> I do not believe that the MAXSPACE is related to 'dropping the OSA > channels', at least not directly. What probably happens is a > long time of > system-wide non-dispatchability in extremely short succession > that causes > some sort of timeout to be reached on this or another system. > If the adresses shown above (842 and 2121) are OSA-channels - > what is their > timeout-value? (IECIOS member?)
That makes more sense to me, thanks. Device 842 is OSA, device 2121 is ficon DASD. The timeout values must be default since they are not listed in IECIOS00. I was contacted by private email from someone who also is experiencing a similar problem, but only with one ficon channel under heavy load. Our problem extends beyond just ficon since OSA is also getting hit consistently. They are pursuing this as a microcode problem, as are we. We applied latest microcode a couple weeks ago but we had got hit again afterwards. Hopefully IBM will get to the bottom of this soon. Thanks, Dave Low ---------------------------------------------------------------------- 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
