
||||
if (!OidIsValid(index_getprocid(index, 1, procnum)))
|
||||
return NULL;
|
||||
|
||||
return index_getprocinfo(rel, 1, procnum);
|
||||
return index_getprocinfo(index, 1, procnum);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -136,7 +136,6 @@ IvfflatInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogStat
|
||||
void
|
||||
IvfflatCommitBuffer(Buffer buf, GenericXLogState *state)
|
||||
{
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
@@ -160,8 +159,6 @@ IvfflatAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **st
|
||||
IvfflatInitPage(newbuf, newpage);
|
||||
|
||||
/* Commit */
|
||||
MarkBufferDirty(*buf);
|
||||
MarkBufferDirty(newbuf);
|
||||
GenericXLogFinish(*state);
|
||||
|
||||
/* Unlock */
|
||||
|
||||
@@ -107,7 +107,6 @@ ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
|
||||
{
|
||||
/* Delete tuples */
|
||||
PageIndexMultiDelete(page, deletable, ndeletable);
|
||||
MarkBufferDirty(buf);
|
||||
GenericXLogFinish(state);
|
||||
}
|
||||
else
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
comment = 'vector data type and ivfflat and hnsw access methods'
|
||||
default_version = '0.5.0'
|
||||
default_version = '0.5.1'
|
||||
module_pathname = '$libdir/vector'
|
||||
relocatable = true
|
||||
|
||||
Reference in New Issue
Block a user