Multitenant Memory Die Grouping to Reduce Metadie Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High-capacity data storage devices with a large number of memory dies face power and resource limitations, preventing all memory dies from being grouped together as a single metadie, leading to inefficient metadie switching and performance degradation due to frequent tenant switching.
Innovation Solution
The data storage device logically groups frequently used tenants together into the same metadie, minimizing metadie switching by assigning them to the same metadie, thereby reducing overhead and enhancing performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If all memory dies are grouped together as a single metadie, then parallel access efficiency is improved, but power consumption exceeds limitations
Solution Approach 1:
The system segments the metadie into multiple sub-metadies, each containing a subset of memory dies that can operate within power limitations. This allows parallel access within each sub-metadie while avoiding excessive power consumption across all dies simultaneously.
Solution Approach 2:
The system dynamically selects and activates only the sub-metadie containing the required data, rather than keeping all memory dies active. This dynamic activation reduces power consumption while maintaining parallel access efficiency within the active sub-metadie.
2Use of energy by moving object
If memory dies are grouped into multiple metadies, then power consumption is reduced, but metadie switching overhead increases
Solution Approach 1:
The system performs preliminary actions by pre-positioning frequently accessed tenants into the same sub-metadie and maintaining a mapping structure that predicts future access patterns. This reduces the frequency of metadie switching and associated overhead.
Solution Approach 2:
The system uses feedback from access patterns to dynamically adjust tenant placement and sub-metadie selection. By monitoring which tenants are frequently accessed together, the system optimizes the grouping to minimize future switching overhead.
3Adaptability or versatility
If tenants are frequently switched between different metadies, then data allocation flexibility is improved, but performance degrades due to switching overhead
Solution Approach 1:
The system performs preliminary analysis of tenant access patterns and pre-positions frequently co-accessed tenants into the same sub-metadie. This preliminary optimization reduces the need for future switching while maintaining allocation flexibility for less frequently accessed data.
Solution Approach 2:
The system applies different strategies to different tenants based on their access patterns. Frequently accessed tenants are placed in optimized sub-metadies with minimal switching, while less frequently accessed tenants maintain flexible allocation. This local differentiation resolves the contradiction between flexibility and performance.
Data Source
AI summary
A data storage device and method are disclosed for providing an efficient multitenancy arrangement in high-capacity data storage devices. In one embodiment, a data storage device is provided comprising a memory and one or more processors. The one or more processors, individually or in combination, are configured to: create a plurality of metadies, wherein each metadie comprises a different subset of memory dies of the plurality of memory dies; determine which tenants of the data storage device are frequently used together; assign the tenants that are frequently used together to a same metadie; and access memory dies of the same metadie in parallel in response to an access request from one of the tenants that is assigned to the same metadie. Other embodiments are provided.