Dynamic Path State Modifications for Data Storage Workload Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data storage systems face challenges in efficiently balancing the workload between nodes to optimize resource utilization and performance, leading to potential overload and inefficiencies in data access.
Innovation Solution
A method and system for determining path states and performing load rebalancing by dynamically changing preferred paths for logical devices between nodes based on workload metrics such as CPU, memory, and I/O rates, shifting workload from overloaded nodes to underutilized ones, and notifying hosts of path changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If workload is concentrated on fewer nodes, then resource utilization on those nodes increases, but system reliability and performance balance deteriorate due to node overload
Solution Approach 1:
The system dynamically adjusts path preferences for logical devices between nodes based on real-time workload measurements. When a node becomes overloaded, the system modifies path state information to redirect I/O operations to less loaded nodes, creating a dynamic load balancing mechanism that adapts to changing conditions rather than using static node assignments
Solution Approach 2:
The system implements a feedback loop by continuously measuring workload on each node and using this information to modify path preferences. The workload measurement unit monitors node conditions, and based on these measurements, the system adjusts preferred paths for logical devices, creating a closed-loop control system that automatically responds to workload changes
2Reliability
If multiple paths are available for logical devices, then system reliability improves, but workload balancing between nodes deteriorates without dynamic path state modifications
Solution Approach 1:
The system applies different path preferences to different logical devices based on local node workload conditions. Instead of uniformly distributing or concentrating all I/O operations, the system individually adjusts preferred paths for each logical device according to the current workload state of nodes, creating localized optimizations that collectively achieve system-wide load balancing
Solution Approach 2:
The system dynamically modifies path state information to change preferred paths for logical devices based on real-time workload measurements. This dynamic adjustment allows the system to maintain multiple available paths for reliability while actively managing workload distribution to prevent node overload
3Device complexity
If path preferences are statically assigned, then system complexity is reduced, but adaptability to workload changes deteriorates
Solution Approach 1:
The system performs self-service by automatically measuring its own workload conditions and autonomously adjusting path preferences without external intervention. The workload measurement unit monitors node conditions and the system automatically modifies path state information, eliminating the need for complex external path management while maintaining adaptability to workload changes
Data Source
AI summary
Rebalancing the workload of logical devices across multiple nodes may include dynamically modifying preferred paths for one or more logical devices in order to rebalance the I/O workload of the logical devices among the nodes of the data storage system. Determining whether to rebalance the I/O workload between the two nodes may be performed in accordance with one or more criteria. Processing may include monitoring the current workloads of both nodes over time and periodically evaluating, in accordance with the one or more criteria, whether the current workloads of the nodes are imbalanced. Responsive to determining, in accordance with the criteria, that rebalancing of workload between the nodes is needed, the rebalancing may be performed. A notification may be sent to the host regarding any path state changes made as a result of the workload rebalancing.