From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: Extensible hashing and RCU Date: Tue, 20 Feb 2007 12:10:22 +0100 Message-ID: <200702201210.22907.dada1@cosmosbay.com> References: <200702191913.08125.dada1@cosmosbay.com> <20070220.021209.39159087.davem@davemloft.net> <20070220103014.GB7237@2ka.mipt.ru> Mime-Version: 1.0 Content-Type: text/plain; charset="koi8-r" Content-Transfer-Encoding: 7bit Cc: David Miller , akepner@sgi.com, linux@horizon.com, netdev@vger.kernel.org, bcrl@kvack.org To: Evgeniy Polyakov Return-path: Received: from pfx2.jmh.fr ([194.153.89.55]:39342 "EHLO pfx2.jmh.fr" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932879AbXBTLKc (ORCPT ); Tue, 20 Feb 2007 06:10:32 -0500 In-Reply-To: <20070220103014.GB7237@2ka.mipt.ru> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Tuesday 20 February 2007 11:30, Evgeniy Polyakov wrote: > On Tue, Feb 20, 2007 at 02:12:09AM -0800, David Miller (davem@davemloft.net) wrote: > > From: Eric Dumazet > > Date: Tue, 20 Feb 2007 11:04:15 +0100 > > > > > Using a jenkin's hash permits a better hash distribution for a litle > > > cpu cost. I will post later a distribution simulation based on the > > > data gathered from the same real server. > > > > Actually someone (I think it was Evgeniy in fact) made such > > comparisons and found in his studies that not only does the current > > ehash xor hash function distribute about as well as jenkins, it's > > significantly cheaper to calculate :-) > > Yep, it happend to be my tests :) > Jenkins hash was slower and had significant artifacts for some usage > cases ended up with extremely long chain length. > One can find more details at > http://tservice.net.ru/~s0mbre/blog/2006/05/14#2006_05_14 > http://tservice.net.ru/~s0mbre/blog/2006/06/01#2006_06_01 Please explain why you chose h = jhash_2words(faddr, laddr, ports); h ^= h >> 16; h ^= h >> 8; jhash is very good, no need to try to be smarter, shufling some bytes... and adding artifacts.