Dynamic Storage Workload Balancing via Logical Device Ownership Transfer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage systems face challenges in balancing I/O workloads between nodes, leading to potential imbalances and inefficiencies in resource utilization, as they lack dynamic mechanisms to redistribute workload based on real-time utilization and imbalance criteria.
Innovation Solution
A method for load balancing that involves determining normalized I/O workloads, identifying imbalances, and dynamically transferring ownership of logical devices between storage server entities, using normalized I/O costs and rates to select and move logical devices to rebalance workloads, thereby adjusting preferred paths and optimizing resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If logical devices are statically assigned to storage server entities, then ownership and processing responsibilities are clearly defined, but I/O workload imbalance occurs between nodes
Solution Approach 1:
The patent implements dynamic workload balancing by allowing logical device ownership to change based on real-time I/O workload conditions. The system continuously monitors normalized I/O workloads and automatically transfers ownership of logical devices from overloaded storage server entities to underutilized ones, transforming the static ownership model into a dynamic one that adapts to changing conditions while maintaining clear ownership at any given moment
2Productivity
If I/O workloads are redistributed between storage server entities, then workload balance improves, but system complexity increases due to dynamic ownership transfer mechanisms
Solution Approach 1:
The patent changes the ownership parameter of logical devices dynamically based on workload conditions. By monitoring normalized I/O workload parameters and comparing them against thresholds, the system automatically adjusts the ownership assignment parameter, transferring logical devices between storage server entities to maintain balance without requiring complex manual intervention or overhaul of the storage architecture
3Measurement precision
If normalized I/O workload monitoring is implemented, then workload imbalance detection improves, but processing overhead increases
Solution Approach 1:
The storage server entities autonomously monitor their own normalized I/O workloads and make self-directed decisions about ownership transfers based on pre-defined imbalance criteria. This self-service approach allows for precise workload measurement and automatic rebalancing without requiring constant external management or coordination overhead, as each entity independently evaluates its own state and acts accordingly
Data Source
AI summary
Load balancing may include: receiving I/O workloads of storage server entities that service I/O operations received for logical devices, wherein each logical device has an owner that is one of the storage server entities that processes I/O operations directed to the logical device; determining normalized I/O workloads corresponding to the I/O workloads of the storage server entities; determining, in accordance with utilization criteria, imbalance criteria and the normalized I/O workloads, whether to rebalance the I/O workloads of the storage server entities; and responsive to determining to rebalance the I/O workloads of the storage server entities, performing processing to alleviate a detected I/O workload imbalance between two storage server entities. The processing may include moving logical device from a first storage server entity to a second storage server entity; and transferring ownership of the logical device from the first to the second storage server entity.