[8586] in Info-AFS_Redistribution
Re: "hard mounts"
daemon@ATHENA.MIT.EDU (Lyle Seaman)
Sat Mar 17 11:07:57 2001
Message-ID: <3AB389F9.D1A5B3F@spinnakernet.com>
Date: Sat, 17 Mar 2001 10:59:53 -0500
From: Lyle Seaman <lws@spinnakernet.com>
MIME-Version: 1.0
To: info-afs@transarc.com
CC: openafs-info@openafs.org
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Phil.Moore@msdw.com wrote:
> We depend on this here at MSDW, and without it, wouldn't be running
> AFS. See the long winded story below if you don't understand why this
> is so important.
>
I think I can explain this concisely. MSDW has (had?) an essentially
data-less configuration. 98% of the client OS executables actually
resided in AFS Read-Only volumes, especially including the X server and
some other critical things.
In the event of a network outage, the client would sequentially time-out
on each of the three or four replicas, and then X would crash, along with
all the applications. Recovery basically involved rebooting,
which turned a four-minute outage into a 15-minute outage.
Worse, if the network outage affected a hundred clients, and then a
hundred clients were forced to reboot more-or-less simultaneously, they
would hit the file servers pretty hard, turning a 15-minute outage into a
half-hour outage.
(how's that? about right? )
