Cloud workflow task clustering method supporting dependency and time balance

A clustering method and workflow technology, applied in the direction of program startup/switching, program control design, instruments, etc., can solve the problem of delaying the start time of the next level task, and achieve the effect of reducing the completion time and clustering scientifically and reasonably

Active Publication Date: 2018-05-15
ZHEJIANG TOPCHEER INFORMATION TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This timing imbalance will delay the start time of the next level task

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
  • Cloud workflow task clustering method supporting dependency and time balance
  • Cloud workflow task clustering method supporting dependency and time balance
  • Cloud workflow task clustering method supporting dependency and time balance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The cloud workflow scheduling method supporting dependency balance clustering provided by the present invention will be described in detail below.

[0032] For the convenience of description, the relevant symbols are defined as follows:

[0033] taskList: The set of tasks contained in a certain level in the flowchart.

[0034] clusterNum: the number of clusters.

[0035] W=(T,E): workflow, where T={t 1 ,t 2 ,...,t m} is a collection of vertices, representing the process

[0036] tasks, E is a set of directed edges, representing dependencies between tasks.

[0037] cor(t i ,t j ): Any two tasks t in this layer of tasksi and t j correlation between.

[0038] c(t i ): Indicates task t i A collection of subtasks.

[0039] |c(t i )|: Indicates task t i The number of subtasks.

[0040] C i : The i-th cluster of a certain level in the flowchart.

[0041] needNum(C i ): for each cluster C i The number of tasks to fill.

[0042] leftTaskTime: The average runn...

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 discloses a cloud workflow task clustering method supporting dependency and time balance. The present invention gives priority to the data dependency between tasks when clustering tasks at the same level in the flow chart, and considers the time balance between clusters. The present invention does not cluster tasks at the same level. Instead of simply grouping parent tasks with the same subtasks together, it comprehensively considers the common subtasks of these tasks and their unique subtasks, and proposes the concept and calculation formula of task relevance to characterize Dependencies between tasks. At the same time, the present invention also considers the running time of each task on the basis of prioritizing the dependency relationship between tasks, and at the same time ensures the dependency balance and time balance of clustering. Through experimental comparison with the traditional clustering method, it can be found that the clustering of tasks in the present invention can more effectively reduce the completion time of the workflow.

Description

technical field [0001] The invention belongs to workflow running time optimization technology in cloud workflow scheduling. When clustering tasks at the same level, based on the data dependencies between tasks and the time balance between clusters, a cloud workflow task clustering method that supports dependencies and time balance is proposed. Background technique [0002] Research in various scientific fields (such as physics, astronomy, and biomedicine) requires running large-scale applications to process data, and these large-scale applications are usually workflow applications. These workflow applications consist of many compute-intensive tasks with dependencies that can vary widely, with some tasks taking seconds to run and others taking hours. When executing these short-running tasks in a cloud computing environment, there will be significant scheduling overhead, and the extra time generated by the scheduling overhead far exceeds the running time of the task itself, t...

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): G06F9/48
CPCG06F9/4881G06F2209/482
Inventor 严伟杨朔杨威吕跃华陶砾施扬朋
Owner ZHEJIANG TOPCHEER INFORMATION TECH
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