Dynamic Power Management for Multi-Tiered Storage Subsystems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current power management models in cloud computing data sites fail to effectively balance power reduction with minimal performance loss during on-demand power reduction, particularly in scenarios like external cooling failures, as they lack real-time mitigation techniques for data processing impact.
Innovation Solution
A method for dynamic power management in storage subsystems that monitors and reports power consumption and data access performance, using heuristics to selectively lower power usage of storage devices while maintaining performance, with feedback loops to adjust device selection and power settings, thereby achieving energy savings with minimal performance impact.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If power consumption of storage devices is reduced, then energy savings are achieved, but data access performance deteriorates
Solution Approach 1:
The patent implements dynamic power management by continuously monitoring data access performance metrics and adjusting power consumption settings of storage devices in real-time. The system transitions storage devices between different power states (active, idle, sleep) based on current workload conditions, thereby achieving energy savings without causing performance deterioration when data access is required.
Solution Approach 2:
The system employs feedback loops where data access performance is continuously measured and fed back to the power management controller. Based on this feedback, the controller adjusts power consumption settings dynamically - if performance degradation is detected, power settings are increased; if performance is adequate, power settings are reduced to achieve energy savings.
2Loss of energy
If power reduction is implemented during cooling failures, then energy costs are reduced, but system reliability worsens due to potential data access interruptions
Solution Approach 1:
The system performs preliminary actions by pre-positioning frequently accessed data in high-performance storage devices before power reduction is needed. When cooling failures occur and power reduction is implemented, this pre-positioning ensures that critical data remains accessible without interruption, thereby maintaining system reliability while achieving energy savings.
Solution Approach 2:
The patent applies different power reduction strategies to different storage devices based on their specific roles and the data they contain. Critical storage devices that hold frequently accessed or mission-critical data are exempted from aggressive power reduction, while non-critical devices undergo more significant power savings measures, thereby maintaining overall system reliability.
Data Source
AI summary
Embodiments of the invention relate to dynamic power management of storage volumes and disk arrays in a storage subsystem to mitigate loss of performance resulting from the power management. The volumes and arrays are prioritized, and in real-time power is selectively reduced in response to both the prioritization and an energy savings goal. A feedback loop is provided to dynamically measure associated power gain based upon a lowering of power consumption, and device selection may be adjusted based upon received feedback.