Data Transfer Optimization via Page Granularity Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data storage systems face inefficiencies when transferring data between systems with different page size granularities, leading to adverse performance and bandwidth issues due to the need for read-modify-write operations on hybrid systems with larger page sizes.
Innovation Solution
Constructing a target page of user data with the larger page size granularity by reading additional data from the source system, allowing a single backend write operation on the target system, which avoids read-modify-write operations and optimizes data transfer by aligning data at sequential logical addresses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is transferred between storage systems with different page size granularities using traditional methods, then data compatibility is maintained, but performance deteriorates due to random read-modify-write operations on hybrid systems
Solution Approach 1:
The patent changes the parameter of page size granularity by constructing target pages with the larger page size from the source system. This parameter transformation allows the target hybrid system to receive data in its native format, eliminating the need for read-modify-write operations and improving transfer efficiency by up to 100 times
Solution Approach 2:
The source system performs preliminary construction of target pages by reading additional data and assembling pages that match the target system's granularity requirements before transfer. This preliminary action ensures that the target system receives pre-formatted data, avoiding the need for subsequent read-modify-write operations
2Ease of operation
If page size granularity is standardized across systems, then data transfer simplicity is improved, but system adaptability deteriorates due to inability to accommodate different backend storage requirements
Solution Approach 1:
The patent dynamically changes the page size parameter based on the target system's requirements. The source system constructs pages with the larger granularity that matches the target hybrid system's backend storage requirements, achieving both transfer simplicity and system adaptability simultaneously
Solution Approach 2:
The solution creates a universal data transfer mechanism that can accommodate different page size granularities and backend storage configurations. By constructing pages that match the target system's native format, the system achieves multi-functionality across different storage architectures without requiring separate transfer protocols
3Reliability
If read-modify-write operations are performed on hybrid systems with larger page sizes, then data integrity is maintained, but bandwidth utilization deteriorates due to inefficient random operations
Solution Approach 1:
The source system performs preliminary assembly of complete target pages by reading additional data and constructing pages that match the target system's granularity. This preliminary action ensures data integrity while enabling sequential write operations that maximize bandwidth utilization and eliminate the inefficient read-modify-write cycle
Solution Approach 2:
The patent merges multiple smaller pages from the source system into a single larger target page that matches the hybrid system's page size granularity. This merging operation maintains data integrity while transforming random small writes into a single efficient sequential write operation, optimizing bandwidth utilization
Data Source
AI summary
Techniques for performing data transfers may include determining a first page of user data to be transferred from a source data storage system to a target data storage system, wherein the source data storage system has a source page size granularity denoting a first size of backend I/O operations on the source data storage system, wherein the target data storage system has a target page size granularity denoting a second size of backend I/O operations on the target data storage system; performing processing on the source data storage system that constructs a second page of user data that is the second size, wherein the second page of user data includes the first page of user data that is the first size and another page of user data that is the first size; and transferring the second page of user data from the source to the target data storage system.


