Compare commits

..

5 Commits

Author SHA1 Message Date
Andrew Kane
61b2ddeb86 Adjust index scan cost based on selectivity [skip ci] 2024-09-22 20:23:56 -07:00
Andrew Kane
97cf990e0f Free TupleDesc [skip ci] 2024-09-21 19:15:34 -07:00
Andrew Kane
55dc735e1a Moved allocations out of GetScanItems [skip ci] 2024-09-21 19:10:25 -07:00
Andrew Kane
be4e9a9df2 Added macros for IvfflatScanList [skip ci] 2024-09-21 18:10:37 -07:00
Andrew Kane
d5e8fc96a5 Changed HnswPairingHeapNode to HnswSearchCandidate to reduce allocations and improve code 2024-09-21 12:07:44 -07:00
8 changed files with 118 additions and 104 deletions

View File

@@ -18,7 +18,6 @@
#endif
int hnsw_ef_search;
int hnsw_time_budget;
int hnsw_lock_tranche_id;
static relopt_kind hnsw_relopt_kind;
@@ -69,10 +68,6 @@ 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);
DefineCustomIntVariable("hnsw.time_budget", "Sets the time budget for search",
NULL, &hnsw_time_budget,
-1, -1, INT_MAX, PGC_USERSET, GUC_UNIT_MS, NULL, NULL, NULL);
MarkGUCPrefixReserved("hnsw");
}

View File

@@ -106,7 +106,6 @@
/* Variables */
extern int hnsw_ef_search;
extern int hnsw_time_budget;
extern int hnsw_lock_tranche_id;
typedef struct HnswElementData HnswElementData;
@@ -156,12 +155,13 @@ struct HnswNeighborArray
HnswCandidate items[FLEXIBLE_ARRAY_MEMBER];
};
typedef struct HnswPairingHeapNode
typedef struct HnswSearchCandidate
{
HnswCandidate *inner;
pairingheap_node c_node;
pairingheap_node w_node;
} HnswPairingHeapNode;
HnswElementPtr element;
float distance;
} HnswSearchCandidate;
/* HNSW index options */
typedef struct HnswOptions
@@ -331,7 +331,6 @@ typedef struct HnswScanOpaqueData
bool first;
List *w;
MemoryContext tmpCtx;
instr_time start;
/* Support functions */
FmgrInfo *procinfo;
@@ -376,14 +375,14 @@ bool HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value);
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
void HnswInitPage(Buffer buf, Page page);
void HnswInit(void);
List *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement, instr_time *start);
List *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
HnswElement HnswGetEntryPoint(Relation index);
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
void *HnswAlloc(HnswAllocator * allocator, Size size);
HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
void HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
void HnswAddHeapTid(HnswElement element, ItemPointer heaptid);

View File

@@ -3,7 +3,6 @@
#include "access/relscan.h"
#include "hnsw.h"
#include "pgstat.h"
#include "portability/instr_time.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "utils/memutils.h"
@@ -23,7 +22,6 @@ GetScanItems(IndexScanDesc scan, Datum q)
int m;
HnswElement entryPoint;
char *base = NULL;
instr_time *start = hnsw_time_budget == -1 ? NULL : &so->start;
/* Get m and entry point */
HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -35,11 +33,11 @@ GetScanItems(IndexScanDesc scan, Datum q)
for (int lc = entryPoint->level; lc >= 1; lc--)
{
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL, start);
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
ep = w;
}
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL, start);
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
}
/*
@@ -92,9 +90,6 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
so->collation = index->rd_indcollation[0];
if (hnsw_time_budget != -1)
INSTR_TIME_SET_CURRENT(so->start);
scan->opaque = so;
return scan;
@@ -166,14 +161,14 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
so->first = false;
#if defined(HNSW_MEMORY)
elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(so->tmpCtx, false) / (1024 * 1024));
elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
#endif
}
while (list_length(so->w) > 0)
{
char *base = NULL;
HnswCandidate *hc = llast(so->w);
HnswSearchCandidate *hc = llast(so->w);
HnswElement element = HnswPtrAccess(base, hc->element);
ItemPointer heaptid;

