hop-count header

maex@Space.Net writes:

>If you work on a solution (wasn't there a kind of a "Received" header
>to be added by caches) I'd have a slightly off topic proposal that
>I am thinking of for quite some time:
>Could we have a kind of a hop-count in the objects? This would be
>set to one 1, if the object is fetched directly from the origin server
>and would be incremented by one if already present (i.e. fetched from
>a parent or neighbor).
>This would allow cache admins to add a "radius" value to the cache_host
>directive.
>The benefit would IMHO be a bit more security: I trust my neighbor that
>it doesn't feed in "false" objects, so I trust the objects this neighbor
>got directly. But I don't know about its neighbors, so I don't want
>to accept objects that this cache got from one of its neighbors. So I
>would set the radius value for this neighbor to 1.
>On the other hand I trust my parent in the choice of neighbors, so I
>set the radius to 2 and would accept objects that my parent got directly
>or with radius 1 from its neighbors.

I've thought about this as well. I think it would be very useful.
I'm thinking of something like

        X-Max-Cache-Hops: 3

And each cache would decrement the counter before forwarding. When
the count reaches zero, the request could only be forwarded to the
origin server.

But how does this affect someones desire to use a parent cache for all
requests? Just yesterday on squid-users was a message from someone
who pays $0.14/MB for parent cache traffic and $0.24/MB for direct
traffic. Is this person willing to pay more just because the hops
header reaches zero?

Duane W.
Received on Tue Jul 29 2003 - 13:15:44 MDT