Memory Partition Layout for Capacity and Interference Isolation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face challenges in balancing user capacity and independence between different memory types and applications, leading to reduced lifetime and effectiveness due to interference and inefficient wear leveling.
Innovation Solution
A memory system with configurable partitions and memory type independence allows for flexible storage configurations, either prioritizing high user capacity by sharing pools or prioritizing independence by isolating partitions with separate pools, thereby managing wear leveling and interference effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If memory pools are shared between different memory types to increase user capacity, then storage efficiency improves, but interference between memory types increases and lifetime decreases
Solution Approach 1:
The memory system is segmented into multiple independent partitions, each dedicated to a specific memory type (e.g., SLC, MLC, TLC). Each partition has its own dedicated pools for wear leveling and bad block management, preventing interference between different memory types while maintaining high user capacity through efficient utilization of each partition's resources.
2Reliability
If memory pools are isolated for each memory type to reduce interference, then reliability improves, but user capacity decreases due to inefficient resource utilization
Solution Approach 1:
The memory system is divided into separate partitions for different memory types, with each partition having dedicated pools. This segmentation ensures complete isolation and independence for each memory type, eliminating interference while maintaining high reliability through partition-specific wear leveling and bad block management.
3Productivity
If wear leveling pools are shared across multiple memory types, then productivity improves, but wear distribution becomes uneven and lifetime reduces
Solution Approach 1:
Wear leveling pools are segmented and dedicated to specific memory type partitions. Each partition performs wear leveling independently within its own pool, ensuring that wear is distributed evenly across blocks of the same memory type without being affected by the different wear characteristics of other memory types, thereby extending overall system lifetime.
4Device complexity
If spare blocks are shared between partitions, then device complexity reduces, but interference increases and effectiveness decreases
Solution Approach 1:
Spare blocks are segmented into partition-specific pools, with each memory type partition having its own dedicated spare block pool. This segmentation ensures complete independence between partitions, preventing interference while maintaining reliability through isolated bad block management and wear leveling operations for each memory type.
Data Source
AI summary
Methods, systems, and devices for configurable partitions and memory type independence in a memory system are described. A memory system may support different storage configurations for provisioning, including a first configuration for prioritizing high user capacity or terabytes written (TBW), and a second configuration for prioritizing independence or Freedom From Interference (FFI). In the first configuration, a memory system may support up to one partition of each supported memory type. A system memory area may share one or more pools with a first partition or memory type, while other pools may be specific to each other partition or memory type. In the second configuration, the memory system may support multiple partitions within some memory types each with one or more respective pools. By enabling different storage configurations for selection at a memory device, greater flexibility in provisioning may be provided while allowing prioritization of different characteristics.