[Swift-user] [SWIFT JOBS]How To Efficiently Set Sites.xml

[Ketan Maheshwari]

Hi Weiyang,

Ideally workerspernode and ppn should be 24 on beagle to reflect 24 cores
per node.

That should make maximum utilization of a node.

--
Ketan


On Thu, Apr 28, 2011 at 7:10 PM, Weiyang Wang <frank.wang04 at gmail.com>wrote:

> Hello,
>
> Currently my submitted SWIFT jobs are seemed run single-thread, while my
> sites.xml is like
>
> <config>
> <pool handle="pbs">
>     <execution provider="pbs" url="none" jobManager="local:pbs"/>
>     <profile namespace="globus" key="maxwalltime">0:20:00</profile>
>     <profile namespace="globus" key="workersPerNode">8</profile>
>     <profile namespace="globus" key="ppn">8</profile>
>     <!-- <profile namespace="globus"
> key="internalHostname">172.5.86.6</profile>-->
>     <profile namespace="globus" key="nodeGranularity">1</profile>
>     <profile namespace="globus" key="maxNodes">5</profile>
>     <profile namespace="karajan" key="jobThrottle">1.99</profile>
>     <profile namespace="karajan" key="initialScore">10000</profile>
>     <profile namespace="globus" key="project">CI-SES000031</profile>
>     <!--gridftp  url="local://localhost" />-->
>     <filesystem provider="local"/>
>     <!--scratch>/home/frankwang/tmp</scratch>-->
>     <workdirectory>/lustre/beagle/scratch</workdirectory>
> </pool>
> </config>
>
> Do any of you have ideas to adjust it so that it'll be more efficient?
>
> _______________________________________________
> Swift-user mailing list
> Swift-user at ci.uchicago.edu
> http://mail.ci.uchicago.edu/mailman/listinfo/swift-user
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/swift-user/attachments/20110428/54d64ad9/attachment.html>