Sub deadline acquisition optimization method based on reverse workflow scheduling

An optimization method and workflow technology, applied in grid computing and cloud computing fields, can solve problems such as measuring the urgency of tasks is not accurate enough, and does not take into account the impact of parallel tasks, etc.

Inactive Publication Date: 2017-07-07
BEIJING UNIV OF TECH
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] This method of obtaining the sub-deadline does not take into account the impact of the number of parallel tasks...

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
  • Sub deadline acquisition optimization method based on reverse workflow scheduling
  • Sub deadline acquisition optimization method based on reverse workflow scheduling
  • Sub deadline acquisition optimization method based on reverse workflow scheduling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The algorithm of the optimization method for obtaining the sub-period of deadline-constrained workflow scheduling is described as follows:

[0034] Input: a group of computing resources R, a DAG task of the running time matrix W on the resource group, data transfer matrix C between tasks, DAG deadline D

[0035] 1: The tasks are arranged in reverse order according to the layer where the tasks are located, and the same layer is arranged in the original order

[0036] 2: Calculate each task n according to formula (2) i Reverse weight rank r (n i )

[0037] 3: Sort all tasks by reverse weight to get the unmapped task list unMapList

[0038] 4: WHILE(unMapList≠Φ)DO

[0039] 5: Take out the task n with the largest reverse weight i

[0040] 6: According to the idea of ​​DAG reverse scheduling, all child tasks (reverse parent tasks) have been mapped to resources, get n i All subtasks

[0041] 7: Calculate n on each processor i The earliest possible end time FT, (FT = subtask execution end ...

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 sub deadline acquisition optimization method based on reverse workflow scheduling, which belongs to the field of grid or cloud computing. When a workflow with a deadline constraint is scheduled on a group of fixed resources, a task sub deadline is an important parameter, the sub deadline acquired in the present method sometimes can not ensure completion of remaining tasks, and the new method provided by the invention is used for acquiring a reasonable and usable sub deadline. In view of workflow scheduling, according to the provided RHEFT method, through a workflow reverse thinking, reverse weight solution and ranking are firstly carried out on tasks; one-by-one traverse resources of the tasks are extracted sequentially to acquire the earliest start time and the finish time of a reverse task; and the sub deadline and the latest start time are finally solved correspondingly. The process not only considers the lengths of remaining key paths but also considers influences of DAG parallelism, and thus, after resource mapping of each task under the sub deadline constraint, the rest tasks can still be ensured to have enough scheduling time. Through influences on the sub deadline by DAG parallelism changes, the sub deadline acquired by the method of the invention is verified to be more reasonable and effective.

Description

Technical field [0001] The invention belongs to the field of grid computing and cloud computing. Specifically, it relates to a method for obtaining and optimizing task sub-periods when a work flow with a deadline constraint is scheduled on a set of fixed resources. Background technique [0002] In the scheduling of DAG workflows with deadline constraints sharing a set of static resources, sub deadlines are usually used as one of the calculation parameters to determine the priority of each task. In addition, regarding the optimization of user scheduling costs, in order to obtain the most reasonable resource allocation, considering the degree to which each task allows cost optimization, sub-period is usually an important indicator [1,2] . Therefore, it is of great practical significance to reasonably obtain the sub-period of each task. [0003] With the famous HEFT scheduling algorithm [3] Assuming the same, suppose that multiple task nodes of a DAG need to be mapped to a group of h...

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
IPC IPC(8): G06Q10/06
CPCG06Q10/0631G06Q10/0633
Inventor 徐秀杰孙婷肖创柏田国忠
Owner BEIJING UNIV OF 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

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