I believe that the original question was about the CPC having only one processor. Since the topic implies sysplex and hence a CF, I would strongly recommend against sharing one processor between a CF and an lpar, especially in production, assuming that the lpar is on the same CPC as the CF and the CF is not running on any type of special processor.
Talking about uniprocessors: Each lpar in our sandbox sysplex is a uni, and every time we hit a cpu loop in a high priority address space, we're dead in the water. Since we cannot even determine who is causing the loop I end up regularly having the operators practise standalone dump. Strangely enough, we are even dead in the water on a two-processor lpar when two tasks are looping at SYSTEM priority. Not to mention that apparently IBM is loath to analyze loops and with the same regularity hand out nonsense like "you don't have a loop" or that our healthy system (that just informed us via IXC402D that the other one is dead) is suffering 'sympathy sickness' and that's why the other system is dead. So with the same regularity I open complaints against incompetent analysis. I shudder to think what customers do that have no choice but to believe the crap they're being told. Regards, Barbara Nitz -- Highspeed-Freiheit. Bei GMX supergünstig, z.B. GMX DSL_Cityflat, DSL-Flatrate für nur 4,99 Euro/Monat* http://www.gmx.net/de/go/dsl ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
