In
<461643955.1081520.1366308196215.javamail.r...@sz0127a.westchester.pa.mail.comcast.net>,
on 04/18/2013
at 06:03 PM, DASDBILL2 <[email protected]> said:
>I strongly suspect, without reading the doc, that "ms" should be
>microseconds instead of milliseconds. I suspect this because of
>the multiplier 128. I advise reading the SMF doc very closely.
>If it says the value is a number of "timer units", then you have
>to find out what a timer unit means. This is defined in the
>Principles of Operations as 128 microseconds.
No; PoOps does not define timer units; 128 microseconds is the
granularity of the channel measurements. The term timer unit is
defined as 26.04166 microseconds in, e.g., z/OS MVS Programming:
Assembler Services Reference, Volume 2 (IAR-XCT), SA22-7607-15. That
value is derived from the updating of bit 30 in the old S/360 Interval
Timer.
--
Shmuel (Seymour J.) Metz, SysProg and JOAT
Atid/2 <http://patriot.net/~shmuel>
We don't care. We don't have to care, we're Congress.
(S877: The Shut up and Eat Your spam act of 2003)
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN
