Re: how hint caching works

On Wednesday 21 November 2001 19.01, Jon Kay wrote:

> Our major goal is minimizing latency. After all, that is what caches
> exist for, at the end of the day. Making life faster for the users.
>
> We recognize that for many countries on limited bandwidth, minimizing
> latency and bandwidth usage are one and the same, but in places with
> plentiful bandwidth, there is a divergence. Permit me to guess that you
> guys probably are OK on local bandwidth, even though your bandwidth
> to anywhere else must needs travel more thousands of miles than we like
> to think about and thus must cost accordingly?

Any thoughts how "Hint cache" compares to other local request routing
mechanisms like CARP in what can be expected real world cache setups?

CARP is quite beautiful in that it has a minimal amont of meta data (only the
actual formation of the "cloud", not the content) and yet allows requests to
always hit the correct cache.. but assumes all members of the same "cloud" is
local to each other unless the requestor also implements CARP routing (in
which case similar proximity to the requestor is assumed).

The drawback is that CARP is somewhat "centralized/static" in it's nature,
with a single request path per URL in a given "cloud" formation, not allowing
it to adopt to different usage patterns.

Regards
Henrik
Received on Wed Nov 21 2001 - 12:31:21 MST