From owner-freebsd-net@FreeBSD.ORG Wed Nov 28 00:04:37 2012 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 04FFC14E; Wed, 28 Nov 2012 00:04:37 +0000 (UTC) (envelope-from zbeeble@gmail.com) Received: from mail-lb0-f182.google.com (mail-lb0-f182.google.com [209.85.217.182]) by mx1.freebsd.org (Postfix) with ESMTP id E3B5A8FC12; Wed, 28 Nov 2012 00:04:35 +0000 (UTC) Received: by mail-lb0-f182.google.com with SMTP id go10so9890367lbb.13 for ; Tue, 27 Nov 2012 16:04:34 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=jApgb7ZMT+nFwY7qUJ1IHjdJUtoyhK5DnSZD4rrknjQ=; b=UzH8D2smXYyEFQhppmULBaWmeCkfaTYwqfyL6/IsT64i+CsGn0pL8O3n6ba7zYER3J Zf3wCvpWatfaUS5CJxIt6Ezr2TiSVEOC58LYGFppHtQ9ZTLVWoHM9BrzGgep1vX19ytH 50an8YN/CL/nEalDvwiyX7/BvZ9C/ntSugtiYaFjgpVf+4+Jtb8KyjWXVMEg82dlUpGa 3Mo8DD0UFDo4BF9PVik1/2fF2IP2x1z5IwXKcF0wYjkt6ikVM5uB9MyrSQptNIVPCL9P zI9o2HJXged/ioqepMVj3CAhk5lsRePXdY1tFj3o6+N30h9l9AHuYgrHovUxrAyTwiH0 X0tw== MIME-Version: 1.0 Received: by 10.112.101.232 with SMTP id fj8mr3665447lbb.83.1354061074686; Tue, 27 Nov 2012 16:04:34 -0800 (PST) Received: by 10.112.61.33 with HTTP; Tue, 27 Nov 2012 16:04:34 -0800 (PST) In-Reply-To: <50B54AE7.3040901@freebsd.org> References: <50B54AE7.3040901@freebsd.org> Date: Tue, 27 Nov 2012 19:04:34 -0500 Message-ID: Subject: Re: 9.1-RC3 IGB dropping connections. From: Zaphod Beeblebrox To: Andre Oppermann Content-Type: text/plain; charset=ISO-8859-1 Cc: FreeBSD Hackers , FreeBSD Stable , FreeBSD Net X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Nov 2012 00:04:37 -0000 To Jack Vogel's comment, this problem only seems to occur on systems that are exceedingly lightly loaded (in this case, not yet in production and I'm the only one using it). On Tue, Nov 27, 2012 at 6:21 PM, Andre Oppermann wrote: > r243570 in CURRENT should likely fix this issue. It's only 27 hours old > and hasn't been MFC'd yet. I'm not sure this addresses what I'm seeing. It's a pause the the traffic in the shell that is "fixed" by causing some traffic on the return channel (watching for the pause --- and then hitting enter a few times seems to fix it). I'd expect that TCP retransmission should take care of this regularly ... but in this case, it doesn't... for whatever reason ...