The patch titled
Subject: ocfs2: o2hb: add some user/debug log
has been added to the -mm tree. Its filename is
ocfs2-o2hb-add-some-user-debug-log.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/ocfs2-o2hb-add-some-user-debug-log.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/ocfs2-o2hb-add-some-user-debug-log.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Junxiao Bi <junxiao.bi@xxxxxxxxxx>
Subject: ocfs2: o2hb: add some user/debug log
Signed-off-by: Junxiao Bi <junxiao.bi@xxxxxxxxxx>
Reviewed-by: Ryan Ding <ryan.ding@xxxxxxxxxx>
Cc: Gang He <ghe@xxxxxxxx>
Cc: rwxybh <rwxybh@xxxxxxx>
Cc: Mark Fasheh <mfasheh@xxxxxxx>
Cc: Joel Becker <jlbec@xxxxxxxxxxxx>
Cc: Joseph Qi <joseph.qi@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/ocfs2/cluster/heartbeat.c | 39 +++++++++++++++++++++++++++------
1 file changed, 32 insertions(+), 7 deletions(-)
diff -puN fs/ocfs2/cluster/heartbeat.c~ocfs2-o2hb-add-some-user-debug-log fs/ocfs2/cluster/heartbeat.c
--- a/fs/ocfs2/cluster/heartbeat.c~ocfs2-o2hb-add-some-user-debug-log
+++ a/fs/ocfs2/cluster/heartbeat.c
@@ -292,6 +292,8 @@ struct o2hb_bio_wait_ctxt {
int wc_error;
};
+#define O2HB_NEGO_TIMEOUT_MS (O2HB_MAX_WRITE_TIMEOUT_MS/2)
+
enum {
O2HB_NEGO_TIMEOUT_MSG = 1,
O2HB_NEGO_APPROVE_MSG = 2,
@@ -359,7 +361,7 @@ static void o2hb_arm_timeout(struct o2hb
cancel_delayed_work(®->hr_nego_timeout_work);
/* negotiate timeout must be less than write timeout. */
schedule_delayed_work(®->hr_nego_timeout_work,
- msecs_to_jiffies(O2HB_MAX_WRITE_TIMEOUT_MS)/2);
+ msecs_to_jiffies(O2HB_NEGO_TIMEOUT_MS));
memset(reg->hr_nego_node_bitmap, 0, sizeof(reg->hr_nego_node_bitmap));
}
@@ -393,14 +395,19 @@ static void o2hb_nego_timeout(struct wor
container_of(work, struct o2hb_region,
hr_nego_timeout_work.work);
unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
- int master_node, i;
+ int master_node, i, ret;
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 (!test_bit(master_node, reg->hr_nego_node_bitmap)) {
+ printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s).\n",
+ o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000,
+ config_item_name(®->hr_item), reg->hr_dev_name);
+ 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
@@ -412,6 +419,8 @@ static void o2hb_nego_timeout(struct wor
return;
}
+ printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%s) is down.\n",
+ config_item_name(®->hr_item), reg->hr_dev_name);
/* approve negotiate timeout request. */
o2hb_arm_timeout(reg);
@@ -421,13 +430,23 @@ static void o2hb_nego_timeout(struct wor
if (i == master_node)
continue;
- o2hb_send_nego_msg(reg->hr_key,
+ mlog(ML_HEARTBEAT, "send NEGO_APPROVE msg to node %d\n", i);
+ ret = o2hb_send_nego_msg(reg->hr_key,
O2HB_NEGO_APPROVE_MSG, i);
+ if (ret)
+ mlog(ML_ERROR, "send NEGO_APPROVE msg to node %d fail %d\n",
+ i, ret);
}
} else {
/* negotiate timeout with master node. */
- o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG,
- master_node);
+ printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s), negotiate timeout with node %d.\n",
+ o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(®->hr_item),
+ reg->hr_dev_name, master_node);
+ ret = o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG,
+ master_node);
+ if (ret)
+ mlog(ML_ERROR, "send NEGO_TIMEOUT msg to node %d fail %d\n",
+ master_node, ret);
}
}
@@ -438,6 +457,8 @@ static int o2hb_nego_timeout_handler(str
struct o2hb_nego_msg *nego_msg;
nego_msg = (struct o2hb_nego_msg *)msg->buf;
+ printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%s).\n",
+ nego_msg->node_num, config_item_name(®->hr_item), reg->hr_dev_name);
if (nego_msg->node_num < O2NM_MAX_NODES)
set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap);
else
@@ -449,7 +470,11 @@ static int o2hb_nego_timeout_handler(str
static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data,
void **ret_data)
{
- o2hb_arm_timeout((struct o2hb_region *)data);
+ struct o2hb_region *reg = (struct o2hb_region *)data;
+
+ printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%s).\n",
+ config_item_name(®->hr_item), reg->hr_dev_name);
+ o2hb_arm_timeout(reg);
return 0;
}
_
Patches currently in -mm which might be from junxiao.bi@xxxxxxxxxx are
ocfs2-o2hb-add-negotiate-timer.patch
ocfs2-o2hb-add-nego_timeout-message.patch
ocfs2-o2hb-add-negotiate_approve-message.patch
ocfs2-o2hb-add-some-user-debug-log.patch
ocfs2-o2hb-dont-negotiate-if-last-hb-fail.patch
ocfs2-o2hb-fix-hb-hung-time.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
