Crash Consistent Snapshot via I/O Splitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data protection systems face challenges in maintaining continuous data protection by keeping pace with high data transaction rates at production sites without slowing them down, leading to potential shutdowns due to backlog issues at backup sites.
Innovation Solution
The method involves splitting I/O operations between multiple storage arrays, creating snapshots, and applying journal entries to these snapshots at a replication site to ensure consistency across arrays, enabling crash-consistent snapshots and efficient data replication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If journaling is used to enable continuous data protection and rollback capability, then data recovery flexibility is improved, but system overhead increases and may force production site shutdown
Solution Approach 1:
The patent segments I/O operations into two separate paths: a first path for normal production data flow and a second path for journaling operations. This segmentation allows the journaling overhead to be handled independently without blocking production I/O, thus maintaining data recovery flexibility while reducing system overhead impact on production performance.
Solution Approach 2:
The patent implements preliminary action by pre-allocating resources for journaling operations and preparing the backup storage system in advance. Journal entries are captured and prepared for potential rollback operations before they are needed, enabling fast recovery without forcing production shutdowns.
2Reliability
If the backup site processes all data transactions to keep pace with production site, then data consistency is improved, but production site performance deteriorates due to forced slowdown
Solution Approach 1:
The patent divides data transaction processing into two separate channels: primary I/O operations for production performance and journaling operations for consistency. This segmentation allows the production site to maintain high performance while the backup site processes journaling entries asynchronously to ensure data consistency.
Solution Approach 2:
The patent introduces a journaling intermediary layer that captures data transactions without forcing the production site to slow down. This intermediary processes and buffers journal entries, then applies them to the backup storage system asynchronously, maintaining data consistency while preserving production performance.
3Reliability
If the backup site cannot keep pace with high data transaction rates, then backlog builds up, but forcing production site to slow down reduces productivity
Solution Approach 1:
The patent implements preliminary action by pre-configuring the backup storage system with sufficient capacity and performance headroom to handle journaling operations. This allows the backup site to process journaling entries without creating backlogs that would force production slowdowns.
Solution Approach 2:
The patent implements dynamic adaptation by allowing the backup site to adjust its processing rate based on incoming journaling workload and available resources. This dynamic approach enables the system to handle varying data transaction rates without forcing production slowdowns while maintaining data protection capability.
Data Source
AI summary
A method, system, and computer program product for splitting IOs directed to a first LUN and a second LUN to a journal on a replication site, creating a snapshot of the first LUN, creating a snapshot of the second LUN, and applying the IO in the journal on the replication site to a copy of the snapshot of the first LUN on the replication site and a copy of the snapshot of the second LUN on the replication site to create a consistent snapshot of the first LUN and the second LUN on the replication site.