Fine-Grained Tiered Storage Management via Dynamic Data Migration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage systems lack efficient automatic management of data throughout its lifecycle, as they do not adapt to changing data value and access frequency, leading to inefficient use of storage resources.
Innovation Solution
A method that utilizes a table to map sections of a logical device to different storage areas with varying characteristics, allowing data to be moved based on user-defined policies considering factors like access frequency, last use time, and user information, and updates the table accordingly to optimize storage allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If data is stored on fast and expensive storage devices, then data access speed is improved, but storage cost increases
Solution Approach 1:
The system dynamically relocates data between different storage tiers (fast/expensive to slow/cheap) based on changing access patterns and data value over time. This allows the storage system to adapt to varying data requirements, ensuring high-speed access for frequently accessed data while reducing costs for less frequently accessed data.
Solution Approach 2:
Different portions of data are assigned to different storage tiers based on their specific access characteristics. Frequently accessed data resides on fast storage devices, while less frequently accessed data is placed on slower, cheaper devices. This localized optimization ensures that each data segment is stored on the most appropriate storage medium for its access pattern.
2Quantity of substance
If data is stored on slow and cheap storage devices, then storage cost is reduced, but data access speed deteriorates
Solution Approach 1:
The system continuously monitors data access patterns and automatically promotes data from slow/cheap storage to fast/expensive storage when access frequency increases. This dynamic adjustment ensures that data access speed requirements are met without permanently allocating expensive storage resources for all data.
Solution Approach 2:
The system performs preliminary assessment of data access patterns and proactively relocates data to appropriate storage tiers before performance degradation occurs. By anticipating access needs based on historical patterns, the system can pre-position data on appropriate storage devices.
3Ease of operation
If manual management of data storage locations is implemented, then storage allocation control is improved, but operational complexity increases
Solution Approach 1:
The system automatically manages data relocation between storage tiers without requiring manual intervention. It self-monitors access patterns, evaluates data value, and performs migrations autonomously based on predefined policies, eliminating the need for complex manual storage management operations.
Solution Approach 2:
The system continuously monitors data access patterns and uses this feedback to automatically adjust storage allocations. By closing the feedback loop between access monitoring and storage management, the system maintains optimal storage allocation without requiring complex manual control mechanisms.
4Productivity
If automatic data relocation between storage tiers is implemented, then storage efficiency is improved, but system complexity increases
Solution Approach 1:
The automatic relocation system operates autonomously using self-service mechanisms. It independently evaluates data characteristics, determines optimal storage locations, and executes migrations without external control, achieving high storage efficiency through automated decision-making processes.
Solution Approach 2:
The system changes storage allocation parameters dynamically based on data access characteristics. By adjusting which data resides on which storage tier based on monitored parameters (access frequency, data value, etc.), the system achieves efficient storage utilization through parameter-driven automation.
Data Source
AI summary
A system for managing data includes providing at least one logical device having a table of information that maps sections of the logical device to sections of at least two storage areas. Characteristics of data associated with a one section of the logical device may be evaluated. The section of the data may moved between the at least two storage areas from a first location to a second location according to a policy and based on the characteristics of the data. A copy of the data may be retained in the first location and a list maintained that indentifies the copy of the data in the first location. The system provides for garbage collection processing for memory management.