From owner-freebsd-performance@FreeBSD.ORG Wed Dec 5 14:58:50 2007 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 20E2416A417 for ; Wed, 5 Dec 2007 14:58:50 +0000 (UTC) (envelope-from cryx-freebsd@h3q.com) Received: from mail.h3q.com (mail.h3q.com [213.73.89.199]) by mx1.freebsd.org (Postfix) with ESMTP id 7ECB513C461 for ; Wed, 5 Dec 2007 14:58:49 +0000 (UTC) (envelope-from cryx-freebsd@h3q.com) Received: (qmail 43222 invoked from network); 5 Dec 2007 14:58:47 -0000 Received: from unknown (HELO goa.cryptophone.de) (smtpsend@62.220.7.20) by mail.h3q.com with AES256-SHA encrypted SMTP; 5 Dec 2007 14:58:47 -0000 Message-ID: <4756BCA6.2030201@h3q.com> Date: Wed, 05 Dec 2007 15:58:46 +0100 From: Philipp Wuensche User-Agent: Thunderbird 2.0.0.9 (Macintosh/20071031) MIME-Version: 1.0 To: Robert Watson References: <4755ED57.6030603@h3q.com> <20071205021327.N41018@fledge.watson.org> In-Reply-To: <20071205021327.N41018@fledge.watson.org> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: "freebsd-performance@freebsd.org" Subject: Re: tuning for high connection rates X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 05 Dec 2007 14:58:50 -0000 Robert Watson wrote: > > Could you show us the output from "top -S" left running for a few > minutes in the steady state. > > Could you try setting the sysctl net.isr.direct to 0, and see how that > affects performance, CPU time reports, and "top -S" output? I first had too look up what net.isr.direct does and I found http://lists.freebsd.org/pipermail/freebsd-performance/2005-October/001561.html Interesting, seems like the CPU usage switches between system and interrupt, "swi1: net" pops up with 65% CPU. Interrupts go up to 2k interrupts/sec. But in general the system usage stays the same, as far as we can tell in this short time. We will keep the system running with net.isr.direct=0 for a day or so to get a better picture how the system performs over the day. With net.isr.direct=1 CPU states: 1.9% user, 0.0% nice, 43.3% system, 9.8% interrupt, 45.0% idle Mem: 163M Active, 139M Inact, 695M Wired, 44K Cache, 213M Buf, 975M Free Swap: 2048M Total, 2048M Free PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COMMAND 23 root 1 -68 - 0K 16K CPU0 0 25.4H 66.46% em0 taskq 11 root 1 171 ki31 0K 16K RUN 1 25.5H 47.22% idle: cpu1 12 root 1 171 ki31 0K 16K RUN 0 17.3H 38.92% idle: cpu0 7467 nobody 3 96 0 152M 146M ucond 1 153:18 24.61% opentracke 13 root 1 -32 - 0K 16K RUN 0 785:03 17.33% swi4: cloc With net.isr.direct=0 CPU states: 1.9% user, 0.0% nice, 11.1% system, 42.1% interrupt, 44.9% idle Mem: 151M Active, 139M Inact, 695M Wired, 44K Cache, 213M Buf, 987M Free Swap: 2048M Total, 2048M Free PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COMMAND 15 root 1 -44 - 0K 16K CPU0 0 2:49 64.70% swi1: net 11 root 1 171 ki31 0K 16K RUN 1 25.5H 46.09% idle: cpu1 12 root 1 171 ki31 0K 16K RUN 0 17.3H 36.18% idle: cpu0 7467 nobody 3 96 0 137M 132M ucond 1 154:28 26.37% opentracke 13 root 1 -32 - 0K 16K WAIT 1 786:38 17.48% swi4: cloc 23 root 1 -68 - 0K 16K - 0 25.4H 2.98% em0 taskq greetings, cryx