Compare commits

..

9 Commits

Author SHA1 Message Date
Andrew Kane
116501f062 Added support for inline filtering with IVFFlat 2024-10-10 17:07:47 -07:00
Andrew Kane
48fe70c219 Fixed sortdesc for multiple attributes [skip ci] 2024-10-10 15:22:23 -07:00
Andrew Kane
29908405ab List assignment does not change with scaling [skip ci] 2024-10-10 15:16:08 -07:00
Andrew Kane
08d0340655 Improved IVFFlat vacuum test [skip ci] 2024-10-10 14:24:26 -07:00
Andrew Kane
7d2eb49c2a Fixed list assignment for cosine distance and non-normalized vectors for IVFFlat 2024-10-10 12:54:13 -07:00
Andrew Kane
772ab69de6 Updated IVFFlat to support multiple attributes (not enabled yet) 2024-10-10 12:34:03 -07:00
Andrew Kane
e13e9a9614 Improved scoping [skip ci] 2024-10-10 12:19:08 -07:00
Andrew Kane
e2fab306ac Added tupdesc to buildstate [skip ci] 2024-10-10 12:18:41 -07:00
Andrew Kane
edc2126a4a Renamed tupdesc to sortdesc [skip ci] 2024-10-10 12:16:57 -07:00
19 changed files with 342 additions and 570 deletions

View File

@@ -1,6 +1,6 @@
## 0.8.0 (unreleased)
- Added support for iterative index scans
- Added support for inline filtering with IVFFlat
- Added casts for arrays to `sparsevec`
- Improved cost estimation
- Improved performance of HNSW inserts and on-disk index builds

View File

@@ -439,6 +439,12 @@ Create an index on one [or more](https://www.postgresql.org/docs/current/indexes
CREATE INDEX ON items (category_id);
```
Or a composite IVFFlat index for approximate search (added in 0.8.0)
```sql
CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops, category_id) WITH (lists = 100);
```
Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search
```sql
@@ -451,77 +457,6 @@ Use [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html
CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(category_id);
```
## Iterative Search [unreleased]
*Added in 0.8.0*
With approximate indexes, you can end up with less results than expected due to filtering conditions in the query.
Starting with 0.8.0, you can enable iterative search. If too few results from the initial index scan match the query filters, it will resume scanning until enough results are found. This can significantly improve recall (at the cost of speed).
```tsql
SET hnsw.streaming = on;
-- or
SET ivfflat.streaming = on;
```
However, there are some important caveats.
### Iterative Caveats
With iterative search, its possible for rows to be slightly out of order by distance. For strict ordering, use:
```sql
WITH approx_order AS MATERIALIZED (
SELECT *, embedding <-> '[1,2,3]' AS distance FROM items WHERE ... ORDER BY distance LIMIT 5
) SELECT * FROM approx_order ORDER BY distance;
```
For distance filters, use a CTE and place the filter outside it.
```sql
WITH approx_order AS MATERIALIZED (
SELECT *, embedding <-> '[1,2,3]' AS distance FROM items WHERE ... ORDER BY distance LIMIT 5
) SELECT * FROM approx_order WHERE distance < 0.1 ORDER BY distance;
```
### Iterative Options
Since scanning a large portion of the index is expensive, there are options to control when the scan ends.
#### HNSW
Specify the max number of additional tuples visited
```sql
SET hnsw.ef_stream = 10000;
```
The scan will also end if reaches `work_mem`. You can see when this happens by enabling debug messages.
```sql
SET client_min_messages = debug1;
```
```text
DEBUG: hnsw index scan exceeded work_mem after 10000 tuples
HINT: Increase work_mem to scan more tuples.
