From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: [PATCH 3/3] Convert the UDP hash lock to RCU Date: Tue, 7 Oct 2008 23:20:56 +0200 Message-ID: <20081007232056.036e26e6@speedy> References: <48EB5D28.7000503@cosmosbay.com> <20081007160729.60c076c4@speedy> <20081007.135548.56141000.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: dada1@cosmosbay.com, benny+usenet@amorsen.dk, minyard@acm.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, paulmck@linux.vnet.ibm.com To: David Miller Return-path: Received: from mail.vyatta.com ([76.74.103.46]:47158 "EHLO mail.vyatta.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757432AbYJGVVE (ORCPT ); Tue, 7 Oct 2008 17:21:04 -0400 In-Reply-To: <20081007.135548.56141000.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On Tue, 07 Oct 2008 13:55:48 -0700 (PDT) David Miller wrote: > From: Stephen Hemminger > Date: Tue, 7 Oct 2008 16:07:29 +0200 > > > The idea of keeping chains short is the problem. That code should > > just be pulled because it doesn't help that much, and also creates > > bias on the port randomization. > > I have that patch from Vitaly Mayatskikh which does exactly this. > > I keep looking at it, but I can't bring myself to apply it since > I'm not completely convinced. Some one on a busy server should run it and measure the delta in hash chains. I would, but don't run anything that has more than a few UDP's open.