VM wasn't designed with the idea that VDISK pages are merely inactive pag es. Linux wasn't around on the mainframe when VDISK was invented. VDISK was design as a fast disk in memory, not specifically as a swap space.
Mostly VM uses LRU algorithms -- the VDISK page is NEW to VM when it is f irst written, so it will be retained longer than unchanged pages in the Linux virtual machine. As others have pointed out, the actual algorithms are more complicated than LRU -- and they tend to favor keeping VDISK pages in memory even longer. What I remember reading, but have not tried, is the suggestion that you h ave multiple levels of swap space, a small VDISK and larger minidisks to back it up. That might help in this case. alan(dot)ackerman(at)Bank of America(dot)com On Tue, 7 Nov 2006 17:00:43 -0500, David Kreuter <[EMAIL PROTECTED] om> wrote: >Dennis: Remember CP doesn't know what's in the vdisk page. It's handles >a write I/O CCW for the guest. Yes normally CP should take vdisk pages >ahead of virtual machine pages for page out. >David >Dennis Schaffer wrote: > >>Now for the question: Since Linux has moved what it considers inactive >>pages to swap/vdisk, why would VM keep any of that machine's vdisk page s in >>central storage in a VM-central-storage-constrained environment? I wou ld >>expect that VM would migrate all of a Linux machine's vdisk pages to >>xstor/disk before it would migrate any of that machine's virtual storag e >>pages away to xstor/pagdisk. The only exception I can think of would b e >>that VM might migrate vdisk pages from pagdisk/xstor to cstor as part o f >>Linux swap migration back to its memory. >> >======================== ========================= ========== ==============
