From owner-freebsd-questions@FreeBSD.ORG Mon Jun 16 14:21:44 2003 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3B9F237B401 for ; Mon, 16 Jun 2003 14:21:44 -0700 (PDT) Received: from pcwin002.win.tue.nl (pcwin002.win.tue.nl [131.155.71.72]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4035543F93 for ; Mon, 16 Jun 2003 14:21:43 -0700 (PDT) (envelope-from stijn@pcwin002.win.tue.nl) Received: from pcwin002.win.tue.nl (localhost [127.0.0.1]) by pcwin002.win.tue.nl (8.12.9/8.12.9) with ESMTP id h5GLLuKX077314; Mon, 16 Jun 2003 23:21:56 +0200 (CEST) (envelope-from stijn@pcwin002.win.tue.nl) Received: (from stijn@localhost) by pcwin002.win.tue.nl (8.12.9/8.12.9/Submit) id h5GLLtwU077313; Mon, 16 Jun 2003 23:21:55 +0200 (CEST) Date: Mon, 16 Jun 2003 23:21:55 +0200 From: Stijn Hoop To: Chuck Swiger Message-ID: <20030616212155.GL49234@pcwin002.win.tue.nl> References: <20030616141153.GH49234@pcwin002.win.tue.nl> <3EEDFC3F.20703@mac.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="DN8g+DOX2TxGxleI" Content-Disposition: inline In-Reply-To: <3EEDFC3F.20703@mac.com> User-Agent: Mutt/1.4.1i X-Bright-Idea: Let's abolish HTML mail! cc: freebsd-questions@freebsd.org Subject: Re: got load > 1 but no CPU state is showing? X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 16 Jun 2003 21:21:44 -0000 --DN8g+DOX2TxGxleI Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Jun 16, 2003 at 01:19:59PM -0400, Chuck Swiger wrote: > Stijn Hoop wrote: > > On a lightly loaded server top is misbehaving: it continuously shows all > > CPU states at 0.0% yet my load varies from 0.50 to about 3. Is there > > any explanation for this? >=20 > Maybe. :-) I was going to say that on fast machines, it's not unusual f= or=20 > processes which start up and then finish quickly to go away before top=20 > "sees" them, but you still see the effect in the aggregate system load. = =20 Yes, that was wat I was babbling about wrt "syncing". > However, that doesn't explain this line: >=20 > > CPU states: 0.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 0.0= %=20 > idle >=20 > Clutching at straws, maybe top can't read /dev/kmem or something? > Try doing a "MAKEDEV all" in /dev... A reboot solved my problems -- while examining this phenomenon PostgreSQL came to a halt and wouldn't restart due to a lack of available shared memor= y, although ipcs(1) didn't show any active handles. Since I needed the database server, I had to reboot. I suspect something hardwarish though, I've never seen this kind of weird behaviour before. --Stijn --=20 The rain it raineth on the just And also on the unjust fella, But chiefly on the just, because The unjust steals the just's umbrella. --DN8g+DOX2TxGxleI Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.2 (FreeBSD) iD8DBQE+7jTzY3r/tLQmfWcRAkFzAJ9l9LycSjA7Za/cNpXfzOgFXo23YACgni0E vLUwI6tB5Q3aF8ZBswUZyl8= =ovli -----END PGP SIGNATURE----- --DN8g+DOX2TxGxleI--