On Thu, 24 Mar 2022 19:49:24 +0000, Michael Watkins wrote: > ... A quick search of the IBM documentation doesn't seem to provide a > conclusive answer. Anyone got a clue? > I'm confident you'll get a knowledgeable answer.
I wonder, which is better: o More single-volume data sets for greater I/O overlap? o Fewer multi-volume data sets using less buffer space? SORT knows best; let it choose. Or using only 64-bit virtual for workspace? The technique should be designed with LoR to optimize paging. Do virtual disks do anticipatory reads? Is bus bandwidth saturation a concern? -- gil ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN
