I apologize, I should have mentioned that both osd.3 and osd.11 crash immediately and if I do not 'set noout', the crash cascades to the rest of the cluster.
Thanks,
Jeff
Sent from my Samsung Galaxy Note™, an AT&T LTE smartphone
-------- Original message --------
From: Samuel Just <sam.just@xxxxxxxxxxx>
Date: 10/21/2013 4:47 PM (GMT-08:00)
To: Jeff Williams <jeff.williams@xxxxxxxxx>
Cc: ceph-users@xxxxxxxxxxxxxx
Subject: Re: Continually crashing osds
What happened when you simply left the cluster to recover without osd.11 in?
-Sam
On Mon, Oct 21, 2013 at 4:01 PM, Jeff Williams <jeff.williams@xxxxxxxxx> wrote:
> What is the best way to do that? I tried ceph pg repair, but it only did
> so much.
>
> On 10/21/13 3:54 PM, "Samuel Just" <sam.just@xxxxxxxxxxx> wrote:
>
>>Can you get the pg to recover without osd.3?
>>-Sam
>>
>>On Mon, Oct 21, 2013 at 1:59 PM, Jeff Williams <jeff.williams@xxxxxxxxx>
>>wrote:
>>> We're running xfs on a 3.8.0-31-generic kernel
>>>
>>> Thanks,
>>> Jeff
>>>
>>> On 10/21/13 1:54 PM, "Samuel Just" <sam.just@xxxxxxxxxxx> wrote:
>>>
>>>>It looks like an xattr vanished from one of your objects on osd.3.
>>>>What fs are you running?
>>>>
>>>>On Mon, Oct 21, 2013 at 9:58 AM, Jeff Williams <jeff.williams@xxxxxxxxx>
>>>>wrote:
>>>>> Hello all,
>>>>>
>>>>> Similar to this post from last month, I am experiencing 2 nodes that
>>>>>are
>>>>> constantly crashing upon start up:
>>>>> http://www.spinics.net/lists/ceph-users/msg04589.html
>>>>>
>>>>> Here are the logs from the 2 without the debug commands, here:
>>>>> http://pastebin.com/cB9ML5md and http://pastebin.com/csHHjC2h
>>>>>
>>>>> I have run the osds with the debug statements per the email, but I'm
>>>>>unsure
>>>>> where to post them, they are 108M each without compression. Should I
>>>>>create
>>>>> a bug on the tracker?
>>>>>
>>>>> Thanks,
>>>>> Jeff
>>>>>
>>>>> _______________________________________________
>>>>> ceph-users mailing list
>>>>> ceph-users@xxxxxxxxxxxxxx
>>>>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>>>>>
>>>
>
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
-Sam
On Mon, Oct 21, 2013 at 4:01 PM, Jeff Williams <jeff.williams@xxxxxxxxx> wrote:
> What is the best way to do that? I tried ceph pg repair, but it only did
> so much.
>
> On 10/21/13 3:54 PM, "Samuel Just" <sam.just@xxxxxxxxxxx> wrote:
>
>>Can you get the pg to recover without osd.3?
>>-Sam
>>
>>On Mon, Oct 21, 2013 at 1:59 PM, Jeff Williams <jeff.williams@xxxxxxxxx>
>>wrote:
>>> We're running xfs on a 3.8.0-31-generic kernel
>>>
>>> Thanks,
>>> Jeff
>>>
>>> On 10/21/13 1:54 PM, "Samuel Just" <sam.just@xxxxxxxxxxx> wrote:
>>>
>>>>It looks like an xattr vanished from one of your objects on osd.3.
>>>>What fs are you running?
>>>>
>>>>On Mon, Oct 21, 2013 at 9:58 AM, Jeff Williams <jeff.williams@xxxxxxxxx>
>>>>wrote:
>>>>> Hello all,
>>>>>
>>>>> Similar to this post from last month, I am experiencing 2 nodes that
>>>>>are
>>>>> constantly crashing upon start up:
>>>>> http://www.spinics.net/lists/ceph-users/msg04589.html
>>>>>
>>>>> Here are the logs from the 2 without the debug commands, here:
>>>>> http://pastebin.com/cB9ML5md and http://pastebin.com/csHHjC2h
>>>>>
>>>>> I have run the osds with the debug statements per the email, but I'm
>>>>>unsure
>>>>> where to post them, they are 108M each without compression. Should I
>>>>>create
>>>>> a bug on the tracker?
>>>>>
>>>>> Thanks,
>>>>> Jeff
>>>>>
>>>>> _______________________________________________
>>>>> ceph-users mailing list
>>>>> ceph-users@xxxxxxxxxxxxxx
>>>>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>>>>>
>>>
>
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
