Re: storeGet() -> storeGetPublic() ?

Adrian Chadd wrote:

> Ok, good point. I was planning on having each FS export a cache digest,
> but this may be impractical for some filesystems. Instead, what could
> happen is that each FS *could* export a cache digest, for example the
> reimplementation of ufs/aufs/diskd will require an in-memory index
> anyway, so building a digest from that shouldn't be terribly difficult.
> Something like reiserfs_raw might not be so easy because the index
> is on-disk.

The FS can only export the index, not a digest, or it would only work
for a single cache_dir. It is far from trivial to merge several
independent digests into one. (well, it might be possible if all are of
identical size and underpopulated in proportion to how many digets are
being merged.. but I do not see that as a viable approach here)

> In this way, cache digest building becomes part of the FS rather than
> squid, and if the administrator chooses to use a FS which doesn't build
> a digest then he doesn't get them.

I'd rather see that he doesn't get filesystems who cannot export the
index in an reasonable manner included in the digest.

/Henrik
Received on Sun Jan 07 2001 - 04:22:07 MST