Memory Transfer Queue Retention for Program Failure Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory sub-systems face inefficiencies in handling program failures, leading to extensive data structure complexities and increased power consumption due to the flushing and reissuing of commands, which result in adverse effects like read disturb, write disturb, and write amplification.
Innovation Solution
The implementation of a transfer queue retention component that maintains a number of commands in the queue after detecting a program failure, eliminating the need for reissue/replay components and reducing data structure complexities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If commands are flushed and reissued after program failure, then system reliability is improved, but power consumption increases and data traffic increases
Solution Approach 1:
The patent extracts the reissue/replay component from the system, eliminating the need to flush and reissue commands after program failure. Instead, the transfer queue retention component maintains commands in the queue, allowing the device to recover from program failures without flushing the queue, thereby reducing power consumption and data traffic while maintaining reliability.
Solution Approach 2:
The patent discards the traditional approach of flushing and reissuing commands after program failure. By retaining commands in the transfer queue and using a different recovery mechanism, the system avoids the power consumption and data traffic overhead associated with command reissuance while still achieving reliable error recovery.
2Reliability
If commands are flushed and reissued after program failure, then system reliability is improved, but device complexity increases
Solution Approach 1:
The patent removes the reissue/replay component and its associated complex data structures from the system. The transfer queue retention component simplifies the architecture by maintaining commands in the queue without requiring the complex flushing and reissuance mechanism, thereby reducing device complexity while preserving reliability through alternative error recovery methods.
3Use of energy by moving object
If commands are pushed to failed LUN instead of reissued, then power consumption is reduced, but system reliability may worsen
Solution Approach 1:
The patent introduces a transfer queue retention component as an intermediary between the command queue and the failed LUN. This component enables commands to be pushed to the failed LUN without full reissuance, reducing power consumption while maintaining reliability through controlled error recovery mechanisms that handle failed commands appropriately.
Data Source
AI summary
A method includes issuing a program command to a logic unit (LUN) of a memory device, writing a plurality of commands to a transfer queue within the memory device, detecting a program failure for the LUN of the memory device, and maintaining a number of the plurality of commands in the transfer queue.