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
