Revert recent changes with durable_rename_excl()

This reverts commits 2c902bb and ccfbd92.  Per buildfarm members
kestrel, rorqual and calliphoridae, the assertions checking that a TLI
history file should not exist when created by a WAL receiver have been
failing, and switching to durable_rename() over durable_rename_excl()
would cause the newest TLI history file to overwrite the existing one.
We need to think harder about such cases, so revert the new logic for
now.

Note that all the failures have been reported in the test
025_stuck_on_old_timeline.

Discussion: https://postgr.es/m/[email protected]

6 files changed, 91 insertions, 13 deletions

diff --git a/contrib/basic_archive/basic_archive.c b/contrib/basic_archive/basic_archive.c
index ed33854c578..e7efbfb9c34 100644
--- a/contrib/basic_archive/basic_archive.c
+++ b/contrib/basic_archive/basic_archive.c
@@ -281,10 +281,9 @@ basic_archive_file_internal(const char *file, const char *path)
 
 	/*
 	 * Sync the temporary file to disk and move it to its final destination.
-	 * Note that this will overwrite any existing file, but this is only
-	 * possible if someone else created the file since the stat() above.
+	 * This will fail if destination already exists.
 	 */
-	(void) durable_rename(temp, destination, ERROR);
+	(void) durable_rename_excl(temp, destination, ERROR);
 
 	ereport(DEBUG1,
 			(errmsg("archived \"%s\" via basic_archive", file)));
diff --git a/src/backend/access/transam/timeline.c b/src/backend/access/transam/timeline.c
index c9344e5e8b4..be21968293c 100644
--- a/src/backend/access/transam/timeline.c
+++ b/src/backend/access/transam/timeline.c
@@ -439,11 +439,14 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI,
 
 	/*
 	 * Now move the completed history file into place with its final name.
-	 * The target file should not exist.
 	 */
 	TLHistoryFilePath(path, newTLI);
-	Assert(access(path, F_OK) != 0 && errno == ENOENT);
-	durable_rename(tmppath, path, ERROR);
+
+	/*
+	 * Perform the rename using link if available, paranoidly trying to avoid
+	 * overwriting an existing file (there shouldn't be one).
+	 */
+	durable_rename_excl(tmppath, path, ERROR);
 
 	/* The history file can be archived immediately. */
 	if (XLogArchivingActive())
@@ -514,11 +517,14 @@ writeTimeLineHistoryFile(TimeLineID tli, char *content, int size)
 
 	/*
 	 * Now move the completed history file into place with its final name.
-	 * The target file should not exist.
 	 */
 	TLHistoryFilePath(path, tli);
-	Assert(access(path, F_OK) != 0 && errno == ENOENT);
-	durable_rename(tmppath, path, ERROR);
+
+	/*
+	 * Perform the rename using link if available, paranoidly trying to avoid
+	 * overwriting an existing file (there shouldn't be one).
+	 */
+	durable_rename_excl(tmppath, path, ERROR);
 }
 
 /*
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 45c84e3959c..61cda56c6ff 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -3323,12 +3323,14 @@ InstallXLogFileSegment(XLogSegNo *segno, char *tmppath,
 		}
 	}
 
-	/* The target file should not exist */
-	Assert(access(path, F_OK) != 0 && errno == ENOENT);
-	if (durable_rename(tmppath, path, LOG) != 0)
+	/*
+	 * Perform the rename using link if available, paranoidly trying to avoid
+	 * overwriting an existing file (there shouldn't be one).
+	 */
+	if (durable_rename_excl(tmppath, path, LOG) != 0)
 	{
 		LWLockRelease(ControlFileLock);
-		/* durable_rename already emitted log message */
+		/* durable_rename_excl already emitted log message */
 		return false;
 	}
 
diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c
index f904f60c086..24704b6a023 100644
--- a/src/backend/storage/file/fd.c
+++ b/src/backend/storage/file/fd.c
@@ -808,6 +808,69 @@ durable_unlink(const char *fname, int elevel)
 }
 
 /*
+ * durable_rename_excl -- rename a file in a durable manner.
+ *
+ * Similar to durable_rename(), except that this routine tries (but does not
+ * guarantee) not to overwrite the target file.
+ *
+ * Note that a crash in an unfortunate moment can leave you with two links to
+ * the target file.
+ *
+ * Log errors with the caller specified severity.
+ *
+ * On Windows, using a hard link followed by unlink() causes concurrency
+ * issues, while a simple rename() does not cause that, so be careful when
+ * changing the logic of this routine.
+ *
+ * Returns 0 if the operation succeeded, -1 otherwise. Note that errno is not
+ * valid upon return.
+ */
+int
+durable_rename_excl(const char *oldfile, const char *newfile, int elevel)
+{
+	/*
+	 * Ensure that, if we crash directly after the rename/link, a file with
+	 * valid contents is moved into place.
+	 */
+	if (fsync_fname_ext(oldfile, false, false, elevel) != 0)
+		return -1;
+
+#ifdef HAVE_WORKING_LINK
+	if (link(oldfile, newfile) < 0)
+	{
+		ereport(elevel,
+				(errcode_for_file_access(),
+				 errmsg("could not link file \"%s\" to \"%s\": %m",
+						oldfile, newfile)));
+		return -1;
+	}
+	unlink(oldfile);
+#else
+	if (rename(oldfile, newfile) < 0)
+	{
+		ereport(elevel,
+				(errcode_for_file_access(),
+				 errmsg("could not rename file \"%s\" to \"%s\": %m",
+						oldfile, newfile)));
+		return -1;
+	}
+#endif
+
+	/*
+	 * Make change persistent in case of an OS crash, both the new entry and
+	 * its parent directory need to be flushed.
+	 */
+	if (fsync_fname_ext(newfile, false, false, elevel) != 0)
+		return -1;
+
+	/* Same for parent directory */
+	if (fsync_parent_path(newfile, elevel) != 0)
+		return -1;
+
+	return 0;
+}
+
+/*
  * InitFileAccess --- initialize this module during backend startup
  *
  * This is called during either normal or standalone backend start.
diff --git a/src/include/pg_config_manual.h b/src/include/pg_config_manual.h
index 830804fdfbf..84ce5a4a5d7 100644
--- a/src/include/pg_config_manual.h
+++ b/src/include/pg_config_manual.h
@@ -164,6 +164,13 @@
 #endif
 
 /*
+ * Define this if your operating system supports link()
+ */
+#if !defined(WIN32) && !defined(__CYGWIN__)
+#define HAVE_WORKING_LINK 1
+#endif
+
+/*
  * USE_POSIX_FADVISE controls whether Postgres will attempt to use the
  * posix_fadvise() kernel call.  Usually the automatic configure tests are
  * sufficient, but some older Linux distributions had broken versions of
diff --git a/src/include/storage/fd.h b/src/include/storage/fd.h
index 2b4a8e0ffe8..69549b000fa 100644
--- a/src/include/storage/fd.h
+++ b/src/include/storage/fd.h
@@ -187,6 +187,7 @@ extern void fsync_fname(const char *fname, bool isdir);
 extern int	fsync_fname_ext(const char *fname, bool isdir, bool ignore_perm, int elevel);
 extern int	durable_rename(const char *oldfile, const char *newfile, int loglevel);
 extern int	durable_unlink(const char *fname, int loglevel);
+extern int	durable_rename_excl(const char *oldfile, const char *newfile, int loglevel);
 extern void SyncDataDirectory(void);
 extern int	data_sync_elevel(int elevel);