Assume that we have 32 shared physical CPs and LPAR
weight is 28% and HiperDispatch is turned on.
If the decimal number of the processor guarantee is ≥ 0.5 = the vertical high processors will be the integer number and there will be 1 vertical medium
𝐏𝐫𝐨𝐜𝐞𝐬𝐬𝐨𝐫 𝐆𝐮𝐚𝐫𝐚𝐧𝐭𝐞𝐞 = 𝟑𝟐 𝐱 𝟎.𝟐𝟖 = 𝟖.𝟗𝟔 = 𝟖 𝐕𝐇 + 𝟏𝐕M
If the decimal number of the processor guarantee is < 0.5 = the vertical high processors will be the integer number minus one and there will be 2 vertical mediums:
𝐏𝐫𝐨𝐜𝐞𝐬𝐬𝐨𝐫 𝐆𝐮𝐚𝐫𝐚𝐧𝐭𝐞𝐞 = 𝟑𝟐 𝐱 𝟎.𝟐𝟔 = 𝟖.𝟑𝟐 = 𝟕 𝐕𝐇 + 𝟐𝐕M
According to the IBM Best Practices recommendation, the number of logical processors should be the quantity required to satisfy the LPAR share/processor guarantee, i.e., the Vertical High and Vertical Medium, and 1 to 2 additional processors (Vertical Low).
The LPAR time slice is sensitive to the number of logical CPs and having more logicals may drive your time slice to a smaller interval for your vertical medium and vertical low logical processors.”
Based on IBM manual: the sum of all logical shared processors should not be more than triple the number of physical processors. Otherwise, the LPAR management time to reassign the PUs to the logical CPUs can increase to an unacceptable level.
Work will run most efficiently if you run within your defined weight, using vertical highs and vertical mediums to support the workload and avoid use of vertical lows except for occasional workload spikes. If the workload in the LPAR relies upon vertical lows for throughput you may want to change the weight to match actual usage.
