I Probably wandering off the main topic of the OP's question, my initial 
response was 


according to SDSF 


ECPU% CPU usage consumed within the address space (RMF) 


to Brians query ---- 



Hello, 

I'm trying to understand the CPU and ECPU times displayed on SDSF and the 
relation to zIIP processing time. 

For example, here is a CICS region running a Java web service. 

*CPU-Time ECPU-Time GCP-Time zIIP-Time zICP-Time zIIP-NTime* 

* 164.42 166.28 90.89 30.21 3.42 71.29* 

Here is a CICS transaction executing in the region to display various ASSB 
fields. 

************ CPU DISPLAY ************* 

*ASCBEJST. . . . . . : 162.20* 

*ASCBSRBT. . . . . . : 2.23* 

*ASSBASST. . . . . . : .00* 

*ASSBPHTM. . . . . . : 1.86* 

*CPU . . . . . . . . : 164.43 (ASCBEJST + ASCBSRBT + ASSBASST)* 

*ECPU. . . . . . . . : 166.29 (ASCBEJST + ASCBSRBT + ASSBPHTM)* 

*ASSB-TIME-ON-ZIIP . : 30.22* 

*ASSB-ZIIP-ENCT. . . : 1.60* 

*ASSB-ZIIP-PHTM. . . : 1.60* 

*ASSB-ASST-TIME-ON-CP: .00* 

The CPU-Time, ECPU-Time, and zIIP-time match (as close as humanly possible to 
switch 3270 emulators and press enter). I was under the assumption that ECPU 
also included time spent on zIIPs, but that must not be true. Is zIIP time 
included in CPU and ECPU? I'm thinking it is not. 

so......this ..... 

and it mutated from there trying to understand the CPU times displayed in SDSF, 
I personally don't use SDSF's ECPUtime, I'll use CPU% then if I see something 
out of the ordinary I'll check CPUtime and EXCP and SIO's use to be a good 
indicator of a looping program if CPU time is accumulating and EXCPs are zero 
or not accumulating . 


Pie in the sky.... 


if at all possible, for me I'd like to see SDSF's CPUtime to include all time, 
GCPU+IIP, it's nice the times and percentages are shown in a separate variable, 
I can see if my workload is really using the specialty engine, but SDSF does 
not report TCB and SRB times separately so why not show all CPUtime combined 


Carmen Vitullo 

----- Original Message -----

From: "Peter Relson" <[email protected]> 
To: [email protected] 
Sent: Thursday, February 28, 2019 7:07:56 AM 
Subject: Re: CPU time and zIIP 

<snip> 
No more assumptions on my part, so what tools would show the correct 
time(s) for real time monitoring if not SDSF? 
RMF? Omegamon? And now that you throw Java in the mix or USS spanned 
tasks I don't think any real time monitor can account for all CPU time 
GCPU and zIIPTIME 
</snip> 

SDSF shows the correct time(s). What in any way leads you to think what is 
shown is not correct? SDSF shows what it shows. The data is what the data 
is. If you have a requirement for some other piece of data, then describe 
that in detail and we can tell you if it is available or not. In general 
the system keeps the data that if finds a need for, often (but not 
necessarily for only that reason) to make its way into SMF records. 

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