Container-Based Performance Isolation for Multi-Tenant SaaS Applications in Micro-Service Architecture

Abstract

Abstract With the development of cloud computing technology, SaaS has become a popular delivery mode in enterprise applications. Since multi-tenant can share a set of customized software applications deployed on the cloud, it significantly reduces the economic cost of providing software services of the cloud service provider. However, the sharing of cloud computing resources leads to service performance competition among tenants. Therefore, how to ensure that all tenants in the cloud have high-quality services becomes the most concerned issue for cloud service provider. To solve the above problem, our research aims at exploring an effective performance isolation mechanism based on container technology and micro-service architecture in multi-tenant scenario. This mechanism includes an SLA-oriented multi-tenant and multi-instance hybrid deployment scheme and a tenant performance isolation algorithm for microservice clusters, which can effectively reduce the performance competition among tenants, guarantee the SLA of tenants, and improve the cost-efficiency of cloud services. Experiments show that the request latency of the tenant working within their assigned quota can be reduced by 88.1% by applying the proposed performance isolation mechanism.