View File

@@ -9,7 +9,6 @@
#include "fmgr.h"
#include "hnsw.h"
#include "lib/pairingheap.h"
#include "portability/instr_time.h"
#include "sparsevec.h"
#include "storage/bufmgr.h"
#include "utils/datum.h"
@@ -609,10 +608,10 @@ GetElementDistance(char *base, HnswElement element, Datum q, FmgrInfo *procinfo,
/*
* Create a candidate for the entry point
*/
HnswCandidate *
HnswSearchCandidate *
HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
{
HnswCandidate *hc = palloc(sizeof(HnswCandidate));
HnswSearchCandidate *hc = palloc(sizeof(HnswSearchCandidate));
HnswPtrStore(base, hc->element, entryPoint);
if (index == NULL)
@@ -622,8 +621,8 @@ HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index,
return hc;
}
#define HnswGetPairingHeapCandidate(membername, ptr) (pairingheap_container(HnswPairingHeapNode, membername, ptr)->inner)
#define HnswGetPairingHeapCandidateConst(membername, ptr) (pairingheap_const_container(HnswPairingHeapNode, membername, ptr)->inner)
#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
/*
* Compare candidate distances
@@ -631,10 +630,10 @@ HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index,
static int
CompareNearestCandidates(const pairingheap_node *a, const pairingheap_node *b, void *arg)
{
if (HnswGetPairingHeapCandidateConst(c_node, a)->distance < HnswGetPairingHeapCandidateConst(c_node, b)->distance)
if (HnswGetSearchCandidateConst(c_node, a)->distance < HnswGetSearchCandidateConst(c_node, b)->distance)
return 1;
if (HnswGetPairingHeapCandidateConst(c_node, a)->distance > HnswGetPairingHeapCandidateConst(c_node, b)->distance)
if (HnswGetSearchCandidateConst(c_node, a)->distance > HnswGetSearchCandidateConst(c_node, b)->distance)
return -1;
return 0;
@@ -646,27 +645,15 @@ CompareNearestCandidates(const pairingheap_node *a, const pairingheap_node *b, v
static int
CompareFurthestCandidates(const pairingheap_node *a, const pairingheap_node *b, void *arg)
{
if (HnswGetPairingHeapCandidateConst(w_node, a)->distance < HnswGetPairingHeapCandidateConst(w_node, b)->distance)
if (HnswGetSearchCandidateConst(w_node, a)->distance < HnswGetSearchCandidateConst(w_node, b)->distance)
return -1;
if (HnswGetPairingHeapCandidateConst(w_node, a)->distance > HnswGetPairingHeapCandidateConst(w_node, b)->distance)
if (HnswGetSearchCandidateConst(w_node, a)->distance > HnswGetSearchCandidateConst(w_node, b)->distance)
return 1;
return 0;
}
/*
* Create a pairing heap node for a candidate
*/
static HnswPairingHeapNode *
CreatePairingHeapNode(HnswCandidate * c)
{
HnswPairingHeapNode *node = palloc(sizeof(HnswPairingHeapNode));
node->inner = c;
return node;
}
/*
* Init visited
*/
@@ -800,7 +787,7 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
* Algorithm 2 from paper
*/
List *
HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement, instr_time *start)
HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
{
List *w = NIL;
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
@@ -826,15 +813,13 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
/* Add entry points to v, C, and W */
foreach(lc2, ep)
{
HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
HnswSearchCandidate *hc = (HnswSearchCandidate *) lfirst(lc2);
bool found;
HnswPairingHeapNode *node;
AddToVisited(base, &v, hc->element, index, &found);
node = CreatePairingHeapNode(hc);
pairingheap_add(C, &node->c_node);
pairingheap_add(W, &node->w_node);
pairingheap_add(C, &hc->c_node);
pairingheap_add(W, &hc->w_node);
/*
* Do not count elements being deleted towards ef when vacuuming. It
@@ -847,21 +832,10 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
while (!pairingheap_is_empty(C))
{
HnswCandidate *c = HnswGetPairingHeapCandidate(c_node, pairingheap_remove_first(C));
HnswCandidate *f = HnswGetPairingHeapCandidate(w_node, pairingheap_first(W));
HnswSearchCandidate *c = HnswGetSearchCandidate(c_node, pairingheap_remove_first(C));
HnswSearchCandidate *f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
HnswElement cElement;
/* Check time budget */
if (start != NULL)
{
instr_time duration;
INSTR_TIME_SET_CURRENT(duration);
INSTR_TIME_SUBTRACT(duration, *start);
if (INSTR_TIME_GET_MILLISEC(duration) >= hnsw_time_budget)
break;
}
if (c->distance > f->distance)
break;
@@ -875,12 +849,11 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
for (int i = 0; i < unvisitedLength; i++)
{
HnswElement eElement;
HnswCandidate *e;
HnswPairingHeapNode *node;
HnswSearchCandidate *e;
float eDistance;
bool alwaysAdd = wlen < ef;
f = HnswGetPairingHeapCandidate(w_node, pairingheap_first(W));
f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
if (index == NULL)
{
@@ -911,13 +884,11 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
continue;
/* Create a new candidate */
e = palloc(sizeof(HnswCandidate));
e = palloc(sizeof(HnswSearchCandidate));
HnswPtrStore(base, e->element, eElement);
e->distance = eDistance;
node = CreatePairingHeapNode(e);
pairingheap_add(C, &node->c_node);
pairingheap_add(W, &node->w_node);
pairingheap_add(C, &e->c_node);
pairingheap_add(W, &e->w_node);
/*
* Do not count elements being deleted towards ef when vacuuming.
@@ -938,7 +909,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
/* Add each element of W to w */
while (!pairingheap_is_empty(W))
{
HnswCandidate *hc = HnswGetPairingHeapCandidate(w_node, pairingheap_remove_first(W));
HnswSearchCandidate *hc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
w = lappend(w, hc);
}
@@ -1303,7 +1274,7 @@ 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, procinfo, collation, m, true, skipElement, NULL);
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
ep = w;
}
@@ -1319,16 +1290,27 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
{
int lm = HnswGetLayerM(m, lc);
List *neighbors;
List *lw;
List *lw = NIL;
ListCell *lc2;
w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement, NULL);
w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
/* Convert search candidates to candidates */
foreach(lc2, w)
{
HnswSearchCandidate *sc = lfirst(lc2);
HnswCandidate *hc = palloc(sizeof(HnswCandidate));
hc->element = sc->element;
hc->distance = sc->distance;
lw = lappend(lw, hc);
}
/* Elements being deleted or skipped can help with search */
/* but should be removed before selecting neighbors */
if (index != NULL)
lw = RemoveElements(base, w, skipElement);
else
lw = w;
lw = RemoveElements(base, lw, skipElement);
/*
* Candidates are sorted, but not deterministically. Could set

