From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: cat /proc/net/tcp takes 0.5 seconds on x86_64 Date: Wed, 27 Aug 2008 16:45:35 -0700 (PDT) Message-ID: <20080827.164535.150037784.davem@davemloft.net> References: <48B5DE9F.4010000@cosmosbay.com> <20080827.161504.183610665.davem@davemloft.net> <48B5E6A3.6@cosmosbay.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: andi@firstfloor.org, davej@redhat.com, netdev@vger.kernel.org, j.w.r.degoede@hhs.nl To: dada1@cosmosbay.com Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:44709 "EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1753690AbYH0Xpk convert rfc822-to-8bit (ORCPT ); Wed, 27 Aug 2008 19:45:40 -0400 In-Reply-To: <48B5E6A3.6@cosmosbay.com> Sender: netdev-owner@vger.kernel.org List-ID: =46rom: Eric Dumazet Date: Thu, 28 Aug 2008 01:43:31 +0200 > David Miller a =E9crit : > > From: Eric Dumazet > > Date: Thu, 28 Aug 2008 01:09:19 +0200 > >=20 > >> Not really, I suspect commit (a7ab4b501f9b8a9dc4d5cee542db67b6ccd1= 088b [TCPv4]: Improve BH latency in /proc/net/tcp) is responsible for l= onger delays. > >> Note that its rather old : > > ... > >> We used to disable bh once, while reading the table. This sucked. > >> > >> In case machine is handling trafic, we now are preemptable by soft= irqs > >> while reading /proc/net/tcp. Thats a good thing. > > Yes, that would account for it, good spotting. > >=20 > >> By the way, I find Andi patch usefull. Same thing could be done fo= r /proc/net/rt_cache. > > Fair enough. If you can cook up a quick rt_cache patch I'll toss i= t and > > Andi's patch into net-next so it can cook for a while. >=20 > Well, first patch I would like to submit is about letting netlink bei= ng able to be faster than /proc/net/tcp again :) Andi just posted a very similar patch :)