[1898] in Release_7.7_team

home help back first fref pref prev next nref lref last post

Re: cluster machines with hesiod information

daemon@ATHENA.MIT.EDU (Thomas Bushnell, BSG)
Sun Aug 1 23:07:47 1999

To: Jonathon Weiss <jweiss@MIT.EDU>
Cc: Garry Zacheiss <zacheiss@MIT.EDU>, release-team@MIT.EDU
From: tb@MIT.EDU (Thomas Bushnell, BSG)
Date: 01 Aug 1999 23:07:35 -0400
In-Reply-To: Jonathon Weiss's message of "Sun, 01 Aug 1999 19:03:48 -0400"
Message-Id: <u1hpv16khhj.fsf@steve-dallas.mit.edu>

Jonathon Weiss <jweiss@MIT.EDU> writes:

> However, it's possible that we decided
> that having more than two or three early machines in the clusters was
> a good thing.

If it's being revisited, I would suggest that we aim for something
like 10% of cluster machines being in early, with some in each
cluster.  

home help back first fref pref prev next nref lref last post