From mboxrd@z Thu Jan  1 00:00:00 1970
From: Daniel Phillips <daniel@phunq.net>
Subject: Re: [FYI] tux3: Core changes
Date: Tue, 26 May 2015 01:08:56 -0700
Message-ID: <a2233e75-a0bc-4732-9d6f-ad4d7cde0bae@phunq.net>
References: <555CB4B6.8050305@phunq.net> <555CE62C.5030202@redhat.com>
 <555D0FDF.3070303@phunq.net> <555D500B.4080901@phunq.net>
 <alpine.DEB.2.02.1505202050530.25699@nftneq.ynat.uz>
 <13c8bcdf-70e8-43d5-a05f-58ad839dbfd0@phunq.net>
 <5563F5C8.2040806@redhat.com>
 <dd591950-58c6-4268-9683-bd4c46cef292@phunq.net>
 <alpine.DEB.2.02.1505252303120.3147@nftneq.ynat.uz>
 <67294911-1776-46b8-916d-0e5642a38725@phunq.net>
 <20150526070910.GA3307@quack.suse.cz>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"; Format="flowed"
Content-Transfer-Encoding: 7bit
Cc: David Lang <david@lang.hm>, Rik van Riel <riel@redhat.com>, tux3@tux3.org,
 linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
 OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
To: Jan Kara <jack@suse.cz>
Return-path: <tux3-bounces@phunq.net>
In-Reply-To: <20150526070910.GA3307@quack.suse.cz>
List-Unsubscribe: <http://phunq.net/mailman/options/tux3>,
 <mailto:tux3-request@phunq.net?subject=unsubscribe>
List-Archive: <http://phunq.net/pipermail/tux3/>
List-Post: <mailto:tux3@phunq.net>
List-Help: <mailto:tux3-request@phunq.net?subject=help>
List-Subscribe: <http://phunq.net/mailman/listinfo/tux3>,
 <mailto:tux3-request@phunq.net?subject=subscribe>
Errors-To: tux3-bounces@phunq.net
Sender: "Tux3" <tux3-bounces@phunq.net>
List-Id: linux-fsdevel.vger.kernel.org

On Tuesday, May 26, 2015 12:09:10 AM PDT, Jan Kara wrote:
>   E.g. video drivers (or infiniband or direct IO for that matter) which
> have buffers in user memory (may be mmapped file), grab references to pages
> and hand out PFNs of those pages to the hardware to store data in them...
> If you fork a page after the driver has handed PFNs to the hardware, you've
> just lost all the writes hardware will do.

Hi Jan,

The page forked because somebody wrote to it with write(2) or mmap write at
the same time as a video driver (or infiniband or direct IO) was doing io 
to
it. Isn't the application trying hard to lose data in that case? It would 
not need page fork to lose data that way.

Regards,

Daniel