Storage Virtualization via Media Extent Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage virtualization systems face limitations in flexibility, leading to resource wastage and inefficiencies, such as fixed RAID subsystem configurations, difficulty in data migration between disk arrays, and performance bottlenecks due to centralized IO access.
Innovation Solution
A storage virtualization method that maps physical storage devices into media extents, using a virtualization module to create virtual volumes with dynamic capacity allocation, allowing for flexible resource utilization, data migration, and distributed IO processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the RAID subsystem presents fixed physical volumes to the host, then the system structure is simple and stable, but the storage utilization flexibility is greatly restricted and resources are wasted
Solution Approach 1:
The patent segments the storage system into multiple layers: physical storage devices are divided into physical volumes, which are further divided into logical drives, and finally presented to hosts as logical volumes. This segmentation allows independent management and allocation of storage resources, enabling flexible reconfiguration without changing the entire system architecture.
Solution Approach 2:
The patent introduces a storage virtualization layer as an intermediary between the physical storage subsystem and the host. This virtualization layer includes components such as the logical volume manager and mapping tables that translate host access requests to physical storage locations, decoupling the host from the physical storage configuration and enabling flexible resource allocation.
2Adaptability or versatility
If the PV configuration is fixed after presentation to the host, then the system stability is maintained, but the storage space cannot be dynamically adjusted leading to resource wastage
Solution Approach 1:
The patent implements dynamic storage allocation where the virtualization layer allows storage capacities to be adjusted in real-time based on actual needs. Logical volumes can be expanded, contracted, or migrated between physical volumes without taking down the system, enabling storage resources to dynamically adapt to changing requirements and eliminate waste from fixed allocations.
Solution Approach 2:
The patent enables changing of storage parameters such as volume capacity, allocation ratios, and mapping relationships without hardware modification. The virtualization layer stores configuration parameters in software, allowing flexible adjustment of storage distribution policies and capacity allocations to match actual usage patterns and prevent resource wastage.
3Adaptability or versatility
If data migration between disk array subsystems is not supported, then the system complexity is reduced, but the utilization flexibility of storage resources is negatively affected
Solution Approach 1:
The patent creates a universal storage namespace that allows data to be accessed and migrated across multiple disk array subsystems through a common interface. The virtualization layer provides unified management of storage resources from different subsystems, enabling data migration between them without requiring subsystem-specific protocols or complex point-to-point migration mechanisms.
Solution Approach 2:
The storage virtualization layer acts as an intermediary that abstracts the physical location of data across different disk array subsystems. It maintains mapping information that allows data to be transparently migrated between subsystems while hosts continue to access data through the same logical volume identifiers, simplifying the migration process and reducing system complexity.
4Productivity
If all IO access commands are issued through a master storage node, then the system control is simplified, but the system performance is determined solely by the master node's processing power
Solution Approach 1:
The patent segments the IO processing function across multiple storage nodes rather than concentrating it all in a master node. Each storage node can independently process IO commands for data it holds, while the virtualization layer coordinates access to distributed data. This segmentation of processing responsibilities enables parallel IO operations and eliminates the single-point bottleneck.
Solution Approach 2:
The patent introduces a new dimension of parallelism in the storage architecture by allowing multiple storage nodes to process IO commands simultaneously. The virtualization layer adds a coordination dimension that manages distributed access without requiring all commands to sequentialize through a single master node, thereby increasing throughput while maintaining control.
Data Source
AI summary
A method for generating a virtual volume (VV) in a storage system architecture. The architecture comprises a host and one or more disk array subsystems. Each subsystem comprises a storage controller. One or more of the subsystems comprises a physical storage device (PSD) array. The method comprises the following steps: mapping the PSD array into a plurality of media extents (MEs), each of the MEs comprises a plurality of sections; providing a virtual pool (VP) to implement a section cross-referencing function, wherein a section index (SI) of each of the sections contained in the VP is defined by the VP to cross-reference VP sections to physical ME locations; providing a conversion method or procedure or function for mapping VP capacity into to a VV; and presenting the VV to the host. A storage subsystem and a storage system architecture performing the method are also provided.