>That's just crazy talk.  While there might be some load balancing related 
>motivations for using similar sized page data sets, ASM most
certainly uses the full capacity of all of the data sets

Okay.
Maybe things have changed.
Maybe my mind has gone.

When I first started in Performance, we were taught to keep all PAGED/S the 
same size.
And, we were taught to use the ZAP documented in INIT&TUNE.
Of course, that was also at the time the Extended Swap IUP was first introduced.
So we had for types of data sets to worry about:
COMMON
LPA
Local &
SWAP.

Plus duplexing, dedicated paths/volumes, and the introduction of 1 cylinder LPA 
& putting it and COMMON on the same pack.

Of course, DASD was **VERY** expensive then. Dollars per MEG instead of pennies 
per GIG.

We had the same cost arguments regarding the dedication of **HUGE** 3350's vs 
Tiny 3330's and *HUMUNGUS* 3380's vs either back then.
3290's not so much.

Anybody remember String-Switching and Fixed-Head 3350's?


-
Ted MacNEIL
[email protected]
Twitter: @TedMacNEIL

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN

Reply via email to