Partition Power Policy Wizard for LPAR Energy Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional power management policies in multipartitioned computer systems uniformly reduce power consumption across all partitions, leading to reduced efficiency for partitions running critical workloads, as they cannot differentiate between partitions based on their workload intensity.
Innovation Solution
A partition power policy wizard is introduced to receive power policy adherence information for each logical partition, calculating and rebalancing processing units to accommodate user-defined power management policies, ensuring that critical partitions are minimally impacted while maintaining overall system efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If conventional power management policies are applied to reduce power consumption, then overall system power usage is reduced, but efficiency of critical partitions is reduced
Solution Approach 1:
The patent segments the uniform power management policy into partition-specific policies. Each logical partition can have its own power management settings, allowing critical partitions to maintain full efficiency while non-critical partitions reduce power consumption. The partition manager independently applies power management policies to each partition based on user-defined criteria.
Solution Approach 2:
The patent implements local quality by allowing different power management characteristics for different partitions. Critical partitions can have power management policies that preserve efficiency, while non-critical partitions can have aggressive power reduction policies. This localized approach ensures that power saving does not uniformly degrade system performance.
2Use of energy by stationary object
If processor frequency and voltage are reduced to apply power management, then power consumption is reduced, but processing capability of all partitions is reduced
Solution Approach 1:
The patent segments the processing capability reduction into partition-specific adjustments. Instead of uniformly reducing processor frequency and voltage for all partitions, the system selectively adjusts power management parameters for specific partitions based on their criticality and workload requirements.
Solution Approach 2:
The patent implements dynamic power management where processor frequency and voltage adjustments are made dynamically on a per-partition basis. The system can adjust power management policies in real-time based on partition workload characteristics, allowing critical partitions to maintain high processing capability while non-critical partitions experience reduced power consumption.
3Loss of energy
If uniform power management policy is applied to all partitions, then system-wide power saving is achieved, but flexibility for different workload requirements is lost
Solution Approach 1:
The patent segments the power management policy application into individual partition-level controls. Users can define which partitions should receive power management policies and with what intensity, allowing flexible adaptation to different workload requirements while achieving system-wide power saving where appropriate.
Solution Approach 2:
The patent changes the parameter of power management from a uniform system-wide setting to variable partition-specific settings. Users can adjust power management parameters such as frequency reduction percentage and voltage scaling factors individually for each partition, enabling adaptability to different workload characteristics.
Data Source
AI summary
A partition power policy wizard receives power policy adherence information for at least one of a plurality of logical partitions (LPAR) and calculates a processing units allotment (PUA) for each LPAR based on the power policy adherence information. In one embodiment, a power management policy reduces an operating frequency of one or more processor(s) allocated to a plurality of LPARs. The power policy adherence information, which is input via a graphical user interface (GUI), specifies whether each LPAR is to be impacted by the power management policy, and if so, by how much. The PUA calculated for each LPAR by the partition policy wizard rebalances the processing units allocated to the individual LPARs to accommodate the power policy adherence information input by the user. Preferably, the partition power policy wizard includes a validation mechanism to validate the executability and/or advisability of each PUA so calculated.