Multi-Tier Storage Write Acceleration via Coordinator Tier
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multi-tier storage systems, writing large amounts of data to low-performance storage tiers is inefficient due to their slower write speeds, which can lead to prolonged data restoration times during disaster recovery or IoT data analysis, as users often prioritize conserving high-performance tier space.
Innovation Solution
The method involves identifying a logical dataset and setting up a logical configuration map to allocate physical memory chunks between priority and coordinator tiers, writing data to the coordinator tier temporarily, and then copying it to the priority tier, allowing for concurrent copying and releasing resources efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is written directly to low-performance storage tiers, then storage capacity is optimized and cost is reduced, but write speed deteriorates
Solution Approach 1:
The patent applies preliminary action by first allocating physical chunks in high-performance storage tiers before writing data. This allows the write operation to proceed at high speed to the fast tier, while separate background processes handle the copying to low-performance tiers, thus resolving the contradiction between write speed and storage capacity utilization
Solution Approach 2:
The high-performance storage tier acts as an intermediary in this patent. Data is first written to the high-performance tier which serves as a temporary buffer, and then copied to the low-performance tier in the background. This intermediary approach allows the system to achieve both fast write speeds and efficient use of low-performance storage capacity
2Speed
If data is written to high-performance storage tiers, then write speed is improved, but storage cost increases and high-performance tier capacity is consumed
Solution Approach 1:
Physical chunks are preliminarily allocated in high-performance storage tiers to enable fast data writing. However, the system immediately initiates background copying to low-performance tiers, ensuring that high-performance capacity is temporarily used only when necessary and is subsequently released after the copy completes
Solution Approach 2:
The patent implements discarding and recovering by releasing the physical chunk allocations in high-performance storage tiers once the data has been successfully copied to low-performance tiers. This ensures that high-performance capacity is recovered and made available for other critical operations, while the data permanently resides in the low-performance tier
3Device complexity
If sequential write process is used for low-performance tiers, then resource usage is simple, but write time is prolonged
Solution Approach 1:
The system performs preliminary allocation of physical chunks in high-performance tiers before the actual data write operation. This setup enables parallel processing where data writing to the fast tier and subsequent copying to the slow tier can overlap in time, significantly reducing total write time while maintaining manageable complexity through structured process separation
Solution Approach 2:
The patent ensures continuity of useful action by initiating background copy operations immediately after data is written to the high-performance tier, without waiting for the write to fully complete. This overlapping of write and copy operations maximizes resource utilization and reduces total write time while keeping the process complexity controlled through automated background handling
Data Source
AI summary
Efficient writing to lower-performance storage tiers of a multi-tier storage system evaluates user intention when determining a write process that ultimately writes target data to a priority storage tier according to the user intention. Temporary high-performance storage tiers serve as coordinator tiers to achieve the efficient writing process for writing substantial or massive datasets to local storage.