[Beowulf] Problems with Dell M620 and CPU power throttling

[Richard Hickey]

Bill Wichser <bill <at> princeton.edu> writes:



> 

> Since January, when we installed an M620 Sandybridge cluster from Dell, 

> we have had issues with power and performance to compute nodes.  Dell 

> apparently continues to look into the problem but the usual responses 

> have provided no solution.  Firmware, BIOS, OS updates all are fruitless.

> 

> The problem is that the node/CPU is power capped.  We first detected 

> this with the STREAM benchmark, a quick run, which shows memory 

> bandwidth around 2000 instead of the normal 13000 MB/s.  When the CPU is 

> in the C0 state, this drops to around 600.

> 

> The effect appears randomly across the entire cluster with 5-10% of the 

> nodes demonstrating some slower performance.  We don't know what 

> triggers this.  Using "turbostat" we can see that the GHz of the cores 

> is >= 1 in most cases, dropping to about 0.2 in some of the worst cases. 

>   Looking at the power consumption by either the chassis GUI or using 

> "impitool sdr list" we see that there is only about 80 watts being used.

> 

> We run the RH 6.x release and are up to date with kernel/OS patches. 

> All firmware is up to date.  Chassis power is configured as 

> non-redundant.  tuned is set for performance.  Turbo mode is 

> on/hyperthreading is off/performance mode is set in BIOS.

> 

> A reboot does not change this problem.  But a power cycle returns the 

> compute node to normal again.  Again, we do not know what triggers this 

> event.  We are not overheating the nodes.  But while applications are 

> running, something triggers an event where this power capping takes 
effect.

> 

> At this point we remain clueless about what is causing this to happen. 

> We can detect the condition now and have been power cycling the nodes in 

> order to reset.

> 

> If anyone has a clue, or better yet, solved the issue, we'd love to hear 

> the solution!

> 

> Thanks,

> Bill

> 





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