[GE users] Monitoring Softwares...

Sriram Sitaraman Sriram.Sitaraman at synopsys.com
Fri Mar 18 21:24:02 GMT 2005


Hi


	I realize the options of using standard SGE commands to check the load values etc... The status script also provides a nice information, but these are not useful to manage and look at historical/real time data, to understand how the cell is working out or to be able to predict times etc. I am looking for some thing that can provide this information as graphs, number etc..

We did evaluate the ARCO module but it seemed very clunky when we initially did the testing, and did not meet our needs. The requirements are standards for any business which is to be able to analyze the log files etc. I am surprised that some thing like this does not exist see how many folks have adopted SGE for their production needs. 

Again, If some one has a link to a package that can do this, I would appriciate it if you could send it along.

thanks
Sriram




>
>
>Date: Fri, 18 Mar 2005 18:23:01 +0100
>From: Reuti <reuti at staff.uni-marburg.de>
>Content-Type: text/plain; charset=ISO-8859-1
>Subject: [GE users] Monitoring Softwares...
>
>
>Hi,
>
>some of the things are already built-in:
>
>Quoting Sriram Sitaraman <Sriram.Sitaraman at synopsys.com>:
>
>> 
>> Hi
>> 
>> 	Seems like this question has come up a few time with no real
>> good solution. Is there "SGE" related monitoring system that
>> consolidates some important values like
>> 
>> 	Machine load
>> 	Machine CPU >>
>> 	Mem_Total
>> 	Mem_Free
>
>qhost
>
>and for a cluster queue
>
>qstat -g c
>
>as CQLOAD is normalized to 1.
> 
>> 	Jobs Submitted
>> 	CPU/ Per User
>> 	Jobs Pending
>
>Have a look at status script from the "Documents & files" page. And use:
>
>status -acl
>
>> 	Average Turn around Time / Average Wait Time/ Average Run Time 
>> 	Job based timings 	
>> 	Idle Jobs
>> 	Job Jobs
>
>What do you mean with "Job Jobs"?!?
> 
>> We have been working on a interface, but managing the accounting file is
>> very hard, as it grows very fast. Also we are on version 6.0. Currently
>> some of the systems out there seem to be more cluster centric, but not
>> related to SGE.
>
>Okay - Mark and Charu were faster here.
>
>
>Cheers - Reuti
>
>

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list