Fail if recovery target is not reached

Before, if a recovery target is configured, but the archive ended
before the target was reached, recovery would end and the server would
promote without further notice.  That was deemed to be pretty wrong.
With this change, if the recovery target is not reached, it is a fatal
error.

Based-on-patch-by: Leif Gunnar Erlandsen <leif@lako.no>
Reviewed-by: Kyotaro Horiguchi <horikyota.ntt@gmail.com>
Discussion: https://www.postgresql.org/message-id/flat/993736dd3f1713ec1f63fc3b653839f5@lako.no

Author: petere

doc/src/sgml/config.sgml

@@ -3571,6 +3571,11 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"'  # Windows
         If <xref linkend="guc-hot-standby"/> is not enabled, a setting of
         <literal>pause</literal> will act the same as <literal>shutdown</literal>.
        </para>
+       <para>
+        In any case, if a recovery target is configured but the archive
+        recovery ends before the target is reached, the server will shut down
+        with a fatal error.
+       </para>
       </listitem>
      </varlistentry>
 

src/backend/access/transam/xlog.c

@@ -6200,7 +6200,7 @@ StartupXLOG(void)
 	XLogCtlInsert *Insert;
 	CheckPoint	checkPoint;
 	bool		wasShutdown;
-	bool		reachedStopPoint = false;
+	bool		reachedRecoveryTarget = false;
 	bool		haveBackupLabel = false;
 	bool		haveTblspcMap = false;
 	XLogRecPtr	RecPtr,
@@ -7103,7 +7103,7 @@ StartupXLOG(void)
 				 */
 				if (recoveryStopsBefore(xlogreader))
 				{
-					reachedStopPoint = true;	/* see below */
+					reachedRecoveryTarget = true;
 					break;
 				}
 
@@ -7258,7 +7258,7 @@ StartupXLOG(void)
 				/* Exit loop if we reached inclusive recovery target */
 				if (recoveryStopsAfter(xlogreader))
 				{
-					reachedStopPoint = true;
+					reachedRecoveryTarget = true;
 					break;
 				}
 
@@ -7270,7 +7270,7 @@ StartupXLOG(void)
 			 * end of main redo apply loop
 			 */
 
-			if (reachedStopPoint)
+			if (reachedRecoveryTarget)
 			{
 				if (!reachedConsistency)
 					ereport(FATAL,
@@ -7327,7 +7327,18 @@ StartupXLOG(void)
 			/* there are no WAL records following the checkpoint */
 			ereport(LOG,
 					(errmsg("redo is not required")));
+
 		}
+
+		/*
+		 * This check is intentionally after the above log messages that
+		 * indicate how far recovery went.
+		 */
+		if (ArchiveRecoveryRequested &&
+			recoveryTarget != RECOVERY_TARGET_UNSET &&
+			!reachedRecoveryTarget)
+			ereport(FATAL,
+					(errmsg("recovery ended before configured recovery target was reached")));
 	}
 
 	/*

src/test/perl/PostgresNode.pm

@@ -653,6 +653,9 @@ Restoring WAL segments from archives using restore_command can be enabled
 by passing the keyword parameter has_restoring => 1. This is disabled by
 default.
 
+If has_restoring is used, standby mode is used by default.  To use
+recovery mode instead, pass the keyword parameter standby => 0.
+
 The backup is copied, leaving the original unmodified. pg_hba.conf is
 unconditionally set to enable replication connections.
 
@@ -669,6 +672,7 @@ sub init_from_backup
 
 	$params{has_streaming} = 0 unless defined $params{has_streaming};
 	$params{has_restoring} = 0 unless defined $params{has_restoring};
+	$params{standby} = 1 unless defined $params{standby};
 
 	print
 	  "# Initializing node \"$node_name\" from backup \"$backup_name\" of node \"$root_name\"\n";
@@ -699,7 +703,7 @@ port = $port
 			"unix_socket_directories = '$host'");
 	}
 	$self->enable_streaming($root_node) if $params{has_streaming};
-	$self->enable_restoring($root_node) if $params{has_restoring};
+	$self->enable_restoring($root_node, $params{standby}) if $params{has_restoring};
 	return;
 }
 
@@ -939,7 +943,7 @@ primary_conninfo='$root_connstr'
 # Internal routine to enable archive recovery command on a standby node
 sub enable_restoring
 {
-	my ($self, $root_node) = @_;
+	my ($self, $root_node, $standby) = @_;
 	my $path = TestLib::perl2host($root_node->archive_dir);
 	my $name = $self->name;
 
@@ -961,7 +965,30 @@ sub enable_restoring
 		'postgresql.conf', qq(
 restore_command = '$copy_command'
 ));
-	$self->set_standby_mode();
+	if ($standby)
+	{
+		$self->set_standby_mode();
+	}
+	else
+	{
+		$self->set_recovery_mode();
+	}
+	return;
+}
+
+=pod
+
+=item $node->set_recovery_mode()
+
+Place recovery.signal file.
+
+=cut
+
+sub set_recovery_mode
+{
+	my ($self) = @_;
+
+	$self->append_conf('recovery.signal', '');
 	return;
 }
 

src/test/recovery/t/003_recovery_targets.pl

@@ -3,7 +3,8 @@
 use warnings;
 use PostgresNode;
 use TestLib;
-use Test::More tests => 8;
+use Test::More tests => 9;
+use Time::HiRes qw(usleep);
 
 # Create and test a standby from given backup, with a certain recovery target.
 # Choose $until_lsn later than the transaction commit that causes the row
@@ -145,3 +146,24 @@ sub test_recovery_standby
 my $logfile = slurp_file($node_standby->logfile());
 ok($logfile =~ qr/multiple recovery targets specified/,
 	'multiple conflicting settings');
+
+# Check behavior when recovery ends before target is reached
+
+$node_standby = get_new_node('standby_8');
+$node_standby->init_from_backup($node_master, 'my_backup',
+								has_restoring => 1, standby => 0);
+$node_standby->append_conf('postgresql.conf',
+						   "recovery_target_name = 'does_not_exist'");
+
+run_log(['pg_ctl', '-D', $node_standby->data_dir,
+		 '-l', $node_standby->logfile, 'start']);
+
+# wait up to 10 seconds for postgres to terminate
+foreach my $i (0..100)
+{
+	last if ! -f $node_standby->data_dir . '/postmaster.pid';
+	usleep(100_000);
+}
+$logfile = slurp_file($node_standby->logfile());
+ok($logfile =~ qr/FATAL:  recovery ended before configured recovery target was reached/,
+	'recovery end before target reached is a fatal error');