ocfs2: o2hb: add negotiate timer

This series of patches is to fix the issue that when storage down, all
nodes will fence self due to write timeout.

With this patch set, all nodes will keep going until storage back
online, except if the following issue happens, then all nodes will do as
before to fence self.

1. io error got
2. network between nodes down
3. nodes panic

This patch (of 6):

When storage down, all nodes will fence self due to write timeout.  The
negotiate timer is designed to avoid this, with it node will wait until
storage up again.

Negotiate timer working in the following way:

1. The timer expires before write timeout timer, its timeout is half
   of write timeout now.  It is re-queued along with write timeout timer.
   If expires, it will send NEGO_TIMEOUT message to master node(node with
   lowest node number).  This message does nothing but marks a bit in a
   bitmap recording which nodes are negotiating timeout on master node.

2. If storage down, nodes will send this message to master node, then
   when master node finds its bitmap including all online nodes, it sends
   NEGO_APPROVL message to all nodes one by one, this message will
   re-queue write timeout timer and negotiate timer.  For any node doesn't
   receive this message or meets some issue when handling this message, it
   will be fenced.  If storage up at any time, o2hb_thread will run and
   re-queue all the timer, nothing will be affected by these two steps.

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>

diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index a8d15be..750c950 100644 (file)
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -272,6 +272,10 @@ struct o2hb_region {
        struct delayed_work     hr_write_timeout_work;
        unsigned long           hr_last_timeout_start;
 
+       /* negotiate timer, used to negotiate extending hb timeout. */
+       struct delayed_work     hr_nego_timeout_work;
+       unsigned long           hr_nego_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+
        /* Used during o2hb_check_slot to hold a copy of the block
         * being checked because we temporarily have to zero out the
         * crc field. */
@@ -319,7 +323,7 @@ static void o2hb_write_timeout(struct work_struct *work)
        o2quo_disk_timeout();
 }
 
-static void o2hb_arm_write_timeout(struct o2hb_region *reg)
+static void o2hb_arm_timeout(struct o2hb_region *reg)
 {
        /* Arm writeout only after thread reaches steady state */
        if (atomic_read(&reg->hr_steady_iterations) != 0)
@@ -337,11 +341,49 @@ static void o2hb_arm_write_timeout(struct o2hb_region *reg)
        reg->hr_last_timeout_start = jiffies;
        schedule_delayed_work(&reg->hr_write_timeout_work,
                              msecs_to_jiffies(O2HB_MAX_WRITE_TIMEOUT_MS));
+
+       cancel_delayed_work(&reg->hr_nego_timeout_work);
+       /* negotiate timeout must be less than write timeout. */
+       schedule_delayed_work(&reg->hr_nego_timeout_work,
+                             msecs_to_jiffies(O2HB_MAX_WRITE_TIMEOUT_MS)/2);
+       memset(reg->hr_nego_node_bitmap, 0, sizeof(reg->hr_nego_node_bitmap));
 }
 
-static void o2hb_disarm_write_timeout(struct o2hb_region *reg)
+static void o2hb_disarm_timeout(struct o2hb_region *reg)
 {
        cancel_delayed_work_sync(&reg->hr_write_timeout_work);
+       cancel_delayed_work_sync(&reg->hr_nego_timeout_work);
+}
+
+static void o2hb_nego_timeout(struct work_struct *work)
+{
+       unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+       int master_node;
+       struct o2hb_region *reg;
+
+       reg = container_of(work, struct o2hb_region, hr_nego_timeout_work.work);
+       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);
+
+       if (master_node == o2nm_this_node()) {
+               set_bit(master_node, reg->hr_nego_node_bitmap);
+               if (memcmp(reg->hr_nego_node_bitmap, live_node_bitmap,
+                               sizeof(reg->hr_nego_node_bitmap))) {
+                       /* check negotiate bitmap every second to do timeout
+                        * approve decision.
+                        */
+                       schedule_delayed_work(&reg->hr_nego_timeout_work,
+                               msecs_to_jiffies(1000));
+
+                       return;
+               }
+
+               /* approve negotiate timeout request. */
+       } else {
+               /* negotiate timeout with master node. */
+       }
+
 }
 
 static inline void o2hb_bio_wait_init(struct o2hb_bio_wait_ctxt *wc)
@@ -1032,7 +1074,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
        /* Skip disarming the timeout if own slot has stale/bad data */
        if (own_slot_ok) {
                o2hb_set_quorum_device(reg);
-               o2hb_arm_write_timeout(reg);
+               o2hb_arm_timeout(reg);
        }
 
 bail:
@@ -1114,7 +1156,7 @@ static int o2hb_thread(void *data)
                }
        }
 
-       o2hb_disarm_write_timeout(reg);
+       o2hb_disarm_timeout(reg);
 
        /* unclean stop is only used in very bad situation */
        for(i = 0; !reg->hr_unclean_stop && i < reg->hr_blocks; i++)
@@ -1762,6 +1804,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
        }
 
        INIT_DELAYED_WORK(&reg->hr_write_timeout_work, o2hb_write_timeout);
+       INIT_DELAYED_WORK(&reg->hr_nego_timeout_work, o2hb_nego_timeout);
 
        /*
         * A node is considered live after it has beat LIVE_THRESHOLD