Add pg_promote function

This function is able to promote a standby with this new SQL-callable
function.  Execution access can be granted to non-superusers so that
failover tools can observe the principle of least privilege.

Catalog version is bumped.

Author: Laurenz Albe
Reviewed-by: Michael Paquier, Masahiko Sawada
Discussion: https://postgr.es/m/6e7c79b3ec916cf49742fb8849ed17cd87aed620.camel@cybertec.at

Author: michaelpq

doc/src/sgml/func.sgml

@@ -19202,6 +19202,9 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup());
    <indexterm>
     <primary>pg_is_wal_replay_paused</primary>
    </indexterm>
+   <indexterm>
+    <primary>pg_promote</primary>
+   </indexterm>
    <indexterm>
     <primary>pg_wal_replay_pause</primary>
    </indexterm>
@@ -19232,6 +19235,22 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup());
        <entry>True if recovery is paused.
        </entry>
       </row>
+      <row>
+       <entry>
+        <literal><function>pg_promote(<parameter>wait</parameter> <type>boolean</type> DEFAULT true, <parameter>wait_seconds</parameter> <type>integer</type> DEFAULT 60)</function></literal>
+        </entry>
+       <entry><type>boolean</type></entry>
+       <entry>
+        Promotes a physical standby server.  Returns <literal>true</literal>
+        if promotion is successful and <literal>false</literal> otherwise.
+        With <parameter>wait</parameter> set to <literal>true</literal>, the
+        default, the function waits until promotion is completed or
+        <parameter>wait_seconds</parameter> seconds have passed, otherwise the
+        function returns immediately after sending the promotion signal to the
+        postmaster.  This function is restricted to superusers by default, but
+        other users can be granted EXECUTE to run the function.
+       </entry>
+      </row>
       <row>
        <entry>
         <literal><function>pg_wal_replay_pause()</function></literal>

doc/src/sgml/high-availability.sgml

@@ -1471,14 +1471,17 @@ synchronous_standby_names = 'ANY 2 (s1, s2, s3)'
    </para>
 
    <para>
-    To trigger failover of a log-shipping standby server,
-    run <command>pg_ctl promote</command> or create a trigger
-    file with the file name and path specified by the <varname>trigger_file</varname>
-    setting in <filename>recovery.conf</filename>. If you're planning to use
-    <command>pg_ctl promote</command> to fail over, <varname>trigger_file</varname> is
-    not required. If you're setting up the reporting servers that are
-    only used to offload read-only queries from the primary, not for high
-    availability purposes, you don't need to promote it.
+    To trigger failover of a log-shipping standby server, run
+    <command>pg_ctl promote</command>, call <function>pg_promote</function>,
+    or create a trigger file with the file name and path specified by the
+    <varname>trigger_file</varname> setting in
+    <filename>recovery.conf</filename>. If you're planning to use
+    <command>pg_ctl promote</command> or to call
+    <function>pg_promote</function> to fail over,
+    <varname>trigger_file</varname> is not required. If you're
+    setting up the reporting servers that are only used to offload read-only
+    queries from the primary, not for high availability purposes, you don't
+    need to promote it.
    </para>
   </sect1>
 

doc/src/sgml/monitoring.sgml

@@ -1268,7 +1268,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
          <entry>Waiting in an extension.</entry>
         </row>
         <row>
-         <entry morerows="33"><literal>IPC</literal></entry>
+         <entry morerows="34"><literal>IPC</literal></entry>
          <entry><literal>BgWorkerShutdown</literal></entry>
          <entry>Waiting for background worker to shut down.</entry>
         </row>
@@ -1388,6 +1388,10 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
          <entry><literal>ProcArrayGroupUpdate</literal></entry>
          <entry>Waiting for group leader to clear transaction id at transaction end.</entry>
         </row>
+        <row>
+         <entry><literal>Promote</literal></entry>
+         <entry>Waiting for standby promotion.</entry>
+        </row>
         <row>
          <entry><literal>ReplicationOriginDrop</literal></entry>
          <entry>Waiting for a replication origin to become inactive to be dropped.</entry>

doc/src/sgml/recovery-config.sgml

@@ -439,7 +439,8 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"'  # Windows
          <para>
           Specifies a trigger file whose presence ends recovery in the
           standby.  Even if this value is not set, you can still promote
-          the standby using <command>pg_ctl promote</command>.
+          the standby using <command>pg_ctl promote</command> or calling
+          <function>pg_promote</function>.
           This setting has no effect if <varname>standby_mode</varname> is <literal>off</literal>.
          </para>
         </listitem>

src/backend/access/transam/xlog.c

@@ -78,12 +78,6 @@
 
 extern uint32 bootstrap_data_checksum_version;
 
