Zone-Based Data Storage Garbage Collection for Fragmentation Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage devices face inefficiencies in managing storage space, particularly in handling full zones and fragmentation, leading to suboptimal data management and storage capacity utilization.
Innovation Solution
A data storage device with a controller that manages memory blocks into zones and performs operations like garbage collection and zone merging to efficiently allocate and relocate data, optimizing storage efficiency by reallocating data from full zones to available space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is stored in multiple zones without consolidation, then storage capacity is utilized, but storage efficiency deteriorates due to fragmentation
Solution Approach 1:
The patent merges data from multiple full zones into a single target zone when finish zone requests are received. The controller consolidates data from victim zones into an available target zone, reducing fragmentation and improving storage efficiency while maintaining capacity utilization.
Solution Approach 2:
The patent dynamically selects victim zones and target zones based on real-time storage state. The controller identifies zones with finish requests as potential victim zones and selects zones with available space as target zones, adapting the garbage collection process to current storage conditions.
2Productivity
If garbage collection is performed frequently to reduce fragmentation, then storage efficiency is improved, but loss of time increases due to repeated data relocation operations
Solution Approach 1:
The patent performs garbage collection periodically when finish zone requests are received from the host. Instead of continuous garbage collection, the system triggers consolidation operations at specific intervals when zone finish requests occur, reducing unnecessary data relocation while maintaining storage efficiency.
Solution Approach 2:
The system uses finish zone requests from the host as triggers for garbage collection operations. The host's own requests serve to initiate the consolidation process, eliminating the need for separate garbage collection scheduling and reducing overhead.
3Quantity of substance
If zones are kept in full state with invalid write pointers, then storage capacity is maximized, but device complexity increases due to zone management overhead
Solution Approach 1:
The patent extracts the management of full zones from the host's responsibility. When the host issues finish zone requests, the controller takes over by identifying victim zones and target zones, and performing the actual data consolidation, simplifying the overall system management.
Solution Approach 2:
The controller acts as an intermediary between the host's finish zone requests and the actual data consolidation process. It translates host requests into specific victim zone and target zone selections, and coordinates the data relocation operation, reducing the complexity burden on the host.
Data Source
AI summary
Data storage devices and methods of operating the data storage devices are disclosed. In an embodiment, a data storage device may include a memory device including a plurality of memory blocks allocated to a plurality of zones that are a storage regions corresponding to a plurality of logical address groups provided from a host, and a controller configured to control the memory device to select a victim zone for moving stored data to a target zone, from among zones for which a finish zone request is received from the host, and move data from a memory block allocated to the victim zone to a remaining space of a memory block allocated to the target zone.