liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-07 13:10:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added iterative search for IVFFlat [skip ci]

Browse Source
This commit is contained in:
Andrew Kane
2024-10-10 18:12:27 -07:00
parent 48fe70c219
commit c91ed7b2c3
6 changed files with 258 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
src/ivfscan.c
View File

@@ -65,7 +65,7 @@ GetScanLists(IndexScanDesc scan, Datum value)
/* Use procinfo from the index instead of scan key for performance */
distance = DatumGetFloat8(so->distfunc(so->procinfo, so->collation, PointerGetDatum(&list->center), value));
if (listCount < so->probes)
if (listCount < so->maxProbes)
{
IvfflatScanList *scanlist;
@@ -78,7 +78,7 @@ GetScanLists(IndexScanDesc scan, Datum value)
pairingheap_add(so->listQueue, &scanlist->ph_node);
/* Calculate max distance */
if (listCount == so->probes)
if (listCount == so->maxProbes)
maxDistance = GetScanList(pairingheap_first(so->listQueue))->distance;
}
else if (distance < maxDistance)
@@ -102,6 +102,11 @@ GetScanLists(IndexScanDesc scan, Datum value)
UnlockReleaseBuffer(cbuf);
}
for (int i = listCount - 1; i >= 0; i--)
so->listPages[i] = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
Assert(pairingheap_is_empty(so->listQueue));
}
/*
@@ -114,11 +119,14 @@ GetScanItems(IndexScanDesc scan, Datum value)
TupleDesc tupdesc = RelationGetDescr(scan->indexRelation);
double tuples = 0;
TupleTableSlot *slot = so->vslot;
int batchProbes = 0;
tuplesort_reset(so->sortstate);
/* Search closest probes lists */
while (!pairingheap_is_empty(so->listQueue))
while (so->listIndex < so->maxProbes && (++batchProbes) <= so->probes)
{
BlockNumber searchPage = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
BlockNumber searchPage = so->listPages[so->listIndex++];
/* Search all entry pages for list */
while (BlockNumberIsValid(searchPage))
@@ -166,13 +174,17 @@ GetScanItems(IndexScanDesc scan, Datum value)
}
}
if (tuples < 100)
if (tuples < 100 && ivfflat_iterative_search == IVFFLAT_ITERATIVE_SEARCH_OFF)
ereport(DEBUG1,
(errmsg("index scan found few tuples"),
errdetail("Index may have been created with little data."),
errhint("Recreate the index and possibly decrease lists.")));
tuplesort_performsort(so->sortstate);
#if defined(IVFFLAT_MEMORY)
elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
#endif
}
/*
@@ -240,6 +252,7 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
int lists;
int dimensions;
int probes = ivfflat_probes;
int maxProbes;
scan = RelationGetIndexScan(index, nkeys, norderbys);
@@ -249,10 +262,21 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
if (probes > lists)
probes = lists;
so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
if (ivfflat_iterative_search != IVFFLAT_ITERATIVE_SEARCH_OFF)
{
if (ivfflat_iterative_search_max_probes == 0)
maxProbes = lists;
else
maxProbes = Min(ivfflat_iterative_search_max_probes, lists);
}
else
maxProbes = probes;
so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + maxProbes * sizeof(IvfflatScanList));
so->typeInfo = IvfflatGetTypeInfo(index);
so->first = true;
so->probes = probes;
so->maxProbes = maxProbes;
so->dimensions = dimensions;
/* Set support functions */
@@ -280,6 +304,8 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
so->bas = GetAccessStrategy(BAS_BULKREAD);
so->listQueue = pairingheap_allocate(CompareLists, scan);
so->listPages = palloc(maxProbes * sizeof(BlockNumber));
so->listIndex = 0;
scan->opaque = so;
@@ -294,11 +320,9 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
{
IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
if (!so->first)
tuplesort_reset(so->sortstate);
so->first = true;
pairingheap_reset(so->listQueue);
so->listIndex = 0;
if (keys && scan->numberOfKeys > 0)
memmove(scan->keyData, keys, scan->numberOfKeys * sizeof(ScanKeyData));
@@ -314,6 +338,8 @@ bool
ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
{
IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
ItemPointer heaptid;
bool isnull;
/*
* Index can be used to scan backward, but Postgres doesn't support
@@ -341,28 +367,25 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
IvfflatBench("GetScanLists", GetScanLists(scan, value));
IvfflatBench("GetScanItems", GetScanItems(scan, value));
so->first = false;
so->value = value;
#if defined(IVFFLAT_MEMORY)
elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
#endif
/* Clean up if we allocated a new value */
if (value != scan->orderByData->sk_argument)
pfree(DatumGetPointer(value));
/* TODO clean up if we allocated a new value */
}
if (tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
{
bool isnull;
ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
if (so->listIndex == so->maxProbes)
return false;
scan->xs_heaptid = *heaptid;
scan->xs_recheck = false;
scan->xs_recheckorderby = false;
return true;
IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
}
return false;
heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
scan->xs_heaptid = *heaptid;
scan->xs_recheck = false;
scan->xs_recheckorderby = false;
return true;
}
/*
@@ -374,6 +397,7 @@ ivfflatendscan(IndexScanDesc scan)
IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
pairingheap_free(so->listQueue);
pfree(so->listPages);
tuplesort_end(so->sortstate);
FreeAccessStrategy(so->bas);
FreeTupleDesc(so->tupdesc);