database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-10-29 22:49:41 +03:00
Code Activity

Re-add GUC track_wal_io_timing

Browse Source 
This commit is a rework of 2421e9a51d, about which Andres Freund has
raised some concerns as it is valuable to have both track_io_timing and
track_wal_io_timing in some cases, as the WAL write and fsync paths can
be a major bottleneck for some workloads.  Hence, it can be relevant to
not calculate the WAL timings in environments where pg_test_timing
performs poorly while capturing some IO data under track_io_timing for
the non-WAL IO paths.  The opposite can be also true: it should be
possible to disable the non-WAL timings and enable the WAL timings (the
previous GUC setups allowed this possibility).

track_wal_io_timing is added back in this commit, controlling if WAL
timings should be calculated in pg_stat_io for the read, fsync and write
paths, as done previously with pg_stat_wal.  pg_stat_wal previously
tracked only the sync and write parts (now removed), read stats is new
data tracked in pg_stat_io, all three are aggregated if
track_wal_io_timing is enabled.  The read part matters during recovery
or if a XLogReader is used.

Extra note: more control over if the types of timings calculated in
pg_stat_io could be done with a GUC that lists pairs of (IOObject,IOOp).

Reported-by: Andres Freund <andres@anarazel.de>
Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Co-authored-by: Michael Paquier <michael@paquier.xyz>
Discussion: https://postgr.es/m/3opf2wh2oljco6ldyqf7ukabw3jijnnhno6fjb4mlu6civ5h24@fcwmhsgmlmzu
This commit is contained in:
Michael Paquier
2025-02-26 09:49:59 +09:00
parent a5cbdeb98a
commit 6c349d83b6
15 changed files with 96 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/backend/storage/buffer/bufmgr.c
View File

@@ -1509,7 +1509,7 @@ WaitReadBuffers(ReadBuffersOperation *operation)
io_pages[io_buffers_len++] = BufferGetBlock(buffers[i]);
}
io_start = pgstat_prepare_io_time();
io_start = pgstat_prepare_io_time(track_io_timing);
smgrreadv(operation->smgr, forknum, io_first_block, io_pages, io_buffers_len);
pgstat_count_io_op_time(io_object, io_context, IOOP_READ, io_start,
1, io_buffers_len * BLCKSZ);
@@ -2402,7 +2402,7 @@ ExtendBufferedRelShared(BufferManagerRelation bmr,
}
}
io_start = pgstat_prepare_io_time();
io_start = pgstat_prepare_io_time(track_io_timing);
/*
* Note: if smgrzeroextend fails, we will end up with buffers that are
@@ -3857,7 +3857,7 @@ FlushBuffer(BufferDesc *buf, SMgrRelation reln, IOObject io_object,
*/
bufToWrite = PageSetChecksumCopy((Page) bufBlock, buf->tag.blockNum);
io_start = pgstat_prepare_io_time();
io_start = pgstat_prepare_io_time(track_io_timing);
/*
* bufToWrite is either the shared buffer or a copy, as appropriate.
@@ -4459,7 +4459,7 @@ FlushRelationBuffers(Relation rel)
PageSetChecksumInplace(localpage, bufHdr->tag.blockNum);
io_start = pgstat_prepare_io_time();
io_start = pgstat_prepare_io_time(track_io_timing);
smgrwrite(srel,
BufTagGetForkNum(&bufHdr->tag),
@@ -5905,7 +5905,7 @@ IssuePendingWritebacks(WritebackContext *wb_context, IOContext io_context)
sort_pending_writebacks(wb_context->pending_writebacks,
wb_context->nr_pending);
io_start = pgstat_prepare_io_time();
io_start = pgstat_prepare_io_time(track_io_timing);
/*
* Coalesce neighbouring writes, but nothing else. For that we iterate

4
src/backend/storage/buffer/localbuf.c
View File

@@ -244,7 +244,7 @@ GetLocalVictimBuffer(void)
PageSetChecksumInplace(localpage, bufHdr->tag.blockNum);
io_start = pgstat_prepare_io_time();
io_start = pgstat_prepare_io_time(track_io_timing);
/* And write... */
smgrwrite(oreln,
@@ -414,7 +414,7 @@ ExtendBufferedRelLocal(BufferManagerRelation bmr,
}
}
io_start = pgstat_prepare_io_time();
io_start = pgstat_prepare_io_time(track_io_timing);
/* actually extend relation */
smgrzeroextend(bmr.smgr, fork, first_block, extend_by, false);

4
src/backend/storage/smgr/md.c
View File

@@ -1391,7 +1391,7 @@ register_dirty_segment(SMgrRelation reln, ForkNumber forknum, MdfdVec *seg)
ereport(DEBUG1,
(errmsg_internal("could not forward fsync request because request queue is full")));
io_start = pgstat_prepare_io_time();
io_start = pgstat_prepare_io_time(track_io_timing);
if (FileSync(seg->mdfd_vfd, WAIT_EVENT_DATA_FILE_SYNC) < 0)
ereport(data_sync_elevel(ERROR),
@@ -1790,7 +1790,7 @@ mdsyncfiletag(const FileTag *ftag, char *path)
need_to_close = true;
}
io_start = pgstat_prepare_io_time();
io_start = pgstat_prepare_io_time(track_io_timing);
/* Sync the file. */
result = FileSync(file, WAIT_EVENT_DATA_FILE_SYNC);