On Wed, 11 Jan 2006 08:12:21 +1000, Shane Ginnane <[EMAIL PROTECTED]> wrote:
>Mark wrote in reply to Skip: > >> >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? >> > >> >> 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. > >As a side contribution, we were one of the customers that got bit by this >originally. >Even on small systems (4Gig and 6Gig) we were unable to discern any adverse >impact of these higher settings. >If you need these settings, just do it - I can't imagine you'll even know >about it. > Exactly. 5000 frames is a small sacrafice even on a system with less than 1G real. What is your avialable frame queue look like? See rmf reports or RMFMON SPAG screen. I do wish the defaults were set based on real storage online at IPL time. 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
