Garbage Collection Scheduling for Solid State Memory
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In solid state memory (SSM) with a multiple die architecture, garbage collection processes are hindered by die conflicts due to simultaneous write and erase operations, leading to stalls and reduced performance, especially under continuous random write workloads.
Innovation Solution
A die tracking module (DTM) is integrated into the storage controller to monitor the busy status of dies and determine an optimal order for garbage collection reads based on an activity table, avoiding busy dies and improving scheduling efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If garbage collection is performed on multiple dies simultaneously, then storage space recovery is improved, but die conflicts occur due to simultaneous write and erase operations causing stalls
Solution Approach 1:
The system performs preliminary tracking of die activity states before initiating garbage collection. The activity table records which dies are currently busy with write operations, allowing the garbage collection scheduler to identify and avoid conflicting dies in advance, thus preventing stalls while maintaining parallel operation capability
Solution Approach 2:
The garbage collection die selection is made dynamic rather than static. The system continuously monitors die activity states and adjusts the order of die access during garbage collection based on real-time activity table data, allowing the system to adapt to changing workload conditions and optimize between parallelism and conflict avoidance
2Productivity
If die access order is fixed during garbage collection, then process simplicity is maintained, but performance is reduced due to conflicts with busy dies
Solution Approach 1:
The activity table serves as a self-updating record of die states that automatically reflects current workload conditions. The system uses this self-maintained data structure to make scheduling decisions without requiring complex external coordination, allowing the garbage collection process to self-adapt to system state
Solution Approach 2:
The activity table acts as an intermediary data structure between the workload generator and the garbage collection scheduler. It mediates the information flow by capturing die state information and presenting it in a format that enables intelligent scheduling decisions, simplifying the interface between monitoring and execution components
Data Source
AI summary
Systems and methods are disclosed for the intelligent scheduling of garbage collection operations on a solid state memory. In certain embodiments, a method may comprise initiating a garbage collection process for a solid state memory (SSM) having a multiple die architecture, determining an order of die access for the garbage collection process based on an activity table indicating a use of one or more die in the multiple die architecture, and performing the garbage collection process based on the determined order of die access. Garbage collection reads may be directed to idle die to avoid conflicts with die busy performing other operations, thereby improving system performance.