```
If the server has enough memory, you can adjust this with:
```sql
SET work_mem = '8MB';
```
#### IVFFlat
Specify the max number of probes
```sql
SET ivfflat.max_probes = 100;
```
## Half-Precision Vectors
*Added in 0.7.0*

View File

@@ -24,3 +24,5 @@ CREATE CAST (double precision[] AS sparsevec)
CREATE CAST (numeric[] AS sparsevec)
WITH FUNCTION array_to_sparsevec(numeric[], integer, boolean) AS ASSIGNMENT;
-- TODO add ivfflat attributes

View File

@@ -916,3 +916,13 @@ CREATE OPERATOR CLASS sparsevec_l1_ops
OPERATOR 1 <+> (sparsevec, sparsevec) FOR ORDER BY float_ops,
FUNCTION 1 l1_distance(sparsevec, sparsevec),
FUNCTION 3 hnsw_sparsevec_support(internal);
-- ivfflat attributes
CREATE OPERATOR CLASS vector_integer_ops
DEFAULT FOR TYPE integer USING ivfflat AS
OPERATOR 2 < ,
OPERATOR 3 <= ,
OPERATOR 4 = ,
OPERATOR 5 >= ,
OPERATOR 6 > ;

View File

@@ -18,18 +18,7 @@
#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
#endif
static const struct config_enum_entry hnsw_iterative_search_options[] = {
{"off", HNSW_ITERATIVE_SEARCH_OFF, false},
{"strict", HNSW_ITERATIVE_SEARCH_STRICT, false},
{"relaxed", HNSW_ITERATIVE_SEARCH_RELAXED, false},
/* TODO Change to strict before merging */
{"on", HNSW_ITERATIVE_SEARCH_RELAXED, false},
{NULL, 0, false}
};
int hnsw_ef_search;
int hnsw_max_iterative_tuples;
int hnsw_iterative_search;
int hnsw_lock_tranche_id;
static relopt_kind hnsw_relopt_kind;
@@ -80,17 +69,6 @@ HnswInit(void)
"Valid range is 1..1000.", &hnsw_ef_search,
HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, 0, NULL, NULL, NULL);
/* TODO Change name */
DefineCustomEnumVariable("hnsw.streaming", "Iterative search mode",
NULL, &hnsw_iterative_search,
HNSW_ITERATIVE_SEARCH_OFF, hnsw_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
/* TODO Change name */
/* TODO Ensure ivfflat.max_probes uses same value for "all" */
DefineCustomIntVariable("hnsw.ef_stream", "Sets the max number of additional candidates to visit for streaming search",
"-1 means all", &hnsw_max_iterative_tuples,
HNSW_DEFAULT_EF_STREAM, HNSW_MIN_EF_STREAM, HNSW_MAX_EF_STREAM, PGC_USERSET, 0, NULL, NULL, NULL);
MarkGUCPrefixReserved("hnsw");
}

View File

@@ -42,9 +42,6 @@
#define HNSW_DEFAULT_EF_SEARCH 40
#define HNSW_MIN_EF_SEARCH 1
#define HNSW_MAX_EF_SEARCH 1000
#define HNSW_DEFAULT_EF_STREAM -1
#define HNSW_MIN_EF_STREAM -1
#define HNSW_MAX_EF_STREAM INT_MAX
/* Tuple types */
#define HNSW_ELEMENT_TUPLE_TYPE 1
@@ -112,17 +109,8 @@
/* Variables */
extern int hnsw_ef_search;
extern int hnsw_max_iterative_tuples;
extern int hnsw_iterative_search;
extern int hnsw_lock_tranche_id;
typedef enum HnswIterativeSearchType
{
HNSW_ITERATIVE_SEARCH_OFF,
HNSW_ITERATIVE_SEARCH_STRICT,
HNSW_ITERATIVE_SEARCH_RELAXED
} HnswIterativeSearchType;
typedef struct HnswElementData HnswElementData;
typedef struct HnswNeighborArray HnswNeighborArray;
@@ -144,7 +132,6 @@ struct HnswElementData
uint8 heaptidsLength;
uint8 level;
uint8 deleted;
uint8 version;
uint32 hash;
HnswNeighborsPtr neighbors;
BlockNumber blkno;
@@ -332,10 +319,10 @@ typedef struct HnswElementTupleData
uint8 type;
uint8 level;
uint8 deleted;
uint8 version;
uint8 unused;
ItemPointerData heaptids[HNSW_HEAPTIDS];
ItemPointerData neighbortid;
uint16 unused;
uint16 unused2;
Vector data;
} HnswElementTupleData;
@@ -344,7 +331,7 @@ typedef HnswElementTupleData * HnswElementTuple;
typedef struct HnswNeighborTupleData
{
uint8 type;
uint8 version;
uint8 unused;
uint16 count;
ItemPointerData indextids[FLEXIBLE_ARRAY_MEMBER];
} HnswNeighborTupleData;
@@ -369,12 +356,6 @@ typedef struct HnswScanOpaqueData
const HnswTypeInfo *typeInfo;
bool first;
List *w;
visited_hash v;
pairingheap *discarded;
HnswQuery q;
int m;
int64 tuples;
double previousDistance;
MemoryContext tmpCtx;
/* Support functions */
@@ -418,7 +399,7 @@ bool HnswCheckNorm(HnswSupport * support, Datum value);
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
void HnswInitPage(Buffer buf, Page page);
void HnswInit(void);
List *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
List *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement);
HnswElement HnswGetEntryPoint(Relation index);
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
void *HnswAlloc(HnswAllocator * allocator, Size size);

View File

@@ -36,7 +36,7 @@ GetInsertPage(Relation index)
* Check for a free offset
*/
static bool
HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage, uint8 *tupleVersion)
HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage)
{
OffsetNumber offno;
OffsetNumber maxoffno = PageGetMaxOffsetNumber(page);
@@ -98,7 +98,6 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
{
*freeOffno = offno;
*freeNeighborOffno = neighborOffno;
