Am 06.08.15 um 10:16 schrieb Lukas Slebodnik:
> On (06/08/15 07:47), Torsten Harenberg wrote:
>> Am 06.08.15 um 07:37 schrieb Torsten Harenberg:
>>> (see plot attached
>>
>> forgot the attachment
>>
> Is the high IO caused by sssd or by other aplication?
>
> If it is casued by other application t
On (06/08/15 07:47), Torsten Harenberg wrote:
>Am 06.08.15 um 07:37 schrieb Torsten Harenberg:
>> (see plot attached
>
>forgot the attachment
>
Is the high IO caused by sssd or by other aplication?
If it is casued by other application then you can mount
directory with sss cache (/var/lib/sss or j
On Thu, Aug 06, 2015 at 07:37:09AM +0200, Torsten Harenberg wrote:
> Thanks for the hints and the pointers.
>
> We found that this
>
> (Thu Aug 6 03:30:01 2015) [sssd[nss]] [id_callback] (0x0010): The
> Monitor returned an error [org.freedesktop.DBus.Error.NoReply]
>
> and this always happens w
Am 06.08.15 um 07:37 schrieb Torsten Harenberg:
> (see plot attached
forgot the attachment
--
<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>
<> <>
<> Dr. Torsten Harenberg harenb...@physik.uni-wuppertal.de <>
Thanks for the hints and the pointers.
We found that this
(Thu Aug 6 03:30:01 2015) [sssd[nss]] [id_callback] (0x0010): The
Monitor returned an error [org.freedesktop.DBus.Error.NoReply]
and this always happens when there are jobs with heavy disc IO and the
nodes (see plot attached from this pa
On (04/08/15 07:56), Torsten Harenberg wrote:
>just realized that it's probably not an instablity, but some process is
>killing sssd:
>
>[root@wn113 sssd]# zcat sssd.log-20150804.gz
>(Mon Aug 3 20:30:55 2015) [sssd] [mt_svc_sigkill] (0x0010):
>[pleiades.uni-wuppertal.de][5957] is not responding to
just realized that it's probably not an instablity, but some process is
killing sssd:
[root@wn113 sssd]# zcat sssd.log-20150804.gz
(Mon Aug 3 20:30:55 2015) [sssd] [mt_svc_sigkill] (0x0010):
[pleiades.uni-wuppertal.de][5957] is not responding to SIGTERM. Sending
SIGKILL.
(Mon Aug 3 20:31:31 2015
Dear all,
is the sssd shipped with CentOS6 known to be unstable? In our cluster
approx. 4-5 nodes out of about 200 are dying on a daily basis:
[root@wn113 ~]# /etc/init.d/sssd status
sssd dead but subsys locked
[root@wn113 ~]# /etc/init.d/sssd stop
[root@wn113 ~]# /etc/init.d/sssd start
Starting