agora inbox for pgsql-committers@postgresql.org  
help / color / mirror / Atom feed
pgsql: Allow IO time to be counted without a matching IO operation in p
2+ messages / 1 participants
[nested] [flat]

* pgsql: Allow IO time to be counted without a matching IO operation in p
@ 2026-07-31 21:47 Melanie Plageman <melanieplageman@gmail.com>
  0 siblings, 0 replies; 2+ messages in thread

From: Melanie Plageman @ 2026-07-31 21:47 UTC (permalink / raw)
  To: pgsql-committers@lists.postgresql.org

Allow IO time to be counted without a matching IO operation in pg_stat_io

Since 999dec9ec6a816680, pg_stat_io can show read time with zero reads
for an IO Context: a foreign IO is counted as a read only in the
initiating backend, while other waiters record only the wait time. That
violates pgstat_bktype_io_stats_valid(). Relax the check to allow time
without a matching operation count, since we want to count read wait
time even in backends that did not initiate the read. This also enables
future accounting of waits on IO resources (e.g., AIO handles) in
backends that didn't start the IO.

Author: Andrey Rachitskiy <pl0h0yp1@gmail.com>
Reported-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Melanie Plageman <melanieplageman@gmail.com>
Reviewed-by: Andrey Borodin <x4mmm@yandex-team.ru>
Discussion: https://postgr.es/m/ak5lccE4qiQpOBHn@pryzbyj2023
Backpatch-through: 19

Branch
------
master

Details
-------
https://git.postgresql.org/pg/commitdiff/c9a669492719db2fe45cd17259ae0fc3bc4d91c5

Modified Files
--------------
doc/src/sgml/monitoring.sgml           |  4 +++-
src/backend/storage/buffer/bufmgr.c    |  8 ++++----
src/backend/utils/activity/pgstat_io.c | 22 +++++++---------------
3 files changed, 14 insertions(+), 20 deletions(-)



^ permalink  raw  reply  [nested|flat] 2+ messages in thread

* pgsql: Allow IO time to be counted without a matching IO operation in p
@ 2026-07-31 21:48 Melanie Plageman <melanieplageman@gmail.com>
  0 siblings, 0 replies; 2+ messages in thread

From: Melanie Plageman @ 2026-07-31 21:48 UTC (permalink / raw)
  To: pgsql-committers@lists.postgresql.org

Allow IO time to be counted without a matching IO operation in pg_stat_io

Since 999dec9ec6a816680, pg_stat_io can show read time with zero reads
for an IO Context: a foreign IO is counted as a read only in the
initiating backend, while other waiters record only the wait time. That
violates pgstat_bktype_io_stats_valid(). Relax the check to allow time
without a matching operation count, since we want to count read wait
time even in backends that did not initiate the read. This also enables
future accounting of waits on IO resources (e.g., AIO handles) in
backends that didn't start the IO.

Author: Andrey Rachitskiy <pl0h0yp1@gmail.com>
Reported-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Melanie Plageman <melanieplageman@gmail.com>
Reviewed-by: Andrey Borodin <x4mmm@yandex-team.ru>
Discussion: https://postgr.es/m/ak5lccE4qiQpOBHn@pryzbyj2023
Backpatch-through: 19

Branch
------
REL_19_STABLE

Details
-------
https://git.postgresql.org/pg/commitdiff/d6792cc58e9c0aead136f381052151e1c246b534

Modified Files
--------------
doc/src/sgml/monitoring.sgml           |  4 +++-
src/backend/storage/buffer/bufmgr.c    |  8 ++++----
src/backend/utils/activity/pgstat_io.c | 22 +++++++---------------
3 files changed, 14 insertions(+), 20 deletions(-)



^ permalink  raw  reply  [nested|flat] 2+ messages in thread


end of thread, other threads:[~2026-07-31 21:48 UTC | newest]

Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2026-07-31 21:47 pgsql: Allow IO time to be counted without a matching IO operation in p Melanie Plageman <melanieplageman@gmail.com>
2026-07-31 21:48 pgsql: Allow IO time to be counted without a matching IO operation in p Melanie Plageman <melanieplageman@gmail.com>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox