The point not missed...or was missed is: Reduce the amount of cache available for z/Linux machines and let MDC handle it.
Of course, you can't turn off Linux caching, and even if you reduce the virtual size of the machine below the working set size (where you are actively paging to the swap file), Linux will still grab a small amount for caching, but let MDC have the resources to provide a high hit ratio. Tom Duerbusch THD Consulting >>> [EMAIL PROTECTED] 09/06/05 1:44 PM >>> Tom Duerbusch wrote: > If you are running low on memory and can't afford the next bumb in > memory (yet), you tune back the z/Linux caching, and let MDC handle more > of the load. MDC is a shared cache, that is shared across all dasd > where it isn't explicitly turned off. If one Linux image becomes very > active, it will load MDC with it's data. But when the image becomes > more idle, the cache will be used for more active images. More bang for > the GB. I agree to your point in general, but you're missing one point: With mdc, both Linux and MDC will cache the same data. MDC does only have a cache hit when Linux has already discarded that data (old, never referenced) but it is still in MDC. If you cache all dasd, that's approximately when your MDC for the given guest exceeds its guest storage setting because almost 100% of the guest storage is used as page cache in Linux. > But then, who gets paid for that? <G>. Not me ;-) -- Carsten Otte IBM Linux technology center ARCH=s390 ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
