Storage Device Memory Node Grouping for Access Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In storage devices configured by connecting memory nodes, direct application of access control from disk array devices leads to increased data transmission standby time and reduced throughput due to access concentration on individual memory nodes, affecting reading efficiency.
Innovation Solution
A storage device with multiple memory nodes connected in different directions, forming groups for data distribution and parity storage, utilizing a control unit to manage data writing and reading across these nodes, and implementing a cyclic writing method to distribute access and reduce congestion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If sequential writing is directly applied to storage device with memory nodes, then writing efficiency is improved, but access concentration on one memory node increases data transmission standby time and deteriorates throughput
Solution Approach 1:
The patent divides memory nodes into multiple groups and segments the sequential writing process across these groups. Instead of concentrating all writing operations on one memory node, the system alternates between different groups, allowing parallel processing and reducing standby time while maintaining writing efficiency.
Solution Approach 2:
The patent introduces a group dimension to the memory node structure, organizing nodes into multiple groups that can be accessed in an alternating manner. This dimensional organization allows the system to perform sequential writing across groups simultaneously, converting a single-node sequential operation into a multi-node parallel operation.
2Reliability
If access control from disk array devices is directly applied to storage device with memory nodes, then data storage is achieved, but access concentration reduces reading efficiency
Solution Approach 1:
The patent segments memory nodes into multiple groups to distribute read access across different groups. This segmentation prevents access concentration on single nodes while maintaining reliable data storage through the distributed group structure.
Solution Approach 2:
The patent implements periodic action by alternately accessing different memory node groups for reading operations. This periodic access pattern distributes the read load over time and across multiple nodes, preventing access concentration and improving overall reading efficiency while maintaining data integrity.
Data Source
AI summary
According to an embodiment, a storage device includes a plurality of memory nodes and a control unit. Each of the memory nodes includes a storage unit including a plurality of storage areas having a predetermined size. The memory nodes are connected to each other in two or more different directions. The memory nodes constitute two or more groups each including two or more memory nodes. The control unit is configured to sequentially allocate data writing destinations in the storage units to the storage areas respectively included in the different groups.