==> In article <FA2FBFCAE6E4CC40990C321ED0BC68921AEE6F AT 
acsanchor1.corp.acsalaska DOT com>, "Levinson, Donald A." <dlevinso AT 
ACSALASKA DOT COM> writes:

> Can anyone tell me how they defined their sequential FILE devclass and how
> the underlying hardware is setup? It seems like the best way to do this is
> to have multiple physical disks and spread the TSM volumes across the disks
> in a way to encourage spreading the i/o across the spindles.


I've got a large LV striped across 5 5-disk RAIDs of 36GB SSA disk.

I use this space in a manner similar to DISK stgpools, as landing-pad space
expected to be emptied most nights, so I'm less concerned about the
fail-one-RAID == fail-whole-filesystem problem.

The 5 disk raids were recommended as sweet spots for performance.  I find the
overhead a little oogey, butI can see that 15-disk RAID might be a wee tad
constraining.

- Allen S. Rout