Stripe Swapping for Storage Tier Migration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage systems face inefficiencies in migrating data between different redundancy levels, leading to increased operational burdens and premature wear on storage devices due to the need for multiple read and write operations.
Innovation Solution
Implement a method called stripe swapping, where data is directly remapped between storage tiers without being rewritten, using a mapping table to associate physical storage locations with different redundancy levels, reducing the number of operations and wear on storage devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is copied from the first tier to cache and then written to the second tier, then data migration between redundancy levels is achieved, but the number of storage device operations increases and device lifespan is reduced
Solution Approach 1:
The patent uses logical copying through mapping table updates rather than physical data copying. The mapping table stores logical-to-physical address mappings, and migration is achieved by updating these mappings to point to different physical locations, eliminating the need to actually copy data blocks between tiers.
Solution Approach 2:
The mapping table acts as an intermediary between the host system and the physical storage devices. By modifying mappings in the mapping table rather than moving actual data, the system achieves data migration functionality while minimizing physical storage operations.
2Reliability
If data is copied from the first tier to cache and then written to the second tier, then data migration between redundancy levels is achieved, but storage device wear increases
Solution Approach 1:
The patent uses logical copying through mapping table updates rather than physical data copying. The mapping table stores logical-to-physical address mappings, and migration is achieved by updating these mappings to point to different physical locations, eliminating the need to actually copy data blocks between tiers.
Solution Approach 2:
The mapping table structure enables the system to self-manage data location information. When migration is needed, the system simply updates the mapping table entries to reflect new physical locations, allowing the storage system to adapt without physically moving data and thereby reducing wear on storage devices.
3Reliability
If multiple read and write operations are performed for data migration, then data is moved between tiers, but operational burden on the controller increases
Solution Approach 1:
The patent uses logical copying through mapping table updates rather than physical data copying. The mapping table stores logical-to-physical address mappings, and migration is achieved by updating these mappings to point to different physical locations, eliminating the need to actually copy data blocks between tiers.
Solution Approach 2:
The patent extracts the data location management function from the physical data storage function. By separating the logical mapping information (stored in the mapping table) from the actual data blocks, the system can migrate data by simply updating the extracted mapping information, significantly reducing controller operational burden.
Data Source
AI summary
A system and method for improving storage system operation is disclosed. A storage system includes a first tier with high-performance redundancy and a second tier with capacity efficient redundancy. The first tier and the second tier are built from the same storage devices in a storage pool so each storage device includes both the first and second tiers. The storage system stores write data initially to the first tier. When demand for the data falls below a threshold, the storage system migrates the write data to the second tier. This is done by changing the mapping of underlying physical locations on the storage devices where the write data is stored so that the underlying physical locations are logically associated with the second tier instead of the first tier. After remapping, the storage system also computes parity information for the migrated write data and stores it in the second tier.