Hello Ilya,
thank you for your help.
I first tried 'ceph osd crush tunables legacy' on each server with
rebooting.
That didn't help anything. I though, that running this command the
feature should be disabled, but the error remains.
In the past i only did rolling ceph-upgrades with 'apt-get upgrade'.
That always went fine, even kernel-upgrades with rolling reboots.
But i never did a downgrade.
Is that easyly possible ? How ? How can i go to a specify version like
0.73 or 0.74 ?
Thank you,
Markus
Am 29.01.2014 13:19, schrieb Ilya Dryomov:
On Wed, Jan 29, 2014 at 1:58 PM, Markus Goldberg
<goldberg@xxxxxxxxxxxxxxxxx> wrote:
Hi,
i can't mount.ceph:
mount.ceph bd-0:/ /mnt/myceph -v -o
name=admin,secretfile=/etc/ceph/admin.secret
parsing options: name=admin,secretfile=/etc/ceph/admin.secret
mount error 5 = Input/output error
ceph -s is OK,
When i look at /var/log/syslog, i can see:
Jan 29 12:22:06 bd-0 kernel: [10333.825859] libceph: mon0
xxx.xxx.xxx.xxx:6789 feature set mismatch, my 4a042aca < server's
104a042aca, missing 1000000000
Jan 29 12:22:06 bd-0 kernel: [10333.827302] libceph: mon0
xxx.xxx.xxx.xxx:6789 socket error on read
So i seems, that a feature should be disabled. I think it is Crush V2.
What should i do ?
Server and Client are Ubuntu 13.04, Kernel 3.12.6. I also tried 3.13 but
without success.
This is ceph 0.75
Yes, it's CRUSH_V2. 0.75 is a development release, so you should
either go back to Emperor (0.72) or use (with caution!) a development
kernel. Support for CRUSH_V2 will be in 3.14 and is in mainline as of
yesterday, however I wouldn't advise running a pre-rc1 kernel.
Instead, you can grab a master branch of ceph-client.git - it has
CRUSH_V2 bits and is based on 3.13-rc3. (I think it can be safely
rebased onto 3.13 final too.)
Thanks,
Ilya
--
MfG,
Markus Goldberg
--------------------------------------------------------------------------
Markus Goldberg Universität Hildesheim
Rechenzentrum
Tel +49 5121 88392822 Marienburger Platz 22, D-31141 Hildesheim, Germany
Fax +49 5121 88392823 email goldberg@xxxxxxxxxxxxxxxxx
--------------------------------------------------------------------------
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
