Don't forget about failed fsync() requests.

If fsync() fails, md.c must keep the request in its bitmap, so that
future attempts will try again.

Back-patch to all supported releases.

Author: Thomas Munro
Reviewed-by: Amit Kapila
Reported-by: Andrew Gierth
Discussion: https://postgr.es/m/87y3i1ia4w.fsf%40news-spur.riddles.org.uk

diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index bfa065d9fb82e7ecc050b76199dde89a0cd4751d..91a290c357f1934689d8a93fff329de766218df0 100644 (file)
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -1148,10 +1148,8 @@ mdsync(void)
                 * The bitmap manipulations are slightly tricky, because we can call
                 * AbsorbFsyncRequests() inside the loop and that could result in
                 * bms_add_member() modifying and even re-palloc'ing the bitmapsets.
-                * This is okay because we unlink each bitmapset from the hashtable
-                * entry before scanning it.  That means that any incoming fsync
-                * requests will be processed now if they reach the table before we
-                * begin to scan their fork.
+                * So we detach it, but if we fail we'll merge it with any new
+                * requests that have arrived in the meantime.
                 */
                for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
                {
@@ -1161,7 +1159,8 @@ mdsync(void)
                        entry->requests[forknum] = NULL;
                        entry->canceled[forknum] = false;
 
-                       while ((segno = bms_first_member(requests)) >= 0)
+                       segno = -1;
+                       while ((segno = bms_next_member(requests, segno)) >= 0)
                        {
                                int                     failures;
 
@@ -1242,6 +1241,7 @@ mdsync(void)
                                                        longest = elapsed;
                                                total_elapsed += elapsed;
                                                processed++;
+                                               requests = bms_del_member(requests, segno);
                                                if (log_checkpoints)
                                                        elog(DEBUG1, "checkpoint sync: number=%d file=%s time=%.3f msec",
                                                                 processed,
@@ -1270,10 +1270,23 @@ mdsync(void)
                                         */
                                        if (!FILE_POSSIBLY_DELETED(errno) ||
                                                failures > 0)
+                                       {
+                                               Bitmapset  *new_requests;
+
+                                               /*
+                                                * We need to merge these unsatisfied requests with
+                                                * any others that have arrived since we started.
+                                                */
+                                               new_requests = entry->requests[forknum];
+                                               entry->requests[forknum] =
+                                                       bms_join(new_requests, requests);
+
+                                               errno = save_errno;
                                                ereport(ERROR,
                                                                (errcode_for_file_access(),
                                                                 errmsg("could not fsync file \"%s\": %m",
                                                                                path)));
+                                       }
                                        else
                                                ereport(DEBUG1,
                                                                (errcode_for_file_access(),