This is for those out there who have an understanding on the subject and how it 
might apply to a non-production service provider environment.

Scenario Example

2964-605 processor
Rated MSU = 577
5 CPs are shared among all LPARs

Customer-A has LPARs 1,2 & 3 grouped with a MSU cap of 300 (contracted MIPS 
converted to MSUs).
Customer-B has LPARs 6,7,8 & 9 grouped with a MSU cap of 250 (contracted MIPS 
converted to MSUs).


Is the 4HRA at the CEC level or the LPAR level?

If the Customer-A LPAR group spikes above its group MSU cap while the 
Customer-B LPAR group is in low usage, what happens when the Customer-B LPAR 
group now needs resources?
Does it have to wait on Customer-A’s 4HRA to complete or does it get what it 
needs by taking back the overage given to the Customer-A LPAR group?

These may be juvenile questions, but I’m not a capacity planner and I’m trying 
to gain some understanding of how this works by reading manuals.

Any insight will be appreciated.

Thanks,

S. Veryl Ellis

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

Reply via email to