Sequestered Recovery Partition for Virtual Multipath Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computing cluster systems face challenges in scalability and cost due to synchronization requirements for state data across nodes, which increases communication overhead, equipment costs, and complexity, while also failing to effectively handle software failures.
Innovation Solution
The system implements asynchronous virtual multipath resource access by establishing sequestered computing domains, allowing a recovery partition to manage host state data independently, reducing the need for synchronized state updates and enabling on-demand access to state data using ordinary server hardware.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If synchronous update messages are sent between all nodes to propagate state data, then reliability is improved, but communication overhead and device complexity increase
Solution Approach 1:
The patent segments the computing cluster into independent computing nodes, each with local state data storage. Instead of requiring all nodes to synchronize simultaneously, each node independently stores and manages its own state data, eliminating the need for complex synchronous communication between all nodes while maintaining availability through local redundancy.
Solution Approach 2:
The patent extracts the state data propagation requirement from the node-by-node synchronization model. By allowing each node to independently store and access state data locally, the system eliminates the need for continuous synchronous communication overhead while maintaining reliability through local data persistence and independent node operation.
2Reliability
If synchronous state updates are implemented, then robustness is improved, but equipment costs and complexity increase
Solution Approach 1:
The patent implements copying of state data locally at each computing node rather than requiring expensive synchronous replication infrastructure. Each node maintains a local copy of relevant state data, enabling robust operation through data redundancy without the need for complex synchronous update mechanisms that would increase equipment costs.
Solution Approach 2:
By segmenting the system into independent nodes with local state storage, the patent reduces the need for expensive synchronous replication equipment. Each node independently manages its local copy of state data, maintaining robustness through simplicity rather than through complex, costly synchronization infrastructure.
3Reliability
If all nodes synchronize state data, then reliability is improved, but scalability fails to achieve
Solution Approach 1:
The patent segments state data management into local node-level storage rather than centralized synchronization. Each computing node independently stores and manages its own state data, allowing the system to scale by simply adding more independent nodes without increasing the complexity of state synchronization across the entire cluster.
Solution Approach 2:
Instead of requiring complete synchronization of all state data across all nodes, the patent implements partial local storage and access of state data at each node. This partial action approach allows nodes to operate independently with sufficient state data for their functionality, enabling scalability while maintaining necessary reliability through local data persistence.
Data Source
AI summary
Technologies for virtual multipath access include a computing device configured to sequester a recovery partition from a host partition while allowing the recovery partition to access one or more resources of the host partition such as host memory or data storage. A remote computing device determines whether the host partition is responsive. The recovery partition receives a request for host state data of the host partition from the remote computing device in response to a determination that the host partition is not responsive. The recovery partition retrieves the requested host state data using a host state index maintained by the host partition and transmits the requested host state data to the remote computing device. The host state index may identify the location of the requested host state data. The remote computing device may perform a recovery operation based on the received host state data. Other embodiments are described and claimed.