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>
/* Message key for negotiate timeout message. */
unsigned int hr_key;
struct list_head hr_handler_list;
/* 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 {
};
struct o2hb_bio_wait_ctxt {
struct o2hb_region *reg;
reg = container_of(work, struct o2hb_region, hr_nego_timeout_work.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);
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);
before_hb = ktime_get_real();
ret = o2hb_do_disk_heartbeat(reg);
before_hb = ktime_get_real();
ret = o2hb_do_disk_heartbeat(reg);
+ reg->hr_last_hb_status = ret;
after_hb = ktime_get_real();
after_hb = ktime_get_real();