From 88dbe98dc72fa0c2b778210e2079cd69d2477b36 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Fri, 27 May 2016 14:27:10 -0700 Subject: 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 Reviewed-by: Ryan Ding Reviewed-by: Mark Fasheh Cc: Gang He Cc: rwxybh Cc: Joel Becker Cc: Joseph Qi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/heartbeat.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'fs') diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 84ebeb5678c6..31a5c0803e0a 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(); -- cgit v1.2.3