Virtual Storage Scaling Using Direct-Mapped Flash and NV RAM
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional storage systems face inefficiencies in data management and reliability due to redundant write operations and lack of centralized control over storage processes, leading to increased latency and reduced reliability.
Innovation Solution
Implementing a direct-mapped flash storage system where the operating system directly addresses data blocks without translation by storage controllers, offloading device management responsibilities, and utilizing non-volatile RAM for quick data buffering and proactive data rebuilding across multiple storage nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional storage controllers translate and manage data blocks, then device management is centralized, but write operations become redundant and latency increases
Solution Approach 1:
The patent extracts the data block translation function from the storage controller and places it directly in the operating system. The OS maintains a direct mapping between logical block addresses and physical flash memory locations, eliminating the controller's translation layer and the associated redundant write operations.
Solution Approach 2:
The patent introduces non-volatile RAM as an intermediary buffer between the OS and flash memory. This allows the OS to perform writes directly to the NV RAM buffer, which then asynchronously transfers data to flash memory, decoupling the write operation from the actual storage commitment and reducing latency.
2Reliability
If storage systems use redundant write operations for data safety, then reliability improves, but write performance deteriorates
Solution Approach 1:
The patent implements proactive data rebuilding by monitoring flash memory cell program counts and identifying worn blocks before they fail. The system pre-replicates data from identified at-risk blocks to healthy blocks during low-I/O periods, ensuring data redundancy is maintained without waiting for actual failures or performing synchronous redundant writes.
Solution Approach 2:
The patent dynamically adjusts the rebuilding strategy based on real-time conditions. The OS monitors I/O workload, flash memory wear levels, and block health status, then adaptively schedules rebuilding operations during low-utilization periods and prioritizes critical data replication when wear thresholds are approached.
3Ease of operation
If storage controllers centrally manage all storage processes, then control is consolidated, but system complexity increases
Solution Approach 1:
The patent segments the storage management functions into distinct components: the OS handles logical-to-physical mapping and write buffering, the NV RAM manages asynchronous data transfer and wear leveling, and the flash memory handles persistent storage. This distribution eliminates the need for a complex centralized controller while maintaining coordinated operation.
Solution Approach 2:
The patent enables the flash memory system to self-manage many operations through hardware-supported features. The NV RAM controller autonomously handles data transfer from the OS buffer to flash memory, performs wear leveling across flash blocks, and manages garbage collection, reducing the control burden on both the OS and any remaining controller logic.
Data Source
AI summary
Dynamic scaling of a virtual storage system, including: detecting, within one or more virtual components of the virtual storage system, a change in performance; determining, in response to the detected change in performance, a scaling response based on the virtual storage system meeting one or more target performance metrics; and scaling, based on one or more available virtual components of the virtual storage system, up or down such that performance of the virtual storage system is in accordance within the one or more target performance metrics.