*tupleVersion = etup->version;
return true;
}
else if (*nbuf != buf)
@@ -154,7 +153,6 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
OffsetNumber freeOffno = InvalidOffsetNumber;
OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
BlockNumber newInsertPage = InvalidBlockNumber;
uint8 tupleVersion;
char *base = NULL;
/* Calculate sizes */
@@ -204,7 +202,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
}
/* Next, try space from a deleted element */
if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage, &tupleVersion))
if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
{
if (nbuf != buf)
{
@@ -214,10 +212,6 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
npage = GenericXLogRegisterBuffer(state, nbuf, 0);
}
/* Set tuple version */
etup->version = tupleVersion;
ntup->version = tupleVersion;
break;
}

View File

@@ -5,7 +5,6 @@
#include "pgstat.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "utils/float.h"
#include "utils/memutils.h"
/*
@@ -22,57 +21,25 @@ GetScanItems(IndexScanDesc scan, Datum value)
int m;
HnswElement entryPoint;
char *base = NULL;
HnswQuery *q = &so->q;
HnswQuery q;
q.value = value;
/* Get m and entry point */
HnswGetMetaPageInfo(index, &m, &entryPoint);
q->value = value;
so->m = m;
if (entryPoint == NULL)
return NIL;
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false));
ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, false));
for (int lc = entryPoint->level; lc >= 1; lc--)
{
w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, NULL, NULL, true, NULL);
w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, false, NULL);
ep = w;
}
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF ? &so->discarded : NULL, true, &so->tuples);
}
/*
* Resume scan at ground level with discarded candidates
*/
static List *
ResumeScanItems(IndexScanDesc scan)
{
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
Relation index = scan->indexRelation;
List *ep = NIL;
char *base = NULL;
int batch_size = hnsw_ef_search;
if (pairingheap_is_empty(so->discarded))
return NIL;
/* Get next batch of candidates */
for (int i = 0; i < batch_size; i++)
{
HnswSearchCandidate *sc;
if (pairingheap_is_empty(so->discarded))
break;
sc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded));
ep = lappend(ep, sc);
}
return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, &so->v, &so->discarded, false, &so->tuples);
return HnswSearchLayer(base, &q, ep, hnsw_ef_search, 0, index, support, m, false, NULL);
}
/*
@@ -116,8 +83,6 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
so->typeInfo = HnswGetTypeInfo(index);
so->first = true;
so->v.tids = NULL;
so->discarded = NULL;
so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Hnsw scan temporary context",
ALLOCSET_DEFAULT_SIZES);
@@ -138,15 +103,7 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
{
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
if (so->v.tids != NULL)
tidhash_reset(so->v.tids);
if (so->discarded != NULL)
pairingheap_reset(so->discarded);
so->first = true;
so->tuples = 0;
so->previousDistance = -get_float8_infinity();
MemoryContextReset(so->tmpCtx);
if (keys && scan->numberOfKeys > 0)
@@ -208,100 +165,22 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
#endif
}
for (;;)
while (list_length(so->w) > 0)
{
char *base = NULL;
HnswSearchCandidate *sc;
HnswElement element;
HnswSearchCandidate *sc = llast(so->w);
HnswElement element = HnswPtrAccess(base, sc->element);
ItemPointer heaptid;
if (list_length(so->w) == 0)
{
if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_OFF)
break;
/* Empty index */
if (so->discarded == NULL)
break;
/* Reached max number of additional tuples */
if (hnsw_max_iterative_tuples != -1 && so->tuples >= hnsw_ef_search + hnsw_max_iterative_tuples)
{
if (pairingheap_is_empty(so->discarded))
break;
/* Return remaining tuples */
so->w = lappend(so->w, HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded)));
}
/* Prevent scans from consuming too much memory */
else if (MemoryContextMemAllocated(so->tmpCtx, false) > (Size) work_mem * 1024L)
{
if (pairingheap_is_empty(so->discarded))
{
ereport(DEBUG1,
(errmsg("hnsw index scan exceeded work_mem after " INT64_FORMAT " tuples", so->tuples),
errhint("Increase work_mem to scan more tuples.")));
break;
}
/* Return remaining tuples */
so->w = lappend(so->w, HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded)));
}
else
{
/*
* Locking ensures when neighbors are read, the elements they
* reference will not be deleted (and replaced) during the
* iteration.
*
* Elements loaded into memory on previous iterations may have
* been deleted (and replaced), so when reading neighbors, the
* element version must be checked.
