From mboxrd@z Thu Jan 1 00:00:00 1970 From: John Heffner Subject: Re: SACK scoreboard Date: Tue, 08 Jan 2008 23:27:08 -0500 Message-ID: <47844D1C.1060706@psc.edu> References: <20080107.233617.203640686.davem@davemloft.net> <4783AA29.3080406@psc.edu> <20080108.144456.173014334.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: David Miller , ilpo.jarvinen@helsinki.fi, lachlan.andrew@gmail.com, netdev@vger.kernel.org, quetchen@caltech.edu To: Andi Kleen Return-path: Received: from mailer1.psc.edu ([128.182.58.100]:60876 "EHLO mailer1.psc.edu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751910AbYAIE1r (ORCPT ); Tue, 8 Jan 2008 23:27:47 -0500 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Andi Kleen wrote: > David Miller writes: >> The big problem is that recovery from even a single packet loss in a >> window makes us run kfree_skb() for a all the packets in a full >> window's worth of data when recovery completes. > > Why exactly is it a problem to free them all at once? Are you worried > about kernel preemption latencies? > > -Andi I also wonder how much of a problem this is (for now, with window sizes of order 10000 packets. My understanding is that the biggest problems arise from O(N^2) time for recovery because every ack was expensive. Have current tests shown the final ack to be a major source of problems? -John