From owner-freebsd-stable  Mon Dec  1 19:17:49 1997
Return-Path: <owner-freebsd-stable>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.7/8.8.7) id TAA19749
          for stable-outgoing; Mon, 1 Dec 1997 19:17:49 -0800 (PST)
          (envelope-from owner-freebsd-stable)
Received: from kinclaith.pdl.cs.cmu.edu (KINCLAITH.PDL.CS.CMU.EDU [128.2.189.18])
          by hub.freebsd.org (8.8.7/8.8.7) with SMTP id TAA19733
          for <freebsd-stable@freebsd.org>; Mon, 1 Dec 1997 19:17:46 -0800 (PST)
          (envelope-from dpetrou@KINCLAITH.PDL.CS.CMU.EDU)
Message-Id: <199712020317.TAA19733@hub.freebsd.org>
Subject: RE: CPU Load
To: freebsd-stable@freebsd.org
Date: Mon, 1 Dec 1997 22:17:39 -0500 (EST)
From: David Petrou <dpetrou@KINCLAITH.PDL.CS.CMU.EDU>
X-Mailer: ELM [version 2.4 PL25-40]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: owner-freebsd-stable@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

It seems that there's a lot of misinformation being posted here re:
cpu load.  Just look at the relevant code from vm/vm_meter.c:

static void
loadav(struct loadavg *avg)
{
        register int i, nrun;
        register struct proc *p;

        for (nrun = 0, p = allproc.lh_first; p != 0; p = p->p_list.le_next) {
                switch (p->p_stat) {
                case SSLEEP:
                        if (p->p_priority > PZERO || p->p_slptime != 0)
                                continue;
                        /* fall through */
                case SRUN:
                case SIDL:
                        nrun++;
                }
        }
        for (i = 0; i < 3; i++)
                avg->ldavg[i] = (cexp[i] * avg->ldavg[i] +
                    nrun * FSCALE * (FSCALE - cexp[i])) >> FSHIFT;
}

The important part is nrun...  If a process is in SRUN or SIDL or it
has a higher priority (lower numerically) than PZERO _AND_ it has
slept less than a second, the process is counted.  (That last clause
covers fast disk operations...)

David