*/
LockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
so->w = ResumeScanItems(scan);
UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
#if defined(HNSW_MEMORY)
elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
#endif
}
if (list_length(so->w) == 0)
break;
}
sc = llast(so->w);
element = HnswPtrAccess(base, sc->element);
/* Move to next element if no valid heap TIDs */
if (element->heaptidsLength == 0)
{
so->w = list_delete_last(so->w);
/* Mark memory as free for next iteration */
if (hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF)
{
pfree(element);
pfree(sc);
}
continue;
}
heaptid = &element->heaptids[--element->heaptidsLength];
if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_STRICT)
{
if (sc->distance < so->previousDistance)
continue;
so->previousDistance = sc->distance;
}
MemoryContextSwitchTo(oldCtx);
scan->xs_heaptid = *heaptid;

View File

@@ -251,8 +251,6 @@ HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel,
element->level = level;
element->deleted = 0;
/* Start at one to make it easier to find issues */
element->version = 1;
HnswInitNeighbors(base, element, m, allocator);
@@ -432,7 +430,6 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
etup->type = HNSW_ELEMENT_TUPLE_TYPE;
etup->level = element->level;
etup->deleted = 0;
etup->version = element->version;
for (int i = 0; i < HNSW_HEAPTIDS; i++)
{
if (i < element->heaptidsLength)
@@ -475,7 +472,6 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
}
ntup->count = idx;
ntup->version = e->version;
}
/*
@@ -486,7 +482,6 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
{
element->level = etup->level;
element->deleted = etup->deleted;
element->version = etup->version;
element->neighborPage = ItemPointerGetBlockNumber(&etup->neighbortid);
element->neighborOffno = ItemPointerGetOffsetNumber(&etup->neighbortid);
element->heaptidsLength = 0;
@@ -613,21 +608,6 @@ CompareNearestCandidates(const pairingheap_node *a, const pairingheap_node *b, v
return 0;
}
/*
* Compare discarded candidate distances
*/
static int
CompareNearestDiscardedCandidates(const pairingheap_node *a, const pairingheap_node *b, void *arg)
{
if (HnswGetSearchCandidateConst(w_node, a)->distance < HnswGetSearchCandidateConst(w_node, b)->distance)
return 1;
if (HnswGetSearchCandidateConst(w_node, a)->distance > HnswGetSearchCandidateConst(w_node, b)->distance)
return -1;
return 0;
}
/*
* Compare candidate distances
*/
@@ -748,11 +728,8 @@ HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation i
ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
/*
* Ensure the neighbor tuple has not been deleted or replaced between
* index scan iterations
*/
if (ntup->version != element->version || ntup->count != (element->level + 2) * m)
/* Ensure expected neighbors */
if (ntup->count != (element->level + 2) * m)
{
UnlockReleaseBuffer(buf);
return false;
@@ -798,13 +775,13 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
* Algorithm 2 from paper
*/
List *
HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement)
{
List *w = NIL;
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
int wlen = 0;
visited_hash vh;
visited_hash v;
ListCell *lc2;
HnswNeighborArray *localNeighborhood = NULL;
Size neighborhoodSize = 0;
@@ -813,19 +790,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
int unvisitedLength;
bool inMemory = index == NULL;
if (v == NULL)
{
v = &vh;
initVisited = true;
}
if (initVisited)
{
InitVisited(base, v, inMemory, ef, m);
if (discarded != NULL)
*discarded = pairingheap_allocate(CompareNearestDiscardedCandidates, NULL);
}
InitVisited(base, &v, inMemory, ef, m);
/* Create local memory for neighborhood if needed */
if (inMemory)
@@ -840,13 +805,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
HnswSearchCandidate *sc = (HnswSearchCandidate *) lfirst(lc2);
bool found;
if (initVisited)
{
AddToVisited(base, v, sc->element, inMemory, &found);
if (tuples != NULL)
(*tuples)++;
}
AddToVisited(base, &v, sc->element, inMemory, &found);
pairingheap_add(C, &sc->c_node);
pairingheap_add(W, &sc->w_node);
@@ -872,12 +831,9 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
cElement = HnswPtrAccess(base, c->element);
if (inMemory)
HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, v, lc, localNeighborhood, neighborhoodSize);
HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, &v, lc, localNeighborhood, neighborhoodSize);
else
HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, v, index, m, lm, lc);
if (tuples != NULL)
(*tuples) += unvisitedLength;
HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, &v, index, m, lm, lc);
for (int i = 0; i < unvisitedLength; i++)
{
@@ -901,25 +857,16 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
