ocfs2: o2hb: don't negotiate if last hb fail

biger410 · torvalds · commit 88dbe98dc72f · 2016-05-27T14:49:37.000-07:00
Sometimes io error is returned when storage is down for a while.  Like
for iscsi device, stroage is made offline when session timeout, and this
will make all io return -EIO.  For this case, nodes shouldn't do
negotiate timeout but should fence self.  So let nodes fence self when
o2hb_do_disk_heartbeat return an error, this is the same behavior with
o2hb without negotiate timer.

Signed-off-by: Junxiao Bi &lt;junxiao.bi@oracle.com&gt;
Reviewed-by: Ryan Ding &lt;ryan.ding@oracle.com&gt;
Reviewed-by: Mark Fasheh &lt;mfasheh@suse.de&gt;
Cc: Gang He &lt;ghe@suse.com&gt;
Cc: rwxybh &lt;rwxybh@126.com&gt;
Cc: Joel Becker &lt;jlbec@evilplan.org&gt;
Cc: Joseph Qi &lt;joseph.qi@huawei.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
@@ -284,6 +284,9 @@ struct o2hb_region {
 	/* Message key for negotiate timeout message. */
 	unsigned int		hr_key;
 	struct list_head	hr_handler_list;
+
+	/* last hb status, 0 for success, other value for error. */
+	int			hr_last_hb_status;
 };
 
 struct o2hb_bio_wait_ctxt {
@@ -395,6 +398,12 @@ static void o2hb_nego_timeout(struct work_struct *work)
 	struct o2hb_region *reg;
 
 	reg = container_of(work, struct o2hb_region, hr_nego_timeout_work.work);
+	/* don't negotiate timeout if last hb failed since it is very
+	 * possible io failed. Should let write timeout fence self.
+	 */
+	if (reg->hr_last_hb_status)
+		return;
+
 	o2hb_fill_node_map(live_node_bitmap, sizeof(live_node_bitmap));
 	/* lowest node as master node to make negotiate decision. */
 	master_node = find_next_bit(live_node_bitmap, O2NM_MAX_NODES, 0);
@@ -1228,6 +1237,7 @@ static int o2hb_thread(void *data)
 		before_hb = ktime_get_real();
 
 		ret = o2hb_do_disk_heartbeat(reg);
+		reg->hr_last_hb_status = ret;
 
 		after_hb = ktime_get_real();
 
