Multi-Tier Cloud Storage Nodes With Software-Defined Pool
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage systems in information processing face challenges with data access performance and scalability, particularly in systems with large numbers of compute nodes, where conventional arrangements are costly and lack efficient failure recovery mechanisms.
Innovation Solution
Implementing a multi-tier storage system with a front-end storage tier using cluster file system storage nodes and a software-defined storage pool on virtual machines in cloud infrastructure, coupled with a back-end object store, which allows for reduced costs, enhanced failure recovery, and improved data access performance and scalability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If conventional storage systems are used in cloud infrastructure, then deployment cost is reduced, but data access performance and scalability deteriorate
Solution Approach 1:
The storage system is segmented into multiple tiers (hot storage tier with cluster file system storage nodes and cold storage tier with object store), allowing different data types to be stored in optimally suited locations. This segmentation enables high-performance access for frequently accessed data while maintaining cost-effectiveness for less frequently accessed data, thus resolving the contradiction between deployment cost and data access performance.
Solution Approach 2:
The patent introduces a hierarchical dimension to storage architecture by implementing multi-tier storage with different performance characteristics. By organizing storage in layers (hot tier using local disk resources of VMs and cold tier using object store), the system achieves both cost efficiency and high performance simultaneously, resolving the contradiction between deployment cost and data access performance.
2Quantity of substance
If conventional storage systems are used in cloud infrastructure, then deployment cost is reduced, but scalability deteriorates
Solution Approach 1:
The cluster file system storage nodes serve multiple functions: they provide high-performance storage for compute nodes, implement software-defined storage pools using local disk resources of VMs, and participate in the hierarchical storage architecture. This multi-functionality enables the system to scale efficiently by allowing storage capacity and performance to grow with the addition of more VMs and storage nodes, resolving the contradiction between deployment cost and scalability.
Solution Approach 2:
The storage system is designed to be dynamic and adaptable, with storage nodes that can be added or removed based on demand. The software-defined storage pool allows flexible allocation of storage resources across the cluster, enabling the system to scale dynamically without requiring complete redesign or incurring prohibitive costs, thus resolving the contradiction between deployment cost and scalability.
3Device complexity
If conventional storage systems are used, then system complexity is reduced, but failure recovery capability deteriorates
Solution Approach 1:
The patent introduces a software-defined storage layer as an intermediary between the physical storage resources and the compute nodes. This software layer provides abstraction and management capabilities that enable automated failure detection, data redundancy, and recovery operations. The intermediary layer handles complexity internally while presenting a simplified interface to users, thus resolving the contradiction between system complexity and failure recovery capability.
Solution Approach 2:
The storage system implements redundancy and fault tolerance mechanisms in advance through the software-defined storage pool and hierarchical architecture. Data is protected through replication and distribution across multiple storage nodes and tiers, providing beforehand cushioning against failures. This allows the system to maintain high reliability without requiring users to directly manage the underlying complexity, resolving the contradiction between system complexity and failure recovery capability.
Data Source
AI summary
An apparatus in one embodiment comprises a multi-tier storage system having at least a front-end storage tier and a back-end storage tier. The multi-tier storage system is implemented at least in part utilizing a plurality of virtual machines of cloud infrastructure. The front-end storage tier comprises a plurality of storage nodes of a cluster file system, with the storage nodes being implemented on respective ones of the virtual machines. The front-end storage tier further comprises a software-defined storage pool accessible to the storage nodes and implemented utilizing local disk resources of respective ones of the virtual machines. The back-end storage tier of the multi-tier storage system comprises at least one object store. At least a subset of the virtual machines may further comprise respective compute nodes configured to access the multi-tier storage system. Other illustrative embodiments include systems, methods and processor-readable storage media.