Peter, as far as I know the restart interrupt from the HMC with options abend-resume-repair are supposed to correspond to the spin(resume)-retry(repair)-term(abend) options of automatic exspin recovery. If you ever want to test this again, put your PHUNLOOP job into sysstc - improves the chances of it running quite a bit! :-)
Santosh, the big dispatcher rewrite that got rid of running tcb chains in every address space once and for all occured with MVS 5.1. That release introduced a completely different mechanism (the WEBs) for indicating that work is ready to run. There have been bits and pieces around this since then, but that design is quite a solid one. And there are (and were) quite more dispatchable units of work than 'just' tcbs; just look at macro IHAWEB for the different types. (Peter was faster than I on this!) And given that an lpar these days uses logical processors, I would be really reluctant to even *attempt* to introduce a machine check to a processor. Whenever I have to stop the processors for a test lpar to see the psw and get an idea if it is doing anything or juat waiting , we have a discussion if that will affect other lpars sharing the same physical processor! Regards, Barbara Nitz -- Psssst! Schon vom neuen GMX MultiMessenger gehört? Der kanns mit allen: http://www.gmx.net/de/go/multimessenger ---------------------------------------------------------------------- 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