摘要：Containerized data centers can improve the computational density of IaaS layers. This intensive high-concurrency environment has high requirements for message scheduling and container processing. In the paper, an elastically scalable strategy for cloud containers based on predictive message scheduling is introduced, in order to reduce the delay of messages and improve the response time of services and the utilization of container resources. According to the busy degree of different containers, a management strategy of multiple containers at message-granularity level is developed, which gives the containers better elasticity. The simulation results show that the proposed strategy improves service processing efficiency and reduces response latency compared with existing solutions.
