Disaster Recovery Write-Order Consistency With Elastic Secondary Resources
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computer systems with remote copy functions incur excessive hardware costs and operational expenses at secondary sites due to overprovisioning for steady-state operations, particularly when using cloud-based resources, despite the need for reduced performance during disaster recovery.
Innovation Solution
Implement a computer system with a specifications changing mechanism that adjusts the hardware specifications of the secondary site during failover and failback processes, optimizing resource usage by increasing capabilities only when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the secondary site is provided with sufficient hardware to handle I/O processing after failover, then the performance of I/O processing is maintained after failover switching, but the cost of introduction and operational cost increases due to excessive hardware performance at steady time
Solution Approach 1:
The patent applies dynamics by making the hardware specifications of the secondary site adjustable rather than fixed. The system dynamically changes the specifications of the secondary site between two states: a first specification during steady operation (lower resources) and a second specification during failover (higher resources). This allows the system to adapt resource allocation to actual operational needs, maintaining I/O performance when required while reducing hardware costs during normal operation.
2Reliability
If cloud-based hardware is used with high performance at the secondary site, then disaster recovery capability is ensured, but operational cost increases due to pay-as-you-go pricing model
Solution Approach 1:
The patent applies parameter changes by modifying the hardware specification parameters of the secondary site based on operational state. The system changes the specification parameter from a first value (lower computational resources) during steady operation to a second value (higher computational resources) during failover. This parameter adjustment aligns resource consumption with actual demand, ensuring disaster recovery capability when needed while minimizing operational costs during normal cloud-based operation.
Data Source
AI summary
A computer system includes a primary site having a primary volume, and having an instance that performs data processing related to input/output data, and a secondary site having a secondary volume, and having an instance. Remote copy is set up between the primary and secondary volumes, and the instance of the primary site transfers data input to or outputted from the primary volume to the secondary site, while the instance of the secondary site stores the transferred data in the secondary volume. The computer system further includes a specifications changing section that changes specifications of the instance of the secondary site when a failover switching process of switching a performer of the data processing from the primary to secondary site is performed, or when a failback switching process of switching the performer of the data processing from the secondary to primary site after the failover switching process is performed.