RE: Scheduling problem with 2.4?

[Mike Galbraith]

At 10:55 AM 5/18/2003 +0200, Mike Galbraith wrote:
>At 05:16 PM 5/17/2003 -0700, David Schwartz wrote:
>
>>         I suggest that a process be permitted to use up at least some 
>> portion of
>>its timeslice exempt from any pre-emption based solely on dynamic
>>priorities.
>
>
>Is there any down-side to not preempting quite as often?  It seems like 
>there should be a bandwidth gain.

(my reply was supposed to be off-list, but..)

The answer appears to be yes, there are down-sides.  Instead of the 
expected throughput gain, I got a loss :-/  which makes sense from the 
cache side I suppose.  While it was instant gratification for the pipe 
testcase, as a general solution it leaves something to be desired... at 
least when implemented in it's simplest form  Oh well.

(hmm.. maybe I should go stare at the cache decay stuff some more.  later)

         -Mike