Disk Command Queue Management Using Address-Time B+ Trees
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing disk devices face challenges in efficiently managing commands received from a host, particularly in handling command addresses and time series effectively.
Innovation Solution
A disk device with a database that associates command addresses and time series using a tree-like array structure, enabling efficient management and execution of commands through a B+ tree data structure with key range and time series handling capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a traditional command management method is used, then the device complexity is low, but the command management efficiency and performance deteriorate
Solution Approach 1:
The patent implements a nested database structure where multiple databases (command queue database, command execution database, command deletion database) are organized in a hierarchical manner. Each database contains tables with related fields, creating a nested arrangement that efficiently manages different aspects of command processing. This nested structure enables the system to handle command queuing, execution, and deletion operations simultaneously with improved efficiency while maintaining organized complexity.
Solution Approach 2:
The patent introduces a time series dimension to command management by incorporating timestamps and time-based fields in the database tables. The command execution database includes fields for execution start time, execution end time, and time series ordering. This temporal dimension allows the system to manage commands not only by their logical sequence but also by their temporal characteristics, improving productivity through better command scheduling and conflict resolution.
2Measurement precision
If commands are managed with detailed tracking and monitoring, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent creates a multi-functional database structure where the same database tables serve multiple purposes. The command execution database, for example, simultaneously tracks command status, execution timing, priority levels, and time series information. This universal approach allows precise measurement and tracking of commands without requiring separate specialized systems, thereby improving measurement precision while controlling overall device complexity through consolidation.
Solution Approach 2:
The patent introduces database tables as intermediary structures between command reception and command execution. These tables act as mediators that systematically organize and track command information, providing precise measurement and tracking capabilities. The intermediary database layer processes and manages command details, enabling accurate tracking without directly increasing the complexity of the core command processing logic.
3Manufacturing precision
If a tree-like array structure with B+ tree is used, then the manufacturing precision of data organization improves, but the ease of manufacture deteriorates
Solution Approach 1:
The patent segments the command management system into distinct database tables and components, each responsible for specific functions. The command queue database handles incoming commands, the command execution database manages executing commands, and the command deletion database handles deleted commands. This segmentation allows for precise data organization through the B+ tree structure in each table while simplifying the overall implementation by dividing the complex system into manageable, independently developable modules.
Data Source
AI summary
According to one embodiment, there is provided a disk device including a disk medium, a memory and a controller. On the disk medium, data is recorded according to an address. The controller generates or updates a database and stores the database in the memory as a command including the address is received. The database is associated with address ranges of commands, and includes a tree-like array in accordance with command addresses and time series. The controller manages commands using the database.