Thanks Peter.

Here is the IBM document that I based my assumptions of the SDSF fields.

*CPU-Time*

Accumulated CPU time consumed by and on behalf of the address space, for
the current job step, in seconds. SDSF obtains this value from RMF, as
follows:



ASCBEJST + ASCBSRBT + ASSBASST (source field R791TCPU)



where



*ASCBEJST*

is elapsed job step time

*ASCBSRBT*

is accumulated SRB time

*ASSBASST*

is the CPU time consumed by preemptible class SRBs running on behalf of
this address space, in milliseconds



*ECPU-Time*

Total CPU time consumed by and within the address space, for the current
job step, in seconds. SDSF obtains this value from RMF, as follows:



ASCBEJST + ASCBSRBT + ASSBPHTM (source field R791TCPC)



where

*ASCBEJST*

is elapsed job step time

*ASCBSRBT*

is accumulated SRB time

*ASSBPHTM*

is the CPU time consumed by preemptible class SRBs running in this address
space, in milliseconds (threads plus enclaves)



https://www.ibm.com/support/knowledgecenter/en/SSLTBW_2.3.0/com.ibm.zosmfsdsf.jobresources.help.doc/izusfhpJobActiveSystemUse.html

I assumed since SDSF compartmentalized the zIIP, zAAP, and zICP times that
they must not be included in the CPU-Time field. Like Carmen noted, when I
add the GCP-Time, zIIP-Time, zAAP-Time, and zICP-Time it does not calculate
out to be the same as the CPU-Time or ECPU-Time amount.


Thank you,

Brian Chapman


On Tue, Feb 26, 2019 at 9:21 AM Peter Relson <[email protected]> wrote:

> If the comment is correct that the SDSF display is using ASCBEJST, then
> the statement
> "ZIIP is not reported as part of CPU."
> is not correct with respect to that display.
>
> ASCBEJST includes all time, whether standard CP or zIIP.
> There are additional fields, such as ASSB_TIME_ON_CP, that do not include
> zIIP.
>
> Fields in SMF records do use ASSB_TIME_ON_CP rather than ASCBEJST. For
> those fields, the statement is correct.
>
> I wasn't sure in what way the OP concluded that zIIP was or was not
> included when he wrote "must not be true" and "I'm thinking it is not".
>
> Peter Relson
> z/OS Core Technology Design
>
>
> ----------------------------------------------------------------------
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to [email protected] with the message: INFO IBM-MAIN
>

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN

Reply via email to