Ah Zoltan, what fun!

How about distributed TSM Servers running Linux with bags of  cheap slow
disk for the primary pools.  Copypools back up to the main TSM server,
using server to server over TCP, SCSI over IP to the tape library or where
feasible dedicated fibre, depending on the circumstances of each
distributed server,

The distributed servers are somewhat standardized and you use config
manager to keep all in synch.  Multiple points of failure sure, but each is
relatively minor impact.  Most backups and restores are local and have only
local performance impact.  Copypool backups/db backups can be trickle fed
all day reducing impact on the Campus WAN.

I'm looking forward to the final design.

Regards

Steve

Steven Harris
TSM Admin, SYdney Australia





             Zoltan
             Forray/AC/VCU
             <zforray AT VCU DOT EDU>                                          
To
             Sent by: "ADSM:           ADSM-L AT VM.MARIST DOT EDU
             Dist Stor                                                  cc
             Manager"
             <[email protected]                                     Subject
             .EDU>                     [ADSM-L] TSM server scaling/sizing
                                       for lots (>20000) nodes

             29/04/2008 04:03
             AM


             Please respond to
             "ADSM: Dist Stor
                 Manager"
             <[email protected]
                   .EDU>






Crazy project time...........

I have been asked to research the
feasability/probability/scaleability/sizing of TSM to possibly handle
backing up thousands (actually close to 20,000 or more) desktops!

Anybody have experience doing very, very large scale backups of so many
nodes?   Don't expect much in storage occupancy since we would exclude
things like MP3, etc.  It would just be the ##### of files/database size
(sounds like this would have to wait for V6 since DB2 should scale much
better).

Does anyone run their TSM servers, open?   Trying to
administer/register/monitor this many clients would be a nightmare.

They are talking about budgeting close to $1M, which would include more
bodies as well as the equipment/software!