Keep in mind the placement on the volume was all about arm movement. On a physical 3390 that meant something. As platters got wider, the arm with the read/write heads had farther to travel from one end to the other. In a DASD array where your 33xx volume is virtualized across a bunch of 3.5 inch drives, worrying about placement for arm movement is not something you can do anything about. And then you have drawer caching, controller caching, array caching, LLA caching, DB2 Bufferpool caching.
In my opinion, way too much time was spent worrying about it anyway, unless you only put a vtoc and one dataset on a volume, there was a whole bunch more activity going on for a volume that had the arm moving anyway. To put a specific dataset next to the vtoc you had to monitor what datasets got accessed the most. If you really had time to monitor which datasets on a volume were accessed the most often then you were overstaffed. Any shop I worked in had more work to do than time to get it done in. On Tue, 11 Sep 2007 19:14:06 +0000, Ted MacNEIL <[EMAIL PROTECTED]> wrote: >>I put the heavily hit loadlibs such as SYS1.LINKLIB on one side of the VTOC, and the ISPF libraries on the other side of the VTOC. With todays heavily cached dasd, that probably will buy you very little anymore. > >Very little. >Especially, since it's been over 15 years since IBM stopped recommending placing the VTOC (VTOCIX, VVDS, & Catalogue [if there is one]) elsewhere than at the beginning of the pack. > >- >Too busy driving to stop for gas! > ---------------------------------------------------------------------- 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
