Implement WAIT FOR command

WAIT FOR is to be used on standby and specifies waiting for
the specific WAL location to be replayed.  This option is useful when
the user makes some data changes on primary and needs a guarantee to see
these changes are on standby.

WAIT FOR needs to wait without any snapshot held.  Otherwise, the snapshot
could prevent the replay of WAL records, implying a kind of self-deadlock.
This is why separate utility command seems appears to be the most robust
way to implement this functionality.  It's not possible to implement this as
a function.  Previous experience shows that stored procedures also have
limitation in this aspect.

Discussion: https://www.postgresql.org/message-id/flat/CAPpHfdsjtZLVzxjGT8rJHCYbM0D5dwkO+BBjcirozJ6nYbOW8Q@mail.gmail.com
Discussion: https://www.postgresql.org/message-id/flat/CABPTF7UNft368x-RgOXkfj475OwEbp%2BVVO-wEXz7StgjD_%3D6sw%40mail.gmail.com
Author: Kartyshov Ivan <i.kartyshov@postgrespro.ru>
Author: Alexander Korotkov <aekorotkov@gmail.com>
Author: Xuneng Zhou <xunengzhou@gmail.com>
Reviewed-by: Michael Paquier <michael@paquier.xyz>
Reviewed-by: Peter Eisentraut <peter.eisentraut@enterprisedb.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Amit Kapila <amit.kapila16@gmail.com>
Reviewed-by: Alexander Lakhin <exclusion@gmail.com>
Reviewed-by: Bharath Rupireddy <bharath.rupireddyforpostgres@gmail.com>
Reviewed-by: Euler Taveira <euler@eulerto.com>
Reviewed-by: Heikki Linnakangas <hlinnaka@iki.fi>
Reviewed-by: Kyotaro Horiguchi <horikyota.ntt@gmail.com>
Reviewed-by: jian he <jian.universality@gmail.com>
Reviewed-by: Álvaro Herrera <alvherre@kurilemu.de>
Reviewed-by: Xuneng Zhou <xunengzhou@gmail.com>

3 files changed, 24 insertions, 0 deletions

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 2cf3d4e92b7..092e197eba3 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -31,6 +31,7 @@
 #include "access/xloginsert.h"
 #include "access/xlogrecovery.h"
 #include "access/xlogutils.h"
+#include "access/xlogwait.h"
 #include "catalog/index.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_enum.h"
@@ -2843,6 +2844,11 @@ AbortTransaction(void)
 	 */
 	LWLockReleaseAll();
 
+	/*
+	 * Cleanup waiting for LSN if any.
+	 */
+	WaitLSNCleanup();
+
 	/* Clear wait information and command progress indicator */
 	pgstat_report_wait_end();
 	pgstat_progress_end_command();
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9900e3e0179..7c959051e11 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -62,6 +62,7 @@
 #include "access/xlogreader.h"
 #include "access/xlogrecovery.h"
 #include "access/xlogutils.h"
+#include "access/xlogwait.h"
 #include "backup/basebackup.h"
 #include "catalog/catversion.h"
 #include "catalog/pg_control.h"
@@ -6228,6 +6229,12 @@ StartupXLOG(void)
 	LWLockRelease(ControlFileLock);
 
 	/*
+	 * Wake up all waiters for replay LSN.  They need to report an error that
+	 * recovery was ended before reaching the target LSN.
+	 */
+	WaitLSNWakeup(WAIT_LSN_TYPE_REPLAY, InvalidXLogRecPtr);
+
+	/*
 	 * Shutdown the recovery environment.  This must occur after
 	 * RecoverPreparedTransactions() (see notes in lock_twophase_recover())
 	 * and after switching SharedRecoveryState to RECOVERY_STATE_DONE so as
diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c
index 93c50831b26..550de6e4a59 100644
--- a/src/backend/access/transam/xlogrecovery.c
+++ b/src/backend/access/transam/xlogrecovery.c
@@ -40,6 +40,7 @@
 #include "access/xlogreader.h"
 #include "access/xlogrecovery.h"
 #include "access/xlogutils.h"
+#include "access/xlogwait.h"
 #include "backup/basebackup.h"
 #include "catalog/pg_control.h"
 #include "commands/tablespace.h"
@@ -1838,6 +1839,16 @@ PerformWalRecovery(void)
 				break;
 			}
 
+			/*
+			 * If we replayed an LSN that someone was waiting for then walk
+			 * over the shared memory array and set latches to notify the
+			 * waiters.
+			 */
+			if (waitLSNState &&
+				(XLogRecoveryCtl->lastReplayedEndRecPtr >=
+				 pg_atomic_read_u64(&waitLSNState->minWaitedLSN[WAIT_LSN_TYPE_REPLAY])))
+				WaitLSNWakeup(WAIT_LSN_TYPE_REPLAY, XLogRecoveryCtl->lastReplayedEndRecPtr);
+
 			/* Else, try to fetch the next WAL record */
 			record = ReadRecord(xlogprefetcher, LOG, false, replayTLI);
 		} while (record != NULL);