| Message ID | 20230629033533.270535-1-xiubli@redhat.com |
|---|---|
| State | New |
| Headers | show |
| Series | ceph: defer stopping the mdsc delayed_work | expand |
Looks good to me. nit: typo for perioudically in commit message Reviewed-by: Milind Changire <mchangir@redhat.com> On Thu, Jun 29, 2023 at 9:07 AM <xiubli@redhat.com> wrote: > > From: Xiubo Li <xiubli@redhat.com> > > Flushing the dirty buffer may take a long time if the Rados is > overloaded or if there is network issue. So we should ping the > MDSs perioudically to keep alive, else the MDS will blocklist > the kclient. > > Cc: stable@vger.kernel.org > Cc: Venky Shankar <vshankar@redhat.com> > URL: https://tracker.ceph.com/issues/61843 > Signed-off-by: Xiubo Li <xiubli@redhat.com> > --- > fs/ceph/mds_client.c | 2 +- > fs/ceph/mds_client.h | 3 ++- > fs/ceph/super.c | 7 ++++--- > 3 files changed, 7 insertions(+), 5 deletions(-) > > diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c > index 65230ebefd51..70987b3c198a 100644 > --- a/fs/ceph/mds_client.c > +++ b/fs/ceph/mds_client.c > @@ -5192,7 +5192,7 @@ static void delayed_work(struct work_struct *work) > > doutc(mdsc->fsc->client, "mdsc delayed_work\n"); > > - if (mdsc->stopping) > + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) > return; > > mutex_lock(&mdsc->mutex); > diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h > index 5d02c8c582fd..befbd384428e 100644 > --- a/fs/ceph/mds_client.h > +++ b/fs/ceph/mds_client.h > @@ -400,7 +400,8 @@ struct cap_wait { > > enum { > CEPH_MDSC_STOPPING_BEGIN = 1, > - CEPH_MDSC_STOPPING_FLUSHED = 2, > + CEPH_MDSC_STOPPING_FLUSHING = 2, > + CEPH_MDSC_STOPPING_FLUSHED = 3, > }; > > /* > diff --git a/fs/ceph/super.c b/fs/ceph/super.c > index 8e1e517a45db..fb694ba72955 100644 > --- a/fs/ceph/super.c > +++ b/fs/ceph/super.c > @@ -1488,7 +1488,7 @@ static int ceph_init_fs_context(struct fs_context *fc) > static bool __inc_stopping_blocker(struct ceph_mds_client *mdsc) > { > spin_lock(&mdsc->stopping_lock); > - if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) { > + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) { > spin_unlock(&mdsc->stopping_lock); > return false; > } > @@ -1501,7 +1501,7 @@ static void __dec_stopping_blocker(struct ceph_mds_client *mdsc) > { > spin_lock(&mdsc->stopping_lock); > if (!atomic_dec_return(&mdsc->stopping_blockers) && > - mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) > + mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) > complete_all(&mdsc->stopping_waiter); > spin_unlock(&mdsc->stopping_lock); > } > @@ -1562,7 +1562,7 @@ static void ceph_kill_sb(struct super_block *s) > sync_filesystem(s); > > spin_lock(&mdsc->stopping_lock); > - mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; > + mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHING; > wait = !!atomic_read(&mdsc->stopping_blockers); > spin_unlock(&mdsc->stopping_lock); > > @@ -1576,6 +1576,7 @@ static void ceph_kill_sb(struct super_block *s) > pr_warn_client(cl, "umount was killed, %ld\n", timeleft); > } > > + mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; > kill_anon_super(s); > > fsc->client->extra_mon_dispatch = NULL; > -- > 2.40.1 >
On 7/21/23 11:19, Milind Changire wrote: > Looks good to me. > > nit: typo for perioudically in commit message Good catch and thanks Milind, I will fix it. -- Xiubo > Reviewed-by: Milind Changire <mchangir@redhat.com> > > > On Thu, Jun 29, 2023 at 9:07 AM <xiubli@redhat.com> wrote: >> From: Xiubo Li <xiubli@redhat.com> >> >> Flushing the dirty buffer may take a long time if the Rados is >> overloaded or if there is network issue. So we should ping the >> MDSs perioudically to keep alive, else the MDS will blocklist >> the kclient. >> >> Cc: stable@vger.kernel.org >> Cc: Venky Shankar <vshankar@redhat.com> >> URL: https://tracker.ceph.com/issues/61843 >> Signed-off-by: Xiubo Li <xiubli@redhat.com> >> --- >> fs/ceph/mds_client.c | 2 +- >> fs/ceph/mds_client.h | 3 ++- >> fs/ceph/super.c | 7 ++++--- >> 3 files changed, 7 insertions(+), 5 deletions(-) >> >> diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c >> index 65230ebefd51..70987b3c198a 100644 >> --- a/fs/ceph/mds_client.c >> +++ b/fs/ceph/mds_client.c >> @@ -5192,7 +5192,7 @@ static void