On Fri, Apr 15, 2016 at 10:18 AM, lin zhou <hnuzhoulin2@xxxxxxxxx> wrote:
> Hi,cephers:
> In one of my ceph cluster,we map rbd then mount it. in node1 and then
> using samba to share it to do backup for several vm,and some web root
> directory.
>
> Yesterday,one of the disk in my cluster is full at 95%,then the
> cluster stop receive write request.
> I have solve the full problem.But these mount directory from mapped
> rbd in node1 do not work correctly.
>
> case 1:I can access some directory in node1 ,but some files can not open
> case 2:If I enter a directory,the cd command hang,the state in ps is
> D,and can not be killed.If I map this rbd in another host and then
> mount it,I can see all files.
>
> so does some option for rbd map and the following mount command to
> deal with this situation that ceph has a little volatility to prevent
> hang.
Can you provide the output of
# ceph -s
# find /sys/kernel/debug/ceph -type f -print -exec cat {} \;
from the faulty host?
Thanks,
Ilya
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
