On Windows, when a file is deleted and another process still has an open

file handle on it, the file goes into "pending deletion" state where it
still shows up in directory listing, but isn't accessible otherwise. That
confuses RemoveOldXLogFiles(), making it think that the file hasn't been
archived yet, while it actually was, and it was deleted along with the .done
file.

Fix that by renaming the file with ".deleted" extension before deleting it.
Also check the return value of rename() and unlink(), so that if the removal
fails for any reason (e.g another process is holding the file locked), we
don't delete the .done file until the WAL file is really gone.

Backpatch to 8.2, which is the oldest version supported on Windows.

1 files changed, 35 insertions, 1 deletions

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9b645785a4..4ddd91cc07 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -3040,6 +3040,9 @@ RemoveOldXlogFiles(uint32 log, uint32 seg, XLogRecPtr endptr)
 	struct dirent *xlde;
 	char		lastoff[MAXFNAMELEN];
 	char		path[MAXPGPATH];
+#ifdef WIN32
+	char		newpath[MAXPGPATH];
+#endif
 	struct stat statbuf;
 
 	/*
@@ -3103,10 +3106,41 @@ RemoveOldXlogFiles(uint32 log, uint32 seg, XLogRecPtr endptr)
 				else
 				{
 					/* No need for any more future segments... */
+					int rc;
+
 					ereport(DEBUG2,
 							(errmsg("removing transaction log file \"%s\"",
 									xlde->d_name)));
-					unlink(path);
+
+#ifdef WIN32
+					/*
+					 * On Windows, if another process (e.g another backend)
+					 * holds the file open in FILE_SHARE_DELETE mode, unlink
+					 * will succeed, but the file will still show up in
+					 * directory listing until the last handle is closed.
+					 * To avoid confusing the lingering deleted file for a
+					 * live WAL file that needs to be archived, rename it
+					 * before deleting it.
+					 *
+					 * If another process holds the file open without
+					 * FILE_SHARE_DELETE flag, rename will fail. We'll try
+					 * again at the next checkpoint.
+					 */
+					snprintf(newpath, MAXPGPATH, "%s.deleted", path);
+					if (rename(path, newpath) != 0)
+						ereport(ERROR,
+								(errcode_for_file_access(),
+								 errmsg("could not rename old transaction log file \"%s\"",
+										path)));
+					rc = unlink(newpath);
+#else
+					rc = unlink(path);
+#endif
+					if (rc != 0)
+						ereport(ERROR,
+								(errcode_for_file_access(),
+								 errmsg("could not remove old transaction log file \"%s\": %m",
+										path)));
 					CheckpointStats.ckpt_segs_removed++;
 				}