/* Avoid any allocations if not adding */
eElement = NULL;
HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd ? NULL : &f->distance, &eElement);
if (eElement == NULL)
continue;
}
if (eElement == NULL || !(eDistance < f->distance || alwaysAdd))
{
if (discarded != NULL)
{
/* Create a new candidate */
e = palloc(sizeof(HnswSearchCandidate));
HnswPtrStore(base, e->element, eElement);
e->distance = eDistance;
pairingheap_add(*discarded, &e->w_node);
}
if (!(eDistance < f->distance || alwaysAdd))
continue;
}
Assert(!eElement->deleted);
/* Make robust to issues */
if (eElement->level < lc)
@@ -943,12 +890,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
/* No need to decrement wlen */
if (wlen > ef)
{
HnswSearchCandidate *d = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
if (discarded != NULL)
pairingheap_add(*discarded, &d->w_node);
}
pairingheap_remove_first(W);
}
}
}
@@ -1283,7 +1225,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
/* 1st phase: greedy search to insert level */
for (int lc = entryLevel; lc >= level + 1; lc--)
{
w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement);
ep = w;
}
@@ -1302,7 +1244,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
List *lw = NIL;
ListCell *lc2;
w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement);
/* Convert search candidates to candidates */
foreach(lc2, w)

View File

@@ -527,14 +527,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
for (int i = 0; i < ntup->count; i++)
ItemPointerSetInvalid(&ntup->indextids[i]);
/* Increment version */
/* This is used to avoid incorrect reads for iterative scans */
/* Reserve some bits for future use */
etup->version++;
if (etup->version > 15)
etup->version = 1;
ntup->version = etup->version;
/*
* We modified the tuples in place, no need to call
* PageIndexTupleOverwrite

View File

@@ -138,7 +138,7 @@ SampleRows(IvfflatBuildState * buildstate)
* Add tuple to sort
*/
static void
AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState * buildstate)
AddTupleToSort(Relation index, ItemPointer tid, Datum *values, bool *isnull, IvfflatBuildState * buildstate)
{
double distance;
double minDistance = DBL_MAX;
@@ -184,6 +184,11 @@ AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState
slot->tts_isnull[1] = false;
slot->tts_values[2] = value;
slot->tts_isnull[2] = false;
for (int i = 1; i < buildstate->tupdesc->natts; i++)
{
slot->tts_values[2 + i] = values[i];
slot->tts_isnull[2 + i] = isnull[i];
}
ExecStoreVirtualTuple(slot);
/*
@@ -215,7 +220,7 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
/* Add tuple to sort */
AddTupleToSort(index, tid, values, buildstate);
AddTupleToSort(index, tid, values, isnull, buildstate);
/* Reset memory context */
MemoryContextSwitchTo(oldCtx);
@@ -226,19 +231,20 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
* Get index tuple from sort state
*/
static inline void
GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, IndexTuple *itup, int *list)
GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, Datum *values, bool *isnull, IndexTuple *itup, int *list)
{
Datum value;
bool isnull;
if (tuplesort_gettupleslot(sortstate, true, false, slot, NULL))
{
*list = DatumGetInt32(slot_getattr(slot, 1, &isnull));
value = slot_getattr(slot, 3, &isnull);
bool unused;
*list = DatumGetInt32(slot_getattr(slot, 1, &unused));
for (int i = 0; i < tupdesc->natts; i++)
values[i] = slot_getattr(slot, 3 + i, &isnull[i]);
/* Form the index tuple */
*itup = index_form_tuple(tupdesc, &value, &isnull);
(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &isnull)));
*itup = index_form_tuple(tupdesc, values, isnull);
(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &unused)));
}
else
*list = -1;
@@ -254,14 +260,16 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
IndexTuple itup = NULL; /* silence compiler warning */
int64 inserted = 0;
TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsMinimalTuple);
TupleDesc tupdesc = RelationGetDescr(index);
TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsMinimalTuple);
TupleDesc tupdesc = buildstate->tupdesc;
Datum *values = palloc(tupdesc->natts * sizeof(Datum));
bool *isnull = palloc(tupdesc->natts * sizeof(bool));
pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_TOTAL, buildstate->indtuples);
GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);
for (int i = 0; i < buildstate->centers->length; i++)
{
@@ -297,7 +305,7 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, ++inserted);
GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);
}
insertPage = BufferGetBlockNumber(buf);
@@ -307,6 +315,9 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
/* Set the start and insert pages */
IvfflatUpdateList(index, buildstate->listInfo[i], insertPage, InvalidBlockNumber, startPage, forkNum);
