mirror of
https://github.com/postgres/postgres.git
synced 2025-06-05 00:02:04 -04:00
Expose the count of index searches/index descents in EXPLAIN ANALYZE's output for index scan nodes. This information is particularly useful with scans that use ScalarArrayOp quals, where the number of index scans isn't predictable in advance (at least not with optimizations like the one added to nbtree by Postgres 17 commit 5bf748b8). It will also be useful when EXPLAIN ANALYZE shows details of an nbtree index scan that uses skip scan optimizations set to be introduced by an upcoming patch. The instrumentation works by teaching index AMs to increment a new nsearches counter whenever a new index search begins. The counter is incremented at exactly the same point that index AMs must already increment the index's pg_stat_*_indexes.idx_scan counter (we're counting the same event, but at the scan level rather than the relation level). The new counter is stored in the scan descriptor (IndexScanDescData), which explain.c reaches by going through the scan node's PlanState. This approach doesn't match the approach used when tracking other index scan specific costs (e.g., "Rows Removed by Filter:"). It is similar to the approach used in other cases where we must track costs that are only readily accessible inside an access method, and not from the executor (e.g., "Heap Blocks:" output for a Bitmap Heap Scan). It is inherently necessary to maintain a counter that can be incremented multiple times during a single amgettuple call (or amgetbitmap call), and directly exposing PlanState.instrument to index access methods seems unappealing. Author: Peter Geoghegan <pg@bowt.ie> Reviewed-By: Tomas Vondra <tomas@vondra.me> Reviewed-By: Robert Haas <robertmhaas@gmail.com> Reviewed-By: Masahiro Ikeda <ikedamsh@oss.nttdata.com> Reviewed-By: Matthias van de Meent <boekewurm+postgres@gmail.com> Discussion: https://postgr.es/m/CAH2-Wz=PKR6rB7qbx+Vnd7eqeB5VTcrW=iJvAsTsKbdG+kW_UA@mail.gmail.com Discussion: https://postgr.es/m/CAH2-WzkRqvaqR2CTNqTZP0z6FuL4-3ED6eQB0yx38XBNj1v-4Q@mail.gmail.com
168 lines
3.4 KiB
C
168 lines
3.4 KiB
C
/*-------------------------------------------------------------------------
|
|
*
|
|
* blscan.c
|
|
* Bloom index scan functions.
|
|
*
|
|
* Copyright (c) 2016-2025, PostgreSQL Global Development Group
|
|
*
|
|
* IDENTIFICATION
|
|
* contrib/bloom/blscan.c
|
|
*
|
|
*-------------------------------------------------------------------------
|
|
*/
|
|
#include "postgres.h"
|
|
|
|
#include "access/relscan.h"
|
|
#include "bloom.h"
|
|
#include "miscadmin.h"
|
|
#include "pgstat.h"
|
|
#include "storage/bufmgr.h"
|
|
|
|
/*
|
|
* Begin scan of bloom index.
|
|
*/
|
|
IndexScanDesc
|
|
blbeginscan(Relation r, int nkeys, int norderbys)
|
|
{
|
|
IndexScanDesc scan;
|
|
BloomScanOpaque so;
|
|
|
|
scan = RelationGetIndexScan(r, nkeys, norderbys);
|
|
|
|
so = (BloomScanOpaque) palloc(sizeof(BloomScanOpaqueData));
|
|
initBloomState(&so->state, scan->indexRelation);
|
|
so->sign = NULL;
|
|
|
|
scan->opaque = so;
|
|
|
|
return scan;
|
|
}
|
|
|
|
/*
|
|
* Rescan a bloom index.
|
|
*/
|
|
void
|
|
blrescan(IndexScanDesc scan, ScanKey scankey, int nscankeys,
|
|
ScanKey orderbys, int norderbys)
|
|
{
|
|
BloomScanOpaque so = (BloomScanOpaque) scan->opaque;
|
|
|
|
if (so->sign)
|
|
pfree(so->sign);
|
|
so->sign = NULL;
|
|
|
|
if (scankey && scan->numberOfKeys > 0)
|
|
memcpy(scan->keyData, scankey, scan->numberOfKeys * sizeof(ScanKeyData));
|
|
}
|
|
|
|
/*
|
|
* End scan of bloom index.
