On Tue, 1 Jun 1999, Dax Kelson wrote:
> I was working on a commercial caching box today, the only feature it had
> that Squid didn't was the following.
Was it CacheFlow or some other product?
> When a user requests a html document, the commercial box scans that html
> document for additional objects (mostly images) and starts retrieving
> those immediately. Shortly after, when the client requests those objects,
> the cache box either has them already, or is already getting them.
>
> Could this be implemented in Squid?
Yes. Anything can be implemented. However, note that your description
already implies that a straightforward implementation is not going to
improve anything (and it does have overheads): The key here is "shortly
after". If a user is going to request embedded objects shortly after the
HTML page, the benefits of prefetching those objects in terms of user
response time are, well, "short". Some people also think that pro-active
prefetching tends to violate resource conservation requirements of HTTP.
One could argue that a cache could manage its resources in a smart,
optimized way if the list of embedded objects is known. If that is
possible and worth doing remains to be seen.
Alex.
Received on Wed Jun 02 1999 - 02:24:22 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:46:42 MST