}
pfree(values);
pfree(isnull);
}
/*
@@ -319,6 +330,7 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
buildstate->index = index;
buildstate->indexInfo = indexInfo;
buildstate->typeInfo = IvfflatGetTypeInfo(index);
buildstate->tupdesc = RelationGetDescr(index);
buildstate->lists = IvfflatGetLists(index);
buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
@@ -329,6 +341,19 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("type not supported for ivfflat index")));
/* TODO See if needed */
if (IndexRelationGetNumberOfKeyAttributes(index) > 3)
elog(ERROR, "index cannot have more than three columns");
if (!OidIsValid(index_getprocid(index, 1, IVFFLAT_DISTANCE_PROC)))
elog(ERROR, "first column must be a vector");
for (int i = 1; i < IndexRelationGetNumberOfKeyAttributes(index); i++)
{
if (OidIsValid(index_getprocid(index, i + 1, IVFFLAT_DISTANCE_PROC)))
elog(ERROR, "column %d cannot be a vector", i + 1);
}
/* Require column to have dimensions to be indexed */
if (buildstate->dimensions < 0)
ereport(ERROR,
@@ -356,12 +381,13 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
errmsg("dimensions must be greater than one for this opclass")));
/* Create tuple description for sorting */
buildstate->tupdesc = CreateTemplateTupleDesc(3);
TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
buildstate->sortdesc = CreateTemplateTupleDesc(2 + buildstate->tupdesc->natts);
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
for (int i = 0; i < buildstate->tupdesc->natts; i++)
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) (3 + i), NULL, buildstate->tupdesc->attrs[i].atttypid, -1, 0);
buildstate->slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsVirtual);
buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);
buildstate->centers = VectorArrayInit(buildstate->lists, buildstate->dimensions, buildstate->typeInfo->itemSize(buildstate->dimensions));
buildstate->listInfo = palloc(sizeof(ListInfo) * buildstate->lists);
@@ -633,7 +659,7 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
InitBuildState(&buildstate, ivfspool->heap, ivfspool->index, indexInfo);
memcpy(buildstate.centers->items, ivfcenters, buildstate.centers->itemsize * buildstate.centers->maxlen);
buildstate.centers->length = buildstate.centers->maxlen;
ivfspool->sortstate = InitBuildSortState(buildstate.tupdesc, sortmem, coordinate);
ivfspool->sortstate = InitBuildSortState(buildstate.sortdesc, sortmem, coordinate);
buildstate.sortstate = ivfspool->sortstate;
scan = table_beginscan_parallel(ivfspool->heap,
ParallelTableScanFromIvfflatShared(ivfshared));
@@ -950,7 +976,7 @@ AssignTuples(IvfflatBuildState * buildstate)
}
/* Begin serial/leader tuplesort */
buildstate->sortstate = InitBuildSortState(buildstate->tupdesc, maintenance_work_mem, coordinate);
buildstate->sortstate = InitBuildSortState(buildstate->sortdesc, maintenance_work_mem, coordinate);
/* Add tuples to sort */
if (buildstate->heap != NULL)

View File

@@ -167,7 +167,7 @@ ivfflathandler(PG_FUNCTION_ARGS)
amroutine->amcanorderbyop = true;
amroutine->amcanbackward = false; /* can change direction mid-scan */
amroutine->amcanunique = false;
amroutine->amcanmulticol = false;
amroutine->amcanmulticol = true;
amroutine->amoptionalkey = true;
amroutine->amsearcharray = false;
amroutine->amsearchnulls = false;

View File

@@ -165,6 +165,7 @@ typedef struct IvfflatBuildState
Relation index;
IndexInfo *indexInfo;
const IvfflatTypeInfo *typeInfo;
TupleDesc tupdesc;
/* Settings */
int dimensions;
@@ -198,7 +199,7 @@ typedef struct IvfflatBuildState
/* Sorting */
Tuplesortstate *sortstate;
TupleDesc tupdesc;
TupleDesc sortdesc;
TupleTableSlot *slot;
/* Memory */

View File

@@ -78,6 +78,8 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
BlockNumber insertPage = InvalidBlockNumber;
ListInfo listInfo;
BlockNumber originalInsertPage;
TupleDesc tupdesc = RelationGetDescr(index);
Datum *newValues = palloc(tupdesc->natts * sizeof(Datum));
/* Detoast once for all calls */
value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -98,12 +100,16 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
IvfflatGetMetaPageInfo(index, NULL, NULL);
/* Find the insert page - sets the page and list info */
FindInsertPage(index, values, &insertPage, &listInfo);
FindInsertPage(index, &value, &insertPage, &listInfo);
Assert(BlockNumberIsValid(insertPage));
originalInsertPage = insertPage;
newValues[0] = value;
for (int i = 1; i < tupdesc->natts; i++)
newValues[i] = values[i];
/* Form tuple */
itup = index_form_tuple(RelationGetDescr(index), &value, isnull);
itup = index_form_tuple(tupdesc, newValues, isnull);
itup->t_tid = *heap_tid;
/* Get tuple size */

View File

