From owner-freebsd-questions@FreeBSD.ORG Sat Nov 11 06:33:23 2006 Return-Path: X-Original-To: freebsd-questions@freebsd.org 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 81A1016A412 for ; Sat, 11 Nov 2006 06:33:23 +0000 (UTC) (envelope-from kris@obsecurity.org) Received: from elvis.mu.org (elvis.mu.org [192.203.228.196]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1E7BA43D60 for ; Sat, 11 Nov 2006 06:33:23 +0000 (GMT) (envelope-from kris@obsecurity.org) Received: from obsecurity.dyndns.org (elvis.mu.org [192.203.228.196]) by elvis.mu.org (Postfix) with ESMTP id 032C51A3C19; Fri, 10 Nov 2006 22:33:23 -0800 (PST) Received: by obsecurity.dyndns.org (Postfix, from userid 1000) id 4CEB3515D9; Sat, 11 Nov 2006 01:33:13 -0500 (EST) Date: Sat, 11 Nov 2006 01:33:13 -0500 From: Kris Kennaway To: Zbigniew Szalbot Message-ID: <20061111063313.GB81772@xor.obsecurity.org> References: <20061109192407.GA43267@xor.obsecurity.org> <20061109220926.GA45759@xor.obsecurity.org> <20061109235515.GA46945@xor.obsecurity.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="zx4FCpZtqtKETZ7O" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.2i Cc: freebsd-questions@freebsd.org, Kris Kennaway Subject: Re: periodic, short freezes X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 11 Nov 2006 06:33:23 -0000 --zx4FCpZtqtKETZ7O Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Nov 10, 2006 at 10:18:59AM +0100, Zbigniew Szalbot wrote: > Dear Kris and others, >=20 > On Thu, 9 Nov 2006, Kris Kennaway wrote: >=20 > >OK, you'll need to do some more diagnosis along the lines of my previous= =20 > >email then. >=20 > Here's my typical load: >=20 > last pid: 96934; load averages: 0.03, 0.06, 0.05 up 29+20:47:07=20 > 10:16:09 > 68 processes: 1 running, 67 sleeping > CPU states: 0.4% user, 0.0% nice, 0.4% system, 0.0% interrupt, 99.2%= =20 > idle > Mem: 140M Active, 35M Inact, 103M Wired, 12M Cache, 41M Buf, 15M Free > Swap: 512M Total, 127M Used, 385M Free, 24% Inuse >=20 > Swap use is around 22%. This box mostly functions as mail server and ther= e=20 > are times when it gets a lot of emails to send. The load goes higher then= .=20 > The highest I recall (with no freeze mind you) was about 7.something. But= =20 > typically it does not go above 1.5. The fact that swap is in use, together with your description, indicates that your system is overloaded; those transient loads are causing it to periodically demand more working memory than is backed by RAM, so the system goes into a frenzy of swapping trying to accomodate, and system performance falls in the toilet until the load goes away. Add more RAM or limit the workload. Kris --zx4FCpZtqtKETZ7O Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.5 (FreeBSD) iD8DBQFFVW6oWry0BWjoQKURAtK+AJsE0p2VQyhgPE4V0bGpuGo8dxwgzwCg4OWe 2tYNH8mZYAJdQaxAEHizIcI= =PmSs -----END PGP SIGNATURE----- --zx4FCpZtqtKETZ7O--