Parallel Data Replication Bypassing Secondary Acknowledgement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The synchronous data transfer mechanism in existing storage systems, such as SRDF/S, increases latency due to the need for write acknowledgement from secondary storage devices, which delays data availability in case of primary storage device failure.
Innovation Solution
Implementing a system that allows data to be written to both primary and secondary storage devices based on specific criteria, such as timing, process identity, and I/O operation size, and logs timing information for performance metrics, enabling bifurcation of I/O operations for parallel processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If synchronous data transfer (SRDF/S) is used to ensure data consistency between primary and secondary storage devices, then data reliability is improved, but write latency increases due to waiting for acknowledgement from secondary storage device
Solution Approach 1:
The host system performs preliminary actions by writing data directly to both primary and secondary storage devices simultaneously, rather than sequentially. This preliminary parallel writing action eliminates the waiting time for secondary storage acknowledgement, while subsequent validation ensures data consistency is maintained.
Solution Approach 2:
The patent inverts the traditional synchronous replication approach by reversing the acknowledgement sequence. Instead of the host waiting for secondary storage confirmation before completing the write operation, the host completes the write operation immediately after writing to primary storage, and the secondary storage validation occurs in the background without blocking the host.
2Productivity
If data is written to both primary and secondary storage devices simultaneously to reduce latency, then write speed is improved, but system complexity increases due to need for coordination and acknowledgement management
Solution Approach 1:
The patent segments the data writing process into independent parallel operations: the host writes to primary storage and secondary storage as separate simultaneous actions. This segmentation eliminates the need for complex coordination between the two write operations, as they are performed independently and concurrently.
Solution Approach 2:
The secondary storage device performs self-validation and self-correction without requiring complex coordination with the primary storage device. If the secondary storage device detects issues with received data, it can autonomously request retransmission or initiate recovery procedures, reducing the overall system coordination complexity.
Data Source
AI summary
Accessing data using a first storage device and a second storage device that is a synchronous mirror of the first storage device includes determining if the first and second storage devices support alternative mirroring that bypasses having the first storage device write data to the second storage device and choosing to write data to the first storage device only or both the first and second storage device based on criteria that includes metrics relating to timing, an identity of a calling process or application, a size of an I/O operation, an identity of a destination volume, a time of day, a particular host id, a particular application or set of applications, and/or particular datasets, extents, tracks, records/blocks. A single I/O operation may be bifurcated to provide a portion of the I/O operation to only the first storage device or to both the first storage device and the second storage device.