From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rick Jones Subject: Re: [PATCH RFC] Per route TCP options Date: Tue, 20 Oct 2009 09:26:44 -0700 Message-ID: <4ADDE4C4.5080501@hp.com> References: <1256052161-14156-1-git-send-email-gilad@codefidence.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, ori@comsleep.com To: Gilad Ben-Yossef Return-path: Received: from g6t0187.atlanta.hp.com ([15.193.32.64]:33074 "EHLO g6t0187.atlanta.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752604AbZJTQ0n (ORCPT ); Tue, 20 Oct 2009 12:26:43 -0400 In-Reply-To: <1256052161-14156-1-git-send-email-gilad@codefidence.com> Sender: netdev-owner@vger.kernel.org List-ID: Gilad Ben-Yossef wrote: > Turn the global sysctls allowing disabling of TCP SACK, DSCAK, > time stamp and window scale into per route entry feature options, > laying the ground to future removal of the relevant global sysctls. > > You really only want to disable SACK, DSACK, time stamp or window > scale if you've got a piece of broken networking equipment somewhere > as a stop gap until you can bring a big enough hammer to deal with > the broken network equipment. It doesn't make sense to "punish" the > entire connections going through the machine to destinations not > related to the broken equipment. Is it really only the case that those options get disabled for broken networking equipment? Does this presage making all TCP options per-route only? rick jones