From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hannes Frederic Sowa Subject: Re: Has RFC4821 been implemented? Date: Fri, 22 Jan 2016 22:19:41 +0100 Message-ID: <56A29CED.4090601@stressinduktion.org> References: Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit To: Tom Herbert , Linux Kernel Network Developers Return-path: Received: from out3-smtp.messagingengine.com ([66.111.4.27]:36352 "EHLO out3-smtp.messagingengine.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752289AbcAVVTn (ORCPT ); Fri, 22 Jan 2016 16:19:43 -0500 Received: from compute6.internal (compute6.nyi.internal [10.202.2.46]) by mailout.nyi.internal (Postfix) with ESMTP id 434272168A for ; Fri, 22 Jan 2016 16:19:43 -0500 (EST) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Hi, On 22.01.2016 20:50, Tom Herbert wrote: > Found it: tcp_mtu_probing Exactly. > On Fri, Jan 22, 2016 at 11:39 AM, Tom Herbert wrote: >> This came up on in one of the IETF mailing lists in the context that >> PMTUD doesn't really work on the Internet so PLPMTUD is the way to >> go. Looking at the code I only see inet_csk_update_pmtu called from >> ICMP PTB error. I am missing something? If I recall correctly we don't store the MSS in the inetpeer tcp metrics cache neither do we update the MTU on the specific path (update the dst_entry). So it is a one connection only thing so far. Bye, Hannes