Thermal Aware Workload Scheduling for Data Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data storage systems face heat-related issues due to the close proximity of multiple data storage devices, leading to potential premature failure, which existing cooling methods like fans may not adequately address, necessitating a more efficient thermal management strategy.
Innovation Solution
A thermal aware workload scheduling system that models thermal characteristics based on inlet air, device performance, and thermal constraints to optimize the distribution of workload among data storage devices, ensuring maximum Input/Output Operations Per Second (IOPS) while maintaining devices within safe temperature thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple data storage devices are held in close proximity within an electronics enclosure to increase storage capacity, then storage system capacity is improved, but heat generation increases leading to premature device failure
Solution Approach 1:
The patent applies local quality by creating temperature-aware workload allocation that treats different physical locations within the enclosure differently. The system models temperature distribution across the enclosure and allocates workloads to specific devices based on their local thermal conditions, rather than treating all devices uniformly. This allows hot regions to receive reduced workload while cooler regions handle more operations.
Solution Approach 2:
The system dynamically changes workload allocation parameters based on thermal conditions. By modeling temperature characteristics and using this information to adjust workload distribution in real-time, the system adapts the operational parameters of storage devices according to their thermal state, preventing overheating while maintaining high utilization of cooler devices.
2Temperature
If uniform workload distribution is used among data storage devices, then average temperature in the enclosure is optimized, but thermal constraints of individual devices are not adequately addressed
Solution Approach 1:
The patent implements feedback by continuously modeling temperature characteristics of the enclosure and using this information to adjust workload allocation. The system monitors thermal conditions and feeds this information back into the workload distribution algorithm, creating a closed-loop control system that adapts to changing thermal conditions and prevents individual devices from exceeding their thermal constraints.
Solution Approach 2:
The system performs preliminary thermal modeling and prediction to anticipate temperature issues before they occur. By modeling temperature characteristics in advance and identifying potential thermal hotspots, the system can proactively adjust workload allocation to prevent thermal constraints from being violated, rather than reacting after problems occur.
3Temperature
If cooling devices like fans are added to manage heat, then temperature control is improved, but device complexity and energy consumption increase
Solution Approach 1:
The patent replaces the mechanical cooling system with a software-based thermal management approach. Instead of relying on physical cooling devices like fans to actively remove heat, the system uses computational modeling and intelligent workload allocation to passively manage thermal conditions. This substitutes mechanical cooling infrastructure with an information-processing-based solution that achieves temperature control through operational optimization rather than active heat removal.
4Productivity
If workload is allocated to maximize IOPS, then productivity is improved, but thermal constraints may be violated leading to device failure
Solution Approach 1:
The patent applies dynamics by making the workload allocation system adaptive and responsive to changing thermal conditions. Rather than using static allocation rules, the system dynamically adjusts workload distribution based on real-time temperature modeling and device thermal states. This allows the system to maximize IOPS during periods when thermal headroom is available while automatically reducing allocation to devices approaching thermal limits.
Data Source
AI summary
Systems, software, devices, and methods of distributing a workload among available data storage devices in a thermal aware manner are described herein. More specifically, the examples herein discuss distributing the workload among the available data storage devices in a thermal aware manner that optimizes collective IOPs of the data storage devices in an enclosure. The thermal aware distribution of the storage operations is determined by a thermal model that predicts thermal characteristics of the data storage system based on inlet air characteristics of the enclosure, performance characteristics and thermal constraints of the data storage devices, and constraints of the workload.