ceph: defer stopping mdsc delayed_work

commit e7e607bd00481745550389a29ecabe33e13d67cf 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>

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 0dc8871a4b66066d3ef774a5142a4a26c8f7ac0c..a0b6ae02a70b82b30d90383a92f7672f2ccb4291 100644 (file)
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4607,7 +4607,7 @@ 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);
@@ -4786,7 +4786,7 @@ 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);

diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 2667350eb72cf083dfc7c60ca1fd953412aec88a..cd943842f0a3c9407470f4be951642e94bf94572 100644 (file)
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -370,6 +370,11 @@ struct cap_wait {
        int                     want;
 };
 
+enum {
+       CEPH_MDSC_STOPPING_BEGIN = 1,
+       CEPH_MDSC_STOPPING_FLUSHED = 2,
+};
+
 /*
  * mds client state
  */

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 202ddde3d62ad1299ee6a14e5688092b7e702058..1723ec21cd47035b34a96e797ba1ca4c6b354e88 100644 (file)
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1227,6 +1227,16 @@ 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;