Storage Virtualization Offload to Hardware
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage virtualization techniques are inefficient due to high latency and throughput requirements, leading to increased CPU load and resource utilization, as they are designed for slower storage devices, and existing solutions fail to fully leverage the performance capabilities of high-speed storage devices like SSDs connected via PCIe buses.
Innovation Solution
Offloading storage virtualization aspects to storage hardware and modifying software to utilize hardware virtualization features, allowing the storage device to manage and expose virtual volumes that align with device storage blocks, thereby reducing indirection overhead and improving throughput and latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If storage virtualization is implemented in software, then flexibility and adaptability are improved, but CPU load and processing overhead increase
Solution Approach 1:
The patent extracts the storage virtualization functionality from the host CPU and relocates it to the storage device itself. The storage device implements a virtualization layer that can create and manage virtual volumes, perform data transformation, and handle I/O operations independently, thereby reducing the computational burden on the host system while maintaining virtualization flexibility
Solution Approach 2:
The patent introduces an intermediary virtualization layer residing in the storage device that mediates between the host system and the physical storage media. This intermediary handles the complex virtualization operations, allowing the host to interact with simplified virtual volumes without directly processing the computational overhead of virtualization management
2Speed
If storage access speed is increased to match processor speed, then throughput is improved, but memory requirements and power consumption increase
Solution Approach 1:
The patent enables the storage device to perform self-service operations through hardware-accelerated data transformation capabilities. The storage device can autonomously transform data formats, perform data reduction, and manage virtual volumes without requiring data to be loaded into host memory, thereby achieving high-speed access while minimizing memory requirements
Solution Approach 2:
The patent replaces the mechanical approach of using large amounts of host memory for data buffering and transformation with hardware-based data transformation capabilities embedded in the storage device. This substitution allows high-speed data processing to occur directly at the storage medium, eliminating the need for extensive memory resources
3Productivity
If storage device throughput is increased, then data exchange rate is improved, but system CPU load increases
Solution Approach 1:
The patent extracts the computationally intensive data transformation and virtualization operations from the host CPU and implements them in hardware within the storage device. This extraction allows high throughput data exchange to occur without proportionally increasing host CPU load, as the storage device handles the processing independently
Solution Approach 2:
The patent changes the operational parameters of the storage system by implementing hardware-accelerated data transformation capabilities. This allows the storage device to process data at high speeds using dedicated hardware circuits rather than general-purpose CPU instructions, thereby achieving high throughput with minimal CPU involvement
4Adaptability or versatility
If software indirection is used to manage storage, then flexibility is improved, but latency is increased
Solution Approach 1:
The patent implements preliminary action by pre-processing and transforming data within the storage device before it needs to be accessed by the host. The storage device performs data reduction, format transformation, and virtualization operations in advance, so that when data is requested, it is already prepared and ready for immediate access, thereby reducing latency while maintaining management flexibility
Data Source
AI summary
Embodiments relate to off-loading aspects of storage virtualization to storage hardware and modifying software to take advantage of hardware virtualization features. A co-design of hardware and software allows a filesystem to provide files such that indirection overhead normally needed to access the content of files can be bypassed while still managing the files as filesystem objects. A storage device manages and exposes a virtual volume which is used to store the content of a file. Virtual volumes can be initialized or populated so that virtual blocks therein align with device storage blocks. A virtual volume can be initialized and populated by parsing a virtual disk file to access virtual disk metadata, which is then used to determine and set features of the virtual volume.