From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH] net-tcp: fix cwnd reduction for non-sack recovery Date: Fri, 24 Aug 2012 13:49:51 -0400 (EDT) Message-ID: <20120824.134951.1258077615464850610.davem@davemloft.net> References: <1345741517-30504-1-git-send-email-ycheng@google.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: nanditad@google.com, ycheng@google.com, mattmathis@google.com, netdev@vger.kernel.org To: ncardwell@google.com Return-path: Received: from shards.monkeyblade.net ([149.20.54.216]:54792 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753761Ab2HXRty (ORCPT ); Fri, 24 Aug 2012 13:49:54 -0400 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: From: Neal Cardwell Date: Thu, 23 Aug 2012 13:25:50 -0400 > On Thu, Aug 23, 2012 at 1:21 PM, Nandita Dukkipati wrote: >> On Thu, Aug 23, 2012 at 10:05 AM, Yuchung Cheng wrote: >>> The cwnd reduction in fast recovery is based on the number of packets >>> newly delivered per ACK. For non-sack connections every DUPACK >>> signifies a packet has been delivered, but the sender mistakenly >>> skips counting them for cwnd reduction. >>> >>> The fix is to compute newly_acked_sacked after DUPACKs are accounted >>> in sacked_out for non-sack connections. >>> >>> Signed-off-by: Yuchung Cheng ... >> Acked-by: Nandita Dukkipati > > Acked-by: Neal Cardwell Applied, and queued up for -stable, thanks. Please use plain "tcp: " as the prefix for pure tcp changes. Thanks.