DFSORT reports cpu time in field ICECPUT. This is basically the step TCB time accumulated between the sort start time and the sort end time. So that time is a subset of the TCB time reported in type 30 records. Also keep in mind that it also means if there are things like user written E15 and E35 exits being used, it's going to include the time spent in those exits so it's not pure DFSORT only cpu time.
Have a nice day, Dave Betten DFSORT Development, Performance Lead IBM Corporation email: [email protected] DFSORT/MVSontheweb at http://www.ibm.com/storage/dfsort/ IBM Mainframe Discussion List <[email protected]> wrote on 12/01/2010 09:51:31 AM: > [image removed] > > SMF data for DFSORT > > Michael Hall > > to: > > IBM-MAIN > > 12/01/2010 09:52 AM > > Sent by: > > IBM Mainframe Discussion List <[email protected]> > > Please respond to IBM Mainframe Discussion List > > Is there additional information about CPU time for DFSORT in the SMF Type 16 > record that is not in the Type 30 step record. In other words, are there any > circumstances where CPU time data is written to the Type 16 records and not > to the Type 30 records? Do you see step information for DFSORT CPU time in > Type 30 records when DFSORT is indirectly invoked from another program? > > ---------------------------------------------------------------------- > 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 ---------------------------------------------------------------------- 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
