From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760152AbZD1KWs (ORCPT ); Tue, 28 Apr 2009 06:22:48 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932457AbZD1KVx (ORCPT ); Tue, 28 Apr 2009 06:21:53 -0400 Received: from mail-bw0-f163.google.com ([209.85.218.163]:45243 "EHLO mail-bw0-f163.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932445AbZD1KVv (ORCPT ); Tue, 28 Apr 2009 06:21:51 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; b=aweSqlow0nefhr9e1s2sp1Id/QXDLM1F4lKVJ26dgO7TZayTWcQnNm5ve0YPoe8oKi 2F3my4WWSGfE7Ut+qlnbxr4Rqj6Lt98BikVrs/z+YTAosl4GjxIvH+xF6DURZJEDy4V9 9VC+yq6WZ09eKotjqXduQDm88p9BMRkRSCXgU= MIME-Version: 1.0 In-Reply-To: <20090428190822.EBED.A69D9226@jp.fujitsu.com> References: <20090428093621.GD21085@elte.hu> <84144f020904280257j57b5b686k91cc4096a8e5ca29@mail.gmail.com> <20090428190822.EBED.A69D9226@jp.fujitsu.com> Date: Tue, 28 Apr 2009 13:21:50 +0300 X-Google-Sender-Auth: d63f090a41de331c Message-ID: <84144f020904280321u4be9fb10t6f0123b589752b80@mail.gmail.com> Subject: Re: [PATCH 5/5] proc: export more page flags in /proc/kpageflags From: Pekka Enberg To: KOSAKI Motohiro Cc: Ingo Molnar , Andi Kleen , Wu Fengguang , Steven Rostedt , =?ISO-2022-JP?B?RnIbJEJxRXFTGyhCaWMgV2Vpc2JlY2tlcg==?= , Larry Woodman , Peter Zijlstra , Eduard - Gabriel Munteanu , Andrew Morton , LKML , Matt Mackall , Alexey Dobriyan , "linux-mm@kvack.org" Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi! 2009/4/28 KOSAKI Motohiro : >> I guess the main question here is whether this approach will scale to >> something like kmalloc() or the page allocator in production >> environments. For any serious workload, the frequency of events is >> going to be pretty high. > > Immediate Values patch series makes zero-overhead to tracepoint > while it's not used. > > So, We have to implement to stop collect stastics way. it restore > zero overhead world. > We don't lose any performance by trace. Sure but I meant the _enabled_ case here. kmalloc() (and the page allocator to some extent) is very performance sensitive in many workloads so you probably don't want to use tracepoints if you're collecting some overall statistics (i.e. tracing all events) like we do here. Pekka From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail172.messagelabs.com (mail172.messagelabs.com [216.82.254.3]) by kanga.kvack.org (Postfix) with SMTP id 0E9186B0047 for ; Tue, 28 Apr 2009 06:21:31 -0400 (EDT) Received: by bwz21 with SMTP id 21so545082bwz.38 for ; Tue, 28 Apr 2009 03:21:50 -0700 (PDT) MIME-Version: 1.0 In-Reply-To: <20090428190822.EBED.A69D9226@jp.fujitsu.com> References: <20090428093621.GD21085@elte.hu> <84144f020904280257j57b5b686k91cc4096a8e5ca29@mail.gmail.com> <20090428190822.EBED.A69D9226@jp.fujitsu.com> Date: Tue, 28 Apr 2009 13:21:50 +0300 Message-ID: <84144f020904280321u4be9fb10t6f0123b589752b80@mail.gmail.com> Subject: Re: [PATCH 5/5] proc: export more page flags in /proc/kpageflags From: Pekka Enberg Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org To: KOSAKI Motohiro Cc: Ingo Molnar , Andi Kleen , Wu Fengguang , Steven Rostedt , =?ISO-2022-JP?B?RnIbJEJxRXFTGyhCaWMgV2Vpc2JlY2tlcg==?= , Larry Woodman , Peter Zijlstra , Eduard - Gabriel Munteanu , Andrew Morton , LKML , Matt Mackall , Alexey Dobriyan , "linux-mm@kvack.org" List-ID: Hi! 2009/4/28 KOSAKI Motohiro : >> I guess the main question here is whether this approach will scale to >> something like kmalloc() or the page allocator in production >> environments. For any serious workload, the frequency of events is >> going to be pretty high. > > Immediate Values patch series makes zero-overhead to tracepoint > while it's not used. > > So, We have to implement to stop collect stastics way. it restore > zero overhead world. > We don't lose any performance by trace. Sure but I meant the _enabled_ case here. kmalloc() (and the page allocator to some extent) is very performance sensitive in many workloads so you probably don't want to use tracepoints if you're collecting some overall statistics (i.e. tracing all events) like we do here. Pekka -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org