Multi-tenant container cloud platform virtual network resource adaptive scheduling method and system

Abstract

The invention belongs to the field of network technology, a method and system for self-adaptive schedule of virtual network resources of a multi-tenant contain cloud platform are disclosed. Based on the data center selection strategy of availability and user preference, a container pair is used to describe the communication path between containers, and each tenant is assigned to the nearest data center from the set of alternative data centers available to cloud service providers to determine the best subset of data centers for multi-tenant data placement. The server selection strategy based onapplication performance and the adaptive scheduling mechanism of network resources under the multi-tenant container cloud data center are implemented. The invention provides a cloud service environment of multi-tenant and multi-data center, in which various network resources in the container cloud platform are self-adaptively scheduled in a cooperative manner, the network resource management problem under the cloud computing environment is considered globally, and under the premise of guaranteeing the service level agreement, the benefit balance between the supply and demand sides of the cloud service is realized.

Description

technical field [0001] The invention belongs to the field of network technology, and in particular relates to a method and system for self-adaptive scheduling of virtual network resources on a multi-tenant container cloud platform. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: [0003] Cloud broker is a new trend of using multi-cloud and hybrid cloud to provide users with services in recent years, and it is recommended as a basic cloud service model, which rents cloud service provider instances for cloud network selection and reuse. Small tenant needs to minimize costs and maximize profits. [0004] Multi-tenant and multi-data center selection A common scenario has a total of 9 tenants and 10 data centers across 4 continents. Different tenants choose multiple data centers according to the availability of data centers and their own preferences. The existing technology only uses the mechanism of one data cen...

AI Technical Summary

Problems solved by technology

[0006] (1) The existing technology only uses a data center mechanism, which cannot meet the needs of comprehensive data analysis, and cannot guarantee faster local data analysis, and does not have lower costs

[0007] (2) The existing technology does not consider the price difference between reserved and real-time resources, nor can it reflect the dynamic characteristics of tenant needs in time

[0008] (3) Limited to choose among multiple cloud platforms owned by the same cloud service provider, it is difficult to expand among multiple cloud service providers

[0011] Complex traffic and high cost of vertical expansion: Due to the Incast problem caused by high-burst and high-dynamic many-to-one communication, the development of computing-intensive applications such as MapReduce and Hadoop, and the widespread use of virtualization technologies not only cause network traffic behavior complexity, but also brings a serious transmission load

At the same time, due to the high occupancy of "east-west traffic" in the data center and the convergence ratio of the tree structure, the cost of vertical expansion of the data center is extremely expensive and unsustainable

[0012] Low resource utilization and various forms: Traditional data exchange (such as VLAN) and communication identification (such as IP) technologies effectively avoid mutual interference when multiple applications are deployed simultaneously in the data center, but at the same time limit the reuse of network resources. Flexibility, resulting in generally low utilization of network resources

Images