Block Storage Management via Virtual Computing Service
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In distributed computing environments, scalability and availability of block-level storage systems are complex due to increased complexity with multiple devices and entities, differing interfaces, and the need for efficient data storage management across various locations.
Innovation Solution
A data storage manager system that maintains a set of rules mapping blocks of a logical data storage volume to storage nodes, allowing hosts to access these blocks directly, with the ability to allocate and update storage resources dynamically and independently from data path updates, ensuring fault tolerance and scalability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If traditional distributed storage management is used with multiple devices and entities, then storage capacity and distribution are improved, but system complexity and management difficulty increase
Solution Approach 1:
The patent introduces a data storage manager as an intermediary component that sits between the host computing device and the distributed storage nodes. This manager maintains rule sets that map logical volume blocks to physical storage locations, abstracting away the complexity of distributed storage management from the host while enabling efficient direct access to storage nodes.
Solution Approach 2:
The patent segments the storage system into distinct functional components: the host computing device, the data storage manager, and multiple storage nodes. The rule set is divided into multiple rules, each mapping specific block ranges to storage locations. This segmentation allows independent management and updating of storage mappings without affecting the entire system.
2Speed
If direct access to storage nodes is implemented, then access latency is reduced, but system reliability and fault tolerance may be impacted
Solution Approach 1:
The patent implements fault tolerance by maintaining multiple rules in the rule set that map to different storage locations. If one storage node fails, the host can use alternative rules to access data from redundant or backup storage locations. The system also includes mechanisms to detect and handle storage node failures while maintaining data accessibility.
3Productivity
If storage resources are allocated dynamically, then resource utilization efficiency is improved, but management complexity increases
Solution Approach 1:
The patent enables dynamic storage resource allocation by allowing the data storage manager to modify the rule set at runtime. Storage blocks can be reallocated between different logical volumes based on demand, and the rule set is updated accordingly. This dynamic management allows efficient utilization of storage resources while the storage manager handles the complexity of coordination and consistency.
4Adaptability or versatility
If multiple storage devices with different interfaces are used, then storage versatility is improved, but integration and management difficulty increase
Solution Approach 1:
The patent creates a universal interface through the data storage manager that can handle multiple types of storage devices with different interfaces. The manager translates between various storage interfaces and protocols, presenting a unified view to the host computing device. This allows the system to incorporate diverse storage technologies (SAS, SATA, FC, NVLink, etc.) while maintaining consistent management and access methods.
Data Source
AI summary
A request to create a volume to store data is received. A block within the storage node is selected, dependent at least in part on metadata indicating regions of available storage space in a storage node, to associate with a volume. Information is generated that includes an address to the block. A second computer system is determined to lacks the address to the block. The second computer system is enabled, by providing at least a portion of the information to the second computer system, to perform an operation to the block.