Miklos, >I have opened a PMR, and after a number of SMF, RMF, component trace >etc, etc still nobody have any idea.
What exactly did IBM ask for? What do the RMF reports show? How many requests to which structures, how many requests to which XCF groups? Buffer sizes of XCF groups? What's your hardware config? How many paths to the CFs defined? How many XCF groups? What do the ctraces (which ones were requested, which options?) show as an activity? I believe that the XCF/XES ctrace entries for the right structures/groups with the right options *will* show what is causing the cpu consumption. Did you look at a full-size system trace for XCFAS? How many EXT/CLKC entries for XCFAS? What are the module names these entries occur in? What tcbs are running for XCFAS? Is there a pattern visible in their dispatch/svc/pc entries? When XCFAS is busy, what does systrace time(local) show for duration of any dispatch/loss of control? Barbara Nitz -- Der GMX SmartSurfer hilft bis zu 70% Ihrer Onlinekosten zu sparen! Ideal für Modem und ISDN: http://www.gmx.net/de/go/smartsurfer ---------------------------------------------------------------------- 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
