On Mar 15, 2011, at 20:38 , Rayson Ho wrote:

> On Tue, Mar 15, 2011 at 6:12 AM, Esztermann, Ansgar
> <[email protected]> wrote:
>> Thanks, that has helped a bit. I know now that most of the CPU time is spent 
>> in the dispatching stage. However, it is still unclear to me why dispatching 
>> should be such a time-consuming task.
> 
> Good, at least we are on the right track!! :-)
...

> But as your cluster is
> spending 5 minutes to decide where the jobs should go, I'm curious
> what kind of resource requirements do they have, and most importantly,
> do they have soft request specified??

After a few quiet weeks, scheduling times are up again. The resource 
requirements are mostly the same as before (h_rt, some booleans) except for the 
soft requirements (which most of our jobs do not have, but a few have cropped 
up just now.

Here's a section from the log:

04/06/2011 17:18:55|schedu|master1|P|PROF: job dispatching took 459.150 s (0 
fast, 0 fast_soft, 25 pe, 3 pe_soft, 5 res)
04/06/2011 17:18:55|schedu|master1|P|PROF: parallel matching            745     
  269524         2235       250306       165939       250306       134687
04/06/2011 17:18:55|schedu|master1|P|PROF: sequential matching            0     
       0            0            0            0            0            0
04/06/2011 17:18:55|schedu|master1|P|PROF: create pending job orders: 0.000 s
04/06/2011 17:18:55|schedu|master1|P|PROF: scheduled in 459.270 (u 485.570 + s 
21.890 = 507.460): 0 sequential, 3 parallel, 764 orders, 846 H, 71 Q, 839 QA, 
25 J(qw), 715 J(r), 0 J(s), 0 J(h), 0 J(e), 4 J(x), 761 J(all), 57 C, 3 ACL, 
149 PE, 33 U, 1 D, 0 PRJ, 1 ST, 0 CKPT, 0 RU, 1 gMes, 0 jMes, 764/4 pre-send, 
0/0/0 pe-alg

04/06/2011 17:18:55|schedu|master1|P|PROF: send orders and cleanup took: 0.030 
(u 0.030,s 0.010) s
04/06/2011 17:18:55|schedu|master1|P|PROF: schedd run took: 459.500 s (init: 
0.010 s, copy: 0.130 s, run:459.300, free: 0.050 s, jobs: 761, categories: 53/0)



Regards,

A.
-- 
Ansgar Esztermann
DV-Systemadministration
Max-Planck-Institut für biophysikalische Chemie, Abteilung 105


_______________________________________________
users mailing list
[email protected]
https://gridengine.org/mailman/listinfo/users

Reply via email to