delayed_work(struct work_struct *work) >> >> doutc(mdsc->fsc->client, "mdsc delayed_work\n"); >> >> - if (mdsc->stopping) >> + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) >> return; >> >> mutex_lock(&mdsc->mutex); >> diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h >> index 5d02c8c582fd..befbd384428e 100644 >> --- a/fs/ceph/mds_client.h >> +++ b/fs/ceph/mds_client.h >> @@ -400,7 +400,8 @@ struct cap_wait { >> >> enum { >> CEPH_MDSC_STOPPING_BEGIN = 1, >> - CEPH_MDSC_STOPPING_FLUSHED = 2, >> + CEPH_MDSC_STOPPING_FLUSHING = 2, >> + CEPH_MDSC_STOPPING_FLUSHED = 3, >> }; >> >> /* >> diff --git a/fs/ceph/super.c b/fs/ceph/super.c >> index 8e1e517a45db..fb694ba72955 100644 >> --- a/fs/ceph/super.c >> +++ b/fs/ceph/super.c >> @@ -1488,7 +1488,7 @@ static int ceph_init_fs_context(struct fs_context *fc) >> static bool __inc_stopping_blocker(struct ceph_mds_client *mdsc) >> { >> spin_lock(&mdsc->stopping_lock); >> - if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) { >> + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) { >> spin_unlock(&mdsc->stopping_lock); >> return false; >> } >> @@ -1501,7 +1501,7 @@ static void __dec_stopping_blocker(struct ceph_mds_client *mdsc) >> { >> spin_lock(&mdsc->stopping_lock); >> if (!atomic_dec_return(&mdsc->stopping_blockers) && >> - mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) >> + mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) >> complete_all(&mdsc->stopping_waiter); >> spin_unlock(&mdsc->stopping_lock); >> } >> @@ -1562,7 +1562,7 @@ static void ceph_kill_sb(struct super_block *s) >> sync_filesystem(s); >> >> spin_lock(&mdsc->stopping_lock); >> - mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; >> + mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHING; >> wait = !!atomic_read(&mdsc->stopping_blockers); >> spin_unlock(&mdsc->stopping_lock); >> >> @@ -1576,6 +1576,7 @@ static void ceph_kill_sb(struct super_block *s) >> pr_warn_client(cl, "umount was killed, %ld\n", timeleft); >> } >> >> + mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; >> kill_anon_super(s); >> >> fsc->client->extra_mon_dispatch = NULL; >> -- >> 2.40.1 >> >
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 65230ebefd51..70987b3c198a 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -5192,7 +5192,7 @@ static void delayed_work(struct work_struct *work) doutc(mdsc->fsc->client, "mdsc delayed_work\n"); - if (mdsc->stopping) + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) return; mutex_lock(&mdsc->mutex); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 5d02c8c582fd..befbd384428e 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -400,7 +400,8 @@ struct cap_wait { enum { CEPH_MDSC_STOPPING_BEGIN = 1, - CEPH_MDSC_STOPPING_FLUSHED = 2, + CEPH_MDSC_STOPPING_FLUSHING = 2, + CEPH_MDSC_STOPPING_FLUSHED = 3, }; /* diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 8e1e517a45db..fb694ba72955 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1488,7 +1488,7 @@ static int ceph_init_fs_context(struct fs_context *fc) static bool __inc_stopping_blocker(struct ceph_mds_client *mdsc) { spin_lock(&mdsc->stopping_lock); - if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) { + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) { spin_unlock(&mdsc->stopping_lock); return false; } @@ -1501,7 +1501,7 @@ static void __dec_stopping_blocker(struct ceph_mds_client *mdsc) { spin_lock(&mdsc->stopping_lock); if (!atomic_dec_return(&mdsc->stopping_blockers) && - mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) + mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) complete_all(&mdsc->stopping_waiter); spin_unlock(&mdsc->stopping_lock); } @@ -1562,7 +1562,7 @@ static void ceph_kill_sb(struct super_block *s) sync_filesystem(s); spin_lock(&mdsc->stopping_lock); - mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; + mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHING; wait = !!atomic_read(&mdsc->stopping_blockers); spin_unlock(&mdsc->stopping_lock); @@ -1576,6 +1576,7 @@ static void ceph_kill_sb(struct super_block *s) pr_warn_client(cl, "umount was killed, %ld\n", timeleft); } + mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; kill_anon_super(s); fsc->client->extra_mon_dispatch = NULL;