If the OSD daemon dies, then it will have closed all of its fd's and
there should be no more lock. Therefore you almost certainly have some
other process running that is holding the lock.
You may have to do a bit of digging in /proc/locks. Determine the
dev+inode number of the file on which the lock is being set and find it
in /proc/locks. Then you can track down the PID that's holding that
lock.
Cheers,
Jeff
On Wed, 2020-02-12 at 09:03 -0800, Yiming Zhang wrote:
> The weird thing is I don’t have systemd-udev installed on my server.
> Is there any other possible solutions?
>
> The error only happens when I redirect osd data to a raw device.
>
> Thanks,
> Yiming
>
> > On Feb 12, 2020, at 8:36 AM, Sage Weil <sage@xxxxxxxxxxxx> wrote:
> >
> > Talib was chasing down a similar issue a while back and found that the
> > root cause was systemd-udev, which spawns a process that opens the device
> > after it is closed. You might try removing or disabling that package
> > and see if it goes away?
> >
> >
> > On Wed, 12 Feb 2020, Yiming Zhang wrote:
> >
> > > Hi All,
> > >
> > > I noticed a locking issue in kernel device.
> > > When I stopped the ceph cluster and all daemons, the kernel device _lock somehow is still held and this line below will return r < 0:
> > >
> > > int KernelDevice::_lock()
> > > {
> > > int r = ::flock(fd_directs[WRITE_LIFE_NOT_SET], LOCK_EX | LOCK_NB);
> > > …
> > > }
> > >
> > > The way I stop the cluster and daemons:
> > >
> > > sudo ../src/stop.sh
> > > sudo bin/init-ceph --verbose forcestop
> > >
> > > This error happens even after the reboot when I try to use vstart:
> > >
> > > bdev _lock flock failed on ceph/build/dev/osd0/block
> > > bdev open failed to lock /home/yzhan298/ceph/build/dev/osd0/block: (11) Resource temporarily unavailable
> > > OSD::mkfs: couldn't mount ObjectStore: error (11) Resource temporarily unavailable
> > > ** ERROR: error creating empty object store in ceph/build/dev/osd0: (11) Resource temporarily unavailable
> > >
> > >
> > > Please advice. (On master branch)
> > >
> > > Thanks,
> > > Yiming
> > > _______________________________________________
> > > Dev mailing list -- dev@xxxxxxx
> > > To unsubscribe send an email to dev-leave@xxxxxxx
> _______________________________________________
> Dev mailing list -- dev@xxxxxxx
> To unsubscribe send an email to dev-leave@xxxxxxx
--
Jeff Layton <jlayton@xxxxxxxxxx>
_______________________________________________
Dev mailing list -- dev@xxxxxxx
To unsubscribe send an email to dev-leave@xxxxxxx
