diff options
| author | Xue jiufei | 2014-06-04 16:06:14 -0700 |
|---|---|---|
| committer | Linus Torvalds | 2014-06-04 16:53:54 -0700 |
| commit | 01c6222f876062355599e5a63560c514b6de25d2 (patch) | |
| tree | bf29b34aac8ea3a95fefc0e11873ea3a77ffa858 /fs/ocfs2 | |
| parent | a9e9acaeb0a981a6dfa54b32dd756103aeefa6a7 (diff) | |
ocfs2/dlm: disallow node joining when recovery is on going
We found a race situation when dlm recovery and node joining occurs
simultaneously if the network state is bad.
N1 N4
start joining dlm and send
query join to all live nodes
set joining node to N1, return OK
send query join to other
live nodes and it may take
a while
call dlm_send_join_assert()
to send assert join message
when N2 is down, so keep
trying to send message to N2
until find N2 is down
send assert join message to
N3, but connection is down
with N3, so it may take a
while
become the recovery master for N2
and send begin reco message to other
nodes in domain map but no N1
connection with N3 is rebuild,
then send assert join to N4
call dlm_assert_joined_handler(),
add N1 to domain_map
dlm recovery done, send finalize message
to nodes in domain map, including N1
receiving finalize message,
trigger the BUG() because
recovery master mismatch.
Signed-off-by: joyce.xue <xuejiufei@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/ocfs2')
| -rw-r--r-- | fs/ocfs2/dlm/dlmdomain.c | 13 |
1 files changed, 12 insertions, 1 deletions
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index c973690dc0bc..8d4690795a5d 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -959,6 +959,14 @@ static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data, * domain. Set him in the map and clean up our * leftover join state. */ BUG_ON(dlm->joining_node != assert->node_idx); + + if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) { + mlog(0, "dlm recovery is ongoing, disallow join\n"); + spin_unlock(&dlm->spinlock); + spin_unlock(&dlm_domain_lock); + return -EAGAIN; + } + set_bit(assert->node_idx, dlm->domain_map); clear_bit(assert->node_idx, dlm->exit_domain_map); __dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN); @@ -1517,6 +1525,7 @@ static int dlm_send_one_join_assert(struct dlm_ctxt *dlm, unsigned int node) { int status; + int ret; struct dlm_assert_joined assert_msg; mlog(0, "Sending join assert to node %u\n", node); @@ -1528,11 +1537,13 @@ static int dlm_send_one_join_assert(struct dlm_ctxt *dlm, status = o2net_send_message(DLM_ASSERT_JOINED_MSG, DLM_MOD_KEY, &assert_msg, sizeof(assert_msg), node, - NULL); + &ret); if (status < 0) mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to " "node %u\n", status, DLM_ASSERT_JOINED_MSG, DLM_MOD_KEY, node); + else + status = ret; return status; } |