Pseudo NDD for Geographical Cluster Communication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cluster solutions fail to scale across geographical boundaries due to limitations in multicast communication, particularly over long distances, where telecommunication companies do not support multicast forwarding, and the lack of reliability in user datagram protocol (UDP) for inter-site communication.
Innovation Solution
Implementing a pseudo Network Device Driver (NDD) interface based on Transmission Control Protocol (TCP) for remote nodes to facilitate reliable communication across geographical boundaries, allowing nodes to exchange heartbeats and data using multiple types of NDDs such as Ethernet, SAN, and DISK, while maintaining redundancy and ensuring packet assembly and processing consistency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multicast architecture is used for cluster communication, then communication efficiency is improved, but scalability across geographical boundaries deteriorates
Solution Approach 1:
The patent introduces a TCP-based communication layer as an intermediary between the multicast architecture and remote nodes. This intermediary translates and adapts multicast communications to work over TCP, enabling reliable long-distance communication while preserving the efficiency benefits of multicast for local nodes.
Solution Approach 2:
The patent segments the cluster communication into two parts: local communication using efficient multicast architecture and remote communication using TCP-based pseudo NDD. This segmentation allows each communication path to use the most appropriate protocol for its specific requirements.
2Speed
If UDP is used for multicast communication, then communication speed is improved, but reliability deteriorates
Solution Approach 1:
The TCP-based pseudo NDD acts as an intermediary that provides reliable delivery guarantees for remote nodes while maintaining UDP-based multicast for local high-speed communication. The TCP layer ensures acknowledgment and retransmission for critical communications across geographical boundaries.
3Reliability
If multiple NDD types are used for redundancy, then reliability is improved, but device complexity increases
Solution Approach 1:
The TCP-based pseudo NDD is designed to work alongside existing NDD types (Ethernet, SAN, DISK) providing universal compatibility. It implements the same NDD interface standards, allowing it to function as another redundant communication path without requiring separate complex handling logic.
Data Source
AI summary
An approach is presented that provides computer clustering support across geographical boundaries. Inter-node communications are managed in a cluster by having each node operate at the network device driver (NDD) level within the kernel. Multiple types of NDD are utilized (Ethernet, SAN, DISK etc.) to provide redundancy so that nodes can reliably exchange heartbeat. To align with this architecture, for remote nodes, a pseudo NDD is used over Transmission Control Protocol (TCP) based communication interface to work along side other NDDs. Thus, the same packet which is sprayed over the NDDs pertaining to local nodes can be sprayed over the TCPSOCK NDD interface for remote nodes. Nodes (local or remote) receive the same packet and reassemble and process it in the same manner.