From owner-freebsd-questions@FreeBSD.ORG Sun Apr 20 09:57:51 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 0676337B404 for ; Sun, 20 Apr 2003 09:57:50 -0700 (PDT) Received: from binder.sasknow.net (binder.sasknow.net [204.83.220.142]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7ADBF43FE0 for ; Sun, 20 Apr 2003 09:57:49 -0700 (PDT) (envelope-from ryan@sasknow.com) Received: from ren (ren.sasknow.com [207.195.92.131]) by binder.sasknow.net (8.12.6p2/8.12.6) with ESMTP id h3KGvlQ4043784; Sun, 20 Apr 2003 10:57:47 -0600 (CST) (envelope-from ryan@sasknow.com) Date: Sun, 20 Apr 2003 10:57:47 -0600 (CST) From: Ryan Thompson To: Paulo Roberto In-Reply-To: <20030420162845.21400.qmail@web14902.mail.yahoo.com> Message-ID: <20030420104446.K68932-100000@ren.sasknow.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Audit: 1 cc: freebsd-questions@freebsd.org Subject: Re: load averages 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: Sun, 20 Apr 2003 16:57:51 -0000 Paulo Roberto wrote to freebsd-questions@freebsd.org: > Hello, Hi Paulo, > Is the "load averages" field in uptime/top in percentage?? No. The load averages represent the number of processes in the run queue (i.e., the number of processes that are ready to run, but must wait for CPU time). Load averages > 1.00 are normal. I haven't seen this discussion on here for awhile, so I'll explain further. Load averages are only loosely correlated with system performance. It is possible to have relatively high load averages, and still have a very responsive system. It is also possible to have load averages below 0.50 on a disk-bound machine, and have an unusable machine. (I've seen both). It is also possible to inadvertently write a fork bomb (in Perl) and watch them peak at about 600, and still manage to obtain a sort-of-responsive root login to kill all of the processes. (Uh.. I've *never* seen that happen). Again, load average is a function of the number of processes waiting for CPU time. *Not* of actual CPU utilization (which will often be quite a bit lower than 100%), or of overall resource utilization (disk, net, etc.) Use load averages for only a very rough sanity check. - Ryan -- Ryan Thompson SaskNow Technologies - http://www.sasknow.com 901-1st Avenue North - Saskatoon, SK - S7K 1Y4 Tel: 306-664-3600 Fax: 306-244-7037 Saskatoon Toll-Free: 877-727-5669 (877-SASKNOW) North America