Re: rbd lock remove unable to parse address

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



2018-07-10 14:37 GMT+02:00 Jason Dillaman <jdillama@xxxxxxxxxx>:
On Tue, Jul 10, 2018 at 2:37 AM Kevin Olbrich <ko@xxxxxxx> wrote:
2018-07-10 0:35 GMT+02:00 Jason Dillaman <jdillama@xxxxxxxxxx>:
Is the link-local address of "fe80::219:99ff:fe9e:3a86%eth0" at least present on the client computer you used? I would have expected the OSD to determine the client address, so it's odd that it was able to get a link-local address. 

Yes, it is. eth0 is part of bond0 which is a vlan trunk. Bond0.X is attached to brX which has an ULA-prefix for the ceph cluster.
Eth0 has no address itself. In this case this must mean, the address has been carried down to the hardware interface.

I am wondering why it uses link local when there is an ULA-prefix available.

The address is available on brX on this client node.

I'll open a tracker ticker to get that issue fixed, but in the meantime, you can run "rados -p <IMAGE POOL> rmxattr rbd_header.<IMAGE ID> lock.rbd_lock" to remove the lock. 

Worked perfectly, thank you very much!
 

- Kevin
 
On Mon, Jul 9, 2018 at 3:43 PM Kevin Olbrich <ko@xxxxxxx> wrote:
2018-07-09 21:25 GMT+02:00 Jason Dillaman <jdillama@xxxxxxxxxx>:
BTW -- are you running Ceph on a one-node computer? I thought IPv6 addresses starting w/ fe80 were link-local addresses which would probably explain why an interface scope id was appended. The current IPv6 address parser stops reading after it encounters a non hex, colon character [1].

No, this is a compute machine attached to the storage vlan where I previously had also local disks.
 


On Mon, Jul 9, 2018 at 3:14 PM Jason Dillaman <jdillama@xxxxxxxxxx> wrote:
Hmm ... it looks like there is a bug w/ RBD locks and IPv6 addresses since it is failing to parse the address as valid. Perhaps it's barfing on the "%eth0" scope id suffix within the address.

On Mon, Jul 9, 2018 at 2:47 PM Kevin Olbrich <ko@xxxxxxx> wrote:
Hi!

I tried to convert an qcow2 file to rbd and set the wrong pool.
Immediately I stopped the transfer but the image is stuck locked:

Previusly when that happened, I was able to remove the image after 30 secs.

[root@vm2003 images1]# rbd -p rbd_vms_hdd lock list fpi_server02
There is 1 exclusive lock on this image.
Locker         ID                  Address                                      
client.1195723 auto 93921602220416 [fe80::219:99ff:fe9e:3a86%eth0]:0/1200385089 

[root@vm2003 images1]# rbd -p rbd_vms_hdd lock rm fpi_server02 "auto 93921602220416" client.1195723
rbd: releasing lock failed: (22) Invalid argument
2018-07-09 20:45:19.080543 7f6c2c267d40 -1 librados: unable to parse address [fe80::219:99ff:fe9e:3a86%eth0]:0/1200385089
2018-07-09 20:45:19.080555 7f6c2c267d40 -1 librbd: unable to blacklist client: (22) Invalid argument

The image is not in use anywhere!

How can I force removal of all locks for this image?

Kind regards,
Kevin
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com


--
Jason

[1] https://github.com/ceph/ceph/blob/master/src/msg/msg_types.cc#L108

--
Jason



--
Jason



--
Jason

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Ceph Dev]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux