From owner-freebsd-questions@FreeBSD.ORG Mon Jul 26 02:21:24 2004 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 10F4016A4CE for ; Mon, 26 Jul 2004 02:21:24 +0000 (GMT) Received: from urchin.rlc.qld.edu.au (urchin.rlc.qld.edu.au [202.9.58.86]) by mx1.FreeBSD.org (Postfix) with ESMTP id 81F6243D53 for ; Mon, 26 Jul 2004 02:21:22 +0000 (GMT) (envelope-from alex@helbig.cc) Received: from tm290xx.helbig.cc (laptop.rlc.qld.edu.au [10.0.0.96]) i6Q2LJMb082828; Mon, 26 Jul 2004 12:21:20 +1000 (EST) (envelope-from alex@helbig.cc) Message-Id: <6.0.0.22.0.20040726121625.01d9fbf0@smtp.muse.org.au> X-Sender: alexh@smtp.muse.org.au X-Mailer: QUALCOMM Windows Eudora Version 6.0.0.22 Date: Mon, 26 Jul 2004 12:21:17 +1000 To: freebsd-questions@freebsd.org From: Alex Helbig Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Content-Filtered-By: Mailman/MimeDel 2.1.1 cc: alex Helbig Subject: High interrupt load under 5.2.1-RELEASE 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: Mon, 26 Jul 2004 02:21:24 -0000 Hi Everyone, I am having some issues with 5.2.1-RELEASE on an Intel SE7500WV2 with an Intel SRCU42L Raid controller. The issue I have is the number of interrupts per second being caught by the code for either the em or iir device. The output of vmstat and top will show what I mean: %vmstat -i interrupt total rate irq1: atkbd0 163 0 irq6: fdc0 3 0 irq8: rtc 803888 127 irq9: em0 em1 iir0+ 360580529 57408 irq13: npx0 1 0 irq15: ata1 49 0 irq0: clk 628017 99 Total 362012650 57636 %top -s last pid: 829; load averages: 0.89, 0.71, 0.62 54 processes: 5 running, 41 sleeping, 7 waiting, 1 lock CPU states: 0.1% user, 0.0% nice, 0.4% system, 14.4% interrupt, 85.2% idle Mem: 6944K Active, 6012K Inact, 39M Wired, 9312K Buf, 1952M Free Swap: 4071M Total, 4071M Free PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND 11 root -16 0 0K 12K CPU3 3 104:59 99.02% 99.02% idle: cpu3 12 root -16 0 0K 12K RUN 2 104:58 99.02% 99.02% idle: cpu2 13 root -16 0 0K 12K CPU1 1 104:42 99.02% 99.02% idle: cpu1 22 root -68 -187 0K 12K *Giant 0 61:32 55.18% 55.18% irq9: em0 em1 iir0+ 14 root -16 0 0K 12K CPU0 0 42:46 40.77% 40.77% idle: cpu0 829 alexh -68 0 2208K 1468K CPU2 2 0:00 6.66% 0.63% top %dmesg | head -n 15 Copyright (c) 1992-2004 The FreeBSD Project. Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 The Regents of the University of California. All rights reserved. FreeBSD 5.2.1-RELEASE #0: Mon Feb 23 20:45:55 GMT 2004 root@wv1u.btc.adaptec.com:/usr/obj/usr/src/sys/GENERIC Preloaded elf kernel "/boot/kernel/kernel" at 0xc0a35000. Preloaded elf module "/boot/kernel/acpi.ko" at 0xc0a35244. ACPI APIC Table: Timecounter "i8254" frequency 1193182 Hz quality 0 CPU: Intel(R) XEON(TM) CPU 2.40GHz (2392.95-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0xf24 Stepping = 4 Features=0x3febfbff Hyperthreading: 2 logical CPUs real memory = 2147418112 (2047 MB) avail memory = 2080645120 (1984 MB) The points that seem relevant to me in diagnosing this are: * This is a default install of 5.2.1-RELEASE. No custom kernel, no additional software installed. * The box is currently doing nothing other than sitting in a rack * The same box with 5.1-RELEASE did not exhibit this behavior * It seems that the em and iir devices are all sitting behind IRQ9 - I suspect this is not a good thing for when the box does become loaded Does anyone have any suggestions that may either clarify my problem or help me resolve it. Please reply to me and to the list as I am not currently subscribed. Thanks in advance Alex Helbig. ------------------------------------------------- Alex Helbig Head of IT Services Redeemer Lutheran College 745 Rochedale Rd Rochedale Q 4123 Australia Ph: +61 7 3341 4555 Fax: +61 7 3341 9143