Re: Regression seen for patch "sched:dont decrease idle sleep avg"
From: Ray Lee
Date: Wed May 17 2006 - 13:21:17 EST
On 5/17/06, Con Kolivas <kernel@xxxxxxxxxxx> wrote:
> Ok, I'll accept that. Spits and stutters _are_ interactivity issues
> though yes?. Knowing full well that plunking long sleepers into the
> queue you are plunking them into causes spits and stutters, why do you
> insist on doing so?
Because I know of no real world workload that thuds us into spits and
`apt-get dist-upgrade` seems to do wonders for making a system
thoroughly unusable. Possibly because it forks a copy of perl and a
few other tasks, all competing for CPU and disk I/O bandwidth -- at
least, competing when they're not sleeping most of the time. Y'all
might add a chroot'd install of Debian as a test case.
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/