On Mar 20, 2007, at 9:33 AM, Jeremy Cook wrote:
> Dear All,
>
> we have a number of jobs hanging around in our torque queue that
> are almost certainly "dead". Possibly due to some transient problem.
>
> What is the best way to clean these up? Can we just qdel them or is
> a more careful approach needed. Jobs seem to be being submitted and
> returning successfully now. The oldest job is from December 2006:
>
Can you do a
qstat -n,
I'm intrested to see if the jobs have been assigned to nodes?
> Job id Name User Time Use S Queue
> ------------------- ---------------- --------------- -------- - -----
> 130863.fire blahjob_X12864 dteam005 0 W dteam
> 147233.fire blahjob_WN2229 atlas002 0 W atlas
> 158035.fire blahjob_l18819 ops000 0 W ops
> 158674.fire blahjob_E25741 bio006 0 W biomed
> 167874.fire blahjob_L27084 dteam005 0 W dteam
> 167897.fire blahjob_a27520 atlassgm 0 W atlas
> 167924.fire blahjob_J30411 atlassgm 0 W atlas
> 167935.fire blahjob_UA2010 dteam005 0 W dteam
> 167945.fire blahjob_P17764 dteam005 0 W dteam
> 167946.fire blahjob_i28037 atlassgm 0 W atlas
> 167965.fire blahjob_T12387 dteam005 0 W dteam
> 167968.fire blahjob_T24466 atlassgm 0 W atlas
> 167987.fire blahjob_t12749 dteam005 0 W dteam
> 167999.fire blahjob_o28280 dteam005 0 W dteam
> 168037.fire blahjob_T11351 atlassgm 0 W atlas
> 168058.fire blahjob_B16890 atlassgm 0 W atlas
> 168069.fire blahjob_H31328 atlassgm 0 W atlas
> 168081.fire blahjob_C11601 dteam005 0 W dteam
> 168088.fire blahjob_m25192 dteam005 0 W dteam
> 168089.fire blahjob_z29489 atlassgm 0 W atlas
> 168097.fire blahjob_s11026 atlassgm 0 W atlas
> 168122.fire blahjob_w16263 dteam005 0 W dteam
> 168143.fire blahjob_ZS4978 atlassgm 0 W atlas
> 168168.fire blahjob_WX7497 dteam005 0 W dteam
> 168174.fire blahjob_n18101 atlassgm 0 W atlas
> 168199.fire blahjob_f15269 atlassgm 0 W atlas
> 168207.fire blahjob_H15897 atlassgm 0 W atlas
> 168238.fire blahjob_M32015 dteam005 0 W dteam
> 168247.fire blahjob_o12266 dteam005 0 W dteam
> 168249.fire blahjob_D10363 atlassgm 0 W atlas
> 168269.fire blahjob_T24019 dteam005 0 W dteam
> 168333.fire blahjob_u17017 atlassgm 0 W atlas
> 168351.fire blahjob_JX2034 atlassgm 0 W atlas
> 168376.fire blahjob_L12945 atlassgm 0 W atlas
> 168388.fire blahjob_f22479 dteam005 0 W dteam
> 168389.fire blahjob_lH6556 atlassgm 0 W atlas
> 168392.fire blahjob_c11102 dteam005 0 W dteam
> 168393.fire blahjob_d15355 dteam005 0 W dteam
> 168394.fire blahjob_O21758 atlassgm 0 W atlas
> 168422.fire blahjob_a24373 atlassgm 0 W atlas
> 168428.fire blahjob_P24837 dteam005 0 W dteam
> 181520.fire blahjob_O18345 dteam005 0 W dteam
> 181536.fire blahjob_p17937 atlassgm 0 W atlas
> 182048.fire blahjob_tt5057 atlassgm 0 W atlas
> 182070.fire blahjob_s20171 dteam005 0 W dteam
> 182591.fire blahjob_XD1531 atlassgm 0 W atlas
> 184076.fire blahjob_m22632 atlassgm 0 W atlas
> 184090.fire blahjob_L32264 atlassgm 0 W atlas
> 184564.fire blahjob_fsk379 dteam005 0 W dteam
> 184925.fire blahjob_Mw8959 atlassgm 0 W atlas
> 184969.fire blahjob_B18995 dteam005 0 W dteam
> 185114.fire blahjob_p18550 alice001 0 W alice
> 185235.fire blahjob_R29826 ops000 0 W ops
> 185402.fire blahjob_oA9076 dteam005 0 W dteam
>
> Thanks for any help.
>
> Jeremy
> --
> [log in to unmask] tlf: +47 55 58 40 65
> Parallab Bergen Centre for Computational Science
--
Steve Traylen
[log in to unmask]
CERN, IT-GD-OPS.
|