Re: Status of the IO scheduler fixes for 2.4
Chris Mason (email@example.com)
03 Jul 2003 08:01:55 -0400
On Thu, 2003-07-03 at 06:58, Stephan von Krawczynski wrote:
> On 02 Jul 2003 22:02:07 -0400
> Chris Mason <firstname.lastname@example.org> wrote:
> > [...]
> > Nick would like to see a better balance of throughput/fairness, I wimped
> > out and went for the userspace toggle instead because I think anything
> > else requires pulling in larger changes from 2.5 land.
> I have a short question on that: did you check if there are any drawbacks on
> network performance through this? We had a phenomenon here with 2.4.21 with
> both samba and simple ftp where network performance dropped to a crawl when
> simply entering "sync" on the console. Even simple telnet-sessions seemed to be
> affected. As we could not create a reproducable setup I did not talk about this
> up to now, but I wonder if anyone else ever checked that out ...
It's possible the network programs involved are actually getting stuck
in atime updates somewhere. A decoded sysrq-t during one of the stalls
would help find the real cause.
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to email@example.com
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/