Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Cluster monitor and management method and system

A monitoring management and clustering technology, applied in the field of cluster monitoring management methods and systems, can solve the problems of large data volume, high pressure on the monitoring end to collect data, slow transmission rate, etc., to achieve high availability, easy group management, and reduce pressure.

Inactive Publication Date: 2015-03-25
SHENZHEN UNIV
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a cluster monitoring and management method, aiming at solving the problem of using XML, JSON and other transmission mechanisms to transmit files between the client and the server, or using binary format to transmit data in the cluster monitoring system provided by the prior art. The large amount of data and the slow transmission rate have caused the problem of high pressure on the monitoring terminal to collect data

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
  • Cluster monitor and management method and system
  • Cluster monitor and management method and system
  • Cluster monitor and management method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Embodiment 1 of the present invention provides a cluster monitoring and management method, including the following steps:

[0052] S1: Monitor the host-side program initialization, and create the first key-value database.

[0053] Embodiment 1 of the present invention hopes to update the data of the computing node to the monitoring node in real time by synchronizing the key-value database between the monitoring host and the computing node. However, since existing key-value databases (such as Redis DB, etc.) provide master-slave mode: a master database instance allows multiple slave database instances to synchronize data, that is, multiple slave database instances are copies of the same master database instance , but a slave database instance can only have one master database instance, and cannot obtain the data of multiple master database instances from one database instance. In this way, the database of the monitoring node cannot obtain the data of all other computing no...

Embodiment 2

[0116] In the existing cluster monitoring system, in order to alleviate the problem of heavy data collection pressure on monitoring nodes, a cluster group management technology is proposed. This technology is to statically group the clusters before the system starts. After the grouping, it cannot be changed, so it cannot be dynamically grouped according to certain criteria. In this way, when it is necessary to know which computing nodes a certain service is running on, or within a minute Information such as the number of computing nodes with an average load in a certain interval, or the need for unified management of a group of nodes that meet other requirements, the existing cluster group management technology does not provide an effective implementation method. At the same time, the existing cluster group management technology is in the same group, only one computing node sends data to the monitoring node, and each computing node in the group broadcasts its own node informati...

Embodiment 3

[0124] In the process of monitoring and managing computing nodes in the existing cluster monitoring system, if a computing node fails, the administrator needs to restore the faults of these computing nodes. If a certain computing node needs to be managed separately, the existing cluster monitoring system using the Linux platform needs to use remote ssh or use tools such as VNC to manually log in to the computing node, and on the windows platform, even third-party tools need to be installed. In this way, if there are many computing nodes in the cluster, the IP address, user name and password of each computing node must be queried and entered, which is cumbersome.

[0125] In order to solve the aforementioned disadvantages existing in the existing cluster grouping management technology. Embodiment 2 of the present invention proposes a cluster monitoring and management method. Different from Embodiment 1, Embodiment 3 further includes the step of managing a single computing node...

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 belongs to the field of network cluster management, and provides a cluster monitor and management method and system. According to the method and system, key value type databases are created on a monitor node and all computing nodes respectively, and updating data of the computing nodes are synchronized to the monitor node through direct synchronization between the key value type databases. Due to the fact that the key value type databases are internal storage type non-relational databases, and have the high read-write speed and flexible data storage types, the time for achieving data synchronization through the databases is short, the competitive relation between the computing nodes is not large, the pressure of the monitor node can be effectively relieved, the network broadband utilization rate can be reduced, data zero redundancy, high availability and high expandability can be achieved, and in addition, a principle and method with grouping management easy are provided.

Description

technical field [0001] The invention belongs to the field of network cluster management, in particular to a cluster monitoring and management method and system. Background technique [0002] Clustering refers to a technology that gathers several servers in the network to perform the same service and is equivalent to one server externally. It has the characteristics of high expansion, high availability, and high cost performance. In order to enable the cluster to provide services more reliably, it is necessary to monitor the status information of the cluster in real time to facilitate administrators to observe and study trends. [0003] The traditional cluster monitoring and management technology is realized by using a proprietary cluster custom monitoring system. Since the proprietary cluster custom monitoring system is generally bound to the cluster produced by its manufacturer, it is not universal, and the price is high, it will be incompatible with other clusters, the fu...

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 Applications(China)
IPC IPC(8): H04L12/26H04L12/24
CPCY02D30/50
Inventor 蔡晔周华洋
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com