SSD RAID Data Placement for Lower Write Amplification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Memory systems with mixed data types in nonvolatile memory experience decreased garbage collection efficiency due to increased write amplification, and RAID systems face similar issues despite their redundancy measures.
Innovation Solution
A storage controller assigns distinct identifiers to original and mirror data, directing them to separate blocks within memory systems, and performs RAID level conversion to optimize data distribution across multiple SSDs, reducing fragmentation and write amplification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If different types of data are mixed in the same block of nonvolatile memory, then storage space utilization is improved, but garbage collection efficiency decreases and write amplification increases
Solution Approach 1:
The patent segments data into different types (original data, mirror data, parity data) and assigns each type to specific dedicated blocks. The controller maintains separate block pools for each data type, preventing mixing and enabling type-specific garbage collection optimization.
Solution Approach 2:
The patent applies different quality characteristics to different block pools based on their intended data types. Original data blocks, mirror data blocks, and parity data blocks are managed with different policies, allowing optimized garbage collection strategies for each data type while maintaining overall system efficiency.
2Reliability
If RAID is used to improve resistance to memory system failures, then system reliability is improved, but write amplification of each memory system becomes large
Solution Approach 1:
The patent segments write operations into distinct types (original data writes, mirror data writes, parity data writes) and routes them to different block pools. This segmentation allows the system to maintain RAID redundancy while reducing overall write amplification by optimizing each write type separately.
Solution Approach 2:
The patent changes the management parameters for different data types within the RAID system. By assigning different block pool management strategies to original data, mirror data, and parity data, the system achieves better write amplification control while maintaining RAID reliability.
Data Source
AI summary
According to one embodiment, an information processing system includes a plurality of memory systems and a storage controller. The storage controller assigns a first identifier and a second identifier to a first write request requesting writing of original data and a second write request requesting writing of mirror data, respectively. A controller of each of the memory systems writes first data to a first write destination block in response to determining that an identifier contained in a write request received from the storage controller is the first identifier, and writes the first data to a second write destination block in response to determining that the identifier contained in the write request is the second identifier.