Gary adds:
Once the SMF data is written to SMF you have a choice of using SAS and/or Culprit. I find Culprit to be faster and easier. You can use standard IBM utilities for SAS to "split out" the IDMS sub-type(s) so that there is less data to process - here is an example:
[font=Courier New][color=#060AFF]//*
//SMFDMP EXEC PGM=IFASMFDP,REGION=512K
//SYSPRINT DD SYSOUT=*
//DUMPIN2 DD DSN=????.SMF.MONTHLY,DISP=SHR
//DUMPOUT2 DD DSN=userId.SMF.D2002011,DISP=(NEW,CATLG,DELETE),
// UNIT=SYSDA,SPACE=(CYL,(20,10),RLSE)
//SYSIN DD *
INDD(DUMPIN2,OPTIONS(DUMP))
OUTDD(DUMPOUT2,TYPE(210,211))
DATE(2002011,2002011)
/* [color][font]
HTH - cheers - Gary