Storage Power Throttling for Tiered Workload Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data centers face significant challenges in managing power consumption while maintaining performance profiles for critical applications, driven by increasing workload power demands, cooling costs, and regulatory compliance, necessitating efficient power optimization techniques.
Innovation Solution
The storage system is utilized as a primary driver to throttle and/or offload workloads when predetermined power consumption thresholds are exceeded, with power management actions based on service tiers assigned to workloads, thereby reducing power consumption and optimizing efficiency across the data path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If power consumption is increased to meet growing workload demands, then productivity and service capability are improved, but energy consumption and operating costs worsen
Solution Approach 1:
The patent implements dynamic power management by continuously monitoring power consumption and adjusting storage system operations in real-time. The system transitions between different operational states (normal operation, power throttling, workload migration) based on current power conditions, enabling the storage system to adapt its power usage to match actual workload demands while maintaining service levels.
Solution Approach 2:
The system changes operational parameters such as I/O throughput limits, power consumption thresholds, and workload allocation based on service tiers. By dynamically adjusting these parameters, the system can reduce power consumption during high-demand periods while maintaining critical workloads, thus resolving the contradiction between productivity and energy usage.
2Use of energy by moving object
If power consumption is reduced through throttling, then energy efficiency is improved, but service level and performance may worsen
Solution Approach 1:
The patent applies differential power management across different workloads based on their service tiers. Critical workloads (higher service tiers) maintain full performance even when power consumption is reduced, while non-critical workloads (lower service tiers) are throttled or migrated. This localized quality approach ensures that service levels for important operations are preserved while achieving overall power reduction.
Solution Approach 2:
The system continuously monitors power consumption, workload performance, and service level metrics, then adjusts power management actions accordingly. This feedback loop ensures that power throttling or workload migration decisions are made based on real-time conditions, preventing service level degradation while achieving power reduction goals.
3Use of energy by moving object
If workload migration is performed to reduce power consumption, then energy efficiency is improved, but system complexity and operational overhead worsen
Solution Approach 1:
The patent creates a universal power management framework that can be applied across multiple storage systems and workload types. The power management module serves multiple functions: monitoring power consumption, determining service tiers, deciding on throttling or migration actions, and executing workload redistribution. This multi-functional approach consolidates complexity into a single manageable system rather than requiring separate mechanisms for each function.
Data Source
AI summary
An example methodology includes, by a computing device, polling a power monitoring device coupled to a storage system for power consumption by the storage system and whether the power consumption exceeds a power consumption threshold. The method also includes, responsive to a determination that the power consumption exceeds the power consumption threshold, managing, by the computing device, the power consumption by the storage system to cause the power consumption to not exceed the power consumption threshold.