From mboxrd@z Thu Jan  1 00:00:00 1970
From: "Kyungmin Park" <kmpark@infradead.org>
Subject: Re: Proposal to improve filesystem/block snapshot interaction
Date: Wed, 31 Oct 2007 08:42:11 +0900
Message-ID: <9c9fda240710301642u79ccb6bar5f84cadf10086b0f@mail.gmail.com>
References: <20070927063113.GD2989@sgi.com> <20071030010453.GF27385@sgi.com>
	 <7fe698080710300235v3ce49613nfe3c5e733f1b6f5b@mail.gmail.com>
	 <200710301115.30376.arnd@arndb.de>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Cc: "Dongjun Shin" <djshin90@gmail.com>, "Greg Banks" <gnb@sgi.com>,
	"Linux Filesystem Mailing List" <linux-fsdevel@vger.kernel.org>,
	"David Chinner" <dgc@melbourne.sgi.com>,
	"Donald Douwsma" <donaldd@melbourne.sgi.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Roger Strassburg" <rls@sgi.com>, "Mark Goodwin" <markgw@sgi.com>,
	"Brett Jon Grandbois" <brettg@melbourne.sgi.com>
To: "Arnd Bergmann" <arnd@arndb.de>
Return-path: <linux-fsdevel-owner@vger.kernel.org>
Received: from wr-out-0506.google.com ([64.233.184.227]:52753 "EHLO
	wr-out-0506.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1753589AbXJ3XmN (ORCPT
	<rfc822;linux-fsdevel@vger.kernel.org>);
	Tue, 30 Oct 2007 19:42:13 -0400
Received: by wr-out-0506.google.com with SMTP id 36so1240669wra
        for <linux-fsdevel@vger.kernel.org>; Tue, 30 Oct 2007 16:42:12 -0700 (PDT)
In-Reply-To: <200710301115.30376.arnd@arndb.de>
Content-Disposition: inline
Sender: linux-fsdevel-owner@vger.kernel.org
List-Id: linux-fsdevel.vger.kernel.org

On 10/30/07, Arnd Bergmann <arnd@arndb.de> wrote:
> On Tuesday 30 October 2007, Dongjun Shin wrote:
> > There is an ongoing discussion about adding 'Trim' ATA command for notifying
> > the drive about the deleted blocks.
> >
> > http://www.t13.org/Documents/UploadedDocuments/docs2007/e07154r3-Data_Set_Management_Proposal_for_ATA-ACS2.pdf
> >
> > This is especially useful for the storage device like Solid State Drive (SSD).
> >
> This make me curious, why would t13 want to invent a new command when
> there is already the erase command from CFA?
>
> It's not exactly the same, but close enough that the proposed BIO_HINT_RELEASE
> should probably be mapped to CFA_ERASE (0xc0) on drives that support it:
> http://t13.org/Documents/UploadedDocuments/technical/d97116r1.pdf
>

IHMO, the main difference is that it requires the physical operation or not.
The CFA_ERAES erases the free blocks, it requires the physical erase operation.
But in trim case, it just unmapped the free blocks at FTL level. it
doesn't require the physical operation.
It's time saving and we can do a lot of works at FTL level internally.

Thank you,
Kyungmin Park

I