Skip Robinson wrote:
> 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?
Actually IBM started changing the default recommendations several years
ago. As Mark indicated, the recommendations vary depending of the real
storage size. From OW55729 (10/23/2002)
TOTAL REAL THRESHOLD
---------- ----------
< 2Gig minimum of MCCAFCTH=(350,400)
2-6Gig minimum of MCCAFCTH=(2000,2500)
> 6Gig minimum of MCCAFCTH=(5000,6000)
Now OA12185 suggests mccafcth=(4000,4500) but doesn't indicate the real
storage size range. It appears you want to be careful with smaller
LPARs, as OA12684 describes a performance hit on systems with only 512MB
of real. Search IBMLink with a keyword of mccafcth for a quick idea of
the problems and recommendations.
----------------------------------------------------------------------
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
