From owner-freebsd-stable@FreeBSD.ORG Wed Jun 6 17:24:23 2012 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 3126D106566C for ; Wed, 6 Jun 2012 17:24:23 +0000 (UTC) (envelope-from sebsta@t-online.de) Received: from mailout06.t-online.de (mailout06.t-online.de [194.25.134.19]) by mx1.freebsd.org (Postfix) with ESMTP id B96398FC0C for ; Wed, 6 Jun 2012 17:24:22 +0000 (UTC) Received: from fwd22.aul.t-online.de (fwd22.aul.t-online.de ) by mailout06.t-online.de with smtp id 1ScJxv-0003nB-UM; Wed, 06 Jun 2012 19:24:15 +0200 Received: from imac.lokal.netz (r1FWm8ZaohfGw48y4GiXzSgFLf3h8ioKNa8Pv4kpv2UWhl8E33afO3VXdHvpPaEgjH@[93.199.50.166]) by fwd22.t-online.de with esmtp id 1ScJxr-0x2q6S0; Wed, 6 Jun 2012 19:24:11 +0200 Content-Type: text/plain; charset=iso-8859-1 Mime-Version: 1.0 (Apple Message framework v1257) From: Sebastian Stach In-Reply-To: <4FCF2E6E.2040902@quip.cz> Date: Wed, 6 Jun 2012 19:24:10 +0200 Content-Transfer-Encoding: quoted-printable Message-Id: <3B262A53-C137-4E4E-B1B7-7471B1FBA258@t-online.de> References: <4FCE37FC.1090405@gmail.com> <878874BA-2F5C-4A7E-8690-2A8A96536AE0@t-online.de> <4FCE6931.6010901@quip.cz> <4FCE786A.2030205@quip.cz> <4FCF2E6E.2040902@quip.cz> To: freebsd-stable X-Mailer: Apple Mail (2.1257) X-ID: r1FWm8ZaohfGw48y4GiXzSgFLf3h8ioKNa8Pv4kpv2UWhl8E33afO3VXdHvpPaEgjH X-TOI-MSGID: 5d4324ed-b36a-4e14-beee-b53eaf8b21cc Subject: Re: em interfaces supermicro X9SCM-F board 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: Wed, 06 Jun 2012 17:24:23 -0000 Thanks for doing the test. My conditions are different in that i have a gigabit network. The only difference in the iperf options is that i'm using -d (dualmode). On the weekend i will have time to do a test with the NICs set to 100MBit. Sebastian Stach Am 06.06.2012 um 12:18 schrieb Miroslav Lachman: > I am running iperf for more than 11 hours without any problem. More = than 450GB were transmitted. > The NIC is connected to old 100Mbps switch and using first port (em0) = in shared mode for remote management. >=20 > em0: flags=3D8843 metric 0 mtu = 1500 > = options=3D4219b > ether 00:25:90:73:d1:76 > inet xx.xx.xx.xx netmask 0xffffff80 broadcast xx.xx.xx.xx > media: Ethernet autoselect (100baseTX ) > status: active >=20 >=20 > The iperf command on Supermicro side was: >=20 > # iperf -c xx.xx.xx.yy --format k -m -p 999 -t 1800 >=20 >=20 > The other side (Cisco UCS C200 M2) was: >=20 > # iperf -s -p 999 >=20 > Server listening on TCP port 999 > TCP window size: 64.0 KByte (default) > ------------------------------------------------------------ > [ 5] local 94.124.105.117 port 999 connected with 94.124.105.115 port = 29787 > [ 5] 0.0-1799.8 sec 19.5 GBytes 93.0 Mbits/sec > [ 4] local 94.124.105.117 port 999 connected with 94.124.105.115 port = 44792 > [ 4] 0.0-1799.9 sec 19.5 GBytes 93.1 Mbits/sec > [ 5] local 94.124.105.117 port 999 connected with 94.124.105.115 port = 11327 > [ 5] 0.0-1799.9 sec 19.5 GBytes 93.0 Mbits/sec >=20 > Both sides are running FreeBSD 8.3-RELEASE amd64 >=20 >=20 > Let me know if I should run iperf with different options to better = simulate your conditions where your NIC hangs. >=20 > Miroslav Lachman