Drop slot's LWLock before returning from SaveSlotToPath()

petere · petere · commit f36a10434a31 · 2020-03-26T13:51:22.000+01:00
When SaveSlotToPath() is called with elevel=LOG, the early exits didn't release the slot's io_in_progress_lock. This could result in a walsender being stuck on the lock forever. A possible way to get into this situation is if the offending code paths are triggered in a low disk space situation. Author: Pavan Deolasee <pavan.deolasee@2ndquadrant.com> Reported-by: Craig Ringer <craig@2ndquadrant.com> Discussion: https://www.postgresql.org/message-id/flat/56a138c5-de61-f553-7e8f-6789296de785%402ndquadrant.com
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
@@ -1251,6 +1251,12 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 						   S_IRUSR | S_IWUSR);
 	if (fd < 0)
 	{
+		/*
+		 * If not an ERROR, then release the lock before returning.  In case
+		 * of an ERROR, the error recovery path automatically releases the
+		 * lock, but no harm in explicitly releasing even in that case.
+		 */
+		LWLockRelease(&slot->io_in_progress_lock);
 		ereport(elevel,
 				(errcode_for_file_access(),
 				 errmsg("could not create file \"%s\": %m",
@@ -1282,6 +1288,7 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 
 		pgstat_report_wait_end();
 		CloseTransientFile(fd);
+		LWLockRelease(&slot->io_in_progress_lock);
 
 		/* if write didn't set errno, assume problem is no disk space */
 		errno = save_errno ? save_errno : ENOSPC;
@@ -1301,6 +1308,7 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 
 		pgstat_report_wait_end();
 		CloseTransientFile(fd);
+		LWLockRelease(&slot->io_in_progress_lock);
 		errno = save_errno;
 		ereport(elevel,
 				(errcode_for_file_access(),
@@ -1315,6 +1323,7 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 	/* rename to permanent file, fsync file and directory */
 	if (rename(tmppath, path) != 0)
 	{
+		LWLockRelease(&slot->io_in_progress_lock);
 		ereport(elevel,
 				(errcode_for_file_access(),
 				 errmsg("could not rename file \"%s\" to \"%s\": %m",
