Register Synchronization for All-Flash Array Node Failure Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The management of accessing Flash memory in all-flash array (AFA) servers is complicated due to differences between SSDs and HDDs, leading to degraded performance, as existing control methods may become improper or invalid.
Innovation Solution
A dual-node architecture where one node acts as a master and the other as a slave, with synchronized registers to ensure data consistency and fault detection, allowing for seamless failover in case of node failure, thereby maintaining high availability and performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If SSDs are used to replace HDDs in AFA servers, then data access speed and performance are improved, but control complexity increases and existing control methods become improper or invalid
Solution Approach 1:
The system is divided into multiple independent storage nodes, each with its own controller and Flash memory devices. This segmentation allows each node to be managed independently, reducing the complexity of controlling the entire system while maintaining high data access speeds through parallel operations.
Solution Approach 2:
A management node is introduced as an intermediary between the host system and storage nodes. The management node handles complex control operations, including register synchronization and fault detection, thereby simplifying the control interface while enabling sophisticated SSD management capabilities.
2Reliability
If multiple storage nodes are implemented for high availability, then system reliability is improved, but register synchronization complexity increases
Solution Approach 1:
The system implements a feedback mechanism where the management node periodically checks register values of storage nodes and detects faults by comparing expected versus actual values. This automated feedback loop maintains reliability across multiple nodes while reducing the manual synchronization complexity through systematic monitoring and automatic fault detection.
Data Source
AI summary
The present invention provides a control method of a server, wherein the control method includes the steps of: periodically controlling a first register and a second register of a first node to have a first value and a second value, respectively; periodically controlling a third register and a fourth register of a second node to have a third value and a fourth value, respectively; controlling the first register and the fourth register to synchronize with each other, wherein the first value is different from the fourth value; controlling the second register and the third register to synchronize with each other, wherein the second value is different from the third value; and periodically checking if the third register has the third value and the fourth register has the fourth value to determine if the first node fails to work.