Remote Copy Journal Volume for Seamless Failover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current remote copy systems experience performance degradation due to stopping I/O operations when a failure occurs, and application programs are not seamlessly transitioned to a secondary site without knowledge of the storage system configuration, leading to delays in reproducing the operation environment.
Innovation Solution
A remote copy system with clustered server systems and storage systems that perform asynchronous remote copying, where the primary storage system records operations in a journal volume and transfers them to the secondary site, allowing for immediate failover and QoS settings to be replicated without stopping I/O operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If I/O operations are stopped when a failure occurs at the primary site, then the operation environment can be reproduced at the secondary site, but performance degradation occurs and productivity is reduced
Solution Approach 1:
The system performs preliminary actions by continuously recording I/O operations and their results in a journal volume at the primary site, and asynchronously transferring these journal records to the secondary site. This preliminary preparation of operational state information enables the secondary site to reproduce the operation environment without stopping I/O operations when a failure occurs.
Solution Approach 2:
The journal volume acts as an intermediary mechanism that captures I/O operation details and transfer results. This intermediary structure allows the system to maintain operational state information independently, enabling failover without interrupting active I/O operations and thus resolving the contradiction between reliability and productivity.
2Reliability
If the same operation environment is reproduced at the copy destination storage system, then failover can be achieved, but I/O operations must be stopped causing performance degradation
Solution Approach 1:
The system ensures continuity of useful action by maintaining I/O operation recording and journal transfer processes that continue uninterrupted during normal operation. When failure occurs, the pre-recorded journal data enables immediate failover without stopping I/O operations, thus eliminating time loss and maintaining continuous productivity.
3Speed
If asynchronous remote copy is used, then write response time is reduced, but untransferred journals remain causing delays in environment reproduction
Solution Approach 1:
The system implements feedback mechanisms where the storage controller records transfer results of I/O operations in the journal volume and the copy destination storage system reflects these results. This feedback loop ensures that even with asynchronous copy operations, all necessary operational state information is captured and transferred, eliminating delays in environment reproduction while maintaining fast write responses.
Data Source
AI summary
A first storage system of a remote copy system includes a data volume, a journal volume, and a storage controller. When an operation is received from a first server system, based on the operation, the storage controller executes any of a work of storing the update content by the operation in the journal volume or a work of executing the operation when the operation is received.