Re: [RFC PATCH v2] sched: Limit idle_balance()

[Peter Zijlstra <peterz@infradead.org>]

On Tue, Jul 23, 2013 at 04:36:46PM +0530, Srikar Dronamraju wrote:

> May be the current max value is a limiting factor, but I think there
> should be a limit to the maximum value. Peter and Ingo may help us
> understand why they limited to the 1ms. But I dont think we should
> introduce a new variable just for this.

/me blames it all on Mike.. I tried to remember why he did that, but
alas.

> If idle balance did succeed, then it means that the system was indeed
> imbalanced. So idle balance was the right thing to do. May be we chose
> the wrong task to pull. May be after numa balancing enhancements go in,
> we pick a better task to pull atleast across nodes. And there could be
> other opportunities/strategies to select a right task to pull.
> 
> Again, schedstats during the application run should give us hints here.

Not necessarily so, IIRC the newidle idx is 0 which means that its very
aggressive at pulling load, there might not actually be an imbalance
with higher idx averages.

> I was saying it the other way. 
> your suggestion is to run idle balance once in n runs .. where n is 10
> to 20. 
> My thinking was to not run idle balance once in n unsuccessful runs. 

I think you're talking past each other. Each having a different N :-)