Re: weakness of runnable load tracking?

[Alex Shi <alex.shi@intel.com>]

On 12/06/2012 05:12 PM, Mike Galbraith wrote:
> On Thu, 2012-12-06 at 16:06 +0800, Alex Shi wrote: 
>>>>
>>>> Hi Paul & Ingo:
>>>>
>>>> In a short word of this issue: burst forking/waking tasks have no time
>>>> accumulate the load contribute, their runnable load are taken as zero.
>>>> that make select_task_rq do a wrong decision on which group is idlest.
>>>
>>> As you pointed out above, new tasks can (and imho should) be born with
>>> full weight.  Tasks _may_ become thin, but they're all born hungry.
>>
>> Thanks for comments. I think so. :)
>>>
>>>> There is still 3 kinds of solution is helpful for this issue.
>>>>
>>>> a, set a unzero minimum value for the long time sleeping task. but it
>>>> seems unfair for other tasks these just sleep a short while.
>>>>
>>>> b, just use runnable load contrib in load balance. Still using
>>>> nr_running to judge idlest group in select_task_rq_fair. but that may
>>>> cause a bit more migrations in future load balance.
>>>>
>>>> c, consider both runnable load and nr_running in the group: like in the
>>>> searching domain, the nr_running number increased a certain number, like
>>>> double of the domain span, in a certain time. we will think it's a burst
>>>> forking/waking happened, then just count the nr_running as the idlest
>>>> group criteria.
>>>>
>>>> IMHO, I like the 3rd one a bit more. as to the certain time to judge if
>>>> a burst happened, since we will calculate the runnable avg at very tick,
>>>> so if increased nr_running is beyond sd->span_weight in 2 ticks, means
>>>> burst happening. What's your opinion of this?
>>>>
>>>> Any comments are appreciated!
>>>
>>> IMHO, for fork and bursty wake balancing, the only thing meaningful is
>>> the here and now state of runqueues tasks are being dumped into.
>>>
>>> Just because tasks are historically short running, you don't necessarily
>>> want to take a gaggle and wedge them into a too small group just to even
>>> out load averages.  If there was a hole available that you passed up by
>>> using average load, you lose utilization.  I can see how this load
>>> tracking stuff can average out to a win on a ~heavily loaded box, but
>>> bursty stuff I don't see how it can do anything but harm, so imho, the
>>> user should choose which is best for his box, instantaneous or history.
>>
>> Do you mean the system administrator need to do this choice?
> 
> That's my gut feeling just from pondering potential pitfalls.
> 
>> It's may a hard decision.  :)
> 
> Yup, very hard.
> 
>> Any suggestions of decision basis?
> 
> Same as most buttons.. poke it and <cringe> see what happens :) 

:D
> 
>>> WRT burst detection: any window you define can be longer than the burst.
>>
>> Maybe we can define 2 waking on same cpu in 1 tick is a burst happened,
>> and if the cpu had taken a waking task. we'd better skip this cpu. :)
>> Anyway, the hard point is we can not predict future.
> 
> No matter what the metric, you'll be reacting after the fact.
> 
> Somebody needs to code up that darn omniscience algorithm.  In a pinch,
> a simple undo the past will suffice :)

Yes. I see.
> 
> -Mike
> 


-- 
Thanks
    Alex