Half-Compressed RAID 1 Storage for Capacity and Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage systems, such as RAID, face challenges in balancing reliability, storage capacity, and response time, particularly in networked environments where data redundancy is critical but storage capacity and access efficiency are compromised.
Innovation Solution
Implementing a data storage system where one copy of a data set is stored uncompressed and the other copy is stored compressed across different physical storage devices, allowing for RAID 1 reliability with reduced storage capacity requirements and improved data access response times through compression striping and delayed compression techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is stored in uncompressed state on both disks in RAID 1, then data reliability is maintained, but storage capacity requirements increase
Solution Approach 1:
The patent applies local quality by maintaining different compression states for different portions of replicated data. Specifically, one copy of the data set is stored in uncompressed state while another copy is stored in compressed state, allowing the system to optimize storage capacity utilization without compromising overall data reliability. This differential treatment of data copies enables more efficient use of storage resources.
2Quantity of substance
If data is compressed before storage, then storage capacity requirements are reduced, but data access response time increases due to decompression requirements
Solution Approach 1:
The patent segments the replicated data into different compression states across multiple storage devices. By maintaining one uncompressed copy and one compressed copy, the system allows read operations to access the uncompressed data directly without decompression overhead, thereby reducing data access response time while still achieving storage capacity benefits from the compressed copy.
Solution Approach 2:
The system dynamically selects which data copy to use for read operations based on current needs. The uncompressed copy can be used when fast access is required, while the compressed copy can be used when storage capacity is the primary concern or when data is being written. This dynamic approach optimizes both response time and storage utilization.
3Quantity of substance
If compression is applied to all data copies, then storage capacity is optimized, but write operation complexity increases
Solution Approach 1:
The patent applies partial action by compressing only one copy of the data set rather than all copies. This approach achieves storage capacity optimization without requiring compression of every data replica, thereby reducing the complexity of write operations while still realizing the benefits of compressed storage.
Data Source
AI summary
In a half-compressed RAID 1 system a first copy of a data set is maintained in an uncompressed state and a second copy of the data set is maintained in a compressed state, where corresponding compressed and uncompressed blocks are stored on different physical devices. The result is RAID 1 reliability with storage space consumption similar to RAID 5-3+1. Compression striping in which the compressed and uncompressed data is distributed across two or more storage devices can be used to reduce data access response time. Further, delayed compression can be used to reduce the time required to perform WRITE ops. Compression may also be performed based on resource availability or storage tier hierarchy.