Garbage Collection Using Logical-to-Physical Table Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing garbage collection methods using a physical-to-logical (P2L) table are prone to corruption, leading to resource-intensive logical-to-physical (L2P) table-based searches, which cause significant delays and potential errors, especially when the P2L table is corrupted, resulting in command timeouts and fatal errors.
Innovation Solution
Implementing a strategy that limits write speed to TLC block stripes, modifies the garbage collection policy to free up space quickly, and periodically records the current position in the L2P table to pause and resume the search, allowing for more resource-efficient L2P table-based searches and using P2L-based garbage collection for other block stripes when the P2L table is corrupted.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If L2P table-based search is used for garbage collection, then accuracy is improved, but processing time increases significantly
Solution Approach 1:
The patent segments the L2P table search process by dividing it into multiple intervals with checkpoint positions. The search is paused at checkpoints and can be resumed later, breaking a single long processing operation into smaller manageable segments that reduce overall processing time while maintaining accuracy.
Solution Approach 2:
The patent implements periodic action by periodically pausing the L2P table search at checkpoint positions and allowing other operations to proceed. This periodic interruption and resumption pattern enables the system to maintain accurate garbage collection while reducing continuous processing time and allowing parallel operations.
2Productivity
If P2L table is used for garbage collection, then processing speed is improved, but reliability deteriorates due to corruption
Solution Approach 1:
The patent uses the L2P table as an intermediary structure to verify the integrity of the P2L table. By periodically checking P2L table entries against the L2P table, the system can detect corruption in the P2L table while maintaining the speed benefits of P2L-based garbage collection for uncorrupted blocks.
Solution Approach 2:
The patent implements feedback mechanisms where the system monitors P2L table integrity and automatically switches between P2L-based and L2P-based garbage collection methods based on detected corruption. This feedback loop maintains reliability by detecting issues and adapting the collection strategy while preserving processing speed where possible.
3Productivity
If write speed to TLC block stripes is increased, then productivity is improved, but garbage collection complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-establishing checkpoint positions in the L2P table before garbage collection operations begin. This preliminary structuring allows for more manageable and less complex garbage collection processes, enabling faster write speeds to TLC block stripes while maintaining organized control over the collection complexity.
Data Source
AI summary
A method is described that includes determining, by a memory subsystem, that a garbage collection process is to be performed on a memory device and selecting a first candidate block stripe for folding into a first target block stripe in response to determining that the garbage collection process is to be performed. The method further includes determining, by the memory subsystem, that a physical-to-logical table stored in the first candidate block stripe is unavailable; reducing a write command rate, which controls a rate at which writes are fulfilled by the memory subsystem, in response to determining that the physical-to-logical table stored in the first candidate block stripe is unavailable; and performing folding of the first candidate block stripe into the first target block stripe using a logical-to-physical table.