[Clusterusers] Stress-testing the cluster tonight

Wm. Josiah Erikson wjerikson at hampshire.edu
Sat May 31 08:51:03 EDT 2014


This was that eth2 problem. I hope the kernel update I just did will 
keep it from happening again... but the kernel parameter line I added 
before was supposed to fix it even without the kernel update. Keep your 
finger crossed...
     -Josiah

On 5/30/14 5:06 PM, Bassam Kurdali wrote:
> Hmm, maybe fly is having problems as a result? tractor just 'went away'
> I can still SSH into fly though, is there anything I can do to restart
> tractor , otherwise we are down for a week :(
> On Thu, 2014-05-29 at 23:05 -0400, Wm. Josiah Erikson wrote:
>> I am ferreting out any weak nodes by running dnetc on anything that
>> isn't doing anything else. My goal is to get rid of/fix any nodes that
>> are not reliable. Please let me know if you feel like this is causing
>> any problems for you. I will stop this tomorrow morning - it's just
>> overnight, as I'm going on vacation for a week starting Saturday. My
>> tentative belief at this point is that all of the nodes are fully
>> functional and reliable.... testing that belief :)
>>
>
> _______________________________________________
> Clusterusers mailing list
> Clusterusers at lists.hampshire.edu
> https://lists.hampshire.edu/mailman/listinfo/clusterusers

-- 
-----
Wm. Josiah Erikson
Head, Systems and Networking
Hampshire College
Amherst, MA 01002



More information about the Clusterusers mailing list