[Clusterusers] compute-1-1

Lee Spector lspector at hampshire.edu
Mon Aug 11 11:10:11 EDT 2014


I nimbyed 17 and 18. 17 sjould still be running my thing nut 18 os done

Sent from my phone

> On Aug 11, 2014, at 9:15 AM, "Wm. Josiah Erikson" <wjerikson at hampshire.edu> wrote:
> 
> I also un-NIMBYed 1-12, 1-16, and 1-17, because I figured that's why they were NIMBYed. Perhaps I'm wrong. Why is 1-18 NIMBYed?
>    -Josiah
> 
> 
>> On 8/11/14 9:11 AM, Wm. Josiah Erikson wrote:
>> Possibly - it's got 8 cores, appears to be running 3 jobs currently, and claims to have 8 slots, which is probably silly. I'll reduce it (and the other 8-core nodes in rack 1) to 4 slots.
>>    -Josiah
>> 
>> 
>>> On 8/7/14 2:36 PM, Thomas Helmuth wrote:
>>> Hi Josiah,
>>> 
>>> I've recently noticed that when I start runs on compute-1-1, often some of the runs take forever to start, while others start just fine. It makes me wonder if something is going on, such as having more slots marked as available than it really can handle.
>>> 
>>> Thanks!
>>> Tom
> 
> -- 
> 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


More information about the Clusterusers mailing list