From 72c946246e21665fc12a5fcbabac553ad0f085c8 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 25 Jul 2023 12:03:59 +0800 Subject: [PATCH] ceph: defer stopping mdsc delayed_work [ Upstream commit e7e607bd00481745550389a29ecabe33e13d67cf ] 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 Reviewed-by: Milind Changire Signed-off-by: Ilya Dryomov Signed-off-by: Sasha Levin --- fs/ceph/mds_client.c | 4 ++-- fs/ceph/mds_client.h | 5 +++++ fs/ceph/super.c | 10 ++++++++++ 3 files changed, 17 insertions(+), 2 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 6ceda2a4791c..f7acf9680c9b 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4074,7 +4074,7 @@ 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); @@ -4246,7 +4246,7 @@ static void wait_requests(struct ceph_mds_client *mdsc) void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc) { dout("pre_umount\n"); - mdsc->stopping = 1; + mdsc->stopping = CEPH_MDSC_STOPPING_BEGIN; lock_unlock_sessions(mdsc); ceph_flush_dirty_caps(mdsc); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 14c7e8c49970..4fbbc33023c9 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -348,6 +348,11 @@ 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 279334f95570..0e38678d5add 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1180,6 +1180,16 @@ 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;