Split brain preventing method for highly available cluster system

A technology of cluster system and prevention method, applied in transmission system, digital transmission system, error prevention, etc., can solve problems such as data corruption, misidentification of standby node in normal operation of master node, split brain, etc.

Active Publication Date: 2012-10-10
GUANGDONG ZHONGXING NEWSTART TECH CO LTD
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the connection between two nodes fails, the master node may run normally but be mistaken for a failure by the standby node, which will cause the two nodes to read and write the storage device at the same time, and the data will be destroyed. This situation is called split brain

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Split brain preventing method for highly available cluster system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention is mainly aimed at a dual-machine high-availability cluster system, which can be easily implemented on various platforms. After multiple implementations and tests by the inventor, the present invention can effectively prevent the occurrence of split-brain.

[0018] figure 1 Shown is a representative dual-machine high-availability cluster system topology diagram, the system has two nodes, server nodes A and B. Each server has four network cards eth0-eth3. eth0 and eth1 are set to bond and adopt hot standby mode, where eth0 is used as Active and connected to switch A, and eth1 is used as Backup and connected to switch B. By setting external service management, a public network card IP (public IP) address is generated as a working link. eth2 and eth3 are connected to the network card corresponding to another node through a crossover network cable, and the two nodes are connected to their first serial ports through a serial cable. These connections w...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides two methods for preventing a brain from splitting of a cluster system. The first method is as follows: whether the brain is split is judged by detecting whether last two heartbeat cables are cut at the same time. The second method is as follows: whether the service is started at a node of the other side is judged by a ping floating IP method, thereby preventing the brain from splitting. The two methods can effectively avoid the brain splitting problem of the dual-computer high-useable cluster system, ensure that data is not damaged, and have the advantage that the support of any other hardware is not needed.

Description

technical field [0001] The invention belongs to the technical field of computer clusters, and in particular relates to two methods for preventing the split-brain problem of cluster systems, so as to ensure the high reliability of the system. Background technique [0002] With the rapid development of communication network technology, key areas such as telecommunications, finance, and e-government have higher and higher requirements for server availability. Stopping service due to server failure will cause huge losses. Using a high-availability cluster system can greatly improve The availability of the system minimizes the impact of failures caused by software, hardware, and human beings on the business. [0003] The dual-machine high-availability cluster system consists of two servers called nodes connected through the network (or other connection methods such as serial ports). Among these two servers A and B, A is the working machine, and B is the backup machine, and they ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): H04L12/24H04L1/22H04L12/26H04L1/00H04B1/74
Inventor 蔡强梁晓君罗锦华邹晟周晶颜定成邵济平
Owner GUANGDONG ZHONGXING NEWSTART TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap