RE: Save/restore Compression algorithms....

["Billy Rowe" <billyrowe@xxxxxxx>]

> We're working on doing some system saves under program/CL 
> control.  One of
> the interesting things we found was that a save *nonsys under 
> CL control
> specifying DTACPR(*YES) took more time and more tape vs the 
> straight GO
> SAVE/21.
> 
> Is there a difference in the algorithm being used by software 
> vs hardware?
> 
> I can see a definate time/performance difference between the 
> 2, and I'm
> curious as to if the newer hardware compression (for a 6385 
> tape drive in
> this case) is different.

I don't know if there is a difference between the hardware/software
compression algorithim, but if your device supports using the Optimum
block parameter usage and if you use data compression/compaction(*DEV)
you will get the fastest with the best compression because it does it
at the hardware level.

I think the software compression option should only be used with
devices where the hardware level doesn't do it for you, so the system
CPU will do it before saving(i.e. slower).


+---
| This is the Midrange System Mailing List!
| To submit a new message, send your mail to MIDRANGE-L@midrange.com.
| To subscribe to this list send email to MIDRANGE-L-SUB@midrange.com.
| To unsubscribe from this list send email to MIDRANGE-L-UNSUB@midrange.com.
| Questions should be directed to the list owner/operator: david@midrange.com
+---