Remove temporary WAL and history files at the end of archive recovery

michaelpq · michaelpq · commit 2a724cdbff0b · 2019-10-02T15:53:51.000+09:00
cbc55da has reworked the order of some actions at the end of archive recovery. Unfortunately this overlooked the fact that the startup process needs to remove RECOVERYXLOG (for temporary WAL segment newly recovered from archives) and RECOVERYHISTORY (for temporary history file) at this step, leaving the files around even after recovery ended. Backpatch to 9.5, like the previous commit. Author: Sawada Masahiko Reviewed-by: Fujii Masao, Michael Paquier Discussion: https://postgr.es/m/CAD21AoBO_eDQub6zojFnWtnmutRBWvYf7=cW4Hsqj+U_R26w3Q@mail.gmail.com Backpatch-through: 9.5
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
@@ -5461,7 +5461,6 @@ validateRecoveryParameters(void)
 static void
 exitArchiveRecovery(TimeLineID endTLI, XLogRecPtr endOfLog)
 {
-	char		recoveryPath[MAXPGPATH];
 	char		xlogfname[MAXFNAMELEN];
 	XLogSegNo	endLogSegNo;
 	XLogSegNo	startLogSegNo;
@@ -5541,17 +5540,6 @@ exitArchiveRecovery(TimeLineID endTLI, XLogRecPtr endOfLog)
 	XLogFileName(xlogfname, ThisTimeLineID, startLogSegNo, wal_segment_size);
 	XLogArchiveCleanup(xlogfname);
 
-	/*
-	 * Since there might be a partial WAL segment named RECOVERYXLOG, get rid
-	 * of it.
-	 */
-	snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYXLOG");
-	unlink(recoveryPath);		/* ignore any error */
-
-	/* Get rid of any remaining recovered timeline-history file, too */
-	snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYHISTORY");
-	unlink(recoveryPath);		/* ignore any error */
-
 	/*
 	 * Remove the signal files out of the way, so that we don't accidentally
 	 * re-enter archive recovery mode in a subsequent crash.
@@ -7429,6 +7417,7 @@ StartupXLOG(void)
 	if (ArchiveRecoveryRequested)
 	{
 		char		reason[200];
+		char		recoveryPath[MAXPGPATH];
 
 		Assert(InArchiveRecovery);
 
@@ -7485,6 +7474,17 @@ StartupXLOG(void)
 		 */
 		writeTimeLineHistory(ThisTimeLineID, recoveryTargetTLI,
 							 EndRecPtr, reason);
+
+		/*
+		 * Since there might be a partial WAL segment named RECOVERYXLOG, get
+		 * rid of it.
+		 */
+		snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYXLOG");
+		unlink(recoveryPath);	/* ignore any error */
+
+		/* Get rid of any remaining recovered timeline-history file, too */
+		snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYHISTORY");
+		unlink(recoveryPath);	/* ignore any error */
 	}
 
 	/* Save the selected TimeLineID in shared memory, too */
diff --git a/src/test/recovery/t/002_archiving.pl b/src/test/recovery/t/002_archiving.pl
@@ -3,7 +3,7 @@
 use warnings;
 use PostgresNode;
 use TestLib;
-use Test::More tests => 1;
+use Test::More tests => 3;
 use File::Copy;
 
 # Initialize master node, doing archives
@@ -49,3 +49,26 @@
 my $result =
   $node_standby->safe_psql('postgres', "SELECT count(*) FROM tab_int");
 is($result, qq(1000), 'check content from archives');
+
+# Check the presence of temporary files specifically generated during
+# archive recovery.  To ensure the presence of the temporary history
+# file, switch to a timeline large enough to allow a standby to recover
+# a history file from an archive.  As this requires at least two timeline
+# switches, promote the existing standby first.  Then create a second
+# standby based on the promoted one.  Finally, the second standby is
+# promoted.
+$node_standby->promote;
+
+my $node_standby2 = get_new_node('standby2');
+$node_standby2->init_from_backup($node_master, $backup_name,
+	has_restoring => 1);
+$node_standby2->start;
+
+# Now promote standby2, and check that temporary files specifically
+# generated during archive recovery are removed by the end of recovery.
+$node_standby2->promote;
+my $node_standby2_data = $node_standby2->data_dir;
+ok( !-f "$node_standby2_data/pg_wal/RECOVERYHISTORY",
+	"RECOVERYHISTORY removed after promotion");
+ok( !-f "$node_standby2_data/pg_wal/RECOVERYXLOG",
+	"RECOVERYXLOG removed after promotion");
