I'm sorry; I should have worded that differently. I did not mean 'time slice' per se but rather the weight assigned to each LPAR. This is a constrained system so as Ted points out the weights are being enforced.
David O'Brien NIH Contractor -----Original Message----- From: Ted MacNEIL [mailto:eamacn...@yahoo.ca] Sent: Wednesday, December 01, 2010 4:58 AM To: IBM-MAIN@bama.ua.edu Subject: Re: Question concerning CMF reporting of CPU Delay >Time slice? Normally PR/SM is running interrupt driven, not time sliced unless >you tell configure it so. Actually, PR/SM always works with time slices (50ms IIRC). But, weights are only enforced when there is processor constraint. The HIPERVISOR doles out CPU in slice increments based on weights, workload need, constraints, and if specified, WAIT_COMPLETE=YES. On the older models, you could actually change the slice size, but it was (at the time) recommended if you 'had to' share CPUs for CF LPARs. And, that was recommended against doing. - Ted MacNEIL eamacn...@yahoo.ca ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
