Re: [PATCH] sched: wakeup buddy

[Michael Wang <wangyun@linux.vnet.ibm.com>]

On 03/08/2013 04:26 PM, Mike Galbraith wrote:
> On Fri, 2013-03-08 at 15:30 +0800, Michael Wang wrote: 
>> On 03/08/2013 02:44 PM, Mike Galbraith wrote:
> 
>>> In general, I think things would work better if we'd just rate limit how
>>> frequently we can wakeup migrate each individual task.  
>>
>> Isn't the wakeup buddy already limit the rate? and by turning the knob,
>> we could change the rate on our demand.
> 
> I was referring to the existing kernel, not as altered. 
> 
>> We want
>>> jabbering tasks to share L3, but we don't really want to trash L2 at an
>>> awesome rate.
>>
>> I don't get it..., it's a task which has 'sleep' for some time, unless
>> there is no task running on prev_cpu when it's sleeping, otherwise
>> whatever the new cpu is, we will trash L2, isn't it?
> 
> I'm thinking if you wake it to it's old home after a microscopic sleep,
> it has a good chance of evicting the current resident, rescuing its L2.
> If tasks which do microscopic sleep can't move around at a high rate,
> they'll poke holes in fewer preempt victims.  If they're _really_ fast
> switchers, always wake affine.  They can't hurt much, they don't do much
> other than schedule off.

I get your point, it's about the task which sleep frequently for a very
short time, you are right, keep them around prev_cpu could gain some
benefit.

There are still many factors need to be considered, for example, if the
cpu around prev_cpu are busier than those around curr_cpu, then pull
from prev to curr still likely to be a good choice...for the consider of
future.

Also for sure, that depends on what's the workload in the system, and
how they cooperate with each other.

IMHO, I think wakeup buddy is a compromising solution for this case,
before we could figure out the correct formular (and a efficient way to
collect all the info we rely on), such a flexible optimization is not bad.

Regards,
Michael Wang

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