Coflow Scheduling Method Based on Deadline to Minimize System Overhead

A deadline and system overhead technology, applied in the transmission system, digital transmission system, data exchange network, etc., to achieve the effect of efficient scheduling

Inactive Publication Date: 2021-12-17
TIANJIN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, existing technical research shows that for every 100ms increase in network delay, Amazon's sales revenue will decrease by 1%, and for every 400ms increase in delay, Google's search volume will decrease by 0.6%. Deadline traffic will bring additional system overhead

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
  • Coflow Scheduling Method Based on Deadline to Minimize System Overhead
  • Coflow Scheduling Method Based on Deadline to Minimize System Overhead
  • Coflow Scheduling Method Based on Deadline to Minimize System Overhead

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The invention aims to solve the flow scheduling problem with deadline requirement. There are two main goals: one is to make as many Coflows as possible before the deadline is reached in the case of limited data center network resources (bandwidth); the other is to design proprietary Coflows beyond the deadline The scheduling scheme minimizes the total system overhead caused by Coflows exceeding the time limit.

[0030]In order to overcome the deficiencies of the prior art, the present invention provides a Coflow scheduling method based on a deadline-based minimum system overhead, which not only makes more Coflows complete before the deadline, but also designs a dedicated Coflow for missing the deadline. The scheduling method minimizes the system overhead caused by Coflow missing the time limit. The scheduling method of the present invention consists of a Coflow scheduling method for meeting deadlines and a Coflow scheduling method for missing deadlines.

[0031] 1 Sat...

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 present invention relates to the field of computer network technology and the field of data center network. In order to propose a Coflow scheduling method that minimizes system overhead based on the deadline, it not only makes as many Coflows as possible before the deadline arrives, but also designs Coflows that miss the time limit. A dedicated scheduling method is provided to minimize the system overhead caused by Coflow missing the time limit. For this reason, the technical scheme that the present invention takes is, the Coflow scheduling method based on the minimum system overhead of deadline, comprises the Coflow scheduling step that meets deadline Deadline and the Coflow scheduling step that misses deadline, and Coflow is a group of communication stages of parallel computing A collection of parallel flows with dependencies. The invention is mainly applied to network communication occasions.

Description

technical field [0001] The invention relates to the technical field of computer network and the field of data center network. Specifically, in the data center network environment, the research and development of Coflow traffic scheduling technology based on deadline. Background technique [0002] The data center is the infrastructure for computing, storage and data transmission, which concentrates various hardware and software resources and key business systems. With the advent of the era of cloud computing, big data, Internet of Things and artificial intelligence, the data traffic in the data center is growing explosively. The traditional data processing technology is not enough to meet the processing requirements of massive data. Parallel computing technology emerges at the historic moment. The mainstream distributed computing platforms are MapReduce, Spark, Dryad and TensorfLow. In the process of big data processing, the proportion of traffic transmission time of parall...

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): H04L12/875H04L12/877H04L47/56H04L47/525
CPCH04L47/564H04L47/525
Inventor 李克秋王春晓周晓波徐仁海
Owner TIANJIN UNIV
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