Virtual Network Address Migration in Multi-Computing Clusters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current multi-computer cluster architectures face reliability issues due to hardware, OS, and application faults, leading to incomplete continuity of services during network connection migration between nodes.
Innovation Solution
A method utilizing a virtual network address for connection migration between primary and secondary nodes, capturing messages at the IP table level, and implementing a non-intrusive dynamic kernel module for TCP/IP protocol compatibility, allowing seamless service switching and replication without modifying the transport protocol or OS.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cold re-start mechanism is implemented for fault tolerance, then reliability is improved, but service continuity is compromised
Solution Approach 1:
The patent implements preliminary action by maintaining hot clones of the application on secondary nodes that are continuously updated with the current state of the primary node before a fault occurs. This ensures that when a fault happens, the secondary node can immediately take over without cold re-start, thus improving both reliability and service continuity.
Solution Approach 2:
The patent creates copies of the application state on secondary nodes through hot cloning mechanisms. These clones are kept up-to-date by capturing and replaying network messages, allowing the secondary node to assume the primary node's role seamlessly upon fault detection, thereby resolving the contradiction between reliability and service continuity.
2Duration of action of moving object
If network connection migration is implemented during service switching, then service continuity is improved, but connection migration complexity increases
Solution Approach 1:
The patent introduces a message capture and replay mechanism as an intermediary between the primary and secondary nodes. This intermediary system captures network messages at the IP table level and replays them on the secondary node, simplifying the connection migration process while maintaining service continuity without requiring complex protocol modifications.
Solution Approach 2:
The patent extracts the connection migration complexity from the transport protocol TCP by implementing the migration mechanism at the IP table level. This extraction allows connection migration to be handled independently of the transport layer, reducing the complexity of modifying TCP while still achieving seamless service switching.
3Adaptability or versatility
If TCP protocol is modified for connection migration, then migration capability is improved, but system stability deteriorates
Solution Approach 1:
The patent segments the connection migration function from the TCP protocol by implementing it at the IP table level. This segmentation allows migration capability to be added without modifying the stable TCP protocol, thus improving adaptability while maintaining system stability. The IP table acts as an independent layer that handles migration logic separately from the transport protocol.
4Adaptability or versatility
If operating system is modified for connection migration, then migration functionality is improved, but ease of operation deteriorates
Solution Approach 1:
The patent extracts the migration functionality from the operating system core by implementing it as an independent dynamic kernel module that loads without modifying the OS. This extraction maintains ease of operation while adding migration functionality, as the module can be loaded and unloaded without affecting the core OS structure or requiring complex OS modifications.
5Reliability
If intermediate server is used for connection migration, then migration reliability is improved, but device complexity increases
Solution Approach 1:
The patent implements self-service by enabling direct peer-to-peer communication between the primary and secondary nodes for connection migration. The secondary node directly captures and replays messages to assume the primary node's role without requiring an intermediate server, thus improving reliability by eliminating the intermediary while reducing device complexity.
Data Source
AI summary
A method for carrying out a connection migration in a multicomputing architecture (cluster), from a first node which is called a primary node or operation node, including a first computer of the cluster on which an initial software application is run, towards at lest one secondary node including another computer of the cluster. The method implements a virtual network address which is carried by the first computer and transferred to the other computer, the virtual network address being embodied in the form of a dialogue link between the cluster and client computers connected thereto and associated with the software application. The associated connections can, for example be associated with a software application which is replicated in another computer in such a way that the initial application service is switched to the replica thereof.