From owner-freebsd-hackers  Wed Feb 14 04:42:18 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.3/8.7.3) id EAA21650
          for hackers-outgoing; Wed, 14 Feb 1996 04:42:18 -0800 (PST)
Received: from tepcogw.tepco.co.jp (tepcogw.tepco.co.jp [202.32.50.1])
          by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id EAA21645
          for <hackers@freebsd.org>; Wed, 14 Feb 1996 04:42:15 -0800 (PST)
From: T0682740@pmail.tepco.co.jp
Received: by tepcogw.tepco.co.jp (8.6.9+2.4W/3.3W995032220)
	id VAA22634; Wed, 14 Feb 1996 21:40:35 +0900
Received: from j1102041 (h1009043) by h1009051.smtpgw.tepco.co.jp (4.1/6.4J.6)
	id AA27706; Wed, 14 Feb 96 21:31:39 JST
Received: from j1101044 by j1102041 (AIX 3.2/UCB 5.64/4.03)
          id AA47501; Wed, 14 Feb 1996 21:30:29 +0900
Received: from loopback by j1101044.pmail.tepco.co.jp (AIX 3.2/UCB 5.64/4.03)
          id AA33384; Wed, 14 Feb 1996 21:31:53 +0900
Received: by pmail.tepco.co.jp (ATSON-1) ; 14 Feb 96 21:31:53 JST
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-2022-JP
Subject: Re: VM question
In-Reply-To: <199602131806.LAA23438@phaeton.artisoft.com>
X-From: =?ISO-2022-JP?B?GyRCP0pGIyEhO3E3MRsoSg==?=
Date: 14 Feb 96 21:31:15 JST
To: terry@lambert.org
Cc: hackers@freebsd.org
Lines: 33
Message-Id: <3121D613.C680.001@pmail.tepco.co.jp>
Content-Type: text/plain; charset=ISO-2022-JP
Sender: owner-hackers@freebsd.org
Precedence: bulk

Hi,

> The Usenix papers are generally available for anonymouse FTP, both by
> the authors home site, and from the Usenix SAGE group ftp site.  The
> SAGE FTP site is:  ftp://ftp/sage.usenix.org/

Unfortunately they don't hold the latest papers. Only up to 1994 or
so.

> FreeBSD does not have a mach VM system any more.  The MACH VM system
> does not operate (implicitly) on a unified buffer cache scheme.  Cache
> unification is an important win.

Is there any paper about unified buffer cache scheme? 

> You could implement an external demand pager on the basis of trapping
> the SIGSEGV signal, and implementing mapping of resources as a result;
> you would robably be better off providing a kernel interface, however,
> since you would have to coalesce domains to keep the number of entries
> small enough to avoid problems.

Actually, I'd like to implement a sort of DSM that provides
page-in/out over the network transparently to the user process.

> There are a couple of Usenix papers on this technique as well; other
> papers are available at the CS department of Washington State University's
> FTP server.

I haven't checked this yet but I'll try it. Thanks!

---
Motonori Shindou