Avoid unlikely data-loss scenarios due to rename() without fsync.

Renaming a file using rename(2) is not guaranteed to be durable in face
of crashes. Use the previously added durable_rename()/durable_link_or_rename()
in various places where we previously just renamed files.

Most of the changed call sites are arguably not critical, but it seems
better to err on the side of too much durability.  The most prominent
known case where the previously missing fsyncs could cause data loss is
crashes at the end of a checkpoint. After the actual checkpoint has been
performed, old WAL files are recycled. When they're filled, their
contents are fdatasynced, but we did not fsync the containing
directory. An OS/hardware crash in an unfortunate moment could then end
up leaving that file with its old name, but new content; WAL replay
would thus not replay it.

Reported-By: Tomas Vondra
Author: Michael Paquier, Tomas Vondra, Andres Freund
Discussion: 56583BDD.9060302@2ndquadrant.com
Backpatch: All supported branches

1 files changed, 11 insertions, 45 deletions

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 00f139a0f38..5b1c3611176 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -3299,34 +3299,16 @@ InstallXLogFileSegment(XLogSegNo *segno, char *tmppath,
 	}
 
 	/*
-	 * Prefer link() to rename() here just to be really sure that we don't
-	 * overwrite an existing logfile.  However, there shouldn't be one, so
-	 * rename() is an acceptable substitute except for the truly paranoid.
+	 * Perform the rename using link if available, paranoidly trying to avoid
+	 * overwriting an existing file (there shouldn't be one).
 	 */
-#if HAVE_WORKING_LINK
-	if (link(tmppath, path) < 0)
+	if (durable_link_or_rename(tmppath, path, LOG) != 0)
 	{
 		if (use_lock)
 			LWLockRelease(ControlFileLock);
-		ereport(LOG,
-				(errcode_for_file_access(),
-				 errmsg("could not link file \"%s\" to \"%s\" (initialization of log file): %m",
-						tmppath, path)));
-		return false;
-	}
-	unlink(tmppath);
-#else
-	if (rename(tmppath, path) < 0)
-	{
-		if (use_lock)
-			LWLockRelease(ControlFileLock);
-		ereport(LOG,
-				(errcode_for_file_access(),
-				 errmsg("could not rename file \"%s\" to \"%s\" (initialization of log file): %m",
-						tmppath, path)));
+		/* durable_link_or_rename already emitted log message */
 		return false;
 	}
-#endif
 
 	if (use_lock)
 		LWLockRelease(ControlFileLock);
@@ -5339,11 +5321,7 @@ exitArchiveRecovery(TimeLineID endTLI, XLogRecPtr endOfLog)
 	 * re-enter archive recovery mode in a subsequent crash.
 	 */
 	unlink(RECOVERY_COMMAND_DONE);
-	if (rename(RECOVERY_COMMAND_FILE, RECOVERY_COMMAND_DONE) != 0)
-		ereport(FATAL,
-				(errcode_for_file_access(),
-				 errmsg("could not rename file \"%s\" to \"%s\": %m",
-						RECOVERY_COMMAND_FILE, RECOVERY_COMMAND_DONE)));
+	durable_rename(RECOVERY_COMMAND_FILE, RECOVERY_COMMAND_DONE, FATAL);
 
 	ereport(LOG,
 			(errmsg("archive recovery complete")));
@@ -6190,7 +6168,7 @@ StartupXLOG(void)
 		if (stat(TABLESPACE_MAP, &st) == 0)
 		{
 			unlink(TABLESPACE_MAP_OLD);
-			if (rename(TABLESPACE_MAP, TABLESPACE_MAP_OLD) == 0)
+			if (durable_rename(TABLESPACE_MAP, TABLESPACE_MAP_OLD, DEBUG1) == 0)
 				ereport(LOG,
 					(errmsg("ignoring file \"%s\" because no file \"%s\" exists",
 							TABLESPACE_MAP, BACKUP_LABEL_FILE),
@@ -6553,11 +6531,7 @@ StartupXLOG(void)
 		if (haveBackupLabel)
 		{
 			unlink(BACKUP_LABEL_OLD);
-			if (rename(BACKUP_LABEL_FILE, BACKUP_LABEL_OLD) != 0)
-				ereport(FATAL,
-						(errcode_for_file_access(),
-						 errmsg("could not rename file \"%s\" to \"%s\": %m",
-								BACKUP_LABEL_FILE, BACKUP_LABEL_OLD)));
+			durable_rename(BACKUP_LABEL_FILE, BACKUP_LABEL_OLD, FATAL);
 		}
 
 		/*
@@ -6570,11 +6544,7 @@ StartupXLOG(void)
 		if (haveTblspcMap)
 		{
 			unlink(TABLESPACE_MAP_OLD);
-			if (rename(TABLESPACE_MAP, TABLESPACE_MAP_OLD) != 0)
-				ereport(FATAL,
-						(errcode_for_file_access(),
-						 errmsg("could not rename file \"%s\" to \"%s\": %m",
-								TABLESPACE_MAP, TABLESPACE_MAP_OLD)));
+			durable_rename(TABLESPACE_MAP, TABLESPACE_MAP_OLD, FATAL);
 		}
 
 		/* Check that the GUCs used to generate the WAL allow recovery */
@@ -7351,11 +7321,7 @@ StartupXLOG(void)
 				 */
 				XLogArchiveCleanup(partialfname);
 
-				if (rename(origpath, partialpath) != 0)
-					ereport(ERROR,
-							(errcode_for_file_access(),
-						 errmsg("could not rename file \"%s\" to \"%s\": %m",
-								origpath, partialpath)));
+				durable_rename(origpath, partialpath, ERROR);
 				XLogArchiveNotify(partialfname);
 			}
 		}
@@ -10911,7 +10877,7 @@ CancelBackup(void)
 	/* remove leftover file from previously canceled backup if it exists */
 	unlink(BACKUP_LABEL_OLD);
 
-	if (rename(BACKUP_LABEL_FILE, BACKUP_LABEL_OLD) != 0)
+	if (durable_rename(BACKUP_LABEL_FILE, BACKUP_LABEL_OLD, DEBUG1) != 0)
 	{
 		ereport(WARNING,
 				(errcode_for_file_access(),
@@ -10934,7 +10900,7 @@ CancelBackup(void)
 	/* remove leftover file from previously canceled backup if it exists */
 	unlink(TABLESPACE_MAP_OLD);
 
-	if (rename(TABLESPACE_MAP, TABLESPACE_MAP_OLD) == 0)
+	if (durable_rename(TABLESPACE_MAP, TABLESPACE_MAP_OLD, DEBUG1) == 0)
 	{
 		ereport(LOG,
 				(errmsg("online backup mode canceled"),