Storage Controller Dynamic Tiering Based on Access Information
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In log structured storage systems, determining the optimal storage tier for data based on access patterns is challenging, as existing automated storage tiering methods rely on static policies and may not adapt dynamically to changing access frequencies, leading to inefficient data placement and potential wear leveling issues in high-speed storage devices.
Innovation Solution
A system and method where access information for each data record is maintained and used by a storage controller to determine the appropriate storage tier for data placement, allowing dynamic adjustment based on access statistics and priority, thereby optimizing data storage across multiple tiers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If automated storage tiering programs use static policies to determine data placement, then device resources are partitioned and managed systematically, but the system cannot adapt dynamically to changing access frequencies and patterns
Solution Approach 1:
The system transitions from static storage tiering policies to dynamic policies that automatically adjust based on real-time access information. The storage controller monitors access patterns and dynamically determines optimal storage tier placement, allowing the system to adapt to changing data access frequencies without manual intervention.
Solution Approach 2:
The system implements feedback mechanisms where access information about stored data is continuously collected and fed back to the storage controller. This feedback loop enables the controller to make informed decisions about data placement and tiering, automatically adjusting to changing access patterns while maintaining systematic resource management.
2Speed
If frequently accessed data is stored on high-speed storage devices, then data access performance is improved, but wear on high-speed storage devices increases
Solution Approach 1:
The system dynamically adjusts data placement between storage tiers based on access information. When data access frequency increases, the system automatically migrates that data to high-speed storage devices to maintain performance. When access frequency decreases, data is migrated to lower-speed devices, reducing wear on high-speed devices and extending their operational life.
Solution Approach 2:
The system changes the storage location parameter of data based on access patterns. By monitoring access information and adjusting where data is physically stored, the system optimizes the balance between access speed and device durability, ensuring frequently accessed data resides on fast devices while less accessed data moves to slower devices.
3Speed
If all data is stored on high-speed storage devices, then data access performance is maximized, but storage cost increases prohibitively
Solution Approach 1:
The system applies different storage qualities to different data based on their access characteristics. Frequently accessed data is placed on high-speed storage devices for optimal performance, while less frequently accessed data is placed on lower-speed, higher-capacity devices. This local differentiation of storage quality optimizes the balance between access speed and storage capacity availability.
Solution Approach 2:
The storage system is segmented into multiple tiers with different performance and capacity characteristics. The system divides data into different categories based on access patterns and places them in appropriate storage tiers, creating a hierarchical structure that maximizes both speed for critical data and capacity for archival data.
Data Source
AI summary
Provided are a computer program product, system, and method for providing access information to a storage controller to determine a storage tier for storing data. Access information is maintained for each data record in a data store, wherein the access information indicates a level of access to each data record in the data store. A write request directed to a data record in the data store is received. A command is generated identifying the data record and including the access information for the data record. The command is transmitted to the storage controller, wherein the storage controller uses the access information to determine one of the plurality of storage tiers on which to store the data record.