Yes the times are in uses of 128 microseconds. If you are a member of CMG or are willing to register on their website you can find my 1998 paper "DOES YOUR INSTALLATION HAVE HALF-SECOND I/O RESPONSE TIME? (A Closer Examination of Disconnect Time)". I believe that paper first explored how to use the SMF 42-6 data to better understand response time for cache hits and cache misses.
Hard to believe that was 15 years ago that I did that work. Al Sherkow ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN
