[mpich-discuss] Hydra issues

[Scott Atchley]

On Aug 26, 2009, at 3:58 PM, Dave Goodell wrote:

> On Aug 26, 2009, at 2:45 PM, Scott Atchley wrote:
>
>> On Aug 26, 2009, at 3:39 PM, Pavan Balaji wrote:
>>
>>>>> However you could use one of the various workarounds for this,  
>>>>> such as an LD_PRELOADed setvbuf call: http://lists.gnu.org/archive/html/bug-coreutils/2008-11/msg00164.html
>>>> This does not change the behavior.
>>>> I am still stumped as to why there is no delay when using  
>>>> persistent (launch-mode=2) versus a delay with no proxies (launch- 
>>>> mode=1).
>>>
>>> This works for me. We need to figure out how to make this portable  
>>> now.
>>>
>>> -- Pavan
>>
>> Thanks for your persistence (no pun intended).
>>
>> When running with 1,024 ranks, launching via MPD can take several  
>> minutes. I am assuming that hydra will launch in seconds.
>
> MPD launches shouldn't be that slow in 1.1.1p1, at least for most  
> common process layouts.  Are you still seeing slow MPD launches with  
> 1.1.1p1 (as opposed to 1.1.0)?
>
> -Dave

Yes. A customer and I were running tests over 128 nodes with 8 ppn. I  
will have access to another cluster next week to test more. We were  
running IMB allgatherv so it requires all processes to connect up.

Scott