[gold-users] Gold : Issue with refunding the reserved amount

akshar bhosale akshar.bhosale at gmail.com
Sat Jul 2 04:25:22 MDT 2011


Hi,
we have gold version 2.1.7.1 running on rhel 5.2. We have PBS +maui+gold
combination for our 48 nodes cluster. We have observed strange problem that
for one of the user, some amount of cpu time is shown as reserved. Now job
for which cpu time is reserved is not in queue, it has been cancelled by
user. Job tried to run and came back 10-12 times and finally it was
cancelled by user.
The total of amount reserved as shown in gold for this job is the amount
which is total of amount reserved for the job whenever it went for
running(10-12 times). Now we have

when listed the jobs run by user rocky, (as shown in the last table) we can
see that total amount blocked is (14*54150) and job with id 257 does nnot
exist.

Also ./grefund -J  257 says that no matching job found also /grefund -J  257
-j 273 also gives same error.

How to clear reserved amount?


 Id    JobId User     Project   Machine    Queue QualityOfService Stage
Charge   Processors Nodes WallDuration StartTime
EndTime             Description
----- ----- -------- --------- ---------- ----- ---------------- -------
-------- ---------- ----- ------------ -------------------
------------------- -----------
273 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64              54150
274 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
275 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
276 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
277 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
281 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
282 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
283 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
284 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
285 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
286 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
287 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64
54150
288 257 rocky simulaton_bio bio-cluster normal DEFAULT
Reserve        0 64              54150
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.supercluster.org/pipermail/gold-users/attachments/20110702/c93a0893/attachment.html 


More information about the gold-users mailing list