Data-Relationship-Based FAST Cache System for Storage Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Fully Automated Storage Tiering (FAST) cache systems treat data chunks independently, leading to inefficiencies in data access and retrieval due to their inability to recognize relationships between frequently accessed data chunks.
Innovation Solution
An Information Handling System that identifies relationships between data chunks based on access differences and moves both chunks to faster storage devices when one chunk exceeds a cache threshold, utilizing a storage controller engine to determine and implement data-relationship-based FAST cache operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional FAST cache systems treat data chunks independently, then the system structure remains simple, but data access efficiency deteriorates due to inability to recognize relationships between frequently accessed data chunks
Solution Approach 1:
The patent merges related data chunks into a unified management unit. When one data chunk is identified for caching, the system automatically identifies and groups related data chunks together, treating them as a single entity for cache management decisions. This combining approach enables the system to recognize and exploit relationships between data chunks, improving data access efficiency without requiring complex individual analysis of each chunk.
Solution Approach 2:
The patent applies preliminary action by pre-identifying and grouping related data chunks before cache operations occur. The system establishes relationships between data chunks in advance and creates preliminary groups, so when a cache operation is triggered, the entire group is already prepared for efficient handling. This eliminates the need for complex real-time relationship analysis during cache operations.
2Productivity
If the system moves only single frequently accessed data chunks to faster storage, then the cache management remains simple, but cache hit rates deteriorate due to inability to anticipate related data access needs
Solution Approach 1:
The patent combines multiple related data chunks into a single cache management unit. When evaluating whether to cache data, the system identifies related chunks and groups them together, so that caching one chunk automatically includes its related chunks. This merging strategy significantly improves cache hit rates by ensuring that when one chunk is accessed, its related chunks are already available in the cache, eliminating the need for complex individual chunk evaluations.
3Loss of time
If conventional systems wait for individual data chunks to exceed cache thresholds before moving them, then the storage tiering remains simple, but warm-up times deteriorate due to sequential rather than grouped data migration
Solution Approach 1:
The patent merges the migration process for related data chunks into a single unified operation. Instead of waiting for each chunk to independently exceed the cache threshold and then migrating them separately, the system identifies related chunks and migrates them together as a group when any one of them triggers the cache condition. This combining approach dramatically reduces warm-up time by eliminating sequential migration delays.
Solution Approach 2:
The patent applies preliminary action by pre-grouping related data chunks before migration operations begin. The system establishes relationships and creates migration groups in advance, so when a cache threshold is exceeded, the entire group is already prepared for simultaneous migration. This eliminates the need for complex real-time decision-making during the migration process and enables faster, more efficient data movement.
Data Source
AI summary
A data-relationship-based FAST cache system includes a storage controller that is coupled to first storage device(s) and second storage device(s). The storage controller identifies a relationship between first data stored in the first storage device(s) and second data stored in the first storage device (s), with the relationship based on a difference between a first number of accesses of the first data associated with a first time period and a second number of accesses of the second data associated with the first time period being within an access difference threshold range. Subsequent to identifying the relationship, the storage controller determines that the first data has been accessed in the first storage device(s) a number of times within a second time period that exceeds a FAST cache threshold and, in response, moves both the first data and the second data to the second storage device(s) based on the relationship.