@@ -104,6 +104,34 @@ GetScanLists(IndexScanDesc scan, Datum value)
}
}
/*
* Check if matches scan keys
*/
static bool
MatchesScanKeys(IndexScanDesc scan, IndexTuple itup, TupleDesc tupdesc)
{
for (int i = 0; i < scan->numberOfKeys; i++)
{
ScanKey key = &scan->keyData[i];
bool attnull = key->sk_flags & SK_ISNULL;
bool isnull;
Datum value = index_getattr(itup, key->sk_attno, tupdesc, &isnull);
if (isnull || attnull)
{
if (isnull != attnull)
return false;
}
else
{
if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
return false;
}
}
return true;
}
/*
* Get items
*/
@@ -140,6 +168,10 @@ GetScanItems(IndexScanDesc scan, Datum value)
ItemId itemid = PageGetItemId(page, offno);
itup = (IndexTuple) PageGetItem(page, itemid);
if (!MatchesScanKeys(scan, itup, tupdesc))
continue;
datum = index_getattr(itup, 1, tupdesc, &isnull);
/*

View File

@@ -6,13 +6,7 @@ use Test::More;
my $dim = 3;
my @r = ();
for (1 .. $dim)
{
my $v = int(rand(1000)) + 1;
push(@r, "i % $v");
}
my $array_sql = join(", ", @r);
my $array_sql = join(",", ('random()') x $dim);
# Initialize node
my $node = PostgreSQL::Test::Cluster->new('node');
@@ -23,19 +17,20 @@ $node->start;
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
# Get size
my $size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");
# Store values
$node->safe_psql("postgres", "CREATE TABLE tmp AS SELECT * FROM tst;");
# Delete all, vacuum, and insert same data
$node->safe_psql("postgres", "DELETE FROM tst;");
$node->safe_psql("postgres", "VACUUM tst;");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
);
$node->safe_psql("postgres", "INSERT INTO tst SELECT * FROM tmp;");
# Check size
my $new_size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");

View File

@@ -1,67 +0,0 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my $dim = 3;
my $array_sql = join(",", ('random()') x $dim);
# Initialize node
my $node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4 PRIMARY KEY, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
);
$node->safe_psql("postgres", qq(
SET maintenance_work_mem = '128MB';
SET max_parallel_maintenance_workers = 2;
CREATE INDEX ON tst USING hnsw (v vector_l2_ops)
));
my $count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.streaming = on;
SET work_mem = '8MB';
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
is($count, 10);
foreach ((30000, 50000, 70000))
{
my $ef_stream = $_;
my $expected = $ef_stream / 10000;
my $sum = 0;
for my $i (1 .. 20)
{
$count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.streaming = on;
SET hnsw.ef_stream = $ef_stream;
SET work_mem = '8MB';
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
));
$sum += $count;
}
my $avg = $sum / 20;
cmp_ok($avg, '>', $expected - 2);
cmp_ok($avg, '<', $expected + 2);
}
my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.streaming = on;
SET client_min_messages = debug1;
SET work_mem = '2MB';
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
like($stderr, qr/hnsw index scan exceeded work_mem after \d+ tuples/);
done_testing();

View File

@@ -0,0 +1,197 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my $node;
my @queries = ();
my @where = ();
my @expected;
my $limit = 20;
my $dim = 3;
my $array_sql = join(",", ('random()') x $dim);
my $nc = 100;
my $nc2 = 10;
sub test_recall
{
my ($probes, $min, $operator) = @_;
my $correct = 0;
my $total = 0;
for my $j (0 .. 2)
{
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = $probes;
EXPLAIN ANALYZE SELECT i FROM tst WHERE $where[$j] ORDER BY v $operator '$queries[$j]' LIMIT $limit;
));
like($explain, qr/Index Cond/);
}
for my $i (0 .. $#queries)
{
my $actual = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = $probes;
SELECT i FROM tst WHERE $where[$i] ORDER BY v $operator '$queries[$i]' LIMIT $limit;
));
my @actual_ids = split("\n", $actual);
my %actual_set = map { $_ => 1 } @actual_ids;
is(scalar(@actual_ids), $limit);
my @expected_ids = split("\n", $expected[$i]);
foreach (@expected_ids)
{
if (exists($actual_set{$_}))
{
$correct++;
}
$total++;
}
}
cmp_ok($correct / $total, ">=", $min, $operator);
}
# Initialize node
$node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int4, c2 int4);");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, i % $nc2 FROM generate_series(1, 50000) i;"
);
# Generate queries
for my $i (1 .. 100)
{
my @r = ();
for (1 .. $dim)
{
push(@r, rand());
}
push(@queries, "[" . join(",", @r) . "]");
if ($i % 3 == 0)
{
my $c = int(rand() * $nc);
push(@where, "c = $c");
}
elsif ($i % 3 == 1)
{
my $c2 = int(rand() * $nc2);
push(@where, "c2 = $c2");
}
else
{
# use c2 to ensure results
my $c2 = int(rand() * $nc2);
push(@where, "c = $c2 AND c2 = $c2");
}
}
# Add index
$node->safe_psql("postgres", qq(
