For once *I* get to ask a question. :-) And perhaps a stoopid one. :-) As many of you - especially those who follow me on Twitter - know, I'm writing the Performance Metrics chapter of the new Redbook on Parallel Sysplex Performance...
It has occurred to me that one can treat XCF as a sophisticated queuing mechanism and that path, transport class, and local buffers are really subqueues. As are the lists in any Coupling Facility List Structures you might use for XCF. So, I'm wondering whether it's better to place the memory centrally in the CF structures. Or distributed via the various in-memory buffer pools. And, yes, I know CTCs don't have an in-built queue (other than the buffer pools I've already mentioned). Note: Though we use the term "buffer pool" these aren't "reread-amenable" areas of memory (unless there's something missing from MY understanding). So I'd be interested in your opinions. Thanks, Martin Martin Packer Performance Consultant IBM United Kingdom Ltd +44-20-8832-5167 +44-7802-245-584 [EMAIL PROTECTED] Twitter / identi.ca : MartinPacker Unless stated otherwise above: IBM United Kingdom Limited - Registered in England and Wales with number 741598. Registered office: PO Box 41, North Harbour, Portsmouth, Hampshire PO6 3AU ---------------------------------------------------------------------- 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
