From tcpsat-bounces@ISI.EDU Thu Apr 13 23:17:55 2006 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1FUEol-0006Gr-Rs for tcpsat-archive@lists.ietf.org; Thu, 13 Apr 2006 23:17:55 -0400 Received: from gamma.isi.edu ([128.9.144.145]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1FUEok-0007wv-Fe; Thu, 13 Apr 2006 23:17:55 -0400 Received: from gamma.isi.edu (localhost [127.0.0.1]) by gamma.isi.edu (8.11.6p2+0917/8.11.2) with ESMTP id k3E2vNY07322; Thu, 13 Apr 2006 19:57:23 -0700 (PDT) Received: from vapor.isi.edu (vapor.isi.edu [128.9.64.64]) by gamma.isi.edu (8.11.6p2+0917/8.11.2) with ESMTP id k3E2uTY07256 for ; Thu, 13 Apr 2006 19:56:29 -0700 (PDT) Received: from mse2fe2.mse2.exchange.ms (mse2fe2.mse2.exchange.ms [66.232.26.194]) by vapor.isi.edu (8.11.6p2+0917/8.11.2) with ESMTP id k3E2tXR05561 for ; Thu, 13 Apr 2006 19:55:33 -0700 (PDT) Received: from piet2.bluelane.com ([64.95.123.130]) by mse2fe2.mse2.exchange.ms with Microsoft SMTPSVC(6.0.3790.1830); Thu, 13 Apr 2006 22:55:27 -0400 From: Piet Delaney To: tcpsat@ISI.EDU Organization: BlueLane Tech, Date: Thu, 13 Apr 2006 19:55:24 -0700 Message-Id: <1144983324.24164.104.camel@piet2.bluelane.com> Mime-Version: 1.0 X-Mailer: Evolution 2.0.4-3mdk X-OriginalArrivalTime: 14 Apr 2006 02:55:27.0928 (UTC) FILETIME=[E297D380:01C65F6E] X-ISI-4-43-8-MailScanner: Found to be clean, Found to be clean, Found to be clean Subject: [tcpsat] Time Stamps with TCP Proxies X-BeenThere: tcpsat@isi.edu X-Mailman-Version: 2.1.6 Precedence: list Reply-To: piet@bluelane.com List-Id: "TCP over Satellite mailing list \(concluded IETF wg\)" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: tcpsat-bounces@ISI.EDU Errors-To: tcpsat-bounces@ISI.EDU X-MailScanner-From: tcpsat-bounces@isi.edu X-Spam-Score: 0.0 (/) X-Scan-Signature: 2409bba43e9c8d580670fda8b695204a We are using a Linux split TCP spoofing proxy that we developed, somewhat similar to PEP, and was looking for a mailing list to discuss issues like tcp time stamp clocks and their involvement with PAWS, and recent additions to 2.6.13; like the congestion control algorithms and Dynamic Right-Sizing (DRS). We currently have a split proxy and a bidirectional proxy. In both cases the proxy Ack's packets from a client. In our split case we Echo Time Stamps from the Client and use Time Stamps from the Server. Packets to the Server have forwarded copies of the echoed time stamps but Time Stamps from the Proxy. Our non-split proxy currently doesn't even try to do congestion control with time stamps. While upgrading to 2.6.13 with it's new congestion control algorithms I was wonder if we should reconsider the current paradigm. -piet -- --- piet@bluelane.com _______________________________________________ tcpsat mailing list tcpsat@isi.edu http://mailman.isi.edu/mailman/listinfo/tcpsat