Remote Copy System Collective Compression Journal Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing remote copy technologies face challenges in maintaining a short Recovery Point Objective (RPO) while achieving a high reduction effect in data transfer volume between primary and secondary storage systems.
Innovation Solution
The implementation of collective compression in the primary storage system, where data from multiple journal entries is compressed together and transferred as a single unit to the secondary storage system, allowing for efficient data expansion and write ordering on the secondary volume.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data compression is applied to reduce transfer volume, then the reduction effect of transfer target data is improved, but the Recovery Point Objective (RPO) deteriorates due to increased processing time
Solution Approach 1:
The patent segments journal data into multiple journals, each containing a subset of write operations. By compressing and transferring multiple journals collectively rather than individually, the system achieves better compression ratios while maintaining manageable processing units that can be handled efficiently by the secondary storage system
Solution Approach 2:
The patent merges multiple journals into a single compressed data stream for transfer. By combining multiple journal data sets before compression, the system achieves higher reduction effects while the metadata within each journal preserves the write order information needed to maintain short RPO
2Quantity of substance
If differential remote copy is used to transfer only changed data, then the reduction effect of transfer target data is improved, but the RPO deteriorates due to dependency on data transfer cycle
Solution Approach 1:
The patent performs preliminary compression of journal data at the primary storage system before transfer. By pre-compressing the journal data and organizing it with metadata indicating write order, the system prepares the data in advance for efficient transfer and reconstruction, eliminating the need for periodic transfer cycles
Solution Approach 2:
The patent uses journal data as an intermediary structure that captures write operations in a compressed format with embedded metadata. This intermediary allows the secondary storage system to reconstruct the original data sequence without requiring periodic snapshots or differential comparisons
Data Source
AI summary
A primary storage system reads a plurality of journal data, and performs collective compression that is compression of data that is at least a part of the plurality of pieces of journal data in the plurality of journals and is larger than a size of one journal data. The collectively compressed data, which is a plurality of pieces of journal data subjected to collective compression, is a transfer target from the primary storage system to the secondary storage system. The journal is journal data and metadata including a write order of the journal data and associated with the journal data. The journal data is a copy of data written in the primary volume. The secondary storage system acquires a plurality of pieces of journal data by decompressing one or more pieces of collectively compressed data, and writes the plurality of pieces of journal data to the secondary volume.