I agree w/Doug here. A good IP network and NFS sounds like it would do the
trick. Netapp has a very good solution in the R150 if you want to integrate
the NFS server function, and their NFS server is extremely solid...
Otherwise, NexSAN and LSI have very good IDE disk solutions, but you have to
worry about load balancing across NFS servers yourself. Depending on how
comfortable you are with large filesystems on Linux, that be preferable.

Make sure you spec out a backup system with this system (if you need one).

--paul



"Leon Woestenberg" wrote in message
...

"Nik Simpson" wrote in message
...
Leon Woestenberg wrote:

I am shopping for a 120 TB SAN solution which will probably be
accessed by a cluster of servers through a shared filesystem.

1. More about the host OS requirements (i.e. which OS platforms does the
solution have to support)

The SAN is written to and read from through a cluster of, say N, Linux
servers.
The cluster processes 200 datastreams coming in a steady 1 Mbit/second
each,
of which the results (also about 1 Mbit/second) are stored.

As a result of processing, some very low bitrate metadata about the
streams
is
entered into a database, which is stored on the SAN as well.

We need redundancy throughout, i.e. no single point of failure. The
cluster
servers will have to fail-over their processing applications.

Every data stream is received by two servers out of the cluster, where the
secondary acts as a hot spare, processing and storing the data stream if
the primary server fails to do so.

The hardest part (IMHO) will be to make sure, that in case of network
or server failure, the secondary will notice exactly where the primary
server
was in the data stream and take over from there.

2. Application for the SAN, is it one application with different OS
platforms, or different OS platforms supporting different applications.
What
I'm really driving at here is the need for a shared filesystem which
will
inevitably slow things down, limit the OS choices (portentially) and
make
things more complex.

I though that having a shared filesystem will limit the complexicity by
offering
a distributed locking mechanism, which is used on the cluster to manage
the application I mentioned above?

Anyway, we envision that all access to the storage (from different
platforms)
goes through the cluster. I.e. the cluster provides a NFS mount and
CIFS share to a range of platforms.

3. Performance requirements, for example if high-performance is a
requirement, then you can probably forget both iSCSI and ATA.

From what I read about SANs, we are asking a low level of
performance.

Leon.