Common Block Pool Reallocation for User and System Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory sub-systems face performance degradation due to garbage collection operations and inefficient allocation of blocks for system data structures, leading to over-provisioning and waste of memory resources.
Innovation Solution
Implementing a common pool of blocks for user data and system data structures, dynamically reallocating blocks based on garbage collection performance conditions and memory usage patterns to optimize performance and endurance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If blocks are separately allocated for system data structures and user data, then system reliability is improved, but memory resource waste occurs due to over-provisioning
Solution Approach 1:
The patent merges the previously separate block allocations for system data structures and user data into a unified common pool. The memory device dynamically manages this shared pool, allocating blocks to system data structures only when necessary and allowing user data to utilize remaining capacity, thereby eliminating over-provisioning waste while maintaining system reliability through on-demand allocation.
Solution Approach 2:
The patent implements dynamic block allocation within the common pool, where the boundaries between system and user data regions are not fixed but adapt based on current needs. The memory device continuously monitors pool usage and reallocates blocks between system data structures and user data dynamically, optimizing resource utilization while ensuring system functionality.
2Reliability
If garbage collection operations are performed frequently, then memory cleanliness is improved, but performance degradation occurs
Solution Approach 1:
The patent combines system data structures and user data into a single common pool, which enables unified garbage collection operations. Instead of performing separate garbage collection on isolated system regions, the memory device can conduct consolidated cleanup operations that are more efficient and cause less performance disruption, thereby improving memory cleanliness with reduced performance impact.
Solution Approach 2:
The patent implements continuous background garbage collection within the common pool that operates seamlessly alongside normal read/write operations. By maintaining continuous cleanup activity rather than periodic intensive operations, the system preserves memory cleanliness while minimizing performance degradation through steady, low-impact background processing.
Data Source
AI summary
A method includes identifying, by a processing device, a common pool of blocks comprising a first plurality of blocks allocated to system data and a second plurality of blocks allocated to user data; determining whether user data has been written to the second plurality of blocks within a threshold period of time; and responsive to determining that the user data has not been written to the second plurality of blocks within the threshold period of time, allocating a block from the second plurality of blocks to the first plurality of blocks.