> We have a 2097-504(E12). Does anyone know if turing on Hiper Dispatching > on a single book box machine would make a difference in performance?
According to "IBM System z10 Business Class Technical Overview" http://www.redbooks.ibm.com/redbooks/pdfs/sg247632.pdf at page 153-154 in topic 7.3.12 HiperDispatch, > On the z10 BC, with its single drawer CPC and L2, > the benefits [of HiperDispatch] are minimal, if any. Contrast the above description of HiperDispatch for z10 BC machines with the below description of current-generation z114 machines, where IBM has added sensitivity to the underlying quad-code chip architecture of these machines to the HiperDispatch function. Reference "IBM zEnterprise 114 Technical Guide" http://www.redbooks.ibm.com/redbooks/pdfs/sg247954.pdf page 90 in the topic HiperDispatch: > z/OS dispatcher manages multiple queues, which are called > affinity queues, with a target number of four processors per > queue, which fits nicely into a single PU chip. These queues > are used to assign work to as few logical processors as are > needed for a given logical partition workload. So, even if the > logical partition is defined with a large number of logical > processors, HiperDispatch optimizes this number of > processors nearest to the required capacity. Brian ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN
