From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: [PATCH 4/4]: Kill fastpath_{skb,cnt}_hint. Date: Wed, 28 Feb 2007 13:08:08 -0800 Message-ID: <20070228130808.4b7a9ea8@localhost.localdomain> References: <20070228.114949.18302561.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org To: David Miller Return-path: Received: from smtp.osdl.org ([65.172.181.24]:43863 "EHLO smtp.osdl.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751973AbXB1VK5 (ORCPT ); Wed, 28 Feb 2007 16:10:57 -0500 In-Reply-To: <20070228.114949.18302561.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Wed, 28 Feb 2007 11:49:49 -0800 (PST) David Miller wrote: > > commit 71b270d966cd42e29eabcd39434c4ad4d33aa2be > Author: David S. Miller > Date: Tue Feb 27 19:28:07 2007 -0800 > > [TCP]: Kill fastpath_{skb,cnt}_hint. > > Now that we have per-skb fack_counts and an interval > search mechanism for the retransmit queue, we don't > need these things any more. > > Instead, as we traverse the SACK blocks to tag the > queue, we use the RB tree to lookup the first SKB > covering the SACK block by sequence number. > > Signed-off-by: David S. Miller I would be happy to see this go. Have you tried this code with a SACK DoS stream? I.e. before you could consume a huge amount of cpu time by giving an certain bad sequence of SACK's. This code should have a better worst case run time.