diff options
| author | Thomas Munro <tmunro@postgresql.org> | 2022-03-16 15:35:16 +1300 |
|---|---|---|
| committer | Thomas Munro <tmunro@postgresql.org> | 2022-03-16 15:35:16 +1300 |
| commit | 3390ef1b7be28eac24dd95af23a4a287e6e7b1a4 (patch) | |
| tree | 457f498334230a7d9af072c61aa57a8de9673f32 | |
| parent | 076f4d9539e9687d68ada32353c0c16d9bfa3cfb (diff) | |
| download | postgresql-3390ef1b7be28eac24dd95af23a4a287e6e7b1a4.tar.gz postgresql-3390ef1b7be28eac24dd95af23a4a287e6e7b1a4.zip | |
Fix waiting in RegisterSyncRequest().
If we run out of space in the checkpointer sync request queue (which is
hopefully rare on real systems, but common with very small buffer pool),
we wait for it to drain. While waiting, we should report that as a wait
event so that users know what is going on, and also handle postmaster
death, since otherwise the loop might never terminate if the
checkpointer has exited.
Back-patch to 12. Although the problem exists in earlier releases too,
the code is structured differently before 12 so I haven't gone any
further for now, in the absence of field complaints.
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 | 5 | ||||
| -rw-r--r-- | src/backend/storage/sync/sync.c | 4 | ||||
| -rw-r--r-- | src/backend/utils/activity/wait_event.c | 3 | ||||
| -rw-r--r-- | src/include/utils/wait_event.h | 1 |
4 files changed, 12 insertions, 1 deletions
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 8620aaddc79..71559442f0b 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -2255,6 +2255,11 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser source (<filename>pg_wal</filename>, archive or stream).</entry> </row> <row> + <entry><literal>RegisterSyncRequest</literal></entry> + <entry>Waiting while sending synchronization requests to the + checkpointer, because the request queue is full.</entry> + </row> + <row> <entry><literal>VacuumDelay</literal></entry> <entry>Waiting in a cost-based vacuum delay point.</entry> </row> diff --git a/src/backend/storage/sync/sync.c b/src/backend/storage/sync/sync.c index e161d57761e..0c4d9ce687f 100644 --- a/src/backend/storage/sync/sync.c +++ b/src/backend/storage/sync/sync.c @@ -31,6 +31,7 @@ #include "storage/bufmgr.h" #include "storage/fd.h" #include "storage/ipc.h" +#include "storage/latch.h" #include "storage/md.h" #include "utils/hsearch.h" #include "utils/inval.h" @@ -606,7 +607,8 @@ RegisterSyncRequest(const FileTag *ftag, SyncRequestType type, if (ret || (!ret && !retryOnError)) break; - pg_usleep(10000L); + WaitLatch(NULL, WL_EXIT_ON_PM_DEATH | WL_TIMEOUT, 10, + WAIT_EVENT_REGISTER_SYNC_REQUEST); } return ret; diff --git a/src/backend/utils/activity/wait_event.c b/src/backend/utils/activity/wait_event.c index 0706e922b53..ff46a0e3c71 100644 --- a/src/backend/utils/activity/wait_event.c +++ b/src/backend/utils/activity/wait_event.c @@ -497,6 +497,9 @@ pgstat_get_wait_timeout(WaitEventTimeout w) case WAIT_EVENT_RECOVERY_RETRIEVE_RETRY_INTERVAL: event_name = "RecoveryRetrieveRetryInterval"; break; + case WAIT_EVENT_REGISTER_SYNC_REQUEST: + event_name = "RegisterSyncRequest"; + break; case WAIT_EVENT_VACUUM_DELAY: event_name = "VacuumDelay"; break; diff --git a/src/include/utils/wait_event.h b/src/include/utils/wait_event.h index d0345c6b49e..1c39ce031a7 100644 --- a/src/include/utils/wait_event.h +++ b/src/include/utils/wait_event.h @@ -145,6 +145,7 @@ typedef enum WAIT_EVENT_PG_SLEEP, WAIT_EVENT_RECOVERY_APPLY_DELAY, WAIT_EVENT_RECOVERY_RETRIEVE_RETRY_INTERVAL, + WAIT_EVENT_REGISTER_SYNC_REQUEST, WAIT_EVENT_VACUUM_DELAY, WAIT_EVENT_VACUUM_TRUNCATE } WaitEventTimeout; |