>Yea, I remember some statements made about NAS's 14 way. Something to the effect of "any more than six"...However, wasn't this due to the memory bus becoming overloaded? And isn't IBM's approach the use of NUMA to overcome that problem? >
I remember when it was 2. Then XA allowed for 4. Then 6. Those were architectural issues within the OS. Then ESA would support 8. Then the ES/9000-9X2 came out. At that point, they had to re-architect the Service Controller. And, the did a good job. Adding 25% more CPU's (2 from 8 to 10) gave 22% more capacity. At that time, we were told that adding the 11th engine would actually take capacity away. But, that was solve with the S/390 9672-Rn6's (or was it 7?). Then the z/900 went to 16, the z/990 to 32. And, now 54! Of course, I would like to see a true feeds & speeds above 16. What is the MP effect, really? And, how scalable is the PR/SM hypervisor? Even if you are running LPARs with 16 (or less) CPs, what is PR/SM doing to manage more physical CPs? -teD In God we Trust! All others bring data! -- W. Edwards Deming ---------------------------------------------------------------------- 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
