walreceiver uses a temporary replication slot by default

If no permanent replication slot is configured using
primary_slot_name, the walreceiver now creates and uses a temporary
replication slot.  A new setting wal_receiver_create_temp_slot can be
used to disable this behavior, for example, if the remote instance is
out of replication slots.

Reviewed-by: Masahiko Sawada <masahiko.sawada@2ndquadrant.com>
Discussion: https://www.postgresql.org/message-id/CA%2Bfd4k4dM0iEPLxyVyme2RAFsn8SUgrNtBJOu81YqTY4V%2BnqZA%40mail.gmail.com

doc/src/sgml/config.sgml

@@ -4124,6 +4124,26 @@ ANY <replaceable class="parameter">num_sync</replaceable> ( <replaceable class="
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-wal-receiver-create-temp-slot" xreflabel="wal_receiver_create_temp_slot">
+      <term><varname>wal_receiver_create_temp_slot</varname> (<type>boolean</type>)
+      <indexterm>
+       <primary><varname>wal_receiver_create_temp_slot</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Specifies whether a WAL receiver should create a temporary replication
+        slot on the remote instance when no permanent replication slot to use
+        has been configured (using <xref linkend="guc-primary-slot-name"/>).
+        The default is on.  The only reason to turn this off would be if the
+        remote instance is currently out of available replication slots.  This
+        parameter can only be set in the <filename>postgresql.conf</filename>
+        file or on the server command line.  Changes only take effect when the
+        WAL receiver process starts a new connection.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-wal-receiver-status-interval" xreflabel="wal_receiver_status_interval">
       <term><varname>wal_receiver_status_interval</varname> (<type>integer</type>)
       <indexterm>

src/backend/replication/libpqwalreceiver/libpqwalreceiver.c

@@ -834,6 +834,10 @@ libpqrcv_create_slot(WalReceiverConn *conn, const char *slotname,
 				break;
 		}
 	}
+	else
+	{
+		appendStringInfoString(&cmd, " PHYSICAL RESERVE_WAL");
+	}
 
 	res = libpqrcv_PQexec(conn->streamConn, cmd.data);
 	pfree(cmd.data);

src/backend/replication/walreceiver.c

@@ -73,6 +73,7 @@
 
 
 /* GUC variables */
+bool		wal_receiver_create_temp_slot;
 int			wal_receiver_status_interval;
 int			wal_receiver_timeout;
 bool		hot_standby_feedback;
@@ -169,6 +170,7 @@ WalReceiverMain(void)
 	char		conninfo[MAXCONNINFO];
 	char	   *tmp_conninfo;
 	char		slotname[NAMEDATALEN];
+	bool		is_temp_slot;
 	XLogRecPtr	startpoint;
 	TimeLineID	startpointTLI;
 	TimeLineID	primaryTLI;
@@ -230,6 +232,7 @@ WalReceiverMain(void)
 	walrcv->ready_to_display = false;
 	strlcpy(conninfo, (char *) walrcv->conninfo, MAXCONNINFO);
 	strlcpy(slotname, (char *) walrcv->slotname, NAMEDATALEN);
+	is_temp_slot = walrcv->is_temp_slot;
 	startpoint = walrcv->receiveStart;
 	startpointTLI = walrcv->receiveStartTLI;
 
@@ -345,6 +348,44 @@ WalReceiverMain(void)
 		 */
 		WalRcvFetchTimeLineHistoryFiles(startpointTLI, primaryTLI);
 
+		/*
+		 * Create temporary replication slot if no slot name is configured or
+		 * the slot from the previous run was temporary, unless
+		 * wal_receiver_create_temp_slot is disabled.  We also need to handle
+		 * the case where the previous run used a temporary slot but
+		 * wal_receiver_create_temp_slot was changed in the meantime.  In that
+		 * case, we delete the old slot name in shared memory.  (This would
+		 * all be a bit easier if we just didn't copy the slot name into
+		 * shared memory, since we won't need it again later, but then we
+		 * can't see the slot name in the stats views.)
+		 */
+		if (slotname[0] == '\0' || is_temp_slot)
+		{
+			bool		changed = false;
+
+			if (wal_receiver_create_temp_slot)
+			{
+				snprintf(slotname, sizeof(slotname),
+						 "pg_walreceiver_%d", walrcv_get_backend_pid(wrconn));
+
+				walrcv_create_slot(wrconn, slotname, true, 0, NULL);
+				changed = true;
+			}
+			else if (slotname[0] != '\0')
+			{
+				slotname[0] = '\0';
+				changed = true;
+			}
+
+			if (changed)
+			{
+				SpinLockAcquire(&walrcv->mutex);
+				strlcpy(walrcv->slotname, slotname, NAMEDATALEN);
+				walrcv->is_temp_slot = wal_receiver_create_temp_slot;
+				SpinLockRelease(&walrcv->mutex);
+			}
+		}
+
 		/*
 		 * Start streaming.
 		 *

src/backend/utils/misc/guc.c

@@ -1969,6 +1969,15 @@ static struct config_bool ConfigureNamesBool[] =
 		NULL, NULL, NULL
 	},
 
+	{
+		{"wal_receiver_create_temp_slot", PGC_SIGHUP, REPLICATION_STANDBY,
+			gettext_noop("Sets whether a WAL receiver should create a temporary replication slot if no permanent slot is configured."),
+		},
+		&wal_receiver_create_temp_slot,
+		true,
+		NULL, NULL, NULL
+	},
+
 	/* End-of-list marker */
 	{
 		{NULL, 0, 0, NULL, NULL}, NULL, false, NULL, NULL, NULL

src/backend/utils/misc/postgresql.conf.sample

@@ -321,6 +321,7 @@
 #max_standby_streaming_delay = 30s	# max delay before canceling queries
 					# when reading streaming WAL;
 					# -1 allows indefinite delay
+#wal_receiver_create_temp_slot = on	# create temp slot if primary_slot_name not set
 #wal_receiver_status_interval = 10s	# send replies at least this often
 					# 0 disables
 #hot_standby_feedback = off		# send info from standby to prevent

src/include/replication/walreceiver.h

@@ -23,6 +23,7 @@
 #include "utils/tuplestore.h"
 
 /* user-settable parameters */
+extern bool wal_receiver_create_temp_slot;
 extern int	wal_receiver_status_interval;
 extern int	wal_receiver_timeout;
 extern bool hot_standby_feedback;
@@ -121,6 +122,12 @@ typedef struct
 	 */
 	char		slotname[NAMEDATALEN];
 
+	/*
+	 * If it's a temporary replication slot, it needs to be recreated when
+	 * connecting.
+	 */
+	bool		is_temp_slot;
+
 	/* set true once conninfo is ready to display (obfuscated pwds etc) */
 	bool		ready_to_display;