Task allocation method, apparatus and system considering host performance degradation of cloud platform

Abstract

The invention discloses a task allocation method considering host performance degradation of a cloud platform, and relates to the field of cloud computing system control. The method comprises the following steps of firstly, monitoring each host and acquiring performance information of the host; secondly, assessing current performance and load of the host, and assessing the performance degradation degree of each host; thirdly, generating a new task allocation scheme according to the performance degradation degree of the host; and finally, automatically allocating a newly arrived task to the host. In addition, the invention discloses a task allocation apparatus considering the host performance degradation of the cloud platform and based on the method, and a system comprising the apparatus. According to the method, the apparatus and the system, during new task allocation and scheduling, the performance degradation degree of each host and an expected accumulated task quantity are assessed, so that the new task is prevented from being allocated to the host with high performance degradation degree and high accumulated task quantity, and the task scheduling scheme is more reasonable.

Description

technical field [0001] The invention belongs to the field of cloud computing system control, and in particular relates to a task allocation method, device and system considering performance attenuation of a cloud platform host. Background technique [0002] Cloud computing is an Internet-based computing method in which shared hardware and software resources and information can be provided to computers and other devices on demand. Compared with traditional software and computing forms, cloud computing has significant advantages such as loose coupling, on-demand, cost control, resource virtualization, heterogeneous collaboration, etc., making it more suitable for today's e-commerce, flexible manufacturing, mobile Internet and other applications . [0003] The cloud platform refers to a distributed computing system composed of multiple heterogeneous hosts connected by a network to carry enterprise-level applications that provide online cloud services. In the cloud platform, c...

AI Technical Summary

Problems solved by technology

If the task scheduling and load balancing strategies ignore performance degradation, it is very easy for tasks accumulated on hosts with degraded performance to collapse in batches, causing heavy losses

Traditional task scheduling and allocation strategies mostly only calculate the allowable new task capacity based on the current load, resource utilization, and reliability status of each host and node, and determine task allocation and scheduling schemes based on these static data, ignoring the The real-time performance fluctuation and attenuation of each host in the cloud computing system does not actively avoid "allocating new tasks to hosts that are currently not low in performance but are in a state of performance degradation"

Images