[Clusterusers] compute-1-18 and 1-3

[Lee Spector]

Thanks,

I'll just let Eva's runs keep going for the moment.

 -Lee



> On Jan 31, 2017, at 11:33 AM, Wm. Josiah Erikson <wjerikson at hampshire.edu> wrote:
> 
> ah OK - yeah it wasn't running tractor so that's why. Unfortunately I
> just screwed that up for you. Compute-1-18 is one of the faster nodes,
> so you chose well. Four of Eva's jobs just got dispatched to that node,
> but I think if you "eject and reschedule" them, it probably won't screw
> things up for her? I have already NIMBYed the node. Sorry about that!
> 
> If you need me to do that because it says you don't have permission, let
> me know.
> 
>    -Josiah
> 
> 
> 
> On 1/31/17 11:23 AM, Lee Spector wrote:
>> Thanks Josiah,
>> 
>> FWIW I'm currently and for the last few days running jobs via ssh on compute-1-18... and it seems to have been working fine.
>> 
>> If you'd rather that I use another node then let me know. I chose it more or less at random, but I think it was lightly loaded when I did so... maybe because of the reboot?
>> 
>> Ideally I'd use the fastest nodes available for these "manual" runs, and dabbling on rack 4 leads me to believe that the nodes with large numbers of cores are a bad idea for this.
>> 
>> -Lee
>> 
>>> On Jan 31, 2017, at 11:10 AM, Wm. Josiah Erikson <wjerikson at hampshire.edu> wrote:
>>> 
>>> These two nodes weren't running tractor - they had rebooted themselves
>>> and reinstalled. Compute-1-18 5 days, 11:39 uptime and compute-1-3 1
>>> day, 5:18. Not sure why - neither has anything in the logs nor shows
>>> anything particularly suspicious in ganglia. I have restarted tractor
>>> and noted this occurrance to see if it's a pattern or random. Sometimes
>>> some jobs do just trigger random reboots if they randomly use up all the
>>> RAM, invoking the oom-killer, but usually that will leave something in
>>> the logs.
>>> 
>>> 
>>> -- 
>>> Wm. Josiah Erikson
>>> Assistant Director of IT, Infrastructure Group
>>> System Administrator, School of CS
>>> Hampshire College
>>> Amherst, MA 01002
>>> (413) 559-6091
>>> 
>>> _______________________________________________
>>> Clusterusers mailing list
>>> Clusterusers at lists.hampshire.edu
>>> https://lists.hampshire.edu/mailman/listinfo/clusterusers
>> --
>> Lee Spector, Professor of Computer Science
>> Director, Institute for Computational Intelligence
>> Hampshire College, Amherst, Massachusetts, USA
>> lspector at hampshire.edu, http://hampshire.edu/lspector/, 413-559-5352
>> 
>> _______________________________________________
>> Clusterusers mailing list
>> Clusterusers at lists.hampshire.edu
>> https://lists.hampshire.edu/mailman/listinfo/clusterusers
> 
> -- 
> Wm. Josiah Erikson
> Assistant Director of IT, Infrastructure Group
> System Administrator, School of CS
> Hampshire College
> Amherst, MA 01002
> (413) 559-6091
> 
> _______________________________________________
> Clusterusers mailing list
> Clusterusers at lists.hampshire.edu
> https://lists.hampshire.edu/mailman/listinfo/clusterusers

--
Lee Spector, Professor of Computer Science
Director, Institute for Computational Intelligence
Hampshire College, Amherst, Massachusetts, USA
lspector at hampshire.edu, http://hampshire.edu/lspector/, 413-559-5352