Re: 2.6.21-rc1: known regressions (v2) (part 2)

[Con Kolivas]

On Thursday 01 March 2007 22:33, Thomas Gleixner wrote:
> On Thu, 2007-03-01 at 22:13 +1100, Con Kolivas wrote:
> > > if then there should be a mechanism /in the hardware/ to set the
> > > priority of a CPU - and then the hardware could decide how to
> > > prioritize between siblings. Doing this in software is really hard.
> >
> > And that's the depressing part because of course I was interested in that
> > as the original approach to the problem (and it was a big problem). When
> > I spoke to Intel and AMD (of course to date no SMT AMD chip exists) at
> > kernel summit they said it was too hard to implement hardware priorities
> > well. Which is real odd since IBM have already done it with Power...
> >
> > Still I think it has been working fine in software till now, but now it
> > has to deal with the added confusion of dynticks, so I already know what
> > will happen to it.
>
> Well, it's not a dyntick problem in the first place. Even w/o dynticks
> we go idle with local_softirq_pending(). Dynticks contains an explicit
> check for that, which makes it visible.

Oops I'm sorry if I made it sound like there's a dynticks problem. That was 
not my intent and I said as much in an earlier email. Even though I'm finding 
myself defending code that has already been softly tagged for redundancy, 
let's be clear here; we're talking about at most a further 70ms delay in 
scheduling a niced task in the presence of a nice 0 task, which is a 
reasonable delay for ksoftirqd which we nice the eyeballs out of in mainline. 
Considering under load our scheduler has been known to cause scheduling 
delays of 10 seconds I still don't see this as a bug. Dynticks just "points 
it out to us".

-- 
-ck
-
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/