summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2/cluster
diff options
context:
space:
mode:
authorJunxiao Bi <junxiao.bi@oracle.com>2016-05-27 14:27:10 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-05-27 14:49:37 -0700
commit88dbe98dc72fa0c2b778210e2079cd69d2477b36 (patch)
treece2ce48ac1b3592e9ba841c49101b72224b2ce94 /fs/ocfs2/cluster
parent1bd1290283d7939478062e80bdd9719d3a21522f (diff)
downloadop-kernel-dev-88dbe98dc72fa0c2b778210e2079cd69d2477b36.zip
op-kernel-dev-88dbe98dc72fa0c2b778210e2079cd69d2477b36.tar.gz
ocfs2: o2hb: don't negotiate if last hb fail
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 <junxiao.bi@oracle.com> Reviewed-by: Ryan Ding <ryan.ding@oracle.com> Reviewed-by: Mark Fasheh <mfasheh@suse.de> Cc: Gang He <ghe@suse.com> Cc: rwxybh <rwxybh@126.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Joseph Qi <joseph.qi@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/ocfs2/cluster')
-rw-r--r--fs/ocfs2/cluster/heartbeat.c10
1 files changed, 10 insertions, 0 deletions
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 84ebeb5..31a5c08 100644
--- 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();
OpenPOWER on IntegriCloud