From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: cat /proc/net/tcp takes 0.5 seconds on x86_64 Date: Thu, 28 Aug 2008 00:57:25 +0200 Message-ID: <87fxoqqd62.fsf@basil.nowhere.org> References: <87zlmyr5nz.fsf@basil.nowhere.org> <20080827.142941.50104491.davem@davemloft.net> <20080827223410.GC26610@one.firstfloor.org> <20080827.153907.157997966.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: davej@redhat.com, netdev@vger.kernel.org, j.w.r.degoede@hhs.nl To: David Miller Return-path: Received: from one.firstfloor.org ([213.235.205.2]:52187 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752874AbYH0W5b (ORCPT ); Wed, 27 Aug 2008 18:57:31 -0400 In-Reply-To: <20080827.153907.157997966.davem@davemloft.net> (David Miller's message of "Wed, 27 Aug 2008 15:39:07 -0700 (PDT)") Sender: netdev-owner@vger.kernel.org List-ID: 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) -Andi [1] ok it got more noticeable over time because people have more memory than they used to have, which made the hash table bigger. -- ak@linux.intel.com