database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-12-21 05:21:08 +03:00
Code Activity

Use streaming I/O in ANALYZE.

Browse Source 
The ANALYZE command prefetches and reads sample blocks chosen by a
BlockSampler algorithm. Instead of calling [Prefetch|Read]Buffer() for
each block, ANALYZE now uses the streaming API introduced in b5a9b18cd0.

Author: Nazir Bilal Yavuz <byavuz81@gmail.com>
Reviewed-by: Melanie Plageman <melanieplageman@gmail.com>
Reviewed-by: Andres Freund <andres@anarazel.de>
Reviewed-by: Jakub Wartak <jakub.wartak@enterprisedb.com>
Reviewed-by: Heikki Linnakangas <hlinnaka@iki.fi>
Reviewed-by: Thomas Munro <thomas.munro@gmail.com>
Discussion: https://postgr.es/m/flat/CAN55FZ0UhXqk9v3y-zW_fp4-WCp43V8y0A72xPmLkOM%2B6M%2BmJg%40mail.gmail.com
This commit is contained in:
Thomas Munro
2024-04-08 13:16:20 +12:00
parent f587338dec
commit 041b96802e
3 changed files with 43 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

85
src/backend/commands/analyze.c
View File

@@ -1102,6 +1102,20 @@ examine_attribute(Relation onerel, int attnum, Node *index_expr)
return stats;
}
/*
* Read stream callback returning the next BlockNumber as chosen by the
* BlockSampling algorithm.
*/
static BlockNumber
block_sampling_read_stream_next(ReadStream *stream,
void *callback_private_data,
void *per_buffer_data)
{
BlockSamplerData *bs = callback_private_data;
return BlockSampler_HasMore(bs) ? BlockSampler_Next(bs) : InvalidBlockNumber;
}
/*
* acquire_sample_rows -- acquire a random sample of rows from the heap
*
@@ -1154,10 +1168,7 @@ 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
ReadStream *stream;
Assert(targrows > 0);
@@ -1170,13 +1181,6 @@ acquire_sample_rows(Relation onerel, int elevel,
randseed = pg_prng_uint32(&pg_global_prng_state);
nblocks = BlockSampler_Init(&bs, totalblocks, targrows, randseed);
#ifdef USE_PREFETCH
prefetch_maximum = get_tablespace_maintenance_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,
nblocks);
@@ -1187,60 +1191,19 @@ acquire_sample_rows(Relation onerel, int elevel,
scan = heap_beginscan(onerel, NULL, 0, NULL, NULL, SO_TYPE_ANALYZE);
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
stream = read_stream_begin_relation(READ_STREAM_MAINTENANCE,
vac_strategy,
scan->rs_rd,
MAIN_FORKNUM,
block_sampling_read_stream_next,
&bs,
0);
/* Outer loop over blocks to sample */
while (BlockSampler_HasMore(&bs))
while (heapam_scan_analyze_next_block(scan, stream))
{
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();
heapam_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.
*/
if (prefetch_maximum && prefetch_targblock != InvalidBlockNumber)
PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, prefetch_targblock);
#endif
while (heapam_scan_analyze_next_tuple(scan, OldestXmin, &liverows, &deadrows, slot))
{
/*
@@ -1290,6 +1253,8 @@ acquire_sample_rows(Relation onerel, int elevel,
++blksdone);
}
read_stream_end(stream);
ExecDropSingleTupleTableSlot(slot);
heap_endscan(scan);