From mboxrd@z Thu Jan 1 00:00:00 1970 From: Werner Almesberger Subject: TCP connection passing, version 4 Date: Fri, 15 Nov 2002 01:34:52 -0300 Sender: netdev-bounce@oss.sgi.com Message-ID: <20021115013452.A11669@almesberger.net> References: <20021031000249.A20233@almesberger.net> <20021031045909.A15756@almesberger.net> <20021031200017.A21544@almesberger.net> <20021101182123.A30594@almesberger.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: To: netdev@oss.sgi.com Content-Disposition: inline In-Reply-To: <20021101182123.A30594@almesberger.net>; from wa@almesberger.net on Fri, Nov 01, 2002 at 06:21:23PM -0300 Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org A minor update: http://www.almesberger.net/tcpcp/tcpcp-4.tar.gz The main changes are that TCP_KICK has turned into the slightly more general TCP_CP_FN option, and that I've written down a few thoughts on "real" checkpointing in doc/README.CHECKPOINTING The funny thing is that, when I started writing, I suspected that checkpointing wouldn't really be possible, but then I realized how it might actually work (okay, with a few hacks, but ... ;-) The patch is now relative to 2.5.47. - Werner ----------------------------------- CHANGES ----------------------------------- Version 4 (15-NOV-2002) ----------------------- - upgraded to the 2.5.47 kernel - added doc/README.CHECKPOINTING with a few reflections on how tcpcp could be abused for "real" checkpointing, where the previous connection owner suddenly dies - renamed TCP_KICK to TCP_CP_FN, and added a sub-function code in optval - renamed tcpcp_kick to tcpcp_activate -- _________________________________________________________________________ / Werner Almesberger, Buenos Aires, Argentina wa@almesberger.net / /_http://www.almesberger.net/____________________________________________/