From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751860Ab1IFEYz (ORCPT ); Tue, 6 Sep 2011 00:24:55 -0400 Received: from mail-yw0-f46.google.com ([209.85.213.46]:61777 "EHLO mail-yw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750731Ab1IFEYw convert rfc822-to-8bit (ORCPT ); Tue, 6 Sep 2011 00:24:52 -0400 MIME-Version: 1.0 In-Reply-To: <201109051704.12040.arnd@arndb.de> References: <4E5B4AAF.2040101@samsung.com> <20110905121840.GA4768@infradead.org> <201109051704.12040.arnd@arndb.de> Date: Tue, 6 Sep 2011 13:24:51 +0900 X-Google-Sender-Auth: Z1Y3ECgh5jGqS2uAAZKaxhuZJ9w Message-ID: Subject: Re: [RFC PATCH v2] support ioctl for tunable user request From: Kyungmin Park To: Arnd Bergmann Cc: Christoph Hellwig , Jens Axboe , Jaehoon Chung , "linux-kernel@vger.kernel.org" , Lin Ming Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Sep 6, 2011 at 12:04 AM, Arnd Bergmann wrote: > On Monday 05 September 2011, Kyungmin Park wrote: >> On Mon, Sep 5, 2011 at 9:18 PM, Christoph Hellwig wrote: >> > On Mon, Sep 05, 2011 at 08:47:58PM +0900, Kyungmin Park wrote: >> >> The concept is similar with DISCARD request except no-wait for request complete >> >> >> >>  #define REQ_DISCARD            (1 << __REQ_DISCARD) >> >> +#define REQ_TUNE               (1 << __REQ_TUNE) >> >> >> >> As it's hard to detect the idle time at device level, user send the >> >> tune request to device when idle. >> > >> > But what does a "tune" request actually do?  It's an overly generic >> > term, but I still can't even think of what it would do to a storage >> >> Yes, tune is generic term, that's reason to send the RFC patch, we >> consider the several names, but not found the proper name, if you >> suggest the proper name, it can change the proper one. > > Would __REQ_GC as a shortcut for garbage collection fit? Right now, > I also think TUNE is not at all describing what we expect the drive > to do, but it's hard to come up with a term that is generic enough > to cover similar concepts in other hardware while still describing > what the drive does. No problem to use the REQ_GC. BTW, does it acceptable to GC request? I hope each devices can do own optimization if REQ_GC is requested, if no need to these one, just ignore it at driver level. Thank you, Kyungmin Park