Cluster inner container scheduling method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention provides a cluster inner container scheduling method and device, a computer readable storage medium and electronic equipment, and relates to the technical field of computers, and the method comprises the steps: obtaining a candidate host unit composed of candidate host machines; obtaining the relevance between the container to be migrated and the existing containerresource time series data of the candidate host machine; and selecting the candidate host machine with the minimum relevance as a target migration host machine of the to-be-migrated container. According to the technical scheme provided by the embodiment of the invention, the candidate host machine with the minimum relevance with the to-be-migrated container is selected as the target migration hostmachine, so that the service performance can be met and the host machine resources can be efficiently utilized at the same time.

Description

technical field [0001] The present invention relates to the field of computer technologies, and in particular, to a container scheduling method, apparatus, computer-readable storage medium and electronic device in a cluster. Background technique [0002] Internet online services often place high requirements on the performance of applications. For example, in e-commerce services, it is usually required to respond to user requests in seconds or even milliseconds. In addition, in special application scenarios such as spikes, group purchases, or promotions in e-commerce services, the number of normal user requests will suddenly increase sharply, and the resource requirements for back-end services will also change frequently. [0003] In order to cope with such complex and changeable business scenarios, when deploying enterprise-level data centers, various data center or cluster-level container placement strategies can be used. [0004] Among them, the container placement strat...

AI Technical Summary

Problems solved by technology

[0004] Among them, the container placement strategy considering a single resource is based on experience and estimation or the analysis of historical resource demand data of virtual machines or containers, and the container is placed on the host that meets the resource requirements. The disadvantage is that it will lead to resource usage on the host. unbalanced

The container placement strategy that considers multiple resources introduces methods such as multi-resource product and vector point set to place containers on the host. The disadvantage is that it does not consider the performance interference between containers on the host.

Host machine resource optimization based on advanced algorithms uses genetic algorithm, ant colony algorithm, or particle swarm algorithm to find a better host machine placement plan in the cluster among the alternative placement plans. The disadvantage is that resource requirements and performance guarantees are not considered comprehensively.

Images