From owner-freebsd-questions@FreeBSD.ORG Wed Feb 13 16:01:51 2008 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 2F19A16A41A for ; Wed, 13 Feb 2008 16:01:51 +0000 (UTC) (envelope-from victor@netmediaservices.net) Received: from fep3.cogeco.net (smtp2.cogeco.ca [216.221.81.29]) by mx1.freebsd.org (Postfix) with ESMTP id ED3A413C474 for ; Wed, 13 Feb 2008 16:01:50 +0000 (UTC) (envelope-from victor@netmediaservices.net) Received: from [127.0.0.1] (d221-71-130.commercial.cgocable.net [216.221.71.130]) by fep3.cogeco.net (Postfix) with ESMTP id 287E2190B; Wed, 13 Feb 2008 11:01:21 -0500 (EST) Message-ID: <47B31441.8040801@netmediaservices.net> Date: Wed, 13 Feb 2008 11:01:05 -0500 From: Victor Farah User-Agent: Thunderbird 2.0.0.9 (Windows/20071031) MIME-Version: 1.0 To: Derek Ragona References: <47B1F883.6020407@netmediaservices.net> <6.0.0.22.2.20080212180525.024f9b80@mail.computinginnovations.com> In-Reply-To: <6.0.0.22.2.20080212180525.024f9b80@mail.computinginnovations.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Antivirus: avast! (VPS 080213-0, 02/13/2008), Outbound message X-Antivirus-Status: Clean Cc: freebsd-questions@freebsd.org Subject: Re: Network Help X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 13 Feb 2008 16:01:51 -0000 I'm updating the system to 6.3-release now. All 13 machines are on the same subnet but they are scattered across different switchs. netstat -m: 7716/399/8115 mbufs in use (current/cache/total) 7388/326/7714/25600 mbuf clusters in use (current/cache/total/max) 7380/41 mbuf+clusters out of packet secondary zone in use (current/cache) 0/0/0/0 4k (page size) jumbo clusters in use (current/cache/total/max) 0/0/0/0 9k jumbo clusters in use (current/cache/total/max) 0/0/0/0 16k jumbo clusters in use (current/cache/total/max) 16705K/751K/17456K bytes allocated to network (current/cache/total) 0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters) 0/0/0 requests for jumbo clusters denied (4k/9k/16k) 0/6/6656 sfbufs in use (current/peak/max) 0 requests for sfbufs denied 0 requests for sfbufs delayed 0 requests for I/O initiated by sendfile 193374 calls to protocol drain routines ifconfig -a: em0: flags=8843 mtu 1500 options=b inet 192.168.X.X netmask 0xffffff00 broadcast 192.168.X.255 ether 00:1b:fc:ef:34:de media: Ethernet autoselect (1000baseTX ) status: active em1: flags=8843 mtu 1500 options=b inet X.X.X.X netmask 0xffffff00 broadcast X.X.X.255 ether 00:1b:fc:ef:34:df media: Ethernet 1000baseTX status: active plip0: flags=108810 mtu 1500 lo0: flags=8049 mtu 16384 inet6 fe80::1%lo0 prefixlen 64 scopeid 0x4 inet6 ::1 prefixlen 128 inet 127.0.0.1 netmask 0xff000000 Derek Ragona wrote: > At 01:50 PM 2/12/2008, Victor Farah wrote: >> Hello, >> I have a machine setup with FreeBSD 6.3-PRERELEASE setup on a >> 10/100/1000 switch. There are a pair of em interfaces, and the >> network traffic on this machine is very spuratic. Both EM interfaces >> reach 100Mbps and falls to 5~10Mbps, the very next minute, the traffic >> is very spuratic. The media of the interfaces is as follows: >> EM0: media: Ethernet autoselect (1000baseTX ) >> EM1: media: Ethernet 1000baseTX >> Currently the EM1 card is in use. >> I watch an MRTG that I have setup to see the machine failing at >> sustaining its bandwidth. >> I have 13 other machines setup the same way but traffic is running >> fine and working very well, the only difference between those and the >> new one, is that it's pushing much more data through it; almost the >> same amount of data the 13 other machines push combined. > > First you should update this system to 6.3 release. > > Also you should post how your interfaces are configured, you can copy > and paste the output from: > ifconfig -a > > You also need to better explain the topology of your network. For > instance are all 13 systems on the same subnet? or are you running > multiple subnets with a switched backbone? How many switches are you > using? Are you checking the throughput across a LAN segment or across > multiple subnet segments? > > -Derek >