Just a bet: have you inconsistant MTU across your network ?
I already had your issue when OSD and client was using jumbo frames, but
MON did not (or something like that)
On 06/07/2018 05:12 AM, Tracy Reed wrote:
>
> Hello all! I'm running luminous with old style non-bluestore OSDs. ceph
> 10.2.9 clients though, haven't been able to upgrade those yet.
>
> Occasionally I have access to rbds hang on the client such as right now.
> I tried to dd a VM image into a mapped rbd and it just hung.
>
> Then I tried to map a new rbd and that hangs also.
>
> How would I troubleshoot this? /var/log/ceph is empty, nothing in
> /var/log/messages or dmesg etc.
>
> I just discovered:
>
> find /sys/kernel/debug/ceph -type f -print -exec cat {} \;
>
> which produces (among other seemingly innocuous things, let me know if
> anyone wants to see the rest):
>
> osd2 (unknown sockaddr family 0) 0% (doesn't exist) 100%
>
> which seems suspicious.
>
> rbd ls works reliably. As does create. Cluster is healthy.
>
> But the processes which hung trying to access that mapped rbd appear to
> be completely unkillable. What
>
> else should I check?
>
> Thanks!
>
>
>
>
> _______________________________________________
> 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
