Parallel Data Storage System Using Segmented Cell Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional parallel data storage systems are limited by the performance of individual data storage devices, leading to idle time for devices waiting for data transfers and insufficient data transfer rates, as they typically handle data one file or sector at a time.
Innovation Solution
A parallel data storage system that segments data sectors into equal-sized data cells, distributing them among multiple data storage devices using a switch and controller to manage data transfer, allowing simultaneous processing and reassembly of data cells into sectors for improved performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is transferred one file or sector at a time to individual data storage devices, then data storage capacity is improved, but data transfer rate is limited to the level of individual devices and devices sit idle waiting for data
Solution Approach 1:
The patent segments data into smaller units called data cells, which are then distributed across multiple data storage devices. This segmentation allows the system to overcome the limitation of transferring data one file or sector at a time by breaking it into smaller, parallelizable units that can be simultaneously processed by multiple devices, thereby increasing the overall data transfer rate while maintaining expanded storage capacity.
2Quantity of substance
If conventional parallel data storage systems are used, then storage capacity is increased through multiple devices, but performance remains limited by individual device capabilities due to sequential data transfer
Solution Approach 1:
By segmenting data into data cells and distributing them across multiple devices simultaneously, the system achieves parallel data transfer that scales with the number of devices, breaking the bottleneck of sequential transfer and enabling the array to achieve data transfer rates greater than any single device could provide.
Solution Approach 2:
The patent introduces a new dimension of parallelism by distributing data cells across multiple devices in parallel rather than sequentially. This dimensional change from sequential to parallel processing allows the system to achieve data transfer rates that scale with the number of devices in the array, overcoming the limitation of individual device performance.
3Reliability
If data storage devices wait for data transfers sequentially, then data integrity is maintained, but devices experience idle time reducing overall system efficiency
Solution Approach 1:
Segmenting data into data cells enables multiple devices to receive and process data simultaneously rather than waiting sequentially. Each device can independently process its assigned data cells while maintaining data integrity through proper segmentation and reassembly protocols, thereby eliminating idle time and improving overall system efficiency without sacrificing reliability.
Solution Approach 2:
The patent implements continuous data transfer by distributing data cells to multiple devices in parallel, ensuring that all devices remain actively engaged in data processing rather than experiencing idle waiting periods. This continuous utilization of all devices maximizes system throughput while maintaining data integrity through coordinated segmentation and reassembly.
Data Source
AI summary
A parallel data storage system for storing data received from, or retrieving data to, a host system using multiple data storage devices. The system includes an interface for communicating with the host system and a buffer configured to store data sectors received from the host system via the interface. A switch is used to selectively connect the interface and the data storage devices to the buffer to facilitate the transfer of data into and out of the buffer. The data sectors are transferred by segmenting each sector into multiple smaller data cells and distributing these data cells among the data storage devices using an arbitrated distribution method.