From owner-freebsd-hackers  Sat Jun  1 09:27:09 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id JAA22629
          for hackers-outgoing; Sat, 1 Jun 1996 09:27:09 -0700 (PDT)
Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.19])
          by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id JAA22608
          for <hackers@FreeBSD.ORG>; Sat, 1 Jun 1996 09:27:04 -0700 (PDT)
Received: (from bde@localhost) by godzilla.zeta.org.au (8.6.12/8.6.9) id CAA23320; Sun, 2 Jun 1996 02:23:12 +1000
Date: Sun, 2 Jun 1996 02:23:12 +1000
From: Bruce Evans <bde@zeta.org.au>
Message-Id: <199606011623.CAA23320@godzilla.zeta.org.au>
To: bde@zeta.org.au, dufault@hda
Subject: Re: Breaking ffs - speed enhancement?
Cc: dufault@hda.zipnet.net, hackers@FreeBSD.ORG, terry@lambert.org
Sender: owner-hackers@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

>> It already permits agressive async behaviour, because update has
>> nothing to do with writing to disk.  It just requires the update
>> marks (if any) to be converted to actual timestamps.

>I know - I meant "more aggressive" by not converting update marks
>to time stamps if you don't care.  Maybe that is overkill, I thought
>the original application called for something like this.

You would still have to keep the update marks somewhere :-).  They
should compress very well since they are only 1 bit to begin with
and have a steady state value of 1 :-).

Bruce