From owner-freebsd-net@FreeBSD.ORG Thu Oct 8 12:14:08 2009 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 64C941065692; Thu, 8 Oct 2009 12:14:08 +0000 (UTC) (envelope-from rihad@mail.ru) Received: from mx40.mail.ru (mx40.mail.ru [94.100.176.54]) by mx1.freebsd.org (Postfix) with ESMTP id 155D98FC1A; Thu, 8 Oct 2009 12:14:07 +0000 (UTC) Received: from [217.25.27.27] (port=64599 helo=[217.25.27.27]) by mx40.mail.ru with asmtp id 1Mvrsk-0007OC-00; Thu, 08 Oct 2009 16:14:06 +0400 Message-ID: <4ACDD789.8030804@mail.ru> Date: Thu, 08 Oct 2009 17:14:01 +0500 From: rihad User-Agent: Mozilla-Thunderbird 2.0.0.22 (X11/20090706) MIME-Version: 1.0 To: Robert Watson References: <4AC9E29B.6080908@mail.ru> <20091005123230.GA64167@onelab2.iet.unipi.it> <4AC9EFDF.4080302@mail.ru> <4ACA2CC6.70201@elischer.org> <4ACAFF2A.1000206@mail.ru> <4ACB0C22.4000008@mail.ru> <20091006100726.GA26426@svzserv.kemerovo.su> <4ACB42D2.2070909@mail.ru> <20091006142152.GA42350@svzserv.kemerovo.su> <4ACB6223.1000709@mail.ru> <20091006161240.GA49940@svzserv.kemerovo.su> <4ACC5563.602@mail.ru> <4ACC56A6.1030808@mail.ru> <4ACC5DEC.1010006@mail.ru> <4ACC65A0.7030900@mail.ru> <4ACC8CC8.8050403@mail.ru> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Spam: Not detected X-Mras: Ok Cc: freebsd-net@freebsd.org, Eugene Grosbein , Luigi Rizzo , Julian Elischer Subject: Re: dummynet dropping too many packets X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 08 Oct 2009 12:14:08 -0000 Robert Watson wrote: > I would suggest making just the HZ -> 4000 change for now and see how it > goes. > Been running for a few hours under these changed sysctls: kern.clockrate: { hz = 4000, tick = 250, profhz = 4000, stathz = 129 } net.inet.ip.dummynet.io_fast: 1 net.inet.ip.dummynet.hash_size: 512 net.isr.direct: 0 net.inet.ip.intr_queue_maxlen: 5000 kern.ipc.nmbclusters=111111 Current stats: net.inet.ip.dummynet.search_steps: 190347891 net.inet.ip.dummynet.searches: 188979871 net.inet.ip.dummynet.io_pkt_drop: 0 net.inet.ip.intr_queue_drops: 0 Around 1800 entries in each of the two ipfw tables. About 420 mbps of traffic passing through. ipfw pipe's created with GRED queuing algorithm, if it matters: ipfw pipe 64 config bw 64kbit/s mask dst-ip 0xffffffff gred 0.002/1800/2000/0.1 queue 2000 etc. 0 global output packet drops per second. top -SH: last pid: 59120; load averages: 0.87, 1.19, 1.27 up 0+04:31:38 17:11:59 141 processes: 9 running, 115 sleeping, 17 waiting CPU: 3.8% user, 0.0% nice, 3.0% system, 8.8% interrupt, 84.4% idle Mem: 1302M Active, 1482M Inact, 350M Wired, 40K Cache, 214M Buf, 801M Free Swap: 2048M Total, 2048M Free PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU COMMAND 16 root 171 ki31 0K 16K CPU2 2 237:10 97.02% idle: cpu2 14 root 171 ki31 0K 16K CPU4 4 225:33 96.48% idle: cpu4 12 root 171 ki31 0K 16K CPU6 6 249:31 88.96% idle: cpu6 15 root 171 ki31 0K 16K CPU3 3 224:18 88.92% idle: cpu3 13 root 171 ki31 0K 16K CPU5 5 228:39 87.74% idle: cpu5 11 root 171 ki31 0K 16K CPU7 7 235:02 87.35% idle: cpu7 18 root 171 ki31 0K 16K RUN 0 198:11 81.98% idle: cpu0 17 root 171 ki31 0K 16K CPU1 1 209:31 71.78% idle: cpu1 21 root -44 - 0K 16K WAIT 0 88:24 47.31% swi1: net 29 root -68 - 0K 16K WAIT 1 34:06 18.95% irq256: bce0 470 root -68 - 0K 16K - 7 21:24 6.01% dummynet 19 root -32 - 0K 16K WAIT 5 13:37 5.86% swi4: clock sio 31 root -68 - 0K 16K WAIT 2 7:45 4.44% irq257: bce1 I'll wait for the number of entries to reach 2000-2200 or so, and post back again.