From owner-freebsd-questions@FreeBSD.ORG Thu Mar 6 00:02:47 2008 Return-Path: Delivered-To: questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 9FE871065679 for ; Thu, 6 Mar 2008 00:02:47 +0000 (UTC) (envelope-from freebsd@insightbb.com) Received: from mxsf00.insightbb.com (mxsf00.insightbb.com [74.128.0.70]) by mx1.freebsd.org (Postfix) with ESMTP id 714838FC16 for ; Thu, 6 Mar 2008 00:02:47 +0000 (UTC) (envelope-from freebsd@insightbb.com) X-IronPort-AV: E=Sophos;i="4.25,453,1199682000"; d="scan'208";a="255371603" Received: from mxsmfpool21.ebay.com (HELO mxip05.insightbb.com) ([66.135.209.218]) by mxsf00.insightbb.com with ESMTP; 05 Mar 2008 19:02:46 -0500 Received: from 208-46-39-11.dia.static.qwest.net (HELO [10.7.44.13]) ([208.46.39.11]) by mxip05.insightbb.com with ESMTP; 05 Mar 2008 19:02:45 -0500 From: Steven Friedrich To: questions@freebsd.org Date: Wed, 5 Mar 2008 19:02:23 -0500 User-Agent: KMail/1.9.7 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200803051902.23298.freebsd@insightbb.com> Cc: Subject: multiple CPUs and vmstat 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: Thu, 06 Mar 2008 00:02:47 -0000 I'm running 7.0 on i386. I'd like to see multiple cpu stats in vmstat. vmstat procs memory page disk faults cpu r b w avm fre flt re pi po fr sr ad0 in sy cs us sy id 0 0 0 398000 77144 7298 1 1 0 5686 12 0 117 18938 1758 32 11 58 The formatting got whacked, sorry. I looked at several man pages and couldn't find any other stat program that showed multiple processors. I have a system monitor running under SuperKaramba, but on a Hyperthreaded system, it shows both processors with identical CPU percentages. I had sent a bug report to KDE, but the guy that picked it up couldn't understand my point. Which is, since a hyperthreaded CPU is actually two pipelines sharing a common execution unit, the "best" it could be doing is complementary precents, i.e., if one CPU is 60% utilized, then the other CPU couldn't be any better than 40 % utilized.