From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yuchung Cheng Subject: Re: [PATCH v2 net-next 1/4] tcp: consolidate SYNACK RTT sampling Date: Tue, 23 Jul 2013 08:54:35 -0700 Message-ID: References: <1374535248-27418-1-git-send-email-ycheng@google.com> <20130722.180255.685921996264320731.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Cc: Neal Cardwell , Eric Dumazet , Nandita Dukkipati , netdev To: David Miller Return-path: Received: from mail-ob0-f170.google.com ([209.85.214.170]:49192 "EHLO mail-ob0-f170.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932138Ab3GWPy4 (ORCPT ); Tue, 23 Jul 2013 11:54:56 -0400 Received: by mail-ob0-f170.google.com with SMTP id ef5so10673689obb.29 for ; Tue, 23 Jul 2013 08:54:55 -0700 (PDT) In-Reply-To: <20130722.180255.685921996264320731.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On Mon, Jul 22, 2013 at 6:02 PM, David Miller wrote: > From: Yuchung Cheng > Date: Mon, 22 Jul 2013 16:20:45 -0700 > >> This patch series improve RTT sampling in three ways: >> 1. Sample RTT during fast recovery and reordering events. >> 2. Favor ack-based RTT to timestamps because of broken TS ECR fields >> 3. Consolidate the RTT measurement logic. >> >> The first patch consolidates SYNACK and other RTT measurement to use a >> central function tcp_ack_update_rtt(). A (small) bonus is now SYNACK >> RTT measurement happens after PAWS check, potentially reducing the >> impact of RTO seeding on bad TCP timestamps values. >> >> Signed-off-by: Yuchung Cheng > > I like this series a lot, applied, thanks! > > Next time please submit a seperate "[PATCH 0/4] xxx" posting. > > If it has non-trivial content, I use the "0" posting as the > commit message of a merge commit when I apply your series. > > What I did here was take the text: > > ==================== > This patch series improve RTT sampling in three ways: > 1. Sample RTT during fast recovery and reordering events. > 2. Favor ack-based RTT to timestamps because of broken TS ECR fields > 3. Consolidate the RTT measurement logic. > ==================== > > and place it into that merge commit, removing it from the patch #1 > commit message. Thank you David. Sorry for the extra hassle. Will definitely do that for next patch series. > > Thanks.