CREATE INDEX ON tst USING ivfflat (v vector_l2_ops, c, c2) WITH (lists = 100);
));
# Insert more rows
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, i % $nc2 FROM generate_series(1, 50000) i;"
);
# Get exact results
@expected = ();
for my $i (0 .. $#queries)
{
my $res = $node->safe_psql("postgres", qq(
SET enable_indexscan = off;
SELECT i FROM tst WHERE $where[$i] ORDER BY v <-> '$queries[$i]' LIMIT $limit;
));
push(@expected, $res);
}
# Test recall
test_recall(10, 0.99, '<->');
# Test vacuum
$node->safe_psql("postgres", "DELETE FROM tst WHERE c > 5;");
$node->safe_psql("postgres", "VACUUM tst;");
# Test less than
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 10 ORDER BY v <-> '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Cond: \(c < 10\)/);
# Test less than or equal
$explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst WHERE c <= 10 ORDER BY v <-> '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Cond: \(c <= 10\)/);
# Test greater than or equal
$explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst WHERE c >= 90 ORDER BY v <-> '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Cond: \(c >= 90\)/);
# Test greater than
$explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst WHERE c > 90 ORDER BY v <-> '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Cond: \(c > 90\)/);
# Test multiple attribute columns
$explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = 1 AND c2 = 1 ORDER BY v <-> '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Cond: \(\(c = 1\) AND \(c2 = 1\)\)/);
# Test only last attribute column
$explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst WHERE c2 = 1 ORDER BY v <-> '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Cond: \(c2 = 1\)/);
# Test only vector column
$explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v <-> '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Scan/);
# Test only attribute columns
$explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = 1;
));
like($explain, qr/Seq Scan/);
# Test columns
my ($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING ivfflat (c);");
like($stderr, qr/first column must be a vector/);
($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING ivfflat (c, v vector_cosine_ops);");
like($stderr, qr/first column must be a vector/);
($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_cosine_ops, c, c, c);");
like($stderr, qr/index cannot have more than three columns/);
($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_cosine_ops, v vector_cosine_ops);");
like($stderr, qr/column 2 cannot be a vector/);
done_testing();

View File

@@ -1,131 +0,0 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my $node;
my @queries = ();
my @expected;
my $limit = 20;
my $dim = 3;
my $array_sql = join(",", ('random()') x $dim);
my @cs = (100, 1000);
sub test_recall
{
my ($c, $ef_search, $min, $operator) = @_;
my $correct = 0;
my $total = 0;
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.ef_search = $ef_search;
SET hnsw.streaming = on;
EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Scan using idx on tst/);
for my $i (0 .. $#queries)
{
my $actual = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.ef_search = $ef_search;
SET hnsw.streaming = on;
SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
));
my @actual_ids = split("\n", $actual);
my @expected_ids = split("\n", $expected[$i]);
my %expected_set = map { $_ => 1 } @expected_ids;
foreach (@actual_ids)
{
if (exists($expected_set{$_}))
{
$correct++;
}
}
$total += $limit;
}
cmp_ok($correct / $total, ">=", $min, $operator);
}
# Initialize node
$node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
);
# Generate queries
for (1 .. 20)
{
my @r = ();
for (1 .. $dim)
{
push(@r, rand());
}
push(@queries, "[" . join(",", @r) . "]");
}
# Check each index type
my @operators = ("<->", "<=>");
my @opclasses = ("vector_l2_ops", "vector_cosine_ops");
for my $i (0 .. $#operators)
{
my $operator = $operators[$i];
my $opclass = $opclasses[$i];
$node->safe_psql("postgres", qq(
SET maintenance_work_mem = '128MB';
CREATE INDEX idx ON tst USING hnsw (v $opclass);
));
foreach (@cs)
{
my $c = $_;
# Get exact results
@expected = ();
foreach (@queries)
{
my $res = $node->safe_psql("postgres", qq(
SET enable_indexscan = off;
WITH top AS (
SELECT v $operator '$_' AS distance FROM tst WHERE i % $c = 0 ORDER BY distance LIMIT $limit
)
SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
));
push(@expected, $res);
}
if ($c == 100)
{
test_recall($c, 40, 0.99, $operator);
}
else
{
if ($operator eq "<->")
{
test_recall($c, 40, 0.99, $operator);
}
else
{
test_recall($c, 40, 0.99, $operator);
}
}
}
$node->safe_psql("postgres", "DROP INDEX idx;");
}
done_testing();