summaryrefslogtreecommitdiff
path: root/fs/ocfs2/dlm/dlmdomain.c
diff options
context:
space:
mode:
authorpiaojun <piaojun@huawei.com>2018-04-05 16:19:11 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-04-05 21:36:22 -0700
commit60c7ec9ee4a3410c2cb08850102d363c7e207f48 (patch)
tree77b1cff7c9c386e7e338c07a1ad66ea249ab0d63 /fs/ocfs2/dlm/dlmdomain.c
parenta43d24cb3b0b395de8bb176355a907a9c9a1c42e (diff)
ocfs2/dlm: wait for dlm recovery done when migrating all lock resources
Wait for dlm recovery done when migrating all lock resources in case that new lock resource left after leaving dlm domain. And the left lock resource will cause other nodes BUG. NodeA NodeB NodeC umount: dlm_unregister_domain() dlm_migrate_all_locks() NodeB down do recovery for NodeB and collect a new lockres form other live nodes: dlm_do_recovery dlm_remaster_locks dlm_request_all_locks: dlm_mig_lockres_handler dlm_new_lockres __dlm_insert_lockres at last NodeA become the master of the new lockres and leave domain: dlm_leave_domain() mount: dlm_join_domain() touch file and request for the owner of the new lockres, but all the other nodes said 'NO', so NodeC decide to be the owner, and send do assert msg to other nodes: dlmlock() dlm_get_lock_resource() dlm_do_assert_master() other nodes receive the msg and found two masters exist. at last cause BUG in dlm_assert_master_handler() -->BUG(); Link: http://lkml.kernel.org/r/5AAA6E25.7090303@huawei.com Fixes: bc9838c4d44a ("dlm: allow dlm do recovery during shutdown") Signed-off-by: Jun Piao <piaojun@huawei.com> Reviewed-by: Alex Chen <alex.chen@huawei.com> Reviewed-by: Yiwen Jiang <jiangyiwen@huawei.com> Acked-by: Joseph Qi <jiangqi903@gmail.com> Cc: Mark Fasheh <mark@fasheh.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Junxiao Bi <junxiao.bi@oracle.com> Cc: Changwei Ge <ge.changwei@h3c.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/ocfs2/dlm/dlmdomain.c')
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c15
1 files changed, 15 insertions, 0 deletions
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 25b76f0d082b..425081be6161 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -461,6 +461,19 @@ redo_bucket:
cond_resched_lock(&dlm->spinlock);
num += n;
}
+
+ if (!num) {
+ if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) {
+ mlog(0, "%s: perhaps there are more lock resources "
+ "need to be migrated after dlm recovery\n", dlm->name);
+ ret = -EAGAIN;
+ } else {
+ mlog(0, "%s: we won't do dlm recovery after migrating "
+ "all lock resources\n", dlm->name);
+ dlm->migrate_done = 1;
+ }
+ }
+
spin_unlock(&dlm->spinlock);
wake_up(&dlm->dlm_thread_wq);
@@ -2038,6 +2051,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
dlm->joining_node = DLM_LOCK_RES_OWNER_UNKNOWN;
init_waitqueue_head(&dlm->dlm_join_events);
+ dlm->migrate_done = 0;
+
dlm->reco.new_master = O2NM_INVALID_NODE_NUM;
dlm->reco.dead_node = O2NM_INVALID_NODE_NUM;