Storage Controller Cache Protection Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The performance of storage systems operating in the write-through method deteriorates significantly due to controller failures, especially when data protection methods like RAID 6 require multiple drive accesses, leading to increased write response times compared to the write-back method.
Innovation Solution
A storage system with multiple controllers, each equipped with a processor and memory, employs a dual memory protection method: data copying between controllers and log saving to a non-volatile medium, allowing for switching between these methods based on operational states to ensure high reliability and performance, particularly during controller failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the storage system operates in the write-through method to ensure data reliability during controller failure, then data reliability is improved, but write response time greatly deteriorates due to multiple drive accesses required by RAID 6
Solution Approach 1:
The storage system dynamically switches between write-back and write-through methods based on the operational state of controllers. When both controllers are normal, the system operates in write-back mode for high performance. When a controller fails, the system transitions to write-through mode to ensure data reliability, thus adapting the data protection method to current system conditions
Solution Approach 2:
The system changes the data protection parameter (cache protection method) based on controller operational status. By monitoring controller health and adjusting the protection method accordingly, the system optimizes the balance between performance and reliability according to actual system state
2Productivity
If the storage system uses the write-back method to improve write response time, then write performance is improved, but data reliability deteriorates when cache redundancy is lost due to controller failure
Solution Approach 1:
The storage system dynamically switches between write-back and write-through methods based on the operational state of controllers. When both controllers are normal, the system operates in write-back mode for high performance. When a controller fails, the system transitions to write-through mode to ensure data reliability, thus adapting the data protection method to current system conditions
Solution Approach 2:
The storage system automatically detects controller failures and switches data protection methods without requiring external intervention. The system monitors its own operational state and self-adjusts the cache protection strategy to maintain appropriate reliability levels
Data Source
AI summary
A storage system includes a non-volatile storage device and a plurality of storage controllers that control reading and writing for the storage device, in which each of the plurality of storage controllers includes a processor and a memory, the storage controller stores a write request from a host for the storage device as cache data in the memory, returns a write completion response to the host after protecting the cache data in a first memory protection method or a second memory protection method, and destages the cache data into the storage device after the write completion response, and the storage controller switches between the first memory protection method and the second memory protection method to be used according to an operation state of another storage controller.