|
|
*/
|
|
void
|
|
blendscan(IndexScanDesc scan)
|
|
{
|
|
BloomScanOpaque so = (BloomScanOpaque) scan->opaque;
|
|
|
|
if (so->sign)
|
|
pfree(so->sign);
|
|
so->sign = NULL;
|
|
}
|
|
|
|
/*
|
|
* Insert all matching tuples into a bitmap.
|
|
*/
|
|
int64
|
|
blgetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
|
|
{
|
|
int64 ntids = 0;
|
|
BlockNumber blkno = BLOOM_HEAD_BLKNO,
|
|
npages;
|
|
int i;
|
|
BufferAccessStrategy bas;
|
|
BloomScanOpaque so = (BloomScanOpaque) scan->opaque;
|
|
|
|
if (so->sign == NULL)
|
|
{
|
|
/* New search: have to calculate search signature */
|
|
ScanKey skey = scan->keyData;
|
|
|
|
so->sign = palloc0(sizeof(BloomSignatureWord) * so->state.opts.bloomLength);
|
|
|
|
for (i = 0; i < scan->numberOfKeys; i++)
|
|
{
|
|
/*
|
|
* Assume bloom-indexable operators to be strict, so nothing could
|
|
* be found for NULL key.
|
|
*/
|
|
if (skey->sk_flags & SK_ISNULL)
|
|
{
|
|
pfree(so->sign);
|
|
so->sign = NULL;
|
|
return 0;
|
|
}
|
|
|
|
/* Add next value to the signature */
|
|
signValue(&so->state, so->sign, skey->sk_argument,
|
|
skey->sk_attno - 1);
|
|
|
|
skey++;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* We're going to read the whole index. This is why we use appropriate
|
|
* buffer access strategy.
|
|
*/
|
|
bas = GetAccessStrategy(BAS_BULKREAD);
|
|
npages = RelationGetNumberOfBlocks(scan->indexRelation);
|
|
pgstat_count_index_scan(scan->indexRelation);
|
|
scan->nsearches++;
|
|
|
|
for (blkno = BLOOM_HEAD_BLKNO; blkno < npages; blkno++)
|
|
{
|
|
Buffer buffer;
|
|
Page page;
|
|
|
|
buffer = ReadBufferExtended(scan->indexRelation, MAIN_FORKNUM,
|
|
blkno, RBM_NORMAL, bas);
|
|
|
|
LockBuffer(buffer, BUFFER_LOCK_SHARE);
|
|
page = BufferGetPage(buffer);
|
|
|
|
if (!PageIsNew(page) && !BloomPageIsDeleted(page))
|
|
{
|
|
OffsetNumber offset,
|
|
maxOffset = BloomPageGetMaxOffset(page);
|
|
|
|
for (offset = 1; offset <= maxOffset; offset++)
|
|
{
|
|
BloomTuple *itup = BloomPageGetTuple(&so->state, page, offset);
|
|
bool res = true;
|
|
|
|
/* Check index signature with scan signature */
|
|
for (i = 0; i < so->state.opts.bloomLength; i++)
|
|
{
|
|
if ((itup->sign[i] & so->sign[i]) != so->sign[i])
|
|
{
|
|
res = false;
|
|
break;
|
|
}
|
|
}
|
|
|
|
/* Add matching tuples to bitmap */
|
|
if (res)
|
|
{
|
|
tbm_add_tuples(tbm, &itup->heapPtr, 1, true);
|
|
ntids++;
|
|
}
|
|
}
|
|
}
|
|
|
|
UnlockReleaseBuffer(buffer);
|
|
CHECK_FOR_INTERRUPTS();
|
|
}
|
|
FreeAccessStrategy(bas);
|
|
|
|
return ntids;
|
|
}
|