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
This commit is contained in:
Andres Freund 2016-03-09 18:53:54 -08:00
parent 43b491a817
commit 4f37d09169
6 changed files with 18 additions and 93 deletions

View File

@ -735,11 +735,7 @@ pgss_shmem_shutdown(int code, Datum arg)
/*
* Rename file into place, so we atomically replace any old one.
*/
if (rename(PGSS_DUMP_FILE ".tmp", PGSS_DUMP_FILE) != 0)
ereport(LOG,
(errcode_for_file_access(),
errmsg("could not rename pg_stat_statement file \"%s\": %m",
PGSS_DUMP_FILE ".tmp")));
(void) durable_rename(PGSS_DUMP_FILE ".tmp", PGSS_DUMP_FILE, LOG);
/* Unlink query-texts file; it's not needed while shutdown */
unlink(PGSS_TEXT_FILE);

View File

@ -418,24 +418,10 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI,
TLHistoryFilePath(path, newTLI);
/*
* Prefer link() to rename() here just to be really sure that we don't
* overwrite an existing file. 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)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not link file \"%s\" to \"%s\": %m",
tmppath, path)));
unlink(tmppath);
#else
if (rename(tmppath, path) < 0)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not rename file \"%s\" to \"%s\": %m",
tmppath, path)));
#endif
durable_link_or_rename(tmppath, path, ERROR);
/* The history file can be archived immediately. */
if (XLogArchivingActive())
@ -508,24 +494,10 @@ writeTimeLineHistoryFile(TimeLineID tli, char *content, int size)
TLHistoryFilePath(path, tli);
/*
* 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)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not link file \"%s\" to \"%s\": %m",
tmppath, path)));
unlink(tmppath);
#else
if (rename(tmppath, path) < 0)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not rename file \"%s\" to \"%s\": %m",
tmppath, path)));
#endif
durable_link_or_rename(tmppath, path, ERROR);
}
/*

View File

@ -3420,34 +3420,16 @@ 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)));
/* durable_link_or_rename already emitted log message */
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)));
return false;
}
#endif
if (use_lock)
LWLockRelease(ControlFileLock);
@ -5428,11 +5410,7 @@ exitArchiveRecovery(TimeLineID endTLI, XLogSegNo endLogSegNo)
* 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")));
@ -6619,11 +6597,7 @@ 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);
}
/* Check that the GUCs used to generate the WAL allow recovery */
@ -10705,7 +10679,7 @@ 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(LOG,
(errmsg("online backup mode canceled"),

View File

@ -469,11 +469,7 @@ KeepFileRestoredFromArchive(char *path, char *xlogfname)
reload = true;
}
if (rename(path, xlogfpath) < 0)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not rename file \"%s\" to \"%s\": %m",
path, xlogfpath)));
durable_rename(path, xlogfpath, ERROR);
/*
* Create .done file forcibly to prevent the restored segment from being
@ -576,12 +572,7 @@ XLogArchiveForceDone(const char *xlog)
StatusFilePath(archiveReady, xlog, ".ready");
if (stat(archiveReady, &stat_buf) == 0)
{
if (rename(archiveReady, archiveDone) < 0)
ereport(WARNING,
(errcode_for_file_access(),
errmsg("could not rename file \"%s\" to \"%s\": %m",
archiveReady, archiveDone)));
(void) durable_rename(archiveReady, archiveDone, WARNING);
return;
}

View File

@ -753,9 +753,5 @@ pgarch_archiveDone(char *xlog)
StatusFilePath(rlogready, xlog, ".ready");
StatusFilePath(rlogdone, xlog, ".done");
if (rename(rlogready, rlogdone) < 0)
ereport(WARNING,
(errcode_for_file_access(),
errmsg("could not rename file \"%s\" to \"%s\": %m",
rlogready, rlogdone)));
(void) durable_rename(rlogready, rlogdone, WARNING);
}

View File

@ -6817,11 +6817,7 @@ AlterSystemSetConfigFile(AlterSystemStmt *altersysstmt)
* at worst it can lose the parameters set by last ALTER SYSTEM
* command.
*/
if (rename(AutoConfTmpFileName, AutoConfFileName) < 0)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not rename file \"%s\" to \"%s\": %m",
AutoConfTmpFileName, AutoConfFileName)));
durable_rename(AutoConfTmpFileName, AutoConfFileName, ERROR);
}
PG_CATCH();
{