Distributed SSD Coding Architecture for Read/Write Failure Protection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Solid-state drives (SSDs) face high error rates leading to read/write failures and data loss due to limited endurance and high raw error rates, which challenges data protection and correction.
Innovation Solution
Implementing a method that performs erasure coding (EC) on data bulk to generate EC codewords, distributing portions across multiple SSDs, and performing error correction coding (ECC) on each SSD to generate ECC codewords, enhancing data protection by reducing error rates and improving reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If erasure coding and error correction coding are implemented in SSDs, then data reliability is improved, but device complexity increases
Solution Approach 1:
The patent divides data protection into two separate coding layers: erasure coding that distributes data across multiple SSDs, and error correction coding that operates within each SSD. This segmentation allows each layer to specialize in specific error types, improving overall reliability while maintaining manageable complexity through modular design
Solution Approach 2:
The patent introduces EC codewords as an intermediary layer between the original data and the ECC codewords stored in SSDs. These EC codewords serve as mediators that distribute data redundancy across multiple drives, enabling recovery from drive failures without requiring complex ECC schemes across the entire storage array
2Reliability
If EC codewords are distributed across multiple SSDs, then data protection is enhanced, but read/write operation complexity increases
Solution Approach 1:
The patent segments EC codewords into multiple portions and distributes them across different SSDs. During read/write operations, the system can selectively access only the necessary portions from relevant SSDs, reducing the operational burden compared to treating the entire distributed code as a single unit
Solution Approach 2:
The patent performs EC encoding in advance to generate distributed EC codewords before data is written to SSDs. This preliminary action prepares the data redundancy structure upfront, so that during actual read/write operations, the system only needs to perform simpler ECC operations on already-prepared codeword portions
Data Source
AI summary
The present disclosure relates to a system and a method for data protection. In some embodiments, an exemplary method for data encoding includes: receiving a data bulk; performing an erasure coding (EC) encoding on the data bulk to generate one or more EC codewords; distributing a plurality of portions of each EC codeword of the one or more EC codewords across a plurality of solid-state drives (SSDs); performing, at each SSD of the plurality of SSDs, an error correction coding (ECC) encoding on portions of the one or more EC codewords distributed to the SSD to generate an ECC codeword; and storing, in each SSD of the plurality of SSDs, the ECC codeword.