[Beowulf] Problems with Dell M620 and CPU power throttling

[Bill Wichser]

One week ago, on Tuesday September 10, we had a system downtime for some 
work on our central filesystem. During that outage we decided to not 
only power of the nodes but to also power off the chassis across 10 
racks of these blades.

Every day we check the systems by running a "stress" benchmark and 
checking the CPU speeds with "turbostat" and every day we find that the 
cores are all exceeding the 2.6GHz E5-2670 rating, mostly settling in at 
3.0 GHz (with turbo mode enabled).  Every day I wait to find that things 
have again degraded but have been happily surprised.

If we get through a whole month then I would say that after all the 
firmware and iDrac and CMC updates that a chassis power cycle is the 
answer.  But tomorrow I will look again and hopefully be happily 
surprised for one more day.

Bill

On 9/17/2013 8:06 PM, Richard Hickey wrote
> You are not alone in seeing this. We discovered it via by some of our
> weather codes running slow. A co-worker started running single node Linpack
> runs and we saw individual nodes running slow. A reboot did not fix,
> however a power cycle did. We can see a 2 to 3 fold increase in
> performance.
>
>
>
> We found that you could either do a physical reseat of the blade, or a
> logical one through the cmc command line. Either way fixes the problem
> temporarily.
>
>
>
> It's good to see that someone else is seeing this. Well, maybe not good,
> but at least we're not the only ones fighting this.
>
>   
>
>
>
> Rich
>
>
>
>
>
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
>
>