Flash Storage Data Consistency Verification via Access Latency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional data consistency detection methods, such as cyclic redundancy check (CRC), are computationally intensive and unsuitable for large-scale storage systems, and fail to accurately pinpoint error locations in flash-based solid state drives (SSDs).

Innovation Solution

The method employs access latency to verify data consistency by measuring the time it takes to read data blocks from SSDs, using a cache hierarchy and flash translation layer (FTL) to determine if data is consistently stored in physical memory, and further evaluates suspicious data content through additional checks if latency thresholds are not met.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If CRC technique is used for data consistency detection, then data accuracy can be verified, but computational intensity increases and server processor/memory resources are consumed

Engineering Contradiction:
Improvedata accuracyVSAvoidcomputational intensity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces the computational CRC verification mechanism with a latency-based detection mechanism. Instead of performing complex mathematical calculations to verify data integrity, the system uses timing information (access latency) to infer data consistency, thereby eliminating the need for resource-intensive processor operations while maintaining detection capability

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a virtual copy of the data verification process by using latency measurements as a proxy for actual data integrity checking. Rather than directly verifying data through computation, the system measures the time characteristics of data access, which serve as an indirect but sufficient indicator of data consistency, thus avoiding the need for actual computational verification

Inventive Principle:
Principle #26Copying

2Reliability

If CRC technique is used for data consistency detection, then error detection capability is provided, but error location precision is insufficient

Engineering Contradiction:
Improveerror detection capabilityVSAvoiderror location precision
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent applies local quality analysis by examining latency characteristics at specific data block levels rather than performing global CRC verification. The system measures access latency for individual data blocks or pages, allowing precise identification of where errors occur within the storage structure, thereby achieving both error detection and accurate location pinpointing

Inventive Principle:
Principle #3Local quality

3Reliability

If CRC technique is used for data consistency detection, then data verification is performed, but server processor and memory resources are occupied

Engineering Contradiction:
Improvedata verificationVSAvoidserver processor and memory resources
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent substitutes the resource-intensive CRC computation system with a latency measurement system that requires minimal processor intervention. By using timing information already available during normal data access operations, the system eliminates the need for additional computational resources and memory bandwidth that would be required for CRC calculations

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system uses the existing data access operations themselves to provide verification information. The latency measurements are obtained during normal read operations without requiring separate verification passes or additional computational processing, allowing the system to self-verify data consistency using its own operational characteristics rather than external computational resources

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS10261705B2Efficient data consistency verification for flash storage
Publication Date: 2019.04.16 CLOUD INTELLIGENCE ASSETS HOLDING (SINGAPORE) PTE LTD
  • US10261705B2 patent drawing
  • US10261705B2 patent drawing
  • US10261705B2 patent drawing

AI summary

Data verification includes obtaining a logical block address (LBA), which is associated with a data block of a file, to be verified. Data verification further includes reading, from a solid state drive (SSD) comprising one or more flash storage elements, data content that corresponds to the LBA. Data verification further includes determining whether an access latency associated with the reading of the data content exceeds a threshold. Data verification further includes, in the event that the access latency does not exceed the threshold, evaluating the data content to determine whether it is consistently stored in a physical memory included in the SSD. Data verification further includes, in the event that the data content is determined not to be consistently stored in the physical memory included in the SSD, recording an indication indicating that the LBA is not successfully verified.