From owner-freebsd-hackers Fri Nov 30 7:48:47 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from exuma.irbs.com (exuma.irbs.com [216.86.160.252]) by hub.freebsd.org (Postfix) with ESMTP id 1F25C37B419; Fri, 30 Nov 2001 07:48:42 -0800 (PST) Received: by exuma.irbs.com (Postfix, from userid 2500) id 523CC1741C; Fri, 30 Nov 2001 10:48:41 -0500 (EST) Date: Fri, 30 Nov 2001 10:48:41 -0500 From: John Capo To: babkin@freebsd.org Cc: jc@irbs.com, freebsd-hackers@freebsd.org Subject: Re: FreeBSD performing worse than Linux? Message-ID: <20011130104841.B90660@exuma.irbs.com> Reply-To: jc@irbs.com References: <20011128153817.T61580@monorchid.lemis.com> <15364.38174.938500.946169@caddis.yogotech.com> <20011129004234.A16101@exuma.irbs.com> <3C0707BD.B8FA31F8@bellatlantic.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2i In-Reply-To: <3C0707BD.B8FA31F8@bellatlantic.net>; from babkin@bellatlantic.net on Thu, Nov 29, 2001 at 11:14:53PM -0500 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG Quoting Sergey Babkin (babkin@bellatlantic.net): > John Capo wrote: > > 21:41:49.001039 client.4427 > server.22: P 144:192(48) ack 12937 win 17376 (DF) [tos 0x10] > > 21:41:49.001073 server.22 > client.4427: . 28049:29497(1448) ack 192 win 17328 (DF) [tos 0x10] > > 21:41:49.001085 server.22 > client.4427: P 29497:30313(816) ack 192 win 17328 (DF) [tos 0x10] > > 21:41:49.109131 client.4427 > server.22: . ack 12937 win 17376 (DF) [tos 0x10] > > And here a _very_ pathological thing has happened: the server > just forgot to send the data between sequence numbers 12937 > and 28049. Since the dump was done on the server side, this suggests > that something very bad has happened with the TCP state on > the server side. Possibly the value of the current sequence number > in the protocol control block got overwritten by something. Very interesting, I overlooked that. Full dumps: http://www.irbs.net/server-dump.html http://www.irbs.net/client-dump.html I was beginning to think it was a client problem since 4.3 clients and Winblows clients work fine. A -stable client built from November 7 CVS code does not see the pause either. The client in the dump is built from CVS on November 11. John Capo To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message