Redundant Storage Servers with Cache for High Availability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Storage area networks for large organizations are expensive to implement and maintain due to high costs associated with high-performance protocols and infrastructure, which limits accessibility and availability of data storage solutions.
Innovation Solution
A computer storage system comprising redundant storage servers and cache servers that replicate and cache data using mass storage disks, employing protocols like RAID-5 and storage area network protocols to ensure high availability and performance, with cache servers providing quick data access and redundant servers handling failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If high-performance protocols and infrastructure are used in storage area networks, then data access performance and availability are improved, but implementation and maintenance costs increase
Solution Approach 1:
The system segments storage functions across multiple server types (disk servers, redundant storage servers, cache servers) with different performance characteristics. Each server handles specific workload segments, allowing the system to achieve high availability without requiring all components to use expensive high-performance infrastructure.
Solution Approach 2:
Different servers in the network are assigned different quality levels based on their specific functions. Cache servers use faster memory for frequently accessed data, while disk servers use cost-effective mass storage for bulk data, creating local optimization rather than uniform high-performance infrastructure throughout.
2Reliability
If redundant storage servers are added to increase availability, then fault tolerance is improved, but system complexity increases
Solution Approach 1:
The redundant storage server is merged with the primary disk server architecture, using the same fundamental components and protocols. The redundant server mirrors the primary server's structure and operates as an identical backup, simplifying the addition of redundancy rather than requiring a completely separate fault-tolerance system.
Solution Approach 2:
The redundant storage server creates a copy of the primary disk server's functionality and data structure. This copying approach allows for straightforward redundancy implementation where the backup server is an exact replica ready to take over immediately upon failure, avoiding complex synchronization mechanisms.
3Speed
If cache servers are introduced to improve data access speed, then response time is reduced, but infrastructure requirements increase
Solution Approach 1:
Cache servers are positioned as intermediary components between clients and disk servers. These intermediaries handle frequently accessed data in faster memory, reducing the burden on the primary disk servers and enabling faster response times without requiring all servers to use high-performance storage infrastructure.
Data Source
AI summary
According to one embodiment, a computer storage system includes one or more redundant storage servers coupled to one or more cache servers. A redundant storage server is coupled to each disk server. A disk server comprises at least one mass storage disk operable to store data. The data is segmented according to logical blocks, where each logical block has an associated logical block identifier. The redundant storage servers are operable to replicate each logical block of at least two of the disk servers. The cache servers comprise a cache memory and are coupled to each redundant storage server. Each cache server is operable to access the replicated logical blocks according to the associated logical block identifiers, and cache, in the cache memory, the replicated logical block according to the associated logical block identifier.