Zone Timestamp Tables for SSD Garbage Collection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current data validity checks and garbage collection operations in solid state drives (SSDs) are inefficient due to the large size of the flash translation layer (FTL) mapping table, leading to slow operations, especially in large capacity SSDs.

Innovation Solution

Implementing a zone-based data validity check system that includes a zone timestamp table and a zone-based defragmentation table, where the controller maintains timestamps for each zone and scans garbage collection blocks to determine data validity, allowing for efficient data relocation and defragmentation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the FTL mapping table is used for data validity checks, then data can be located using LBA, but the operation becomes slow due to the large size of the FTL mapping table

Engineering Contradiction:
Improvedata validity check accuracyVSAvoidgarbage collection speed
Core Design Contradiction:
Measurement precisionVSSpeed

Solution Approach 1:

The patent divides the large FTL mapping table into zone-specific timestamp tables. Instead of searching the entire FTL mapping table, the system maintains separate timestamp tables for different zones (e.g., zone 0, zone 1, etc.), allowing faster localized validity checks within each zone without scanning the complete mapping table.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts only the essential timestamp information from the FTL mapping table entries and stores it in separate zone timestamp tables. This extraction of critical validity indicators (timestamps) allows the system to perform validity checks without accessing the full FTL mapping table, significantly improving speed while maintaining accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

2Reliability

If the FTL mapping table is scanned to identify valid data, then data validity can be determined, but the large table size causes slow operations

Engineering Contradiction:
Improvedata validity determinationVSAvoidtime for garbage collection
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by maintaining zone timestamp tables that are updated whenever data is written to or erased from a zone. These tables pre-compute and store timestamp information that indicates data validity, so when garbage collection is needed, the system can immediately query these pre-prepared tables rather than scanning the entire FTL mapping table at that moment.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The zone timestamp tables act as intermediary structures between the FTL mapping table and the garbage collection process. Instead of directly querying the large FTL mapping table, the system uses these intermediate timestamp tables to determine data validity, reducing the complexity and time of validity checks.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If traditional garbage collection is performed on large capacity SSDs, then invalid data can be reclaimed, but the operation is slow due to the large FTL mapping table

Engineering Contradiction:
Improvespace reclamation efficiencyVSAvoidgarbage collection operation speed
Core Design Contradiction:
ProductivityVSSpeed

Solution Approach 1:

The patent segments the garbage collection process into zone-specific operations. By dividing the SSD into zones and maintaining separate timestamp tables for each zone, the system can perform garbage collection on individual zones independently and in parallel, significantly improving overall productivity and speed compared to scanning the entire FTL mapping table sequentially.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the parameter used for validity checking from full FTL mapping table entries to compact zone timestamps. This parameter change allows the system to work with smaller, more manageable data structures that can be processed faster, thereby improving garbage collection speed while maintaining the ability to accurately identify valid and invalid data.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11640260B2Fast garbage collection in zoned namespaces SSDs
Publication Date: 2023.05.02 SANDISK TECHNOLOGIES LLC
  • US11640260B2 patent drawing
  • US11640260B2 patent drawing
  • US11640260B2 patent drawing

AI summary

A data storage device includes a memory device and a controller coupled to the memory device. The data storage device supports zoned namespace. The controller is configured to maintain a zone timestamp table that includes a corresponding timestamp for each zone and add a timestamp to each garbage collection block of the memory device. The controller is further configured to scan a garbage collection block from a last physical block address (PBA) entry to a first PBA entry, determine a zone timestamp for the scanned PBA entry, and compare the zone timestamp to a timestamp of the garbage collection block. The controller is further configured to create and maintain a zone timestamp table and create and maintain a zone based defragmentation table.