From owner-freebsd-stable@FreeBSD.ORG Wed Sep 26 15:02:19 2007 Return-Path: Delivered-To: freebsd-stable@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CDD2C16A468 for ; Wed, 26 Sep 2007 15:02:19 +0000 (UTC) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (lurza.secnetix.de [83.120.8.8]) by mx1.freebsd.org (Postfix) with ESMTP id 3C3C313C4B0 for ; Wed, 26 Sep 2007 15:02:18 +0000 (UTC) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (localhost [127.0.0.1]) by lurza.secnetix.de (8.14.1/8.14.1) with ESMTP id l8QF0veq059493; Wed, 26 Sep 2007 17:01:02 +0200 (CEST) (envelope-from oliver.fromme@secnetix.de) Received: (from olli@localhost) by lurza.secnetix.de (8.14.1/8.14.1/Submit) id l8QF0vuI059492; Wed, 26 Sep 2007 17:00:57 +0200 (CEST) (envelope-from olli) Date: Wed, 26 Sep 2007 17:00:57 +0200 (CEST) Message-Id: <200709261500.l8QF0vuI059492@lurza.secnetix.de> From: Oliver Fromme To: freebsd-stable@FreeBSD.ORG, matrix@itlegion.ru In-Reply-To: <000f01c7ff9a$03b887e0$0c00a8c0@Artem> X-Newsgroups: list.freebsd-stable User-Agent: tin/1.8.3-20070201 ("Scotasay") (UNIX) (FreeBSD/6.2-STABLE-20070808 (i386)) MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-2.1.2 (lurza.secnetix.de [127.0.0.1]); Wed, 26 Sep 2007 17:01:03 +0200 (CEST) Cc: Subject: Re: device polling and weird timer interrupt count from vmstat X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: freebsd-stable@FreeBSD.ORG, matrix@itlegion.ru List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Sep 2007 15:02:19 -0000 Artem Kuchin wrote: > Well, problem with top is that on dual 3GHZ box it alsway s > shows 0% load when not loaded with real traffic (web traffic) no matter > if it is polling of int handling. Great, so your machine doesn't have any significant overhead for the timer interrupt. That was your question, wasn't it? > And when loaded with real traffic > web server eat a lot more cpu power then traffic handling, so, no > separate measurement of traffic cpu load is possible. By "traffic cpu load" you mean the handling in the TCP/IP stack and in the device driver, right? That's always the same, no matter whether polling is enabled or not. In fact, with polling enabled you get _less_ interrupts, so the overhead caused by the actual interrupt handling is smaller. > Also, when it comes to public web server i can never be secure enough and > crazy load of traffic can come any time from DDOS attack which can bring > down any box. So, for public web server it is a matter of security and > managebility to have server interactive even on high traffic load. So, even from > this poing of view polling can be usefull. Not really. DDoS attacks against web servers usually work on userland level, not on kernel level. For example, a simple way to perform such an attack would be to make many requests so that your apache runs out of resources. Polling does not help at all in that case. Polling only helps when the _kernel_ side is saturated with network traffic, but that's usually not the case on a web server where the Apache kicks the bucket much earlier than the kernel. Best regards Oliver -- Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing b. M. Handelsregister: Registergericht Muenchen, HRA 74606, Geschäftsfuehrung: secnetix Verwaltungsgesellsch. mbH, Handelsregister: Registergericht Mün- chen, HRB 125758, Geschäftsführer: Maik Bachmann, Olaf Erb, Ralf Gebhart FreeBSD-Dienstleistungen, -Produkte und mehr: http://www.secnetix.de/bsd "Being really good at C++ is like being really good at using rocks to sharpen sticks." -- Thant Tessman