Commit 1bd12902 authored by Junxiao Bi's avatar Junxiao Bi Committed by Linus Torvalds

ocfs2: o2hb: add some user/debug log

Signed-off-by: default avatarJunxiao Bi <junxiao.bi@oracle.com>
Reviewed-by: default avatarRyan Ding <ryan.ding@oracle.com>
Reviewed-by: default avatarMark 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: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent e76f8237
...@@ -292,6 +292,8 @@ struct o2hb_bio_wait_ctxt { ...@@ -292,6 +292,8 @@ struct o2hb_bio_wait_ctxt {
int wc_error; int wc_error;
}; };
#define O2HB_NEGO_TIMEOUT_MS (O2HB_MAX_WRITE_TIMEOUT_MS/2)
enum { enum {
O2HB_NEGO_TIMEOUT_MSG = 1, O2HB_NEGO_TIMEOUT_MSG = 1,
O2HB_NEGO_APPROVE_MSG = 2, O2HB_NEGO_APPROVE_MSG = 2,
...@@ -358,7 +360,7 @@ static void o2hb_arm_timeout(struct o2hb_region *reg) ...@@ -358,7 +360,7 @@ static void o2hb_arm_timeout(struct o2hb_region *reg)
cancel_delayed_work(&reg->hr_nego_timeout_work); cancel_delayed_work(&reg->hr_nego_timeout_work);
/* negotiate timeout must be less than write timeout. */ /* negotiate timeout must be less than write timeout. */
schedule_delayed_work(&reg->hr_nego_timeout_work, schedule_delayed_work(&reg->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)); memset(reg->hr_nego_node_bitmap, 0, sizeof(reg->hr_nego_node_bitmap));
} }
...@@ -389,7 +391,7 @@ static int o2hb_send_nego_msg(int key, int type, u8 target) ...@@ -389,7 +391,7 @@ static int o2hb_send_nego_msg(int key, int type, u8 target)
static void o2hb_nego_timeout(struct work_struct *work) static void o2hb_nego_timeout(struct work_struct *work)
{ {
unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
int master_node, i; int master_node, i, ret;
struct o2hb_region *reg; struct o2hb_region *reg;
reg = container_of(work, struct o2hb_region, hr_nego_timeout_work.work); reg = container_of(work, struct o2hb_region, hr_nego_timeout_work.work);
...@@ -398,7 +400,12 @@ static void o2hb_nego_timeout(struct work_struct *work) ...@@ -398,7 +400,12 @@ static void o2hb_nego_timeout(struct work_struct *work)
master_node = find_next_bit(live_node_bitmap, O2NM_MAX_NODES, 0); master_node = find_next_bit(live_node_bitmap, O2NM_MAX_NODES, 0);
if (master_node == o2nm_this_node()) { 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(&reg->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, if (memcmp(reg->hr_nego_node_bitmap, live_node_bitmap,
sizeof(reg->hr_nego_node_bitmap))) { sizeof(reg->hr_nego_node_bitmap))) {
/* check negotiate bitmap every second to do timeout /* check negotiate bitmap every second to do timeout
...@@ -410,6 +417,8 @@ static void o2hb_nego_timeout(struct work_struct *work) ...@@ -410,6 +417,8 @@ static void o2hb_nego_timeout(struct work_struct *work)
return; return;
} }
printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%s) is down.\n",
config_item_name(&reg->hr_item), reg->hr_dev_name);
/* approve negotiate timeout request. */ /* approve negotiate timeout request. */
o2hb_arm_timeout(reg); o2hb_arm_timeout(reg);
...@@ -419,13 +428,23 @@ static void o2hb_nego_timeout(struct work_struct *work) ...@@ -419,13 +428,23 @@ static void o2hb_nego_timeout(struct work_struct *work)
if (i == master_node) if (i == master_node)
continue; 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); O2HB_NEGO_APPROVE_MSG, i);
if (ret)
mlog(ML_ERROR, "send NEGO_APPROVE msg to node %d fail %d\n",
i, ret);
} }
} else { } else {
/* negotiate timeout with master node. */ /* negotiate timeout with master node. */
o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG, printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s), negotiate timeout with node %d.\n",
master_node); o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(&reg->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);
} }
} }
...@@ -436,6 +455,8 @@ static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data, ...@@ -436,6 +455,8 @@ static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data,
struct o2hb_nego_msg *nego_msg; struct o2hb_nego_msg *nego_msg;
nego_msg = (struct o2hb_nego_msg *)msg->buf; 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(&reg->hr_item), reg->hr_dev_name);
if (nego_msg->node_num < O2NM_MAX_NODES) if (nego_msg->node_num < O2NM_MAX_NODES)
set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap); set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap);
else else
...@@ -447,7 +468,11 @@ static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data, ...@@ -447,7 +468,11 @@ static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data,
static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data, static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data,
void **ret_data) void **ret_data)
{ {
o2hb_arm_timeout(data); struct o2hb_region *reg = data;
printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%s).\n",
config_item_name(&reg->hr_item), reg->hr_dev_name);
o2hb_arm_timeout(reg);
return 0; return 0;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment