Re: another new paradigm

From: Henrik Nordstrom <hno@dont-contact.us>
Date: Thu, 23 Apr 1998 23:38:18 +0200

--MimeMultipartBoundary
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Martin Hamilton wrote:

> I'm thinking that it should be up to the admin of the requesting cache
> who they want to honour referrals for - perhaps by piggybacking off
> the multicast-responder code. The bottom line is that if you get
> redirected to a server you don't have configured as a peer already,
> you probably don't want to trust the redirection ? Trust is indicated
> by the presence of a cache_peer entry of some sort in squid.conf

I was not thinking so much about trust, but rather fault detection. If
the requesting cache detects that the "redirected" cache is unavailable,
should the grand central be notified about this?

While speaking about trust. If the grand central has records of more
than one cache having the object then it probably should respond with
more than one cache address, to give the requesting cache a option to
select which cache to fetch the object from based on trust, bandwidth or
cost configuration.

/Henrik

--MimeMultipartBoundary--
Received on Tue Jul 29 2003 - 13:15:47 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:11:45 MST