Where does this load come from?

From: Jurgen Kramer (gtm.kramer_at_inter.nl.net)
Date: 02/28/04

  • Next message: Con Kolivas: "Re: sched domains kernbench improvements" 
    To: linux-kernel@vger.kernel.org
Date:	Sat, 28 Feb 2004 13:27:47 +0100

    Hi,

    I am seeing some strange load figures on my P4 Celeron based system
    which I cannot explain. There always seem to be some load while there
    are no real apps running. Stopping all daemons doesn't seem to effect
    things at all.

    Output from top with 2.6.4-rc1:

     13:16:38 up 38 min, 1 user, load average: 1.67, 1.74, 1.57
    62 processes: 59 sleeping, 3 running, 0 zombie, 0 stopped
    CPU states: 47.5% user 52.4% system 0.0% nice 0.0% iowait 0.0%
    idle
    Mem: 515552k av, 93544k used, 422008k free, 0k shrd, 10980k
    buff
            49632k active, 29284k inactive
    Swap: 265064k av, 0k used, 265064k free 59836k
    cached

    Is this a real problem or is top screwing things up here? 0.0% idle
    doesn't seem right as for the load average. This system runs on RH9.

    Compared to my P4 HT system running 2.6.4-rc1 on Fedore Core-1:

     13:17:42 up 30 min, 5 users, load average: 0.12, 0.63, 0.64
    91 processes: 90 sleeping, 1 running, 0 zombie, 0 stopped
    CPU states: cpu user nice system irq softirq iowait idle
               total 1.2% 0.0% 0.4% 0.0% 0.0% 0.0% 198.0%
               cpu00 0.9% 0.0% 0.1% 0.0% 0.0% 0.0% 98.8%
               cpu01 0.1% 0.0% 0.3% 0.0% 0.0% 0.0% 99.4%
    Mem: 1034456k av, 433712k used, 600744k free, 0k shrd, 26496k
    buff
           239752k active, 152112k inactive
    Swap: 787176k av, 0k used, 787176k free 290452k
    cached

    This looks more like it.

    What can be the problem here (if there is a real problem)?

    Jurgen

    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  • Next message: Con Kolivas: "Re: sched domains kernbench improvements"

    Relevant Pages