From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755663Ab2ERPbN (ORCPT ); Fri, 18 May 2012 11:31:13 -0400 Received: from mail-pb0-f46.google.com ([209.85.160.46]:50839 "EHLO mail-pb0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754871Ab2ERPbJ (ORCPT ); Fri, 18 May 2012 11:31:09 -0400 Message-ID: <4FB66B31.3020509@gmail.com> Date: Fri, 18 May 2012 23:30:57 +0800 From: Nai Xia Reply-To: nai.xia@gmail.com Organization: NJU User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:12.0) Gecko/20120430 Thunderbird/12.0.1 MIME-Version: 1.0 To: Rik van Riel CC: Johannes Weiner , linux-mm@kvack.org, Andrea Arcangeli , Peter Zijlstra , Mel Gorman , Andrew Morton , Minchan Kim , Hugh Dickins , KOSAKI Motohiro , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [patch 0/5] refault distance-based file cache sizing References: <1335861713-4573-1-git-send-email-hannes@cmpxchg.org> <4FB33A4E.1010208@gmail.com> <20120516065132.GC1769@cmpxchg.org> <4FB3A416.9010703@gmail.com> <20120517210849.GE1800@cmpxchg.org> <4FB5C5A7.6080000@gmail.com> <4FB665B8.8000300@redhat.com> In-Reply-To: <4FB665B8.8000300@redhat.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 2012年05月18日 23:07, Rik van Riel wrote: > On 05/17/2012 11:44 PM, Nai Xia wrote: > >> But I do think that Clock-pro deserves its credit, since after all >> it's that research work firstly brought the idea of "refault/reuse >> distance" to the kernel community. > > The ARC people did that, too. Well, I think you said "take the good parts of clock-pro"... Anyway, then I think you should credit either of the previous works... :D > >> Further more, it's also good >> to let the researchers and the community to together have some >> brain-storm of this problem if it's really hard to deal with in >> reality. > > How much are researchers interested in the real world > constraints that OS developers have to deal with? I think there will be nobody, if we don't try to let them know about the constraints. Honestly, LKML are hard for researchers to follow. They really need abstract view of a problem. Surely there is a gap...between researchers and developers. > > Often scalability is as much of a goal as being good > at selecting the right page to replace... > Then scalability might be a good research topic as long as they have the chance to understand the details. Ok, all I want to say is another way that may help the kernel world better. I am actually quite positive about the patch itself.