[Swift-devel] Re: Request for control over throttle algorithm

[Ian Foster]

I seem no reason to assume that our understanding will not advance as we 
study more cases.

Mihael Hategan wrote:
> On Mon, 2007-08-27 at 20:04 -0500, Ian Foster wrote:
>   
>> These are good questions: where do different things belong.
>>
>> Working out the right approach in this specific example will surely 
>> provide insights into how to do things in other cases.
>>     
>
> Will it? The exact same statement could have been made when such
> "concepts" were put into cog/karajan, or when Yong figured out specific
> numbers (and on all the occasions that have worked to build up to what
> we have today).
>
>   
>> Ian.
>>
>> Ben Clifford wrote:
>>     
>>> it seems superficially to say "we shouldn't be forcing our execution 
>>> management semantics on the underlying execution system"; which perhaps 
>>> means both that we shouldn't be rate limiting but also that we shouldn't 
>>> be doing retries and things like that - we either expect someone else to 
>>> deal with this stuff or we do it ourselves.
>>>
>>>   
>>>       
>
>   

-- 

   Ian Foster, Director, Computation Institute
Argonne National Laboratory & University of Chicago
Argonne: MCS/221, 9700 S. Cass Ave, Argonne, IL 60439
Chicago: Rm 405, 5640 S. Ellis Ave, Chicago, IL 60637
Tel: +1 630 252 4619.  Web: www.ci.uchicago.edu.
      Globus Alliance: www.globus.org.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/swift-devel/attachments/20070828/c4c9c0a0/attachment.html>