Decoupling parallel scheduling method for rely tasks in cloud computing

Abstract

The invention belongs to the field of cloud computing application, and relates to method for task rely relation description, decoupling, parallel scheduling and the like in cloud service. Rely task relations are provided, and a decoupling parallel scheduling method of rely tasks are constructed. The method comprises first decoupling the task rely relations with incoming degree being zero to construct a set of ready tasks and dynamically describing tasks capable of being scheduled parallelly at a moment; then scheduling the set of the ready tasks in distribution type and multi-target mode according to real time resource access so as to effectively improve schedule parallelism; and during the distribution of the tasks, further considering task execution and expenditure of communication (E / C) between the tasks to determine whether task copy is used to replace rely data transmission so as to reduce the expenditure of communication. The whole scheduling method can schedule a plurality of tasks in the set of the ready tasks in dynamic parallel mode, well considers performance indexes including real time performance, parallelism, expenditure of communication, loading balance performance and the like, and effectively improves integral performance of the system through the dynamic scheduling strategy.

Description

technical field [0001] The invention belongs to the field of cloud computing applications and relates to methods such as task dependency description, decoupling and parallel scheduling in cloud services. Background technique [0002] Distributed computing technology has become the mainstream of current information technology, such as mobile computing and cloud computing. Large-scale application services in the cloud environment are often decomposed into multiple tasks for scheduling and execution, and there are often certain constraints and dependencies among the decomposed tasks, that is, they have strong coupling. The existence of inter-task dependencies poses new challenges to task scheduling. At present, the research on task scheduling in a distributed environment often only considers the simple case of independent tasks without interdependence between tasks. Although it solves the problem of heterogeneity and availability of system resources to a certain extent, it is ...

AI Technical Summary

Problems solved by technology

In cloud computing, due to the heterogeneity and distribution of resources, there are not only huge differences in processing capabilities between resources, but also the network connection status between resources is also very different, so the factors to be considered in the dependent task scheduling problem in cloud environment are far from There are more than isomorphic systems, and their scheduling algorithms are far more complex than isomorphic systems

Although a considerable number of heterogeneous systems rely on task scheduling algorithms, most of them are improvements to homogeneous system algorithms. Usually, task queues are scheduled sequentially based on dependencies, and static scheduling with a single performance indicator as the goal is difficult. The real-time information of system resources is dynamically scheduled; the parallelism dependent on task scheduling is ignored, that is, the coupling problem cannot be effectively solved, system resources cannot be fully utilized, and system utilization is reduced; communication overhead costs and task execution overheads are not considered. relationship, making system resources partially idle [①Cathy H.Xia, George Michailidis, Nicholas Bambos.Dynamic on-line task scheduling on parallel processors.Performance Evaluation Vol.46, 2001, 219-233.②Tei-Wei Kuo, Wang-Ru Yang and Kwei-Jay Lin. A class of rate-based real-time scheduling algorithms. IEEE Transaction on computers, Vol 51, No.6, June 2002, 708-720. ③ He Kun, Zhao Yong, Chen Yang. In a distributed environment Analysis and Solution of Multi-task Scheduling Problems [J]. Systems Engineering Theory and Practice. 2007, 5: 119-125. ④ Shi Wei, Zheng Weimin. Balanced Dynamic Critical Path Scheduling Algorithm for Dependent Task Graphs [J]. Journal of Computers. 2001 . , Wu M Y. Performance-effective and low-complexity task scheduling for heterogeneous computing. IEEE Transactions on Parallel and Distributed Systems. 2002, 13(3): 260-274.]

Images