Messages in this thread | | | Date | Mon, 7 Dec 1998 23:59:04 +0100 (CET) | From | Rik van Riel <> | Subject | Re: 2.1.131: Strange percent idle time measurement |
| |
On Mon, 7 Dec 1998, Pavel Machek wrote:
> > Some questions arise: > > > > 1. 101% is obviously wrong and should never be reported. > > Is this a "top" thing, or a number reported by the kernel? > > Top is so broken that it does not surprise me.
We should get some volunteer to rewrite top so that it uses the time stats from /proc/stat instead of doing expensive calculations to produce stats full of errors itself :)
> > 2. The idle time shows some interesting jumps. > > I'd expect 0% all the time. Is this top's calculations again? > > It can be exited proces. If proces exits before top can see it, its > time will be reported as idle. This can be easily seen while compiling > with kernel (top reports up-to 50% free cupu when in fact there's no > free cpu...).
Using top and vmstat together on different terminals will show this effect beautifully :)
cheers,
Rik -- the flu hits, the flu hits, the flu hits -- MORE +-------------------------------------------------------------------+ | Linux memory management tour guide. H.H.vanRiel@phys.uu.nl | | Scouting Vries cubscout leader. http://www.phys.uu.nl/~riel/ | +-------------------------------------------------------------------+
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |