Cache Transfer Time Mitigation via Elliptical to Spiral Track Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cache service time in data storage systems is prolonged due to factors such as storage media type, cache location, and data transfer speeds, particularly in systems that perform large amounts of read and write operations, leading to inefficiencies in data transfer between main store and cache regions.
Innovation Solution
Implementing a method that involves reading data from elliptical tracks in the main store and writing it to spiral tracks within the cache storage region, optimizing transducer head selection based on linear storage density capability, and reformatting data to increase cache transfer speed by eliminating seek-and-settle time and enhancing data track width and density.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If data is transferred from main store to cache using conventional track formats, then data transfer occurs, but cache transfer time is prolonged due to seek-and-settle operations
Solution Approach 1:
The patent segments the cache storage area into multiple cache zones, each accessible by specific transducer heads. This segmentation allows parallel data transfer operations across multiple zones simultaneously, eliminating the need for sequential seek-and-settle operations between tracks and significantly reducing cache transfer time while maintaining high data transfer rates.
Solution Approach 2:
The patent transitions from conventional two-dimensional track-based data organization to a three-dimensional cache zone structure with multiple stacks and zones. This dimensional change enables simultaneous access to multiple data regions by different transducer heads, eliminating seek operations and reducing cache transfer time while increasing overall data transfer throughput.
2Speed
If transducer heads are selected based on highest linear storage density capability, then data transfer speed increases, but device complexity increases due to head selection and configuration
Solution Approach 1:
The patent performs preliminary classification of transducer heads during manufacturing or initialization, assigning each head to specific cache zones based on its linear storage density capability. This preliminary action creates a fixed head-to-zone mapping that maximizes data transfer speed while simplifying operational complexity, as the system no longer requires dynamic head selection during data transfer operations.
Solution Approach 2:
The patent changes the operational parameter from dynamic head selection to static head-to-zone assignment based on predetermined performance characteristics. This parameter change simplifies the system by eliminating the need for real-time evaluation of transducer head capabilities, reducing device complexity while maintaining optimal data transfer speeds through pre-optimized head assignments.
3Quantity of substance
If cache zone capacity is increased to store more data, then cache service capability improves, but seek-and-settle time increases across larger cache regions
Solution Approach 1:
The patent divides the large cache storage capacity into multiple smaller cache zones stacked vertically and arranged horizontally. This segmentation allows the cache to store large quantities of data while maintaining small zone dimensions that can be accessed without extensive seek-and-settle operations. Multiple transducer heads can simultaneously access different zones, effectively increasing throughput while minimizing individual access times.
Solution Approach 2:
The patent enables continuous data transfer operations by having multiple transducer heads write to different cache zones simultaneously without interruption. This continuity eliminates the need for seek-and-settle operations between zones, as each head operates continuously on its assigned zone, thereby maintaining high data transfer rates while accommodating large cache storage capacities.
Data Source
AI summary
In accordance with one implementation, a method for mitigating cache transfer time entails reading data into memory from at least two consecutive elliptical data tracks in a main store region of data storage and writing the data read from the at least two consecutive elliptical data tracks to a spiral data track within a cache storage region.