From 82c04e4836adddffe7c78ead525ff61fd5871645 Mon Sep 17 00:00:00 2001
From: Fujii Masao <fujii@postgresql.org>
Date: Tue, 10 Mar 2020 00:14:43 +0900
Subject: [PATCH] Fix bug that causes to report waiting in PS display twice, in
 hot standby.

Previously "waiting" could appear twice via PS in case of lock conflict
in hot standby mode. Specifically this issue happend when the delay
in WAL application determined by max_standby_archive_delay and
max_standby_streaming_delay had passed but it took more than 500 msec
to cancel all the conflicting transactions. Especially we can observe this
easily by setting those delay parameters to -1.

The cause of this issue was that WaitOnLock() and
ResolveRecoveryConflictWithVirtualXIDs() added "waiting" to
the process title in that case. This commit prevents
ResolveRecoveryConflictWithVirtualXIDs() from reporting waiting
in case of lock conflict, to fix the bug.

Back-patch to all back branches.

Author: Masahiko Sawada
Reviewed-by: Fujii Masao
Discussion: https://postgr.es/m/CA+fd4k4mXWTwfQLS3RPwGr4xnfAEs1ysFfgYHvmmoUgv6Zxvmg@mail.gmail.com
---
 src/backend/storage/ipc/standby.c | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)

diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index 25b7e314af..b40ccc4fc4 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -43,7 +43,7 @@ int			max_standby_streaming_delay = 30 * 1000;
 static HTAB *RecoveryLockLists;
 
 static void ResolveRecoveryConflictWithVirtualXIDs(VirtualTransactionId *waitlist,
-												   ProcSignalReason reason);
+												   ProcSignalReason reason, bool report_waiting);
 static void SendRecoveryConflictWithBufferPin(ProcSignalReason reason);
 static XLogRecPtr LogCurrentRunningXacts(RunningTransactions CurrRunningXacts);
 static void LogAccessExclusiveLocks(int nlocks, xl_standby_lock *locks);
@@ -216,19 +216,24 @@ WaitExceedsMaxStandbyDelay(void)
  * recovery processing. Judgement has already been passed on it within
  * a specific rmgr. Here we just issue the orders to the procs. The procs
  * then throw the required error as instructed.
+ *
+ * If report_waiting is true, "waiting" is reported in PS display if necessary.
+ * If the caller has already reported that, report_waiting should be false.
+ * Otherwise, "waiting" is reported twice unexpectedly.
  */
 static void
 ResolveRecoveryConflictWithVirtualXIDs(VirtualTransactionId *waitlist,
-									   ProcSignalReason reason)
+									   ProcSignalReason reason, bool report_waiting)
 {
-	TimestampTz waitStart;
+	TimestampTz waitStart = 0;
 	char	   *new_status;
 
 	/* Fast exit, to avoid a kernel call if there's no work to be done. */
 	if (!VirtualTransactionIdIsValid(*waitlist))
 		return;
 
-	waitStart = GetCurrentTimestamp();
+	if (report_waiting)
+		waitStart = GetCurrentTimestamp();
 	new_status = NULL;			/* we haven't changed the ps display */
 
 	while (VirtualTransactionIdIsValid(*waitlist))
@@ -243,7 +248,7 @@ ResolveRecoveryConflictWithVirtualXIDs(VirtualTransactionId *waitlist,
 			 * Report via ps if we have been waiting for more than 500 msec
 			 * (should that be configurable?)
 			 */
-			if (update_process_title && new_status == NULL &&
+			if (update_process_title && new_status == NULL && report_waiting &&
 				TimestampDifferenceExceeds(waitStart, GetCurrentTimestamp(),
 										   500))
 			{
@@ -311,7 +316,8 @@ ResolveRecoveryConflictWithSnapshot(TransactionId latestRemovedXid, RelFileNode
 										 node.dbNode);
 
 	ResolveRecoveryConflictWithVirtualXIDs(backends,
-										   PROCSIG_RECOVERY_CONFLICT_SNAPSHOT);
+										   PROCSIG_RECOVERY_CONFLICT_SNAPSHOT,
+										   true);
 }
 
 void
@@ -339,7 +345,8 @@ ResolveRecoveryConflictWithTablespace(Oid tsid)
 	temp_file_users = GetConflictingVirtualXIDs(InvalidTransactionId,
 												InvalidOid);
 	ResolveRecoveryConflictWithVirtualXIDs(temp_file_users,
-										   PROCSIG_RECOVERY_CONFLICT_TABLESPACE);
+										   PROCSIG_RECOVERY_CONFLICT_TABLESPACE,
+										   true);
 }
 
 void
@@ -402,8 +409,15 @@ ResolveRecoveryConflictWithLock(LOCKTAG locktag)
 		VirtualTransactionId *backends;
 
 		backends = GetLockConflicts(&locktag, AccessExclusiveLock, NULL);
+
+		/*
+		 * Prevent ResolveRecoveryConflictWithVirtualXIDs() from reporting
+		 * "waiting" in PS display by disabling its argument report_waiting
+		 * because the caller, WaitOnLock(), has already reported that.
+		 */
 		ResolveRecoveryConflictWithVirtualXIDs(backends,
-											   PROCSIG_RECOVERY_CONFLICT_LOCK);
+											   PROCSIG_RECOVERY_CONFLICT_LOCK,
+											   false);
 	}
 	else
 	{