> -----Original Message----- > From: IBM Mainframe Discussion List > [mailto:[EMAIL PROTECTED] On Behalf Of Eric Bielefeld > Sent: Friday, June 03, 2005 11:26 AM > To: [email protected] > Subject: Re: Performance and Capacity Planning > > > Chris, > > Two things. > > 1. What is a NUMA machine. How does being NUMA affect > performance or MIPS > values.
NUMA == Non Uniform Memory Access. In the z990, there are multiple "books". Each "book" contains CPU, Memory, and I/O resources. A process running in one "book" will run faster if all its resources (memory and I/O) are in that same "book". That simply because the speed between components within a "book" are faster than referencing a component in the other "book". If you measure MIPS when all the resources (CPU & memory) are in a single book, they will be higher than the MIPS when the CPU in one book must wait for memory access on the other book. Like the PC timings where they try to get the entire program in L1 cache to reduce memory latency. > <snip> > > Eric Bielefeld > P&H Mining Equipment > -- John McKown Senior Systems Programmer UICI Insurance Center Information Technology This message (including any attachments) contains confidential information intended for a specific individual and purpose, and its' content is protected by law. If you are not the intended recipient, you should delete this message and are hereby notified that any disclosure, copying, or distribution of this transmission, or taking any action based on it, is strictly prohibited. ---------------------------------------------------------------------- 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
