Storage Controller Data Redistribution for SSD Write Performance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The degradation of write performance in storage systems due to increased data amounts during data copy processing between storage devices with nonvolatile memories, such as SSDs, leads to reduced performance for hosts and users.
Innovation Solution
A system that manages data distribution across multiple storage devices by inhibiting writes to a designated device while allowing reads, and redistributes update data to other devices, utilizing an address translation table to maintain data integrity and optimize free space usage, thereby maintaining performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data copy processing is executed between storage devices, then data backup is achieved, but write performance is degraded due to increased total data amount
Solution Approach 1:
The patent segments the storage system into multiple storage devices (first storage device, second storage device, third storage device) and divides data management into separate logical address spaces. By segmenting data distribution across multiple devices and using independent logical address spaces for each device, the system can perform data copy processing without concentrating all write operations on a single device, thereby maintaining write performance while achieving data backup.
Solution Approach 2:
The patent introduces a storage controller as an intermediary that manages data distribution across multiple storage devices. The storage controller uses an address translation table to map logical addresses to physical storage locations across different devices. This intermediary coordinates data copy operations, allowing backup processing to occur without directly impacting host write performance, as the controller can manage these operations transparently.
2Quantity of substance
If data is redistributed to multiple storage devices, then free space is optimized, but system complexity increases
Solution Approach 1:
The patent creates a universal address translation table that can map logical addresses to physical locations across multiple storage devices with different capacities and characteristics. This multi-functional address translation mechanism handles data distribution, free space management, and device heterogeneity through a single unified approach, optimizing free space utilization without requiring separate complex management systems for each device.
Solution Approach 2:
The patent uses copying of data between storage devices as a fundamental mechanism for both backup and free space optimization. By copying data from one device to another and updating the address translation table, the system can redistribute data to optimize free space across devices. This copying approach is simpler than complex data migration or reorganization schemes, as it leverages existing write operations to achieve redistribution.
Data Source
AI summary
According to one embodiment, when it is determined that a first storage device of a plurality of storage devices is to be removed and an additional storage device is connected to a storage controller, the storage controller writes update data portions corresponding to data portions already written to the first storage device to any storage device selected from remaining one or more storage devices of the plurality of storage devices except for the first storage device and the additional storage device. Further, the storage controller writes update data portions corresponding to data portions already written to the remaining one or more storage devices to any storage device selected from the remaining one or more storage devices and the additional storage device.


