More and more attention has been paid to microservices from traditional monolithic workflows. How to rent on-demand and spot instances for microservice tasks in cloud computing is crucial to save rental costs for customers. According to the out-of-bid failure risks of spot instances and application deadline constraints, it is challenging to adaptively determine the number of on-demand and spot instances, allocate microservice tasks to the rented instances, and reschedule interrupted tasks. In this paper, we consider the problem of scheduling microservice workflows with hybrid resource provisioning. An adaptive-learning based scheduling algorithmic framework is proposed to intelligently sequence, allocate and online adjust tasks as well as monitor spot instance. Strategies for each component are developed. Components and parameter values are statistically calibrated over a comprehensive set of random instances. The proposed algorithm is compared to modified classical algorithms for similar problems. Experimental results demonstrate the effectiveness of the proposal for the considered problem.

越来越多的关注来自传统单体工作流的微服务。如何为云计算中的微服务任务按需租用实例和现货实例，对于为客户节省租用成本至关重要。根据竞价实例的竞价失败风险和应用期限限制，自适应确定按需实例和竞价实例的数量，将微服务任务分配给租用的实例，以及重新安排中断的任务是具有挑战性的。在本文中，我们考虑使用混合资源供应来调度微服务工作流的问题。提出了一种基于自适应学习的调度算法框架，用于智能排序、分配和在线调整任务以及监控现场实例。为每个组件制定策略。组件和参数值在一组全面的随机实例上进行统计校准。针对类似问题，将所提出的算法与改进的经典算法进行了比较。实验结果证明了该提议对所考虑问题的有效性。