Memory Controller Bad Block Replacement Across Planes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage devices face inefficiencies in maintaining operating speed due to the inability to effectively manage bad blocks, leading to performance overhead when replacing bad blocks within the same plane, which limits multi-plane operations and increases processing time.
Innovation Solution
A memory controller is implemented with a bad block management unit that detects bad blocks and replaces them with reserved blocks, either within the same plane if available or from a different die, to minimize operational disruption and maintain multi-plane operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If bad blocks are replaced with reserved blocks within the same plane, then reliability is improved, but operating speed deteriorates due to performance overhead
Solution Approach 1:
The patent extends bad block replacement from a single-plane dimension to a multi-die dimension. When a bad block is detected in a plane, the system first attempts replacement within the same plane using reserved blocks. When no reserved blocks are available in the same plane, the system transitions to another dimension by selecting reserved blocks from different planes within the same die, and ultimately from different dies. This dimensional expansion allows the system to maintain reliability while avoiding the performance overhead that would result from restricting replacements to a single plane.
2Reliability
If multi-plane operations are limited for bad block replacement, then reliability is improved, but productivity deteriorates
Solution Approach 1:
The patent implements a dynamic bad block replacement strategy that adapts to the availability of reserved blocks. The system dynamically adjusts the replacement scope based on real-time conditions: it prefers same-plane replacement when reserved blocks are available, but dynamically expands to cross-plane and cross-die replacement when needed. This dynamic approach allows multi-plane operations to continue uninterrupted, maintaining both reliability and productivity, rather than statically limiting operations to a single plane.
3Device complexity
If reserved blocks are allocated within the same die, then device complexity is reduced, but reliability deteriorates when no reserved blocks are available
Solution Approach 1:
The patent makes reserved blocks universal by allowing them to serve multiple functions across different planes and dies. Reserved blocks are not permanently assigned to a specific plane but are made available as a shared resource pool. When a bad block occurs in any plane, the system can allocate any available reserved block from any plane or die, making the reserved block system multi-functional and universally applicable throughout the entire memory device, thereby enhancing reliability without significantly increasing complexity.
Data Source
AI summary
Provided herein may be a storage device having improved operating speed and a method of operating the same. The storage device may include a memory controller configured to control the plurality of dies, each including two or more planes. The memory controller may include a reserved block information storage unit configured to store reserved block information that is information related to reserved blocks included in the plurality of dies; and a bad block management control unit configured to set, when a bad block occurs among memory blocks respectively included in the plurality of dies, a reserved block to replace the bad block depending on whether any one of available reserved blocks are included in a plane to which the bad block belongs, among the two or more planes included in a die including the bad block, based on the reserved block information.