On Thu, Jan 14, 2010 at 7:24 AM, Magarshak, Roman
<roman.magars...@sap.com>wrote:
> Hi all ,
>
> We have tried to run ceph on 2 nodes without btrfs and encountered the
> following problem?
>
>
>
> *The system:*
>
> 2 Virtual (on vmware) 32 bit machines , running Debian Lenny unstable
>
> Both have access to NFS (where the configuration file is kept)
>
>
>
> Kernel version: 2.6.32-trunk-vserver-686
>
> Ceph is installed from tar.gz including kernel and fuse clients (version
> 0.18)
>
> Ceph1=10.26.236.93
>
> Ceph2=10.26.236.94
>
> On both servers /ceph /ceph/out /ceph/log exists.
>
>
>
> *The scenario: *
>
>
>
> On ceph1 the following commands are executed:
>
> $ mkcephfs --allhosts -c /mnt/nfs/ceph/ceph.conf
>
> $ /etc/init.d/ceph -a -c /mnt/nfs/ceph/ceph.conf start
>
>
>
> After that the cmds , cmon, cosd are running
>
>
>
> Now the following commands on ceph2 are executed:
>
> $ mount -t ceph ceph1:6789:/ /mnt/ceph
>
> The mount succeeds
>
> After ‘ls’ and ‘touch’ commands, the console gets stuck.
>
> Dmesg log is attached.
>
>
>
> On ceph1 cmds no longer appears on ps.
>
Probably the mds went down for some reason. Maybe there's a core file
around?
Yehuda
------------------------------------------------------------------------------
Throughout its 18-year history, RSA Conference consistently attracts the
world's best and brightest in the field, creating opportunities for Conference
attendees to learn about information security's most important issues through
interactions with peers, luminaries and emerging and established companies.
http://p.sf.net/sfu/rsaconf-dev2dev
_______________________________________________
Ceph-devel mailing list
Ceph-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ceph-devel
