Re: [PATCH 2/7] sched: Add NEED_RESCHED to the preempt_count

[Andy Lutomirski]

On Wed, Sep 11, 2013 at 11:05 AM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> On Wed, Sep 11, 2013 at 09:35:08AM -0700, Andy Lutomirski wrote:
>> I bet that this improves cross-cpu wakeup latency, too -- the old code
>> would presumably wake up the cpu and then immediately interrupt it.
>
> Yeah,. its what clued Mike in to there being a problem.
>
>> It might be nice to rename one or both of need_resched and
>> test_need_resched, though -- the difference is somewhat inscrutable.
>
> I agreed, I've just been unable to come up with anything sane.
>
> The best I could come up with is renaming
> {set,clear,test}_need_resched() to {}_tif_need_resched(), so we then end
> up with test_tif_need_resched(), which is slightly more different from
> need_resched().

Nothing great.  That's at least better than the current state, I think.

--Andy
--
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/