From 1556cb2fc5c774c3f7390dd6fb19190ee0c73f8b Mon Sep 17 00:00:00 2001
From: Thomas Munro <tmunro@postgresql.org>
Date: Mon, 19 Nov 2018 13:30:58 +1300
Subject: [PATCH] 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
---
src/backend/storage/smgr/md.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index 86013a5c8b..04c1069a60 100644
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -1123,10 +1123,8 @@ 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++)
{
@@ -1136,7 +1134,8 @@ 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;
@@ -1217,6 +1216,7 @@ 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,
@@ -1245,10 +1245,23 @@ 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(),
--
2.40.0