On Tue, 10 Jan 2006 11:10:38 -0800, Skip Robinson <[EMAIL PROTECTED]> wrote:
>We lost a production system a while back because of a spin loop in RSM. >Apparently RSM needed some storage, but before demand paging operations >could complete, the system got partitioned out of the sysplex for lack of >heartbeat activity. > >IBM pointed us to OA12185, which recommends this value for available frame >queue: MCCAFCTH=(4000,4500) . What's startling about this recommendation is >that it's ten times (!) the default value of MCCAFCTH=(400,600) . We're >concerned that such a high value will increase paging rates considerably. >Maybe it's overkill. > >Any thoughts? > Skip, How much real storage do you have on the LPAR in question? It's probably a nit for large LPARs (like the ones you most likley care about). If you followed some of the recommendations for RSM problems when 64-bit came along, you set it back then also. I think we talked about this one at SHARE in Boston in the EWCP free for all. BTW, ours is set at 5000,6000 in one of our large sysplexes. The bigger LPARs in that sysplex have 20G-25G of real. Regards, Mark -- Mark Zelden Sr. Software and Systems Architect - z/OS Team Lead Zurich North America and Farmers Insurance Group mailto: [EMAIL PROTECTED] Systems Programming expert at http://Search390.com/ateExperts/ Mark's MVS Utilities: http://home.flash.net/~mzelden/mvsutil.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
