基于Docker swarm集群的动态加权调度策略

Dynamic weighted scheduling strategy based on Docker swarm cluster

针对目前的Docker swarm内置的调度策略无法很好地实现Docker集群的负载均衡并且对集群资源的使用率不高的问题,提出了一种动态加权调度算法。所提算法对资源设置权重系数,引入参数bias针对不同服务对资源权重进行动态调整,根据各个节点的实际资源利用情况,对节点资源按照权重进行加权计算,用权值反映节点负载,并将此作为调度依据。在和Docker原始调度策略以及无参数调整的加权调度策略的对比实验中,该算法使得集群中各个节点上的各项资源利用率更加均衡;同时,在集群负载比较高的情况下,该算法实现了更快的服务运行速度。

As the built-in scheduling strategy of Docker swarm cannot implement load balance of cluster very well and the utilization rate of cluster resource is not very high, a dynamic weighted scheduling algorithm was proposed. The weight coefficient was set on the resource, and the parameter bias was introduced to dynamically adjust the resource weight for different services. According to the actual resource utilization of each node, the node weight was calculated to reflect node load, and was used for scheduling. Compared with the original Docker scheduling strategy and the weighted scheduling strategy without parameter adjustment, the proposed algorithm makes all the resource utilization of each node in the cluster more balanced. At the same time, the proposed algorithm can achieve faster service running speed under the condition of high cluster load.