We have found some performance regressions (e.g. SPECjbb) with the
scheduler on a large IA-64 NUMA machine, and we are debugging it. On SMP
machines, we haven't seen performance regressions.
Jun
>-----Original Message-----
>From: Andi Kleen [mailto:[email protected]]
>Sent: Wednesday, March 24, 2004 8:56 PM
>To: Ingo Molnar
>Cc: [email protected]; [email protected];
[email protected];
>[email protected]; [email protected]; Nakajima, Jun;
>[email protected]; [email protected]; [email protected];
>[email protected]
>Subject: Re: [Lse-tech] [patch] sched-domain cleanups,
sched-2.6.5-rc2-mm2-
>A3
>
>On Thu, 25 Mar 2004 09:28:09 +0100
>Ingo Molnar <[email protected]> wrote:
>
>> i've reviewed the sched-domains balancing patches for upstream
inclusion
>> and they look mostly fine.
>
>The main problem it has is that it performs quite badly on Opteron NUMA
>e.g. in the OpenMP STREAM test (much worse than the normal scheduler)
>
>-Andi
> We have found some performance regressions (e.g. SPECjbb) with the
> scheduler on a large IA-64 NUMA machine, and we are debugging it. On SMP
> machines, we haven't seen performance regressions.
Is this the SPECjbb / Java thing that believes that sched_yield is a
stable locking primitive? If so, it needs to be ignored ;-) That's
the problem we had here, at least ...
M.
> Jun
>
>> -----Original Message-----
>> From: Andi Kleen [mailto:[email protected]]
>> Sent: Wednesday, March 24, 2004 8:56 PM
>> To: Ingo Molnar
>> Cc: [email protected]; [email protected];
> [email protected];
>> [email protected]; [email protected]; Nakajima, Jun;
>> [email protected]; [email protected]; [email protected];
>> [email protected]
>> Subject: Re: [Lse-tech] [patch] sched-domain cleanups,
> sched-2.6.5-rc2-mm2-
>> A3
>>
>> On Thu, 25 Mar 2004 09:28:09 +0100
>> Ingo Molnar <[email protected]> wrote:
>>
>>> i've reviewed the sched-domains balancing patches for upstream
> inclusion
>>> and they look mostly fine.
>>
>> The main problem it has is that it performs quite badly on Opteron NUMA
>> e.g. in the OpenMP STREAM test (much worse than the normal scheduler)
>>
>> -Andi
>
>