Storage Controller Data Collation via No-Compression Read
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing data collation methods in storage arrays with compression capabilities suffer from low efficiency due to the need for decompression and re-compression of data, leading to incorrect storage space utilization and reduced ability to utilize physical addresses fully.
Innovation Solution
A data collation method that includes sending a read instruction with a no-decompression flag and mapping logical and physical addresses to improve data collation efficiency, allowing the storage controller to manage logical addresses based on the actual physical address length, thereby avoiding unnecessary decompression and re-compression, and ensuring optimal storage space utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the storage device decompresses data before sending to the storage controller during data collation, then the storage controller can manage data with logical addresses based on uncompressed size, but the data collation efficiency deteriorates due to unnecessary decompression and re-compression operations
Solution Approach 1:
The patent extracts the decompression operation from the data collation process by introducing a no-decompression flag in the read instruction. When this flag is set, the storage device sends compressed data directly to the storage controller without performing decompression, thereby eliminating unnecessary decompression and re-compression operations while maintaining accurate tracking of logical address space through the mapping relationship between logical and physical addresses.
2Device complexity
If the storage controller records logical address length based on uncompressed data size, then the address mapping is simplified, but the storage space utilization deteriorates because the controller cannot make full use of physical addresses
Solution Approach 1:
The patent introduces an intermediary mechanism in the form of a mapping relationship between logical addresses and physical addresses. The storage controller assigns logical addresses based on uncompressed data size for simplified management, while the mapping relationship tracks the actual physical address space occupied by compressed data. This intermediary mapping layer resolves the contradiction by decoupling the logical address allocation from the physical address consumption.
Data Source
AI summary
A data collation method in a storage array including reading first data from a first logical address without decompression, assigning, by a storage controller, a second logical address to the first data, storing the first data to the second logical address, establishing, by the storage controller, a mapping relationship between an address of a storage array and the second logical address, where the first logical address is mapped to a first physical address of a storage device, a length of the first physical address is equal to a length of first data, a length of the first logical address is equal to a length of second data, and the first data is compressed data of the second data, and receiving, by the storage controller, the first data from the storage device.