Low-delay containerized task deployment method and device based on cloud edge collaboration

Abstract

The invention discloses a low-delay containerized task deployment method and device based on cloud edge collaboration, and the method comprises the steps: building a containerized task deployment model in a cloud edge collaboration scene, and representing the bandwidth from a mobile terminal to an edge node and a cloud data center and the deployment cost of a container mirror image layer, wherein the response time delay of the containerized task is subjected to formalized analysis which specifically comprises task transmission time delay, container mirror image deployment time delay and task execution time delay, and an optimization problem of response time delay minimization is established; and relaxing the optimization problem into a linear programming problem, and using a container deployment algorithm designed based on a random rounding technology to complete the deployment of a containerized task. According to the method, the containerized task is processed in parallel based on the cloud edge collaboration scene, so that the aim of optimizing the response time delay of the containerized task is fulfilled.

Description

technical field [0001] The invention relates to the field of distributed computing and task scheduling, in particular to a low-latency containerized task deployment method and device. Background technique [0002] With the advent of the Internet of Everything era, more and more terminal devices are connected to the network to process widely generated terminal data. However, terminal devices with limited computing power and energy consumption cannot independently handle resource-intensive data analysis tasks, which makes The task deployment architecture of cloud-edge collaboration has become the main way to solve the resource bottleneck of terminal equipment. A rapidly growing ecosystem of open source data processing frameworks, toolkits, and hardware has created a high degree of complexity in data analytics application stacks. In order to obtain a consistent and portable application operating environment, users usually use container virtualization technology to encapsulate ...

AI Technical Summary

Problems solved by technology

This resource-constrained scheduling strategy can ensure the resource requirements of tasks, but for containerized tasks with complex image layer dependencies, there are the following two problems: 1) The bandwidth of the wide area network is extremely limited, and the cost of image deployment is not considered. Significant pull latency when deploying images

2) Even in the high-speed interconnected cloud data center, due to the complex image layer dependencies of the container image, there is a serial decompression process when the cloud data center server node retrieves the local missing image layer from the image registry, which is greatly affected. Limited to single-core CPU frequency resulting in significant decompression delay

Images