From owner-soc-status@FreeBSD.ORG Mon Jun 4 20:18:45 2012 Return-Path: Delivered-To: soc-status@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4BC3B106566C for ; Mon, 4 Jun 2012 20:18:45 +0000 (UTC) (envelope-from rudotx@gmail.com) Received: from mail-wg0-f50.google.com (mail-wg0-f50.google.com [74.125.82.50]) by mx1.freebsd.org (Postfix) with ESMTP id D6BF58FC0C for ; Mon, 4 Jun 2012 20:18:44 +0000 (UTC) Received: by wgbds11 with SMTP id ds11so4421465wgb.31 for ; Mon, 04 Jun 2012 13:18:44 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:from:date:message-id:subject:to:content-type; bh=El3mJ1KQMtCI526bsXQtJ+0JXoBNovVPX72jq1KrFkU=; b=a3GMat+GpfvITu1HBXpTKU7JCS5XLpphY1RFnnn0cloG4ziDZsWtyIzXXBXM5U0usd kSLHHJLZoZ5qA+B+hJM1F3bd/Cje3QMD9AaqfnArcaYVvviaVKaGAodeUc7KhvM7kgqQ SBznYqh1OgBOmgOwVu+l6ccuUxb2z+ndcw1xtRVHA5nkRgRl5mkhR2NDLffSa2xp0sE/ 8Zp7b+rZFbdvPtXro6azGBJ8+AaoGfraW7/5srb7GFjeqDdEtfvhu+l2QAh7ZwzP7gPu Uj+9MjyU3LMZ27O64AzzMTVXbjeelnE3rRN9OuP4v/fxWrkk+29gp08ZgRKov5wf4fN0 haHA== Received: by 10.216.143.148 with SMTP id l20mr7842202wej.115.1338841123911; Mon, 04 Jun 2012 13:18:43 -0700 (PDT) MIME-Version: 1.0 Received: by 10.216.231.98 with HTTP; Mon, 4 Jun 2012 13:18:23 -0700 (PDT) From: rudo tomori Date: Mon, 4 Jun 2012 22:18:23 +0200 Message-ID: To: soc-status@freebsd.org Content-Type: text/plain; charset=ISO-8859-1 Subject: cpu limits status report X-BeenThere: soc-status@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Summer of Code Status Reports and Discussion List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 Jun 2012 20:18:45 -0000 Hi, the goal of my gsoc project is to enable the system administrators to configure %CPU limits using the rctl command. So that they can for example limit a particular user to 50% cpu time. Last week I updated the formula that calculates the %cpu process utilization. I now use the same formula that is used in the ps(1) command. In the ps(1) command, the exp(x) and ln(x) floating point functions are used. To avoid this in kernel, I used fixed point arithmetic and a precomputed table of exp(x) values for a specified range. I also fixed the problem with per-used %CPU utilization that I mentioned in the previous status report. This week I am going to test the per-process %CPU limits on real hw because I do the development on virtual machines. If I encounter any problems, I will try to solve them. After that I will start working on per-user %CPU limits. rudo