Memory Controller BF Scan Scheduling Across Die Groups
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory sub-systems inefficiently allocate memory components for block family scan operations, leading to performance loss due to unbalanced distribution and underutilization of maximum allowable quantity of memory components during measurement periods.
Innovation Solution
A memory sub-system controller dynamically distributes the maximum allowable quantity of memory components across groups based on storage characteristics, ensuring all components are scanned efficiently by adaptively adjusting the number of components included in each measurement period.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If memory components are distributed evenly across groups, then each group receives equal attention, but the maximum allowable quantity of memory components is underutilized during measurement periods
Solution Approach 1:
The system dynamically adjusts the distribution of memory components across groups based on real-time conditions. The controller modifies which memory components are included in BF scan operations during each measurement period, transitioning from static even distribution to dynamic adaptive distribution that maximizes the number of components scanned while ensuring all components are eventually scanned.
Solution Approach 2:
The invention changes the parameter of memory component allocation from fixed equal distribution to variable distribution. By adjusting the number of memory components included from each group based on group characteristics and system state, the system optimizes scan throughput while maintaining fairness across all memory components over time.
2Reliability
If all memory components are included in BF scan operations, then comprehensive scanning is achieved, but performance loss occurs due to unbalanced distribution
Solution Approach 1:
The system applies different scanning strategies to different groups of memory components based on their local characteristics. Instead of treating all memory components uniformly, the controller identifies specific groups that benefit most from inclusion in BF scan operations at each measurement period, optimizing overall scan efficiency while ensuring comprehensive coverage.
Solution Approach 2:
The invention implements partial scanning by selecting only certain memory components for inclusion in BF scan operations during each measurement period. This partial action approach allows the system to scan the maximum allowable quantity of memory components efficiently, while a scheduling mechanism ensures that all memory components are scanned across multiple measurement periods, preventing starvation.
Data Source
AI summary
Aspects of the present disclosure configure a system component, such as a memory sub-system controller, to perform adaptive die selection for block family scan operations. The controller assigns a set of memory components to one or more groups of a plurality of groups based on respective storage characteristics of the set of memory components, each of the plurality of groups corresponding to different storage characteristics. The controller determines a maximum quantity of memory components to perform block family (BF) scan operations at an individual measurement period. The controller distributes the maximum quantity of memory components across the one or more groups to which the set of memory components are assigned and, at the individual measurement period, performs the BF scan operations on a portion of the set of memory components corresponding to the maximum quantity of memory components.