Re: Vary, store interface

From: Robert Collins <robert.collins@dont-contact.us>
Date: Thu, 18 Jan 2001 08:57:31 +1100

So do you see storeGetPublicRange for partials?

----- Original Message -----
From: "Henrik Nordstrom" <hno@hem.passagen.se>
To: "Adrian Chadd" <adrian@creative.net.au>
Cc: <squid-dev@squid-cache.org>
Sent: Thursday, January 18, 2001 7:53 AM
Subject: Re: Vary, store interface

> Adrian Chadd wrote:
>
> > You know, it might make sense to change the semantics of
> > storeGet() to take a request_t or something.
>
> Did just that ;-)
>
> StoreEntry *storeGetPublicByRequest(request_t *);
> StireEntry *storeGetPublicByRequestMethod(request_t *, method_t);
> store_key *storeKeyPublicByRequest(request_t *);
> store_key *storeKeyPublicByRequestMethod(request_t *, method_t);
>
> The old method are still used at some places, where no request_t
> structure is available.
>
> > I'm just trying to see how we could extend the store interface here.
>
> Me too, at least in the long run. This excersise gives quite a bit of
> light on what a full proper Vary implementation requires from the store.
>
> > The vary work is nice but I'd like it to sit under one interface.
>
> In the end I guess storeGet/storeOpen/whatever has to implement Vary,
> and accept a request_t structure as input and work it out from there.
> The other access methods should be killed I guess.
>
> There should also be a storeDelete interface working similarily. There
> is a number of places where the cache needs to be purged even if no new
> object are added. For example on methods known to modify the origin
> server.
>
> /Henrik
>
>
Received on Wed Jan 17 2001 - 14:45:35 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:13:24 MST