Add a new slot sync worker to synchronize logical slots.

By enabling slot synchronization, all the failover logical replication
slots on the primary (assuming configurations are appropriate) are
automatically created on the physical standbys and are synced
periodically. The slot sync worker on the standby server pings the primary
server at regular intervals to get the necessary failover logical slots
information and create/update the slots locally. The slots that no longer
require synchronization are automatically dropped by the worker.

The nap time of the worker is tuned according to the activity on the
primary. The slot sync worker waits for some time before the next
synchronization, with the duration varying based on whether any slots were
updated during the last cycle.

A new parameter sync_replication_slots enables or disables this new
process.

On promotion, the slot sync worker is shut down by the startup process to
drop any temporary slots acquired by the slot sync worker and to prevent
the worker from trying to fetch the failover slots.

A functionality to allow logical walsenders to wait for the physical will
be done in a subsequent commit.

Author: Shveta Malik, Hou Zhijie based on design inputs by Masahiko Sawada and Amit Kapila
Reviewed-by: Masahiko Sawada, Bertrand Drouvot, Peter Smith, Dilip Kumar, Ajin Cherian, Nisha Moond, Kuroda Hayato, Amit Kapila
Discussion: https://postgr.es/m/514f6f2f-6833-4539-39f1-96cd1e011f23@enterprisedb.com

6 files changed, 26 insertions, 5 deletions

diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 43c393d6fe8..9d6e0673827 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -338,6 +338,7 @@ pgstat_tracks_io_bktype(BackendType bktype)
 		case B_BG_WORKER:
 		case B_BG_WRITER:
 		case B_CHECKPOINTER:
+		case B_SLOTSYNC_WORKER:
 		case B_STANDALONE_BACKEND:
 		case B_STARTUP:
 		case B_WAL_SENDER:
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 6464386b779..4fffb466255 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -53,6 +53,8 @@ LOGICAL_APPLY_MAIN	"Waiting in main loop of logical replication apply process."
 LOGICAL_LAUNCHER_MAIN	"Waiting in main loop of logical replication launcher process."
 LOGICAL_PARALLEL_APPLY_MAIN	"Waiting in main loop of logical replication parallel apply process."
 RECOVERY_WAL_STREAM	"Waiting in main loop of startup process for WAL to arrive, during streaming recovery."
+REPLICATION_SLOTSYNC_MAIN	"Waiting in main loop of slot sync worker."
+REPLICATION_SLOTSYNC_SHUTDOWN	"Waiting for slot sync worker to shut down."
 SYSLOGGER_MAIN	"Waiting in main loop of syslogger process."
 WAL_RECEIVER_MAIN	"Waiting in main loop of WAL receiver process."
 WAL_SENDER_MAIN	"Waiting in main loop of WAL sender process."
diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index 23f77a59e58..77fd8047563 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -40,6 +40,7 @@
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
 #include "postmaster/postmaster.h"
+#include "replication/slotsync.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
@@ -293,6 +294,9 @@ GetBackendTypeDesc(BackendType backendType)
 		case B_LOGGER:
 			backendDesc = "logger";
 			break;
+		case B_SLOTSYNC_WORKER:
+			backendDesc = "slotsync worker";
+			break;
 		case B_STANDALONE_BACKEND:
 			backendDesc = "standalone backend";
 			break;
@@ -835,9 +839,10 @@ InitializeSessionUserIdStandalone(void)
 {
 	/*
 	 * This function should only be called in single-user mode, in autovacuum
-	 * workers, and in background workers.
+	 * workers, in slot sync worker and in background workers.
 	 */
-	Assert(!IsUnderPostmaster || IsAutoVacuumWorkerProcess() || IsBackgroundWorker);
+	Assert(!IsUnderPostmaster || IsAutoVacuumWorkerProcess() ||
+		   IsLogicalSlotSyncWorker() || IsBackgroundWorker);
 
 	/* call only once */
 	Assert(!OidIsValid(AuthenticatedUserId));
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 7797876d008..5ffe9bdd987 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -43,6 +43,7 @@
 #include "postmaster/autovacuum.h"
 #include "postmaster/postmaster.h"
 #include "replication/slot.h"
+#include "replication/slotsync.h"
 #include "replication/walsender.h"
 #include "storage/bufmgr.h"
 #include "storage/fd.h"
@@ -876,10 +877,11 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	 * Perform client authentication if necessary, then figure out our
 	 * postgres user ID, and see if we are a superuser.
 	 *
-	 * In standalone mode and in autovacuum worker processes, we use a fixed
-	 * ID, otherwise we figure it out from the authenticated user name.
+	 * In standalone mode, autovacuum worker processes and slot sync worker
+	 * process, we use a fixed ID, otherwise we figure it out from the
+	 * authenticated user name.
 	 */
-	if (bootstrap || IsAutoVacuumWorkerProcess())
+	if (bootstrap || IsAutoVacuumWorkerProcess() || IsLogicalSlotSyncWorker())
 	{
 		InitializeSessionUserIdStandalone();
 		am_superuser = true;
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index 70652f0a3fc..37be0669bba 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -67,6 +67,7 @@
 #include "postmaster/walwriter.h"
 #include "replication/logicallauncher.h"
 #include "replication/slot.h"
+#include "replication/slotsync.h"
 #include "replication/syncrep.h"
 #include "storage/bufmgr.h"
 #include "storage/large_object.h"
@@ -2054,6 +2055,15 @@ struct config_bool ConfigureNamesBool[] =
 		NULL, NULL, NULL
 	},
 
+	{
+		{"sync_replication_slots", PGC_SIGHUP, REPLICATION_STANDBY,
+			gettext_noop("Enables a physical standby to synchronize logical failover slots from the primary server."),
+		},
+		&sync_replication_slots,
+		false,
+		NULL, NULL, NULL
+	},
+
 	/* End-of-list marker */
 	{
 		{NULL, 0, 0, NULL, NULL}, NULL, false, NULL, NULL, NULL
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index e10755972ae..c97f9a25f05 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -361,6 +361,7 @@
 #wal_retrieve_retry_interval = 5s	# time to wait before retrying to
 					# retrieve WAL after a failed attempt
 #recovery_min_apply_delay = 0		# minimum delay for applying changes during recovery
+#sync_replication_slots = off			# enables slot synchronization on the physical standby from the primary
 
 # - Subscribers -