mirror of
https://github.com/postgres/postgres.git
synced 2025-07-08 11:42:09 +03:00
Use pre-fetching for ANALYZE
When we have posix_fadvise() available, we can improve the performance of an ANALYZE by quite a bit by using it to inform the kernel of the blocks that we're going to be asking for. Similar to bitmap index scans, the number of buffers pre-fetched is based off of the maintenance_io_concurrency setting (for the particular tablespace or, if not set, globally, via get_tablespace_maintenance_io_concurrency()). Reviewed-By: Heikki Linnakangas, Tomas Vondra Discussion: https://www.postgresql.org/message-id/VI1PR0701MB69603A433348EDCF783C6ECBF6EF0%40VI1PR0701MB6960.eurprd07.prod.outlook.com
This commit is contained in:
@ -63,6 +63,7 @@
|
||||
#include "utils/pg_rusage.h"
|
||||
#include "utils/sampling.h"
|
||||
#include "utils/sortsupport.h"
|
||||
#include "utils/spccache.h"
|
||||
#include "utils/syscache.h"
|
||||
#include "utils/timestamp.h"
|
||||
|
||||
@ -1127,6 +1128,7 @@ acquire_sample_rows(Relation onerel, int elevel,
|
||||
double liverows = 0; /* # live rows seen */
|
||||
double deadrows = 0; /* # dead rows seen */
|
||||
double rowstoskip = -1; /* -1 means not set yet */
|
||||
long randseed; /* Seed for block sampler(s) */
|
||||
BlockNumber totalblocks;
|
||||
TransactionId OldestXmin;
|
||||
BlockSamplerData bs;
|
||||
@ -1135,6 +1137,10 @@ acquire_sample_rows(Relation onerel, int elevel,
|
||||
TableScanDesc scan;
|
||||
BlockNumber nblocks;
|
||||
BlockNumber blksdone = 0;
|
||||
#ifdef USE_PREFETCH
|
||||
int prefetch_maximum = 0; /* blocks to prefetch if enabled */
|
||||
BlockSamplerData prefetch_bs;
|
||||
#endif
|
||||
|
||||
Assert(targrows > 0);
|
||||
|
||||
@ -1144,7 +1150,15 @@ acquire_sample_rows(Relation onerel, int elevel,
|
||||
OldestXmin = GetOldestNonRemovableTransactionId(onerel);
|
||||
|
||||
/* Prepare for sampling block numbers */
|
||||
nblocks = BlockSampler_Init(&bs, totalblocks, targrows, random());
|
||||
randseed = random();
|
||||
nblocks = BlockSampler_Init(&bs, totalblocks, targrows, randseed);
|
||||
|
||||
#ifdef USE_PREFETCH
|
||||
prefetch_maximum = get_tablespace_io_concurrency(onerel->rd_rel->reltablespace);
|
||||
/* Create another BlockSampler, using the same seed, for prefetching */
|
||||
if (prefetch_maximum)
|
||||
(void) BlockSampler_Init(&prefetch_bs, totalblocks, targrows, randseed);
|
||||
#endif
|
||||
|
||||
/* Report sampling block numbers */
|
||||
pgstat_progress_update_param(PROGRESS_ANALYZE_BLOCKS_TOTAL,
|
||||
@ -1156,14 +1170,69 @@ acquire_sample_rows(Relation onerel, int elevel,
|
||||
scan = table_beginscan_analyze(onerel);
|
||||
slot = table_slot_create(onerel, NULL);
|
||||
|
||||
#ifdef USE_PREFETCH
|
||||
|
||||
/*
|
||||
* If we are doing prefetching, then go ahead and tell the kernel about
|
||||
* the first set of pages we are going to want. This also moves our
|
||||
* iterator out ahead of the main one being used, where we will keep it so
|
||||
* that we're always pre-fetching out prefetch_maximum number of blocks
|
||||
* ahead.
|
||||
*/
|
||||
if (prefetch_maximum)
|
||||
{
|
||||
for (int i = 0; i < prefetch_maximum; i++)
|
||||
{
|
||||
BlockNumber prefetch_block;
|
||||
|
||||
if (!BlockSampler_HasMore(&prefetch_bs))
|
||||
break;
|
||||
|
||||
prefetch_block = BlockSampler_Next(&prefetch_bs);
|
||||
PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, prefetch_block);
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
/* Outer loop over blocks to sample */
|
||||
while (BlockSampler_HasMore(&bs))
|
||||
{
|
||||
bool block_accepted;
|
||||
BlockNumber targblock = BlockSampler_Next(&bs);
|
||||
#ifdef USE_PREFETCH
|
||||
BlockNumber prefetch_targblock = InvalidBlockNumber;
|
||||
|
||||
/*
|
||||
* Make sure that every time the main BlockSampler is moved forward
|
||||
* that our prefetch BlockSampler also gets moved forward, so that we
|
||||
* always stay out ahead.
|
||||
*/
|
||||
if (prefetch_maximum && BlockSampler_HasMore(&prefetch_bs))
|
||||
prefetch_targblock = BlockSampler_Next(&prefetch_bs);
|
||||
#endif
|
||||
|
||||
vacuum_delay_point();
|
||||
|
||||
if (!table_scan_analyze_next_block(scan, targblock, vac_strategy))
|
||||
block_accepted = table_scan_analyze_next_block(scan, targblock, vac_strategy);
|
||||
|
||||
#ifdef USE_PREFETCH
|
||||
|
||||
/*
|
||||
* When pre-fetching, after we get a block, tell the kernel about the
|
||||
* next one we will want, if there's any left.
|
||||
*
|
||||
* We want to do this even if the table_scan_analyze_next_block() call
|
||||
* above decides against analyzing the block it picked.
|
||||
*/
|
||||
if (prefetch_maximum && prefetch_targblock != InvalidBlockNumber)
|
||||
PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, prefetch_targblock);
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Don't analyze if table_scan_analyze_next_block() indicated this
|
||||
* block is unsuitable for analyzing.
|
||||
*/
|
||||
if (!block_accepted)
|
||||
continue;
|
||||
|
||||
while (table_scan_analyze_next_tuple(scan, OldestXmin, &liverows, &deadrows, slot))
|
||||
|
Reference in New Issue
Block a user