From mboxrd@z Thu Jan  1 00:00:00 1970
From: Matthew Wilcox <matthew@wil.cx>
Subject: Re: NFSv4/pNFS possible POSIX I/O API standards
Date: Tue, 28 Nov 2006 08:08:52 -0700
Message-ID: <20061128150852.GS14076@parisc-linux.org>
References: <6.2.3.4.2.20061127213243.04f786c0@cic-mail.lanl.gov>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: linux-fsdevel@vger.kernel.org
Return-path: <linux-fsdevel-owner@vger.kernel.org>
Received: from palinux.external.hp.com ([192.25.206.14]:10677 "EHLO
	mail.parisc-linux.org") by vger.kernel.org with ESMTP
	id S1758683AbWK1PIx (ORCPT <rfc822;linux-fsdevel@vger.kernel.org>);
	Tue, 28 Nov 2006 10:08:53 -0500
To: Gary Grider <ggrider@lanl.gov>
Content-Disposition: inline
In-Reply-To: <6.2.3.4.2.20061127213243.04f786c0@cic-mail.lanl.gov>
Sender: linux-fsdevel-owner@vger.kernel.org
List-Id: linux-fsdevel.vger.kernel.org

On Mon, Nov 27, 2006 at 09:34:05PM -0700, Gary Grider wrote:
> >Things like
> >openg()  - on process opens a file and gets a key that is passed to 
> >lots of processes which
> >use the key to get a handle (great for thousands of processes opening a 
> >file)

I don't understand how this leads to a more efficient implementation.
It seem to just add complexity.  What does 'sutoc' mean anyway?

> >readx/writex - scattergather readwrite - more appropriate and 
> >complete than the real time extended read/write

These don't seem to be documented on the website.