From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932231Ab2I1Sxs (ORCPT ); Fri, 28 Sep 2012 14:53:48 -0400 Received: from mail-pa0-f46.google.com ([209.85.220.46]:51579 "EHLO mail-pa0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932205Ab2I1Sxn (ORCPT ); Fri, 28 Sep 2012 14:53:43 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org, stable@vger.kernel.org Cc: Greg KH , alan@lxorguk.ukuu.org.uk, Anton Mich , Eric Dumazet , "David S. Miller" Subject: [ 001/262] codel: refine one condition to avoid a nul rec_inv_sqrt Date: Fri, 28 Sep 2012 11:48:50 -0700 Message-Id: <20120928182958.162174904@linuxfoundation.org> X-Mailer: git-send-email 1.7.10.1.362.g242cab3 In-Reply-To: <20120928182957.993484211@linuxfoundation.org> References: <20120928182957.993484211@linuxfoundation.org> User-Agent: quilt/0.60-2.1.2 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Greg KH 3.5-stable review patch. If anyone has any objections, please let me know. ------------------ From: Eric Dumazet [ Upstream commit 2359a47671fc4fb0fe5e9945f76c2cb10792c0f8 ] One condition before codel_Newton_step() was not good if we never left the dropping state for a flow. As a result rec_inv_sqrt was 0, instead of the ~0 initial value. codel control law was then set to a very aggressive mode, dropping many packets before reaching 'target' and recovering from this problem. To keep codel_vars_init() as efficient as possible, refine the condition to make sure rec_inv_sqrt initial value is correct Many thanks to Anton Mich for discovering the issue and suggesting a fix. Reported-by: Anton Mich Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/codel.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) --- a/include/net/codel.h +++ b/include/net/codel.h @@ -305,6 +305,8 @@ static struct sk_buff *codel_dequeue(str } } } else if (drop) { + u32 delta; + if (params->ecn && INET_ECN_set_ce(skb)) { stats->ecn_mark++; } else { @@ -320,9 +322,11 @@ static struct sk_buff *codel_dequeue(str * assume that the drop rate that controlled the queue on the * last cycle is a good starting point to control it now. */ - if (codel_time_before(now - vars->drop_next, + delta = vars->count - vars->lastcount; + if (delta > 1 && + codel_time_before(now - vars->drop_next, 16 * params->interval)) { - vars->count = (vars->count - vars->lastcount) | 1; + vars->count = delta; /* we dont care if rec_inv_sqrt approximation * is not very precise : * Next Newton steps will correct it quadratically.