Non-Volatile Storage Open Block Boundary Reliability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Open block boundary regions in non-volatile storage devices, such as flash memory, exhibit worse data reliability compared to closed blocks due to the impact of write operations on neighboring portions, leading to erroneous readings and elevated bit error rates.

Innovation Solution

The storage device manages open blocks by receiving a shut-down request, identifying boundary regions, programming contiguous regions with data or a predefined pattern, and updating an XOR parity table to enhance data recovery, thereby improving reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If write operations are performed in open block boundary regions, then data can be stored, but data reliability deteriorates due to charge interference from subsequent write operations

Engineering Contradiction:
Improvedata reliabilityVSAvoidcharge interference from write operations
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent applies preliminary action by programming the contiguous region with data or a predefined pattern before the open block is fully written. This pre-programming creates a protective buffer that compensates for the charge interference that will occur during subsequent write operations in the boundary region, thereby maintaining data reliability despite the harmful effects of neighboring writes.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent uses copying by storing data in the contiguous region adjacent to the boundary region. This creates a redundant copy or proxy for the boundary region data, which can be used for error detection and correction. The copied data serves as a backup that is less susceptible to charge interference, thereby improving overall data reliability.

Inventive Principle:
Principle #26Copying

2Reliability

If contiguous regions are programmed with data for recovery purposes, then data reliability improves, but storage capacity is reduced

Engineering Contradiction:
Improvedata recovery capabilityVSAvoidusable storage capacity
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The patent applies local quality by programming only the contiguous regions adjacent to boundary regions with recovery data or patterns, rather than programming entire blocks. This localized approach provides error protection where it is most needed (at vulnerable boundary regions) while leaving the rest of the storage capacity available for user data, thus balancing reliability improvement with capacity preservation.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent uses a predefined pattern (such as all zeros or all ones) to program the contiguous region, which serves as a disposable or sacrificial structure. This pattern does not need to be preserved long-term like user data, as it can be regenerated or replaced during block management operations. Using such simple, replaceable patterns minimizes the overhead cost while still providing the necessary error protection functionality.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Data Source

PatentUS10613943B2Method and system for improving open block data reliability
Publication Date: 2020.04.07 SANDISK TECHNOLOGIES LLC
  • US10613943B2 patent drawing
  • US10613943B2 patent drawing
  • US10613943B2 patent drawing

AI summary

Systems, methods, and/or devices are used to manage open blocks within non-volatile storage devices, in order to improve the reliability of non-volatile storage devices. In some embodiments, when a shut-down request is received from a host device, the storage device fetches information about open blocks and their boundary regions susceptible to data reliability issues, and for each identified boundary region, the storage device programs a region contiguous to the identified boundary region. In some embodiments, the device updates an XOR parity table used for XOR parity management with the information that the region contiguous to the identified boundary is programmed. Subsequently, in some embodiments, the storage device can use the information, stored in the contiguous region and/or the XOR parity table, for data recovery in the event of a data loss. As a result, the reliability of the non-volatile storage device is improved.