Zone-Based Storage Devices for RAID and In-Storage Compression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage devices struggle to efficiently implement Redundant Arrays of Inexpensive Disks (RAID) while handling large data volumes and compressing data for improved memory usage efficiency.
Innovation Solution
A data processing system that includes a host and storage devices with memory controllers capable of dividing memory blocks into superblocks, configuring file systems in a RAID manner, and utilizing In Storage Compression (ICS) to manage data efficiently across multiple storage devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is compressed in storage devices to increase memory usage efficiency, then storage capacity utilization is improved, but device complexity increases due to compression/decompression operations
Solution Approach 1:
The patent combines multiple storage devices into a RAID array configuration, merging their capabilities to provide redundancy and improved storage efficiency. The memory controllers of multiple storage devices work together to handle compression and decompression operations, distributing the computational load and reducing the complexity burden on individual devices.
Solution Approach 2:
The storage devices in the RAID configuration are designed with multi-functionality, capable of performing both storage operations and compression/decompression operations. The memory controllers can operate in different modes (compression, decompression, or direct storage) depending on the data characteristics and system requirements, making the system more versatile while maintaining efficiency.
2Reliability
If RAID configuration is implemented across multiple storage devices, then data reliability is improved, but device complexity and management overhead increase
Solution Approach 1:
The patent divides the RAID array into multiple storage devices, each managed by its own memory controller. This segmentation allows independent operation and failure isolation - if one device fails, the others continue to function. The memory controllers independently manage their respective devices while coordinating through the host, reducing the complexity of centralized management.
Solution Approach 2:
Each storage device in the RAID configuration operates with its own memory controller that autonomously manages compression, decompression, and data operations. The devices self-organize into the RAID structure without requiring complex external management, as each controller handles its device's operations independently while contributing to the overall RAID functionality.
3Productivity
If memory blocks are divided into superblocks for efficient memory operation control, then productivity is improved, but device complexity increases due to additional control mechanisms
Solution Approach 1:
The patent segments memory blocks into larger superblocks that are managed as unified units across multiple storage devices in the RAID array. This segmentation reduces the number of individual management operations required, as the memory controller handles superblock-level operations rather than individual block operations, improving productivity while keeping control mechanisms manageable.
Data Source
AI summary
A data processing system includes a host including a host memory storing file systems, each file system including file pages, and storage devices. Each storage device includes a memory device including memory blocks, and a memory controller dividing the memory blocks into superblocks, and controlling a memory operation of the memory device based on a result of dividing the memory blocks. The host requests a first storage device of the storage devices to write a first file page of a first file system of the file systems to a first memory block of the first storage device, and requests a second storage device of the storage devices to write a second file page of the first file system of the file systems to a first memory block of the second storage device. The first file system is configured in a RAID manner using at least some of the storage devices.