ceph: defer stopping mdsc delayed_work

commit e7e607bd00 upstream.

Flushing the dirty buffer may take a long time if the cluster is
overloaded or if there is network issue. So we should ping the
MDSs periodically to keep alive, else the MDS will blocklist
the kclient.

Cc: stable@vger.kernel.org
Link: https://tracker.ceph.com/issues/61843
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Xiubo Li 2023-07-25 12:03:59 +08:00 committed by Greg Kroah-Hartman
parent c29cc7eef9
commit 0b39dfaf25
3 changed files with 17 additions and 2 deletions

View file

@ -4762,7 +4762,7 @@ static void delayed_work(struct work_struct *work)
dout("mdsc delayed_work\n");
if (mdsc->stopping)
if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED)
return;
mutex_lock(&mdsc->mutex);
@ -4941,7 +4941,7 @@ void send_flush_mdlog(struct ceph_mds_session *s)
void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc)
{
dout("pre_umount\n");
mdsc->stopping = 1;
mdsc->stopping = CEPH_MDSC_STOPPING_BEGIN;
ceph_mdsc_iterate_sessions(mdsc, send_flush_mdlog, true);
ceph_mdsc_iterate_sessions(mdsc, lock_unlock_session, false);

View file

@ -380,6 +380,11 @@ struct cap_wait {
int want;
};
enum {
CEPH_MDSC_STOPPING_BEGIN = 1,
CEPH_MDSC_STOPPING_FLUSHED = 2,
};
/*
* mds client state
*/

View file

@ -1374,6 +1374,16 @@ static void ceph_kill_sb(struct super_block *s)
ceph_mdsc_pre_umount(fsc->mdsc);
flush_fs_workqueues(fsc);
/*
* Though the kill_anon_super() will finally trigger the
* sync_filesystem() anyway, we still need to do it here
* and then bump the stage of shutdown to stop the work
* queue as earlier as possible.
*/
sync_filesystem(s);
fsc->mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED;
kill_anon_super(s);
fsc->client->extra_mon_dispatch = NULL;