From owner-freebsd-current@FreeBSD.ORG Sat Oct 6 18:17:15 2007 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 114DA16A417 for ; Sat, 6 Oct 2007 18:17:15 +0000 (UTC) (envelope-from matrix@itlegion.ru) Received: from corpmail.itlegion.ru (corpmail.itlegion.ru [84.21.226.211]) by mx1.freebsd.org (Postfix) with SMTP id 32C4313C4A6 for ; Sat, 6 Oct 2007 18:17:13 +0000 (UTC) (envelope-from matrix@itlegion.ru) Received: (qmail 17195 invoked from network); 6 Oct 2007 22:17:12 +0400 Received: from unknown (HELO Artem) (192.168.0.12) by 84.21.226.211 with SMTP; 6 Oct 2007 22:17:12 +0400 X-AntiVirus: Checked by Dr.Web [version: 4.44, engine: 4.44.0.09170, virus records: 246988, updated: 6.10.2007] Message-ID: <010401c80845$1d6ae710$0c00a8c0@Artem> From: "Artem Kuchin" To: "Jack Vogel" References: <012901c8078a$400faeb0$0c00a8c0@Artem> <2a41acea0710051322w214cb284x68d8bad3c4edcdc1@mail.gmail.com> Date: Sat, 6 Oct 2007 22:17:10 +0400 Organization: IT Legion MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="ISO-8859-1"; reply-type=original Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.3138 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.3138 Cc: freebsd-current@freebsd.org Subject: Re: TSO4 network problems and scheduler selection X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 06 Oct 2007 18:17:15 -0000 >I had our test/validation group attempt to repro your problem > with TSO and they were unable to do so. I do not know what > hardware/config ingredients in your environment are causing > a problem but something odd is going on. Test suggested > something like a speed mismatch, but we don't know for > sure. > > Right now I see no evidence to suggest that its important > to disable TSO. If anyone has a scenario I can reproduce > I'd be happy to look further. > Jack, i have played with kernel settings all day today trying to repoduce the bug and recompiled kernel probably 20 times ;) This is all totally weird, i went to back 4BSD scheduler, set polliing option in kernel, set HZ=1000, so, effectivelly i went back to the setup where i had this problem BUT the problem never appeared again. I did not do any cvsup since then, so, it is all the same source. But now everythig work flawlessly with TSO4 option on interface. I am really sorry to waste your and other peoples' time, but beleave me, the problem was really persistent and it was there for more than a month. I think you are right and it was some kind of speed mismatch with the cisco router or some kind of electrical problems, either way it went away and now everything works. -- Regards, Artem