Chad Smykay wrote:

Vito,

Next time you run the big ASM test I recommend you run a test with 2 clients
with 4 big ASM directive each.  And then kick off a group with both of those
clients in it and list those 4 "saveset" ASM for each client and see what
you get.  Also what is your Server Parallelism set to?  What is you're your
juke box max parallelism set to?  And what is your max target sessions for
the drive you are using set to?

Jukebox max parallelism is irrelevant here. It is a common misconception
that this value affects backup operation, it does not; it simply affects
the number of jukebox operations (e.g. load, unload, label, inventory,
etc.) that can take place simultaneously. Thus a value for this higher
than the number of drives in the jukebox is nonsense.

The other factors that could apply in the case in point are:
server parallelism
client parallelism
savegrp parallelism
target sessions

--
Note: To sign off this list, send a "signoff networker" command via email
to listserv AT listmail.temple DOT edu or visit the list's Web site at
http://listmail.temple.edu/archives/networker.html where you can
also view and post messages to the list.
=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=