From owner-freebsd-stable@FreeBSD.ORG Thu Nov 24 19:38:20 2011 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 A998A106566B for ; Thu, 24 Nov 2011 19:38:20 +0000 (UTC) (envelope-from raul@turing.b2n.org) Received: from mail1.isdefe.es (mail1.isdefe.es [194.15.213.239]) by mx1.freebsd.org (Postfix) with ESMTP id 3609A8FC0C for ; Thu, 24 Nov 2011 19:38:20 +0000 (UTC) Received: from mail1.isdefe.es (localhost [127.0.0.1]) by localhost.isdefe.es (Postfix) with ESMTP id 720BD31A320 for ; Thu, 24 Nov 2011 20:19:46 +0100 (CET) Received: from turing.b2n.org (unknown [172.24.1.14]) by mail1.isdefe.es (Postfix) with ESMTP id 5CAE72BAC34 for ; Thu, 24 Nov 2011 20:19:46 +0100 (CET) Received: from [10.10.10.15] (ramc-desktop.pinlabs.b2n.org [10.10.10.15]) by turing.b2n.org (Postfix) with ESMTP id 08807A2116 for ; Thu, 24 Nov 2011 20:20:03 +0100 (CET) Message-ID: <4ECE9914.6020502@turing.b2n.org> Date: Thu, 24 Nov 2011 20:20:52 +0100 From: Raul User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: freebsd-stable@freebsd.org References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 8bit Subject: Re: TCP Reassembly Issues X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 24 Nov 2011 19:38:20 -0000 El 24/11/2011 17:07, kerbzo escribió: > I 'm experiencing a similar issue but I don't know if mine could be > considered normal behaviour: even if net.inet.tcp.reass.curesegments > is set to 1680 and does not icrease, the output of vmstat -z shows a > high tcpreass fail value that I don't remember in previous (8-STABLE) > builds: I see both, 'net.inet.tcp.reass.cursegments' reaching default 'net.inet.tcp.reass.maxsegments' after 38 minutes of uptime, apparently for never going down despite the amount of traffic and vmstat -z also show tcpreass failures. I also see sudden packet 'bursts' discarded by memory problems maybe related: [....] %date && netstat -s -p tcp | grep mem jueves, 24 de noviembre de 2011, 19:39:23 CET 5115 discarded due to memory problems %date && netstat -s -p tcp | grep mem jueves, 24 de noviembre de 2011, 19:39:30 CET 5268 discarded due to memory problems [....] My settings: [....] %cat /etc/sysctl.conf | grep -v ^\# debug.cpufreq.lowest=1000 %cat /boot/loader.conf | grep -v ^\# vfs.zfs.prefetch_disable=0 aio_load="YES" cc_cubic_load="YES" %sysctl net.isr net.isr.numthreads: 1 net.isr.maxprot: 16 net.isr.defaultqlimit: 256 net.isr.maxqlimit: 10240 net.isr.bindthreads: 0 net.isr.maxthreads: 1 net.isr.direct: 0 net.isr.direct_force: 0 net.isr.dispatch: direct [....] cc cubic although loaded, not used in this 'pristine' reboot. About firewalling, pf using altq. Pretty recent compile: [....] %sysctl -a | grep RC2 kern.osrelease: 9.0-RC2 kern.version: FreeBSD 9.0-RC2 #0: Thu Nov 24 00:39:07 CET 2011 [....] Regards, Raúl.