Memory Write Path Selection for Heterogeneous Storage Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern data storage systems face inefficiencies in data reliability and access schemes when dealing with heterogeneous types and sizes of storage class and non-storage class memory, leading to sub-optimal operations with different types of data and metadata.
Innovation Solution
The implementation of storage systems that select from multiple write paths, including direct writing to storage class memory bypassing non-storage class memory, and optimize paths based on data type and memory conditions to enhance data reliability and access efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single data reliability scheme and access scheme are used for all types of data and memory configurations, then the system is simple to operate, but the system performance becomes sub-optimal for heterogeneous memory types and data types
Solution Approach 1:
The patent implements dynamic selection of data reliability schemes and access schemes based on real-time conditions. The system automatically chooses between different write paths (e.g., direct write to storage class memory vs. write through non-storage class memory) depending on the type of data being written and the current memory configuration state, allowing optimal performance without manual intervention
Solution Approach 2:
The system changes operational parameters (data reliability scheme and access scheme) based on varying conditions such as data type and memory configuration. By adjusting these parameters dynamically, the system adapts to different scenarios to maintain optimal performance across heterogeneous memory types without requiring complex manual configuration
2Reliability
If data is always written through non-storage class memory to storage class memory, then data reliability is improved through buffering, but access efficiency decreases due to additional write operations
Solution Approach 1:
The patent applies different write paths based on the local characteristics of the data being written. For certain data types where immediate persistence is critical, the system uses direct write to storage class memory, bypassing non-storage class memory buffering. For other data types where buffering provides sufficient reliability, the system uses the traditional write-through path, optimizing for each case locally rather than applying a uniform approach
3Productivity
If multiple data reliability schemes and access schemes are implemented for different data types and memory configurations, then system performance is optimized, but the complexity of the system increases
Solution Approach 1:
The system performs self-service by automatically selecting appropriate data reliability schemes and access schemes based on the data type and memory configuration. The controller autonomously determines the optimal write path without requiring external intervention or complex manual configuration, managing the complexity internally while presenting a simplified interface to users
Data Source
AI summary
A storage system has a first memory, and a second memory that includes storage memory. The storage system has a processing device. The processing device is to select whether to write data to the first memory and write the data from the first memory to the second memory, or to write the data to the second memory bypassing the first memory. The processing device is to write portions of data for storage according to such selection.