Fix waiting in RegisterSyncRequest().

macdice · macdice · commit cfdb303be756 · 2022-03-16T15:37:15.000+13:00
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
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
@@ -2160,6 +2160,11 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
       <entry>Waiting during recovery when WAL data is not available from any
        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>
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
@@ -3919,6 +3919,9 @@ 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/backend/storage/sync/sync.c b/src/backend/storage/sync/sync.c
@@ -27,6 +27,7 @@
 #include "postmaster/bgwriter.h"
 #include "storage/bufmgr.h"
 #include "storage/ipc.h"
+#include "storage/latch.h"
 #include "storage/md.h"
 #include "utils/hsearch.h"
 #include "utils/inval.h"
@@ -585,7 +586,8 @@ 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/include/pgstat.h b/src/include/pgstat.h
@@ -902,7 +902,8 @@ typedef enum
 	WAIT_EVENT_PG_SLEEP,
 	WAIT_EVENT_RECOVERY_APPLY_DELAY,
 	WAIT_EVENT_RECOVERY_RETRIEVE_RETRY_INTERVAL,
-	WAIT_EVENT_VACUUM_DELAY
+	WAIT_EVENT_VACUUM_DELAY,
+	WAIT_EVENT_REGISTER_SYNC_REQUEST
 } WaitEventTimeout;
 
 /* ----------
