File Replication via Application Layer IO Interception
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data protection systems face challenges in maintaining continuous data protection, as they struggle to keep pace with high data transaction rates at production sites without slowing down the production site, leading to potential shutdowns due to backlog of un-logged transactions.
Innovation Solution
The method involves intercepting IO operations at the application layer, determining if files are being replicated, and sending these operations to a data recovery appliance for journaling, enabling replication at the file level and dynamically managing transactions to prevent backlog.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If journaling is used to enable continuous data protection and rollback to any point in time, then reliability is improved, but the overhead of multiple data transactions at the backup site causes the backup site to fall behind the production site, leading to system shutdowns when transaction rates are high
Solution Approach 1:
The patent segments the data transaction processing into two distinct paths: a fast path for normal operations that allows the production site to operate at full speed without waiting for backup confirmation, and a separate journaling path that handles the replication overhead. This segmentation resolves the contradiction by isolating the reliability-critical journaling function from the productivity-critical production transaction path, allowing both to operate optimally independently.
Solution Approach 2:
The patent introduces an intermediary journaling layer that acts as a buffer between the production site and backup site. Instead of requiring direct synchronous communication between production and backup systems, the journal serves as an intermediary that captures transactions asynchronously, allowing the production site to maintain high transaction rates while the backup site processes journal entries at its own pace without causing system shutdowns.
2Reliability
If the backup site processes all data transactions synchronously to ensure data consistency, then reliability is improved, but the production site must slow down to match backup processing speed, reducing productivity
Solution Approach 1:
The patent applies preliminary action by having the production site write transactions to the journal first, before requiring confirmation from the backup site. This preliminary journaling step allows the production site to maintain high transaction rates without being blocked by backup processing speed, while still ensuring data consistency through subsequent backup verification of the journal entries.
3Device complexity
If tape backup drives are used for periodic data storage, then device complexity is reduced, but downtime increases during backup operations and recovery time is extended
Solution Approach 1:
The patent implements continuity of useful action by establishing an ongoing continuous journaling process that operates in the background without requiring system shutdowns. Unlike periodic tape backups that halt production, the journaling system continuously captures transactions asynchronously, eliminating backup-induced downtime while maintaining simplified backup infrastructure.
Data Source
AI summary
A method, system, and computer program product for use in replication comprising intercepting an IO for a file at an application layer at the production site, determining if the file is being replicated, and based on a determination the file is being replicated, sending the IO to a first data recovery appliance and recording the IO in a journal.