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

diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c
index 7d1e62abfce6818b24fa5cf3a02c4f62373a42e0..18e8a8051ddd4f3b5ecdf01ceb56915db64bed81 100644 (file)
--- a/contrib/pg_stat_statements/pg_stat_statements.c
+++ b/contrib/pg_stat_statements/pg_stat_statements.c
@@ -588,11 +588,7 @@ pgss_shmem_shutdown(int code, Datum arg)
        /*
         * Rename file into place, so we atomically replace the 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);
 
        return;
 

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 0397686f5a4ab8ce2ab1ddc60a364d77aff3c8aa..8a3c2817c92fc1099e865eec7c8640d165b508bd 100644 (file)
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -1380,12 +1380,7 @@ 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;
        }
 
@@ -2773,34 +2768,16 @@ InstallXLogFileSegment(uint32 *log, uint32 *seg, 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 %u, segment %u): %m",
-                                               tmppath, path, *log, *seg)));
-               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 %u, segment %u): %m",
-                                               tmppath, path, *log, *seg)));
+               /* durable_link_or_rename already emitted log message */
                return false;
        }
-#endif
 
        if (use_lock)
                LWLockRelease(ControlFileLock);
@@ -3048,11 +3025,7 @@ 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
@@ -4882,24 +4855,10 @@ 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 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);
 
        /* The history file can be archived immediately. */
        if (XLogArchivingActive())
@@ -5882,11 +5841,7 @@ exitArchiveRecovery(TimeLineID endTLI, uint32 endLogId, uint32 endLogSeg)
         * 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")));
@@ -6795,11 +6750,7 @@ 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 */
@@ -10486,7 +10437,7 @@ 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"),

diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 9729c02a827034d5ab1f32fd7a04c8900fa211fe..5b2a071c78fd58d84fda0268f0d9b6a954f27df6 100644 (file)
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -749,9 +749,5 @@ 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);
 }