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

[Srivatsa Vaddagiri]

* Peter Zijlstra <peterz@xxxxxxxxxxxxx> [2012-06-04 17:33:34]:

> Now I'm not as opposed to this as Mike is, the load cpu_power thing can
> also happen due to excessive IRQ time,

Yes good point.

> Thing is, you can create an arbitrary hard problem by creating lots of
> tasks with tricky masks, we shouldn't bend over backwards trying to
> solve it just because.

Agreed. The change proposed here however seems simple enough to warrant
consideration?

> [ Also, I suspect I wrecked the ALL_PINNED muck, shouldn't we reset
> env.loop_break? ]

Yeah I think so. That was one of the bug we had in first version of the
patch (where we had not reset loop_break and redo was failing to pull task 
because of that).

- vatsa

--
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/