Distributed CAS System Control Data Plane Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional storage systems face challenges in supporting content-based storage with ultra-high performance due to intensive computational load, need to break large blocks into smaller sizes, inability to maintain sequential data block location, and architectural difficulties in distributing content-based mapping across multiple processing elements.
Innovation Solution
A distributed Content Addressable Storage (CAS) system with a networked memory architecture, using hashing for content addressing, and separating control and data planes to optimize performance and scalability, allowing for inline deduplication and efficient use of memory resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If traditional storage systems use content-based storage with hashing, then storage capacity efficiency is improved through inline deduplication, but computational load increases and performance decreases
Solution Approach 1:
The system segments the storage architecture into separate control plane and data plane components. The control plane handles content-based operations like hashing and deduplication, while the data plane handles high-speed data retrieval. This segmentation allows each plane to be optimized for its specific function, resolving the contradiction between content-based storage efficiency and performance.
Solution Approach 2:
The patent introduces a content addressable memory (CAM) table as an intermediary structure that maps content hashes to physical storage locations. This intermediary enables fast lookup of data without requiring full content scanning, thus maintaining high performance while achieving content-based deduplication.
2Adaptability or versatility
If storage systems break large blocks into smaller sizes for content addressing, then content-based mapping is enabled, but sequential data block location is lost and access time increases
Solution Approach 1:
The patent extracts the content-based mapping function from the data storage structure itself and places it in a separate control plane with CAM tables. This allows the data plane to maintain sequential block structures for fast access, while the control plane handles content-based mapping operations independently.
Solution Approach 2:
The system adds a content hash dimension to the traditional address-based storage dimension. Instead of only accessing data through sequential block addresses, the system can also access data through content hashes, creating a two-dimensional addressing space that resolves the contradiction between content-based mapping and sequential access speed.
3Adaptability or versatility
If storage systems distribute content-based mapping across multiple processing elements, then scalability is improved, but system complexity increases
Solution Approach 1:
The control plane components are designed with multi-functionality, handling content hashing, deduplication, and mapping operations across multiple processing elements. This universal design simplifies the overall architecture by reducing the number of specialized components needed while maintaining scalability.
Data Source
AI summary
Example embodiments of the present invention relate to a method, a system, and a computer program product for data protection. The method includes creating a snapshot of a volume and maintaining the snapshot as a logical point in time copy of the volume for data protection of the volume.