-/* File path names (all relative to $PGDATA) */
-#define RECOVERY_COMMAND_FILE	"recovery.conf"
-#define RECOVERY_COMMAND_DONE	"recovery.done"
-#define PROMOTE_SIGNAL_FILE		"promote"
-#define FALLBACK_PROMOTE_SIGNAL_FILE "fallback_promote"
-
 
 /* User-settable parameters */
 int			max_wal_size_mb = 1024; /* 1 GB */

src/backend/access/transam/xlogfuncs.c

@@ -16,13 +16,16 @@
  */
 #include "postgres.h"
 
+#include <unistd.h>
+
 #include "access/htup_details.h"
 #include "access/xlog.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
 #include "catalog/pg_type.h"
 #include "funcapi.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "replication/walreceiver.h"
 #include "storage/smgr.h"
 #include "utils/builtins.h"
@@ -697,3 +700,77 @@ pg_backup_start_time(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(xtime);
 }
+
+/*
+ * Promotes a standby server.
+ *
+ * A result of "true" means that promotion has been completed if "wait" is
+ * "true", or initiated if "wait" is false.
+ */
+Datum
+pg_promote(PG_FUNCTION_ARGS)
+{
+	bool		wait = PG_GETARG_BOOL(0);
+	int			wait_seconds = PG_GETARG_INT32(1);
+	FILE	   *promote_file;
+	int			i;
+
+	if (!RecoveryInProgress())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+				 errmsg("recovery is not in progress"),
+				 errhint("Recovery control functions can only be executed during recovery.")));
+
+	if (wait_seconds <= 0)
+		ereport(ERROR,
+				(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
+				 errmsg("\"wait_seconds\" cannot be negative or equal zero")));
+
+	/* create the promote signal file */
+	promote_file = AllocateFile(PROMOTE_SIGNAL_FILE, "w");
+	if (!promote_file)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not create file \"%s\": %m",
+						PROMOTE_SIGNAL_FILE)));
+
+	if (FreeFile(promote_file))
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not write file \"%s\": %m",
+						PROMOTE_SIGNAL_FILE)));
+
+	/* signal the postmaster */
+	if (kill(PostmasterPid, SIGUSR1) != 0)
+	{
+		ereport(WARNING,
+				(errmsg("failed to send signal to postmaster: %m")));
+		(void) unlink(PROMOTE_SIGNAL_FILE);
+		PG_RETURN_BOOL(false);
+	}
+
+	/* return immediately if waiting was not requested */
+	if (!wait)
+		PG_RETURN_BOOL(true);
+
+	/* wait for the amount of time wanted until promotion */
+#define WAITS_PER_SECOND 10
+	for (i = 0; i < WAITS_PER_SECOND * wait_seconds; i++)
+	{
+		ResetLatch(MyLatch);
+
+		if (!RecoveryInProgress())
+			PG_RETURN_BOOL(true);
+
+		CHECK_FOR_INTERRUPTS();
+
+		WaitLatch(MyLatch,
+				  WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
+				  1000L / WAITS_PER_SECOND,
+				  WAIT_EVENT_PROMOTE);
+	}
+
+	ereport(WARNING,
+			(errmsg("server did not promote within %d seconds", wait_seconds)));
+	PG_RETURN_BOOL(false);
+}

src/backend/catalog/system_views.sql

@@ -1027,6 +1027,11 @@ CREATE OR REPLACE FUNCTION pg_stop_backup (
   RETURNS SETOF record STRICT VOLATILE LANGUAGE internal as 'pg_stop_backup_v2'
   PARALLEL RESTRICTED;
 
