From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752777AbbFVSvA (ORCPT ); Mon, 22 Jun 2015 14:51:00 -0400 Received: from www.sr71.net ([198.145.64.142]:44774 "EHLO blackbird.sr71.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751248AbbFVSux (ORCPT ); Mon, 22 Jun 2015 14:50:53 -0400 Message-ID: <5588590A.7080001@sr71.net> Date: Mon, 22 Jun 2015 11:50:50 -0700 From: Dave Hansen User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.7.0 MIME-Version: 1.0 To: paulmck@linux.vnet.ibm.com, Peter Zijlstra CC: Andi Kleen , dave.hansen@linux.intel.com, akpm@linux-foundation.org, jack@suse.cz, viro@zeniv.linux.org.uk, eparis@redhat.com, john@johnmccutchan.com, rlove@rlove.org, tim.c.chen@linux.intel.com, linux-kernel@vger.kernel.org Subject: Re: [RFC][PATCH] fs: optimize inotify/fsnotify code for unwatched files References: <20150619215025.4F689817@viggo.jf.intel.com> <20150619233306.GT25760@tassilo.jf.intel.com> <5584B62F.5080506@sr71.net> <20150620022135.GF3913@linux.vnet.ibm.com> <5585AAA0.1030305@sr71.net> <20150621013058.GH3913@linux.vnet.ibm.com> <20150622132821.GB12596@twins.programming.kicks-ass.net> <20150622151121.GK3913@linux.vnet.ibm.com> In-Reply-To: <20150622151121.GK3913@linux.vnet.ibm.com> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 06/22/2015 08:11 AM, Paul E. McKenney wrote: > But if Dave is willing to test it, I would be happy to send along > a fast-readers patch, easy to do. I'm always willing to test, but the cost of the srcu_read_lock() barrier shows up even on my 2-year-old "Intel(R) Core(TM) i5-3320M CPU @ 2.60GHz" laptop. The numbers I shared in this thread are on a newer CPU than that, so I'm fairly confident this will show up on just about any (big core) Intel CPU newer than SandyBridge. The tests I've been running are: https://github.com/antonblanchard/will-it-scale with two new 1-byte read/write tests copied in to "tests/": https://www.sr71.net/~dave/intel/read1byte.c https://www.sr71.net/~dave/intel/write1byte.c The one-byte thing is silly but it does help isolate the kernel's overhead from what the app is doing. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in Please read the FAQ at http://www.tux.org/lkml/