Re: [PATCH] sched: balance_cpu to consider other cpus in its group as target of (pinned) task migration

[Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>]

* Mike Galbraith <efault@gmx.de> [2012-06-04 16:30:34]:

> Yeah, this is true, it is a latency source and a fairness violation.
> Slow path balance consideration does make some sense to me.
> 
> But, if you have an RT requirement, you can't afford to mix unknown
> entities, nor over-commit etc.  A realtime application will assign all
> resources, so the load balancer becomes essentially unemployed.  No?
> Non critical worker-bees may be allowed to bounce around in say a
> cpuset, but none of the CPUs which do critical work will ever be
> over-committed, else application just lost the war.  In that regard,
> twiddling the load balancer to accommodate strange sounding case still
> seems wrong to me.

Btw the patch should help non-rt case as well (where a high
priority SCHED_OTHER is hogging cpu while low-priority SCHED_OTHER task
on that same cpu suffers as we choose not to move it to another
cpu (because of the way balance_cpu based load balance is written).

- vatsa