Distributed ECC Architecture for Storage Data Path Bottlenecks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage systems using ECC engines face performance bottlenecks due to centralized ECC computation, which can be economically inefficient and require specialized storage media devices with added logic, and there is a need for a distributed approach that optimizes ECC computations without affecting system performance.
Innovation Solution
The solution involves distributing ECC engines across multiple storage media devices, with each ECC engine handling computations for a corresponding group of devices, allowing parallel ECC operations on multiple data parts, and integrating ECC engines into storage DMA controllers or interface controllers to perform encoding, detection, and correction operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a centralized ECC engine is placed in the main storage controller, then ECC computation can be performed, but it creates a performance bottleneck in the data path
Solution Approach 1:
The patent divides the centralized ECC engine into multiple distributed ECC engines, with each engine handling ECC computations for a specific group of storage media devices. This segmentation eliminates the single-point bottleneck by distributing the computational load across multiple parallel processing units in the data path.
2Productivity
If ECC engines are embedded on each storage device, then the data path bottleneck is eliminated, but it increases device complexity and cost
Solution Approach 1:
The patent makes standard storage interface controllers multi-functional by integrating ECC engine capabilities into them. This allows the interface controllers to perform both their standard storage interface functions and ECC computation functions, eliminating the need for specialized storage media devices with added logic while maintaining parallel processing capability.
3Productivity
If ECC engines are embedded on each storage device, then parallel processing is achieved, but it requires specialized storage media devices with added logic
Solution Approach 1:
The patent enables standard storage interface controllers to perform ECC computations by integrating ECC engine functionality into them. This approach maintains storage device standardization and ease of manufacture while achieving parallel ECC processing, as no specialized storage media devices are required.
Data Source
AI summary
Embodiments of the present invention relate to an apparatus, method, and/or sequence for a distributed ECC that may be used in a storage system. In another embodiment of the invention, an apparatus for handling distributed error correction code (ECC) operations, includes: a plurality of ECC engines configured to perform ECC operations in parallel on multiple data parts; the plurality of ECC engines distributed in parallel to receive some of the multiple data parts that are read from storage media devices and to receive some of the other multiple data parts that are to be written to the storage media devices; and the plurality of ECC engines configured to use respective ECC bytes corresponding to respective ones of the multiple data parts.