StarCluster - (<a href="http://web.mit.edu/starcluster">http://web.mit.edu/starcluster</a>) (v. 0.93.3)<br><br>If I starcluster sshmaster -X mycluster and type qmon, then the splash screen for it shows up but it doesn't seem to progress from there. How long should it take to get past that?<br>
<br>Scott<br><br><br><div class="gmail_quote">On Fri, May 11, 2012 at 8:15 PM, Rayson Ho <span dir="ltr"><<a href="mailto:raysonlogin@gmail.com" target="_blank">raysonlogin@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
If you have a recent enough version of StarCluster, then you should be<br>
able to run qmon without any special settings that forward X in SSH.<br>
<br>
This was added in: <a href="https://github.com/jtriley/StarCluster/issues/81" target="_blank">https://github.com/jtriley/StarCluster/issues/81</a><br>
<br>
Rayson<br>
<div class="im HOEnZb"><br>
================================<br>
Open Grid Scheduler / Grid Engine<br>
<a href="http://gridscheduler.sourceforge.net/" target="_blank">http://gridscheduler.sourceforge.net/</a><br>
<br>
Scalable Grid Engine Support Program<br>
<a href="http://www.scalablelogic.com/" target="_blank">http://www.scalablelogic.com/</a><br>
<br>
<br>
<br>
</div><div class="HOEnZb"><div class="h5">On Fri, May 11, 2012 at 10:58 PM, Scott Le Grand <<a href="mailto:varelse2005@gmail.com">varelse2005@gmail.com</a>> wrote:<br>
> This is a stupid question but...<br>
><br>
> Given I access a starcluster cluster indirectly, how do I run an X<br>
> application such that it displays on my remote system?<br>
><br>
> I would normally type ssh -X <a href="mailto:ec2-user@amazoninstance.com">ec2-user@amazoninstance.com</a> qmon in order to<br>
> fire up qmon, yes?<br>
><br>
> How do I do the equivalent here?<br>
><br>
> On Fri, May 11, 2012 at 2:45 PM, Rayson Ho <<a href="mailto:raysonlogin@yahoo.com">raysonlogin@yahoo.com</a>> wrote:<br>
>><br>
>> Hi Scott,<br>
>><br>
>> You can set up a consumable resource to track usage of GPUs:<br>
>><br>
>> <a href="http://gridscheduler.sourceforge.net/howto/consumable.html" target="_blank">http://gridscheduler.sourceforge.net/howto/consumable.html</a><br>
>><br>
>> And we also have a load sensor that monitors the GPU devices:<br>
>><br>
>><br>
>> <a href="https://gridscheduler.svn.sourceforge.net/svnroot/gridscheduler/trunk/source/dist/gpu/gpu_sensor.c" target="_blank">https://gridscheduler.svn.sourceforge.net/svnroot/gridscheduler/trunk/source/dist/gpu/gpu_sensor.c</a><br>
>><br>
>> If you want to use the (2nd - ie. dynamic) method, then you will need to<br>
>> set it up by following this HOWTO:<br>
>><br>
>> <a href="http://gridscheduler.sourceforge.net/howto/loadsensor.html" target="_blank">http://gridscheduler.sourceforge.net/howto/loadsensor.html</a><br>
>><br>
>> The first method of using a consumable resource works best if you don't<br>
>> run GPU<br>
>> programs outside of Open Grid Scheduler/Grid Engine.<br>
>><br>
>> Also note that in the next release of StarCluster GPU support will be<br>
>> enhanced.<br>
>><br>
>> Rayson<br>
>><br>
>> =================================<br>
>> Open Grid Scheduler / Grid Engine<br>
>> <a href="http://gridscheduler.sourceforge.net/" target="_blank">http://gridscheduler.sourceforge.net/</a><br>
>><br>
>> Scalable Grid Engine Support Program<br>
>> <a href="http://www.scalablelogic.com/" target="_blank">http://www.scalablelogic.com/</a><br>
>><br>
>><br>
>> ________________________________<br>
>> From: Scott Le Grand <<a href="mailto:varelse2005@gmail.com">varelse2005@gmail.com</a>><br>
>> To: <a href="mailto:starcluster@mit.edu">starcluster@mit.edu</a><br>
>> Sent: Friday, May 11, 2012 5:25 PM<br>
>> Subject: [StarCluster] CG1 plus StarCluster Questions<br>
>><br>
>> Hey guys, I'm really impressed with StarCluster and I've used it to create<br>
>> clusters ranging from 2 to 70 instances...<br>
>><br>
>> I've also customized it to use CUDA 4.2 and 295.41, the latest toolkit and<br>
>> driver, because my code has GTX 680 support and I don't want to have to<br>
>> comment it out just to build it (and 4.1 had a horrendous perf regression).<br>
>><br>
>> Anyway, 2 questions, one of which I think you already answered:<br>
>><br>
>> 1. I'd like to setup a custom AMI that by default has configured 2 GPUs as<br>
>> a consumable resource. I already have code to utilize exclusive mode and<br>
>> choose whichever GPU isn't in use in my app, but that all falls down because<br>
>> the queueing system is based on CPU cores rather than GPU count. How would<br>
>> I set this up once so I can save the customized AMI and never have to do it<br>
>> again?<br>
>><br>
>> 2. I'm also seeing the .ssh directories disappear on restart. But I'll<br>
>> look at your solution as I've just been restarting the whole cluster up to<br>
>> now.<br>
>><br>
>><br>
>><br>
>><br>
>> _______________________________________________<br>
>> StarCluster mailing list<br>
>> <a href="mailto:StarCluster@mit.edu">StarCluster@mit.edu</a><br>
>> <a href="http://mailman.mit.edu/mailman/listinfo/starcluster" target="_blank">http://mailman.mit.edu/mailman/listinfo/starcluster</a><br>
>><br>
>><br>
><br>
><br>
> _______________________________________________<br>
> StarCluster mailing list<br>
> <a href="mailto:StarCluster@mit.edu">StarCluster@mit.edu</a><br>
> <a href="http://mailman.mit.edu/mailman/listinfo/starcluster" target="_blank">http://mailman.mit.edu/mailman/listinfo/starcluster</a><br>
><br>
<br>
<br>
<br>
</div></div><span class="HOEnZb"><font color="#888888">--<br>
==================================================<br>
Open Grid Scheduler - The Official Open Source Grid Engine<br>
<a href="http://gridscheduler.sourceforge.net/" target="_blank">http://gridscheduler.sourceforge.net/</a><br>
</font></span></blockquote></div><br>