Re: Soft-Lockup/Race in networking in 2.6.31-rc1+195 ( possibly?caused by netem)

[Andres Freund]

On Monday 06 July 2009 18:31:06 Jarek Poplawski wrote:
> On Mon, Jul 06, 2009 at 06:13:29PM +0200, Andres Freund wrote:
> > > > Btw, I ran netem with delay for more than 48h on around 80mbit...
> > > > That does  not exclude such a rarely triggered race, but makes it a
> > > > bit more unlikely. (With migration thats around 3sec or so)
> > Sorry once more.
> Andres, the bisection + the above - you did 'the whole lotta work' and
> you shouldn't be sorry at all! ;-)
To be fair I have to admit I did run netem for 48hours for other reasons ;-)
I also ran my modified netem, but all it currently does is adjusing 
delay/jitter by other means, so that should have no influence.
I am trying to produce artificial loss patterns similar to really occuring 
network loss.

I just switched mail client btw ;-)

ATM I have no further ideas except maybe trying different timers or a lower 
timer resolution?

Andres
--
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/