View File

@@ -57,6 +57,39 @@ ivfflatbuildphasename(int64 phasenum)
}
}
/*
* Estimate the number of probes needed to get requested tuples
*/
static int
EstimateProbes(PlannerInfo *root, IndexPath *path, int lists)
{
double selectivity = 1;
ListCell *lc;
double tuplesPerList;
/* Cannot estimate without limit */
/* limit_tuples includes offset */
if (root->limit_tuples < 0)
return 0;
/* Get the selectivity of non-index conditions */
foreach(lc, path->indexinfo->indrestrictinfo)
{
RestrictInfo *rinfo = lfirst(lc);
/* Skip DEFAULT_INEQ_SEL since it may be a distance filter */
if (rinfo->norm_selec >= 0 && rinfo->norm_selec <= 1 && rinfo->norm_selec != (Selectivity) DEFAULT_INEQ_SEL)
selectivity *= rinfo->norm_selec;
}
tuplesPerList = path->indexinfo->tuples * selectivity / (double) lists;
if (tuplesPerList == 0)
return lists;
/* No need to cap at this point */
return root->limit_tuples / tuplesPerList;
}
/*
* Estimate the cost of an index scan
*/
@@ -68,6 +101,7 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
{
GenericCosts costs;
int lists;
int probes;
double ratio;
double spc_seq_page_cost;
Relation index;
@@ -89,8 +123,10 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
IvfflatGetMetaPageInfo(index, &lists, NULL);
index_close(index, NoLock);
probes = Max(ivfflat_probes, EstimateProbes(root, path, lists));
/* Get the ratio of lists that we need to visit */
ratio = ((double) ivfflat_probes) / lists;
ratio = ((double) probes) / lists;
if (ratio > 1.0)
ratio = 1.0;

View File

@@ -253,8 +253,9 @@ typedef struct IvfflatScanOpaqueData
/* Sorting */
Tuplesortstate *sortstate;
TupleDesc tupdesc;
TupleTableSlot *slot;
bool isnull;
TupleTableSlot *vslot;
TupleTableSlot *mslot;
BufferAccessStrategy bas;
/* Support functions */
FmgrInfo *procinfo;

