Cluster assignment dispatching method and device

A job scheduling and clustering technology, applied in the computer field, can solve the problems that affect the operating efficiency of the system, cannot monitor the resources of the job scheduling system, and cannot perform reasonable and effective scheduling of cluster jobs, and achieve the effect of high fault tolerance and high availability.

Active Publication Date: 2014-10-29
INSPUR BEIJING ELECTRONICS INFORMATION IND
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since heartbeat can only monitor the management node, it cannot monitor the resources of the job scheduling system. Once the monitored resources fail, such as the failure of the Maui service, resource switching cannot be effectively performed, which will also cause the entire cluster job to fail. Reasonable and effective scheduling cannot be carried out, which seriously affects the operating efficiency of the system

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 assignment dispatching method and device
  • Cluster assignment dispatching method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in detail below in conjunction with specific embodiments shown in the accompanying drawings.

[0023] The cluster job scheduling system of the present invention includes management nodes, virtual machines and shared storage, wherein,

[0024] The management node is a physical node, and the cluster job scheduling system includes at least two management nodes;

[0025] Deploy the virtual machine on the management node through Kernel-based Virtual Machine (KVM, Kernel-based Virtual Machine). KVM is an open source system virtualization module and a virtual machine tool that comes with the kernel of the Linux operating system. Create and manage virtual machines through KVM, multiple virtual machines can be deployed on one management node, and each virtual machine can deploy an independent job scheduling operating system;

[0026] Deploy shared storage on the management node. The shared storage can be Network File System (NFS, Network ...

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 a cluster assignment dispatching method and device. The method comprises the steps that assignments are grouped, the grouped assignments are dispatched to at least two virtual machines on management nodes, and the virtual machines use shared resources, configured in advance, in shared storages for assignment processing; if the virtual machines for assignment processing break down, the assignments are switched to a backup virtual machine; if the management nodes are maintained or break down, the virtual machines on the management nodes are transferred to other management nodes. As the assignments are grouped, the grouped assignments are dispatched to the different virtual machines, and the different virtual machines use the shared resources in the shared storages for assignment processing, high fault tolerance and high availability of an assignment dispatching system are achieved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a cluster job scheduling method and device. Background technique [0002] At present, network-based computer technology has promoted the development and wide application of cluster systems. Use a high-speed network to connect high-performance workstations or personal computers into clusters in a certain structure to achieve parallel computing, and you can get the performance of mainframes and parallel computers with only a small cost. With the continuous expansion of the application scale of high-performance computer clusters, the problem of cluster management becomes more and more prominent. [0003] The job scheduling system is generally deployed on the management node of the high-performance cluster system. It is mainly responsible for receiving job requests submitted by users, and selecting appropriate resources to complete user job requests according to specific s...

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): G06F9/48G06F9/455G06F11/16
Inventor 马四腾
Owner INSPUR BEIJING ELECTRONICS INFORMATION IND
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