[GE users] SGE 6.2U3 question

reuti reuti at staff.uni-marburg.de
Wed Mar 31 18:55:26 BST 2010


Am 31.03.2010 um 19:48 schrieb templedf:

> Check the qacct(1) man page.  -b and -e are what you want.  Now that 
> will only show you jobs that ended within the specified constraints.  If 
> you want to know what was running, you'll need to have ARCo installed, 
> or at least have the reporting file turned on.

It is also possible to use AWK to get it out of the accounting file.

-- Reuti


> The IO stats are always 0 on OSes that don't report per-process IO info.
> 
> Daniel
> 
> On 03/31/10 10:27, gtatachar wrote:
>> I am running 6.2U3 open source version on Linux. I am using NFS FS for spooling. Recently we have seen an exponential increace NFS latency on our netapp filer. I have the following questions:
>> 
>> 1. How can I find out the jobs that ran during a specific time interval? (I tried the qacct command; only reports the summary and can not list the jobs in a particular interval - at least that's what I thought)
>> 
>> 2. Also, in the accounting field the IO and IOW fields are always "0" ; it some how doesn't make sense.
>> 
>> Any help/info is appreciated.
>> 
>> Thanks
>> Gopi
>> 
>> ------------------------------------------------------
>> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=251963
>> 
>> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].
> 
> ------------------------------------------------------
> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=251964
> 
> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=251966

To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].



More information about the gridengine-users mailing list