RE: [Lse-tech] [patch] sched-domain cleanups, sched-2.6.5-rc2-mm2-A3

[Martin J. Bligh]

> 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:ak@xxxxxxx]
>> Sent: Wednesday, March 24, 2004 8:56 PM
>> To: Ingo Molnar
>> Cc: piggin@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx;
> akpm@xxxxxxxx;
>> kernel@xxxxxxxxxxx; rusty@xxxxxxxxxxxxxxx; Nakajima, Jun;
>> ricklind@xxxxxxxxxx; anton@xxxxxxxxx; lse-tech@xxxxxxxxxxxxxxxxxxxxx;
>> mbligh@xxxxxxxxxxx
>> 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 <mingo@xxxxxxx> 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
> 
> 


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/