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 16:07:10 -0700 (PDT) Message-ID: <20080827.160710.80433973.davem@davemloft.net> References: <20080827223410.GC26610@one.firstfloor.org> <20080827.153907.157997966.davem@davemloft.net> <87fxoqqd62.fsf@basil.nowhere.org> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: davej@redhat.com, netdev@vger.kernel.org, j.w.r.degoede@hhs.nl To: andi@firstfloor.org Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:50897 "EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1753833AbYH0XHP (ORCPT ); Wed, 27 Aug 2008 19:07:15 -0400 In-Reply-To: <87fxoqqd62.fsf@basil.nowhere.org> Sender: netdev-owner@vger.kernel.org List-ID: From: Andi Kleen Date: Thu, 28 Aug 2008 00:57:25 +0200 > David Miller writes: > > > From: Andi Kleen > > Date: Thu, 28 Aug 2008 00:34:10 +0200 > > > >> It fixes an old performance problem at least. I'm not aware > >> of any new ones in this area because the code in this > >> function hasn't changed since I last looked. > > > > That's exactly what this thread is about, things got slower for > > some reason even though nothing specifically changed in this area. > > I reread the original bug and it says nothing about a regression > (unless I'm blind). I think the reporter just ran into the slowness that > was pretty much always there[1] (and which my patch improves) It's a regression compared to older kernels. It got slower by a factor of 5 or something like that.