Controller Node Volume Allocation for Storage Hierarchy Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current information processing systems face challenges in allocating volumes with suitable attributes to virtual machines running different middleware types and node roles within replication configurations, leading to increased operational costs due to inefficient storage resource utilization.
Innovation Solution
The system employs a controller node that classifies storage devices into hierarchies based on drive type and allocates volumes to nodes within replication groups, ensuring that each node receives a virtual volume from a storage hierarchy suitable for its middleware type and role, thereby optimizing storage resource allocation and reducing costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If volumes are allocated without considering node type and middleware type, then storage allocation is simple, but system operation cost increases due to inefficient storage resource utilization
Solution Approach 1:
The patent applies local quality by allocating different storage hierarchy types to different node types and middleware types. Specifically, SSD-based volumes are allocated to nodes requiring high I/O performance (such as primary nodes in replication groups), while HDD-based volumes are allocated to nodes with lower performance requirements (such as secondary nodes). This differentiated allocation strategy optimizes storage resource utilization and reduces system operation costs by matching storage performance characteristics with actual workload requirements.
Solution Approach 2:
The patent changes the allocation parameters from a uniform approach to a multi-dimensional approach that considers node type, middleware type, and storage hierarchy type. The controller node determines appropriate storage hierarchies by evaluating these parameters and allocates volumes accordingly, transforming the allocation system from simple but inefficient to complex but cost-effective.
2Productivity
If storage devices are classified into multiple hierarchies, then storage resource allocation becomes optimized, but device complexity increases
Solution Approach 1:
The patent implements a universal volume allocation mechanism that handles multiple storage hierarchy types (SSD, HDD, etc.) through a single controller node. The controller node universally manages all storage devices, classifies them into appropriate hierarchies based on performance characteristics, and allocates them to suitable nodes based on node type and middleware type. This universal approach consolidates management complexity into a centralized component while enabling efficient multi-hierarchy resource allocation across the entire system.
3Loss of energy
If volumes with suitable attributes are allocated to each node type, then system cost is reduced, but allocation process becomes more complex
Solution Approach 1:
The patent applies preliminary action by having the controller node determine the appropriate storage hierarchy type for each node before allocating volumes. The controller node evaluates node type, middleware type, and performance requirements in advance, then pre-determines the suitable storage hierarchy (SSD, HDD, etc.) for each node. This preliminary determination simplifies the subsequent volume allocation process and ensures cost-effective storage resource utilization from the outset.
Data Source
AI summary
The present invention proposes an information processing system and a volume allocation method making it feasible to reduce overall system operation cost. A replication group to carry out replication is comprised of one or multiple nodes. A storage node classifies respective storage devices mounted thereon into plural storage hierarchies according to the drive type of each of the storage devices for management of the storage devices. A controller node allocates, to each node of the nodes constituting the replication group, a volume for which a storage device of a storage hierarchy suitable for a type of middleware that the node uses and a node type of the node acting in the replication group provides a storage area.