Hybrid Storage Replication for Latency and Consistency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data replication techniques face challenges in maintaining high availability and performance, particularly over large geographical distances, as synchronous replication is impractical due to latency issues and asynchronous replication may result in data inconsistencies and lost updates.
Innovation Solution
A method combining asynchronous and synchronous storage replication techniques, where data is copied within an active group synchronously and replicated to passive groups asynchronously, ensuring zero data loss and reducing latency by allowing the system to operate over larger distances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If synchronous storage replication is used to ensure data consistency and zero data loss, then data reliability is improved, but system latency increases and performance decreases
Solution Approach 1:
The storage system is segmented into a primary storage device and multiple secondary storage devices. The primary device handles write operations locally, providing immediate acknowledgment to the host, while replication to secondary devices occurs asynchronously. This segmentation allows the system to achieve both fast response times and data consistency by separating the critical write path from the replication path.
Solution Approach 2:
The system performs preliminary local writing to the primary storage device before initiating replication to secondary devices. This preliminary action ensures that the host receives immediate acknowledgment of the write operation, maintaining high performance, while the data is subsequently replicated to ensure consistency and zero data loss across all storage devices.
2Productivity
If asynchronous storage replication is used to reduce latency and improve performance, then system speed is improved, but data consistency may be compromised and updates may be lost
Solution Approach 1:
The system implements a feedback mechanism where the primary storage device sends data to secondary storage devices and receives acknowledgments. Once the primary device receives confirmation that data has been successfully written to the secondary devices, it can confirm completion of the replication process. This feedback loop ensures data consistency is maintained while allowing asynchronous operation to preserve system performance.
3Quantity of substance
If tape storage is used for backups to reduce cost, then storage cost is reduced, but backup time increases and data availability decreases
Solution Approach 1:
Instead of using slow tape storage for backups, the system creates digital copies of data on secondary storage devices that can be rapidly accessed. These digital copies serve as immediate backups that can be restored quickly if needed, eliminating the long backup times and data unavailability associated with tape storage while maintaining cost-effectiveness through the use of standard storage hardware.
Data Source
AI summary
A method and system of replicating data where data is copied from a host server to a storage device in a first group of storage devices. A receipt is sent from the first group of storage devices to the host server when the data has been copied to all storage devices within the first group. The data is copied from the first group to at least one further group of storage devices. A receipt is sent from each further group of storage devices to the first group of storage devices when the data has been copied to all storage devices within each further group.