Task allocation method and apparatus for distributed system

A distributed system and task allocation technology, applied in the field of distributed systems, can solve the problems of resource fragmentation, task execution delay, time performance reduction, etc., to achieve the effect of improving resource utilization, system execution efficiency, and reducing resource fragmentation

Inactive Publication Date: 2018-07-10
HUAWEI TECH CO LTD
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

That is, after resource scheduling through the DRF algorithm, it may appear that the remaining resources of each node are not enough to meet the resource requirements of a certain task, but from the perspective of the distributed system as a whole, the sum of the remaining resources on each node is greater than the Resource requirements for tasks, resulting in resource fragmentation
The resource fragmentation problem will lead to a decrease in resource utilization, and because resource fragmentation cannot be applied, some tasks will be delayed and time performance will be reduced

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
  • Task allocation method and apparatus for distributed system
  • Task allocation method and apparatus for distributed system
  • Task allocation method and apparatus for distributed system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0043] combine Figure 1A , is a system schematic diagram of a possible implementation scenario of the embodiment of the present invention. Figure 1A Is a simplified illustration of a distributed system 100 comprising one or more interconnected computing devices. Three types of devices are shown: computing devices, management devices, and clients and servers. However, the number and type of devices are for illustration purposes only and are not critical to the invention.

[0044] Hosts such as hosts 1011, 1012 and 1013 are shown. A host may be a computing device that, among other functions, provides one or more services to other computing devices. By way of example, a host can be a server in an enterprise network, a database, or any...

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 relates to the field of a distributed system, in particular to a resource scheduling technology in the distributed system. According to a task allocation method, a share of allocated resources of a user is obtained; a to-be-allocated task is selected from a to-be-allocated task list; based on a highest threshold, the to-be-allocated task is allocated to a first computing node with residual resources capable of meeting the to-be-allocated task; and after the to-be-allocated task is allocated to the first computing node, at least one monitored resource exists in the first computingnode, and the residual quantity of the monitored resources is greater than or equal to the highest threshold corresponding to the monitored resources. Through the scheme provided by the task allocation method and apparatus, resource fragments in the distributed system can be reduced, so that the resource utilization rate of the distributed system is increased.

Description

technical field [0001] The present application relates to the field of distributed systems, in particular to resource scheduling technology in distributed systems. Background technique [0002] In various distributed computing frameworks (such as Hadoop, spark, etc.) A core problem with scheduling platforms. In resource scheduling, how to realize the fair allocation of resources and the improvement of resource utilization is a key issue, and it is also a hot topic in the field of distributed resource management and scheduling technology. [0003] At present, some mainstream distributed resource management and scheduling frameworks such as Mesos and Yarn have adopted the DRF (Dominant Resource Fairness) algorithm. The main idea of ​​this algorithm is that in a multi-dimensional resource environment, a user's resource allocation should be determined by the user's dominant share (dominant share). The dominant share is the maximum value of the total resources among all the var...

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): G06F9/50
CPCG06F9/5027G06F9/5083G06F2209/508G06F9/4881G06F9/5005G06F9/5061G06F9/5072
Inventor 曾艳林宗芳朱冠宇
Owner HUAWEI 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