View File

@@ -15,16 +15,19 @@
#include "utils/memutils.h"
#endif
#define GetScanList(ptr) pairingheap_container(IvfflatScanList, ph_node, ptr)
#define GetScanListConst(ptr) pairingheap_const_container(IvfflatScanList, ph_node, ptr)
/*
* Compare list distances
*/
static int
CompareLists(const pairingheap_node *a, const pairingheap_node *b, void *arg)
{
if (((const IvfflatScanList *) a)->distance > ((const IvfflatScanList *) b)->distance)
if (GetScanListConst(a)->distance > GetScanListConst(b)->distance)
return 1;
if (((const IvfflatScanList *) a)->distance < ((const IvfflatScanList *) b)->distance)
if (GetScanListConst(a)->distance < GetScanListConst(b)->distance)
return -1;
return 0;
@@ -76,14 +79,14 @@ GetScanLists(IndexScanDesc scan, Datum value)
/* Calculate max distance */
if (listCount == so->probes)
maxDistance = ((IvfflatScanList *) pairingheap_first(so->listQueue))->distance;
maxDistance = GetScanList(pairingheap_first(so->listQueue))->distance;
}
else if (distance < maxDistance)
{
IvfflatScanList *scanlist;
/* Remove */
scanlist = (IvfflatScanList *) pairingheap_remove_first(so->listQueue);
scanlist = GetScanList(pairingheap_remove_first(so->listQueue));
/* Reuse */
scanlist->startPage = list->startPage;
@@ -91,7 +94,7 @@ GetScanLists(IndexScanDesc scan, Datum value)
pairingheap_add(so->listQueue, &scanlist->ph_node);
/* Update max distance */
maxDistance = ((IvfflatScanList *) pairingheap_first(so->listQueue))->distance;
maxDistance = GetScanList(pairingheap_first(so->listQueue))->distance;
}
}
@@ -110,19 +113,12 @@ GetScanItems(IndexScanDesc scan, Datum value)
IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
TupleDesc tupdesc = RelationGetDescr(scan->indexRelation);
double tuples = 0;
TupleTableSlot *slot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsVirtual);
/*
* Reuse same set of shared buffers for scan
*
* See postgres/src/backend/storage/buffer/README for description
*/
BufferAccessStrategy bas = GetAccessStrategy(BAS_BULKREAD);
TupleTableSlot *slot = so->vslot;
/* Search closest probes lists */
while (!pairingheap_is_empty(so->listQueue))
{
BlockNumber searchPage = ((IvfflatScanList *) pairingheap_remove_first(so->listQueue))->startPage;
BlockNumber searchPage = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
/* Search all entry pages for list */
while (BlockNumberIsValid(searchPage))
@@ -131,7 +127,7 @@ GetScanItems(IndexScanDesc scan, Datum value)
Page page;
OffsetNumber maxoffno;
buf = ReadBufferExtended(scan->indexRelation, MAIN_FORKNUM, searchPage, RBM_NORMAL, bas);
buf = ReadBufferExtended(scan->indexRelation, MAIN_FORKNUM, searchPage, RBM_NORMAL, so->bas);
LockBuffer(buf, BUFFER_LOCK_SHARE);
page = BufferGetPage(buf);
maxoffno = PageGetMaxOffsetNumber(page);
@@ -170,8 +166,6 @@ GetScanItems(IndexScanDesc scan, Datum value)
}
}
FreeAccessStrategy(bas);
if (tuples < 100)
ereport(DEBUG1,
(errmsg("index scan found few tuples"),
@@ -274,7 +268,16 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
/* Prep sort */
so->sortstate = InitScanSortState(so->tupdesc);
so->slot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsMinimalTuple);
/* Need separate slots for puttuple and gettuple */
so->vslot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsVirtual);
so->mslot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsMinimalTuple);
/*
* Reuse same set of shared buffers for scan
*
* See postgres/src/backend/storage/buffer/README for description
*/
so->bas = GetAccessStrategy(BAS_BULKREAD);
so->listQueue = pairingheap_allocate(CompareLists, scan);
@@ -348,9 +351,10 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
pfree(DatumGetPointer(value));
}
if (tuplesort_gettupleslot(so->sortstate, true, false, so->slot, NULL))
if (tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
{
ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->slot, 2, &so->isnull));
bool isnull;
ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
scan->xs_heaptid = *heaptid;
scan->xs_recheck = false;
@@ -371,6 +375,10 @@ ivfflatendscan(IndexScanDesc scan)
pairingheap_free(so->listQueue);
tuplesort_end(so->sortstate);
FreeAccessStrategy(so->bas);
FreeTupleDesc(so->tupdesc);
/* TODO Free vslot and mslot without freeing TupleDesc */
pfree(so);
scan->opaque = NULL;

View File

@@ -5,7 +5,7 @@ use PostgreSQL::Test::Utils;
use Test::More;
my $dim = 3;
my $nc = 50;
my $nc = 100;
my $limit = 20;
my $array_sql = join(",", ('random()') x $dim);
@@ -102,15 +102,13 @@ $node->safe_psql("postgres", "CREATE INDEX attribute_idx ON tst (c);");
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Use attribute index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Index Scan on attribute_idx/);
# Test partial index
$node->safe_psql("postgres", "CREATE INDEX partial_idx ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 5) WHERE (c = $c);");
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Use partial index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Index Scan using partial_idx/);
done_testing();