IBM Mainframe Discussion List <IBM-MAIN@BAMA.UA.EDU> wrote on 04/25/2006
09:24:37 AM:
> IBM has some undocumented monitor call
> instructions inside the I/O first level interrupt handler for
> instrumentation
> purposes. Maybe they also have some way to measure the overhead of
> building an
> SMF record. And maybe they can report on it some day if they do.
> There is no
> way we can find out. The only part of the overhead we can measure is
that
> belonging to the SMF writing service in the SMF address space, and
that's a
> small part of the total.
The "undocumented montitor call instructions" (generated by the
COUNT macro, and in many places besides the I/O FLIH) are for the
purpose of determining the frequency of some events. They do not assist
in determining duration or CPU consumption.
IBM does not, to my knowledge, have any way to measure the cost of
building SMF records.
Some components/products may check to see whether a particular
record type is being recorded before incurring the cost to build it.
Here is an example from IEFTB721:
RFY (REG15) RSTD; /* @G742PJW*/
/* CHECK IF RECORD TYPE 30 IS BEING
COLLECTED @G742PJW*/
GEN REFS(SMCAMACR,SMCABASE); /* @G742PJW*/
SMFRTEST RECTYPE=30 @G742PJW
@ENDGEN; /* @G742PJW*/
IF REG15=RECGATH THEN /*IF TYPE 30 IS COLLECTED @G742PJW*/
DO; /* BEGIN - TYPE 30 collected @G742PJW*/
RFY (REG1) UNRSTD; /* @ZA43580*/
CALL IEFSMF30(LCTPTR,SWBLKPTR(JOBACT)->IEFAACTB); /* CALL
ROUTINE TO BUILD DUMMY PROTOTYPE
RECORDS @G742PJW*/
/* FILL IN STEP ACCT FIELDS
@G742PJW*/
I do not know if use of this technique is pervasive
within IBM products.
Jim Mulder z/OS System Test IBM Corp. Poughkeepsie, NY
----------------------------------------------------------------------
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
