Dredging up a conversation from last year.  I know in theory the horse
is dead, but I think I might have seen a twitch.

>> On Thu, 8 Feb 2007 10:35:56 +0100, Remco Post <r.post AT SARA DOT NL> said:

> Really I've never seen anybody recommend anything above one zone per
> HBA.


The 'Implementing IBM Tape in Unix Systems' redbook talks about
dynamic load balancing (per tape open) across all available HBAs.
This leads me to think that, if I have 4 HBAs devoted to tape traffic,
I want to have each one zoned with all my (dual ported, natch) tape
connections.  This sounds sane, so far.  But then I do math and get


8 drives * 2 ports * 4 HBAs = 64 rmt devices for my 8 drives.  I know
that instAtape will collapse those down so I only need to use the -PRI
devices for e.g. paths.  but it just makes me feel odd to have so
many.  So, I'm wondering:

Am I being silly?  Just go ahead and do it?  Should I be zoning some
of the HBAs for port 0 on the tapes, others for port 1?

I have an inclination, which I am working to stifle, to have this neat
spirograph of a venn diagram so that HBA 1 is connected to odd ports
of even tapes, and HBA 2 is connected to ...



- Allen S. Rout
- Maybe that was just maggots?