+CREATE OR REPLACE FUNCTION
+  pg_promote(wait boolean DEFAULT true, wait_seconds integer DEFAULT 60)
+  RETURNS boolean STRICT VOLATILE LANGUAGE INTERNAL AS 'pg_promote'
+  PARALLEL RESTRICTED;
+
 -- legacy definition for compatibility with 9.3
 CREATE OR REPLACE FUNCTION
   json_populate_record(base anyelement, from_json json, use_json_as_text boolean DEFAULT false)
@@ -1138,6 +1143,7 @@ REVOKE EXECUTE ON FUNCTION pg_rotate_logfile() FROM public;
 REVOKE EXECUTE ON FUNCTION pg_reload_conf() FROM public;
 REVOKE EXECUTE ON FUNCTION pg_current_logfile() FROM public;
 REVOKE EXECUTE ON FUNCTION pg_current_logfile(text) FROM public;
+REVOKE EXECUTE ON FUNCTION pg_promote(boolean, integer) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset() FROM public;
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_shared(text) FROM public;

src/backend/postmaster/pgstat.c

@@ -3663,6 +3663,9 @@ pgstat_get_wait_ipc(WaitEventIPC w)
 		case WAIT_EVENT_PROCARRAY_GROUP_UPDATE:
 			event_name = "ProcArrayGroupUpdate";
 			break;
+		case WAIT_EVENT_PROMOTE:
+			event_name = "Promote";
+			break;
 		case WAIT_EVENT_REPLICATION_ORIGIN_DROP:
 			event_name = "ReplicationOriginDrop";
 			break;

src/include/access/xlog.h

@@ -319,10 +319,16 @@ extern void do_pg_abort_backup(void);
 extern SessionBackupState get_backup_status(void);
 
 /* File path names (all relative to $PGDATA) */
+#define RECOVERY_COMMAND_FILE	"recovery.conf"
+#define RECOVERY_COMMAND_DONE	"recovery.done"
 #define BACKUP_LABEL_FILE		"backup_label"
 #define BACKUP_LABEL_OLD		"backup_label.old"
 
 #define TABLESPACE_MAP			"tablespace_map"
 #define TABLESPACE_MAP_OLD		"tablespace_map.old"
 
+/* files to signal promotion to primary */
+#define PROMOTE_SIGNAL_FILE		"promote"
+#define FALLBACK_PROMOTE_SIGNAL_FILE  "fallback_promote"
+
 #endif							/* XLOG_H */

src/include/catalog/catversion.h

@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	201810111
+#define CATALOG_VERSION_NO	201810251
 
 #endif

src/include/catalog/pg_proc.dat

@@ -5824,6 +5824,10 @@
   proname => 'pg_backup_start_time', provolatile => 's',
   prorettype => 'timestamptz', proargtypes => '',
   prosrc => 'pg_backup_start_time' },
+{ oid => '3436', descr => 'promote standby server',
+  proname => 'pg_promote', provolatile => 'v',
+  prorettype => 'bool', proargtypes => 'bool int4', proargnames => '{wait,wait_seconds}',
+  prosrc => 'pg_promote' },
 { oid => '2848', descr => 'switch to new wal file',
   proname => 'pg_switch_wal', provolatile => 'v', prorettype => 'pg_lsn',
   proargtypes => '', prosrc => 'pg_switch_wal' },

src/include/pgstat.h

@@ -829,6 +829,7 @@ typedef enum
 	WAIT_EVENT_PARALLEL_CREATE_INDEX_SCAN,
 	WAIT_EVENT_PARALLEL_FINISH,
 	WAIT_EVENT_PROCARRAY_GROUP_UPDATE,
+	WAIT_EVENT_PROMOTE,
 	WAIT_EVENT_REPLICATION_ORIGIN_DROP,
 	WAIT_EVENT_REPLICATION_SLOT_DROP,
 	WAIT_EVENT_SAFE_SNAPSHOT,

src/test/recovery/t/004_timeline_switch.pl

@@ -6,7 +6,7 @@
 use File::Path qw(rmtree);
 use PostgresNode;
 use TestLib;
-use Test::More tests => 1;
+use Test::More tests => 2;
 
 $ENV{PGDATABASE} = 'postgres';
 
@@ -37,9 +37,14 @@
 $node_master->wait_for_catchup($node_standby_1, 'replay',
 	$node_master->lsn('write'));
 
-# Stop and remove master, and promote standby 1, switching it to a new timeline
+# Stop and remove master
 $node_master->teardown_node;
-$node_standby_1->promote;
+
+# promote standby 1 using "pg_promote", switching it to a new timeline
+my $psql_out = '';
+$node_standby_1->psql('postgres', "SELECT pg_promote(wait_seconds => 300)",
+	stdout => \$psql_out);
+is($psql_out, 't', "promotion of standby with pg_promote");
 
 # Switch standby 2 to replay from standby 1
 rmtree($node_standby_2->data_dir . '/recovery.conf');