User-Defined Data Archiving Storage System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Storage systems, such as USB devices and external SSDs, face inefficiencies in determining whether data is for long-term archiving or temporary storage, leading to inaccurate routing and management of data, as existing algorithms often rely on speculation rather than user-defined intentions.
Innovation Solution
A storage system that receives a user-defined indicator to differentiate between archive and temporary data, routing it to appropriate memory cells, including multi-level cells for archiving, and using this indicator for backup and garbage collection decisions, thereby optimizing storage and endurance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If host or storage system learning algorithms are used to determine data intent, then automated data routing is achieved, but accuracy of determining whether data is for archiving or temporary storage deteriorates
Solution Approach 1:
The host system performs preliminary action by tagging data with intent indicators (archive or temporary storage) before transferring to the storage system. This eliminates the need for storage system algorithms to speculate about data intent, achieving both automation and high accuracy in data routing decisions.
2Productivity
If data is stored in multi-level cells for archiving, then storage efficiency is improved, but write speed deteriorates compared to single-level cells
Solution Approach 1:
The storage system applies local quality by routing different data types to different memory cell types based on their requirements. Archive data is stored in multi-level cells optimized for density and long-term retention, while temporary data is stored in single-level cells optimized for fast write speeds. This ensures each data type receives the appropriate storage characteristics for its specific needs.
3Ease of operation
If storage system learns data patterns autonomously, then user intervention is reduced, but reliability of data classification deteriorates due to speculation
Solution Approach 1:
The host system performs self-service by automatically tagging its own data with intent indicators before transfer. This eliminates the need for storage system learning algorithms while maintaining high classification reliability, as the host has direct knowledge of its own data purposes. The storage system simply follows the host's classification without needing to speculate.
Data Source
AI summary
A storage system and method for user-defined data archiving are provided. In one embodiment, the method comprises: receiving a write command from a host; determining whether the storage system received an indicator from the host indicating that data of the write command is archive data; in response to determining that the storage system received the indicator, storing the data in the multi-level memory cells; and in response to determining that the storage system did not receive the indicator, storing the data in the single-level memory cells. Other embodiments are provided.