diff options
| author | Thomas Munro <tmunro@postgresql.org> | 2022-03-16 13:37:58 +1300 |
|---|---|---|
| committer | Thomas Munro <tmunro@postgresql.org> | 2022-03-16 13:57:59 +1300 |
| commit | 5e6368b42ee6d4b59e085301ca7b0e50f37a897b (patch) | |
| tree | 770884f4f9157bb286c3b86d6f7aa2040ab2d5ce | |
| parent | a56e7b66010f330782243de9e25ac2a6596be0e1 (diff) | |
| download | postgresql-5e6368b42ee6d4b59e085301ca7b0e50f37a897b.tar.gz postgresql-5e6368b42ee6d4b59e085301ca7b0e50f37a897b.zip | |
Wake up for latches in CheckpointWriteDelay().
The checkpointer shouldn't ignore its latch. Other backends may be
waiting for it to drain the request queue. Hopefully real systems don't
have a full queue often, but the condition is reached easily when
shared_buffers is small.
This involves defining a new wait event, which will appear in the
pg_stat_activity view often due to spread checkpoints.
Back-patch only to 14. Even though the problem exists in earlier
branches too, it's hard to hit there. In 14 we stopped using signal
handlers for latches on Linux, *BSD and macOS, which were previously
hiding this problem by interrupting the sleep (though not reliably, as
the signal could arrive before the sleep begins; precisely the problem
latches address).
Reported-by: Andres Freund <andres@anarazel.de>
Reviewed-by: Andres Freund <andres@anarazel.de>
Discussion: https://postgr.es/m/20220226213942.nb7uvb2pamyu26dj%40alap3.anarazel.de
| -rw-r--r-- | doc/src/sgml/monitoring.sgml | 4 | ||||
| -rw-r--r-- | src/backend/postmaster/checkpointer.c | 8 | ||||
| -rw-r--r-- | src/backend/utils/activity/wait_event.c | 3 | ||||
| -rw-r--r-- | src/include/utils/wait_event.h | 1 |
4 files changed, 15 insertions, 1 deletions
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 9fb62fec8ec..8620aaddc79 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -2236,6 +2236,10 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <entry>Waiting during base backup when throttling activity.</entry> </row> <row> + <entry><literal>CheckpointerWriteDelay</literal></entry> + <entry>Waiting between writes while performing a checkpoint.</entry> + </row> + <row> <entry><literal>PgSleep</literal></entry> <entry>Waiting due to a call to <function>pg_sleep</function> or a sibling function.</entry> diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c index 4488e3a4435..a59c3cf0201 100644 --- a/src/backend/postmaster/checkpointer.c +++ b/src/backend/postmaster/checkpointer.c @@ -484,6 +484,9 @@ CheckpointerMain(void) } ckpt_active = false; + + /* We may have received an interrupt during the checkpoint. */ + HandleCheckpointerInterrupts(); } /* Check for archive_timeout and switch xlog files if necessary. */ @@ -726,7 +729,10 @@ CheckpointWriteDelay(int flags, double progress) * Checkpointer and bgwriter are no longer related so take the Big * Sleep. */ - pg_usleep(100000L); + WaitLatch(MyLatch, WL_LATCH_SET | WL_EXIT_ON_PM_DEATH | WL_TIMEOUT, + 100, + WAIT_EVENT_CHECKPOINT_WRITE_DELAY); + ResetLatch(MyLatch); } else if (--absorb_counter <= 0) { diff --git a/src/backend/utils/activity/wait_event.c b/src/backend/utils/activity/wait_event.c index 60972c3a750..0706e922b53 100644 --- a/src/backend/utils/activity/wait_event.c +++ b/src/backend/utils/activity/wait_event.c @@ -485,6 +485,9 @@ pgstat_get_wait_timeout(WaitEventTimeout w) case WAIT_EVENT_BASE_BACKUP_THROTTLE: event_name = "BaseBackupThrottle"; break; + case WAIT_EVENT_CHECKPOINT_WRITE_DELAY: + event_name = "CheckpointWriteDelay"; + break; case WAIT_EVENT_PG_SLEEP: event_name = "PgSleep"; break; diff --git a/src/include/utils/wait_event.h b/src/include/utils/wait_event.h index 395d325c5fe..d0345c6b49e 100644 --- a/src/include/utils/wait_event.h +++ b/src/include/utils/wait_event.h @@ -141,6 +141,7 @@ typedef enum typedef enum { WAIT_EVENT_BASE_BACKUP_THROTTLE = PG_WAIT_TIMEOUT, + WAIT_EVENT_CHECKPOINT_WRITE_DELAY, WAIT_EVENT_PG_SLEEP, WAIT_EVENT_RECOVERY_APPLY_DELAY, WAIT_EVENT_RECOVERY_RETRIEVE_RETRY_INTERVAL, |