G'day,

I am in the process of setting up a _home_ fileserver with twin 80-gig
disks (RAID-1 mirrored) and am looking for a distributed filesystem
which will permit replication of some of my data (onto smaller ~40 gig
drives I already have), scalability (up to the 200+ gig range) and
single namespace across my network (mostly 100baseT linux boxes but
also some Windoze and one colocated server across an untrusted WAN).

I thought that CODA was the answer but it seems that it does not scale
to that extent (Ref: some postings in 1999 and one or two in this list in
early 2002). The documentation says the RVM metadata needs to be 4%
of the total shared size and it needs to be backed by virtual memory
for that same quantity.

So for an 80 gig server that would be 3.2 gigs of RVM metadata, but
does it really need 3.2 gigs of main memory and/or 3.2 gigs of swap
space? My server has only 512 megs of main memory, soon 1024.

Perhaps the question is moot, I think somebody said that 80 gigs
was about the absolute maximum possible on the i386 architecture.

Is any work being done on making CODA scale more?

I have spent many hours slaving over a google search window and
investigating distributed filesystems for linux. At the moment
the most appropriate choice for any replicated data seems to be
Inter-Mezzo because it uses a real filesystem as a base (and a
real or virtual filesystem on the client). However I can't
replicate 80+ gigs on every client, so the LAN-connected
clients may well end up mounting the large filesystem using NFS.
It's ugly, and I'm not sure how well I can mix Inter-Mezzo and
NFS.

What would be nice is a transparent filesystem or union filesystem
so that I can acquire data in different ways and put it all together
into one namespace which never has to change (just gets bigger)
but I think that linux doesn't have a union filesystem, and if
it did, it's not clear how that would be distributed.

Does anybody have suggestions for a product, patch or architecture
which I haven't considered here?

Nick.