基于Docker swarm集群的动态加权调度策略

doi:10.11772/j.issn.1001-9081.2017102789

计算机应用 ›› 2018, Vol. 38 ›› Issue (5): 1399-1403.DOI: 10.11772/j.issn.1001-9081.2017102789

基于Docker swarm集群的动态加权调度策略

黄凯¹, 孟庆永¹, 谢雨来^1,2, 冯丹^1,2, 秦磊华^1,2

1. 华中科技大学计算机科学与技术学院, 武汉 430074;
2. 武汉国家光电实验室(华中科技大学), 武汉 430074

收稿日期:2017-11-27 修回日期:2017-11-27 出版日期:2018-05-10 发布日期:2018-05-24
通讯作者: 谢雨来
作者简介:黄凯(1993-),男,湖北武汉人,硕士研究生,CCF会员,主要研究方向:Docker容器、虚拟化、集群调度;孟庆永(1995-),男,河南南阳人,主要研究方向:Docker容器、集群调度;谢雨来(1984-),男,湖北潜江人,副教授,博士,CCF会员,主要研究方向:溯源系统、网络存储、计算机系统结构;冯丹(1970-),女,湖北荆门人,教授,博士,CCF杰出会员,主要研究方向:计算机系统结构、海量存储系统、并行文件系统、磁盘阵列、固态盘;秦磊华(1968-),男,湖北鄂州人,教授,博士,CCF会员,主要研究方向:网络存储、网络仿真、溯源系统。
基金资助:
国家自然科学基金资助项目（61402189）；CCF-启明星辰鸿雁基金资助项目（2016-015）；武汉市应用基础研究计划项目（2017010201010104）。

Dynamic weighted scheduling strategy based on Docker swarm cluster

HUANG Kai¹, MENG Qingyong¹, XIE Yulai^1,2, FENG Dan^1,2, QIN Leihua^1,2

1. College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan Hebei 430074, China;
2. Wuhan National Laboratory for Optoelectronics(Huazhong University of Science and Technology), Wuhan Hebei 430074, China

Received:2017-11-27 Revised:2017-11-27 Online:2018-05-10 Published:2018-05-24
Contact: 谢雨来
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61402189), the CCF-Venustech Hongyan Research Fund (2016-015), the Wuhan Municipal Applied Basic Research Program (2017010201010104).

摘要/Abstract

摘要： 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。

关键词: Docker, swarm, 集群, 权值, 调度策略

Abstract: 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.

Key words: Docker, swarm, cluster, weight, scheduling strategy

中图分类号:

TP393.09

黄凯, 孟庆永, 谢雨来, 冯丹, 秦磊华. 基于Docker swarm集群的动态加权调度策略[J]. 计算机应用, 2018, 38(5): 1399-1403.

HUANG Kai, MENG Qingyong, XIE Yulai, FENG Dan, QIN Leihua. Dynamic weighted scheduling strategy based on Docker swarm cluster[J]. Journal of Computer Applications, 2018, 38(5): 1399-1403.

参考文献

[1] HARTER T, SALMON B, LIU R, et al. Slacker:fast distribution with lazy Docker containers[C]//Proceedings of the 14th Usenix Conference on File and Storage Technologies. Berkeley:USENIX, 2016:181-195.
[2] TIHFON G M, PARK S, KIM J, et al. An efficient multi-task PaaS cloud infrastructure based on docker and AWS ECS for application deployment[J]. Cluster Computing, 2016, 19(3):1585-1597.
[3] NGUYEN N, BEIN D. Distributed MPI cluster with docker swarm mode[C]//Proceedings of the 2017 IEEE 7th Annual Computing and Communication Workshop and Conference. Piscataway, NJ:IEEE, 2017:1-7.
[4] JULIAN S, SHUEY M, COOK S. Containers in research:initial experiences with lightweight infrastructure[C]//Proceedings of the XSEDE16 Conference on Diversity, Big Data, and Science at Scale. New York:ACM, 2016:25.
[5] 卢胜林, 倪明, 张翰博. 基于Docker Swarm集群的调度策略优化[J]. 信息技术, 2016, 40(7):147-151. (LU S L, NI M, ZHANG H B. The optimization of scheduling strategy based on the Docker Swarm duster[J]. Information Technology, 2016, 40(7):147-151.)
[6] DUSIA A, YANG Y, TAUFER M. Network quality of service in docker containers[C]//Proceedings of the 2015 IEEE International Conference on Cluster Computing. Piscataway, NJ:IEEE, 2015:527-528.
[7] McDANIEL S, HERBEIN S, TAUFER M. A two-tiered approach to I/O quality of service in Docker containers[C]//Proceedings of the 2015 IEEE International Conference on Cluster Computing. Piscataway, NJ:IEEE, 2015:490-491.
[8] MONSALVE J, LANDWEHR A, TAUFER M. Dynamic CPU resource allocation in containerized cloud environments[C]//Proceedings of the 2015 IEEE International Conference on Cluster Computing. Piscataway, NJ:IEEE, 2015:535-536.
[9] KANG D K, CHOI G B, KIM S H, et al. Workload-aware resource management for energy efficient heterogeneous Docker containers[C]//Proceedings of the 2016 IEEE Region 10 Conference. Piscataway, NJ:IEEE, 2016:2428-2431.
[10] CALHEIROS R N, MASOUMI E, RANJAN R, et al. Workload prediction using ARIMA model and its impact on cloud applications' QoS[J]. IEEE Transactions on Cloud Computing, 2015, 3(4):449-458.
[11] TURNBULL J. The Docker Book:Containerization is the New Virtualization[M].[S. l.]:James turnbull, 2014:9-10.
[12] NAIK N. Building a virtual system of systems using Docker swarm in multiple clouds[C]//Proceedings of the 2016 IEEE International Symposium on Systems Engineering. Piscataway, NJ:IEEE, 2016:1-3.

[1]	蔡彪, 李蕊岑, 吴媛媛. 相似性特征对链路预测的影响与增强[J]. 计算机应用, 2021, 41(9): 2569-2577.
[2]	葛丽娜, 胡雨谷, 张桂芬, 陈园园. 云计算环境基于客体属性匹配的逆向混合访问控制方案[J]. 计算机应用, 2021, 41(6): 1604-1610.
[3]	尹飞, 龙玲莉, 孔峥, 邵涵, 李鑫, 钱柱中. 面向动态负载的集群容器部署方法[J]. 计算机应用, 2021, 41(6): 1581-1588.
[4]	平凡, 汤小春, 潘彦宇, 李战怀. 不规则任务在图形处理器集群上的调度策略[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3295-3301.
[5]	王明芬. 软件定义无线局域网的切换接入机制[J]. 计算机应用, 2020, 40(9): 2706-2711.
[6]	孙忠凡, 周正华, 赵建伟. 基于空间元学习的放大任意倍的超分辨率重建方法[J]. 计算机应用, 2020, 40(12): 3471-3477.
[7]	周德运, 刘斌, 苏茜. 基于“新息误差”的粒子流滤波算法[J]. 计算机应用, 2020, 40(11): 3127-3132.
[8]	赵旭浩, 王轶群, 刘健, 徐春晖. 基于能量约束的自主水下航行器任务规划算法[J]. 计算机应用, 2019, 39(9): 2529-2534.
[9]	张栩源, 王艳. 用于灰度不均图像分割的自适应灰度拟合模型[J]. 计算机应用, 2019, 39(9): 2719-2725.
[10]	韩丽, 刘书宁, 于冰, 徐圣斯, 唐棣. 基于最优最小生成树的三维模型形状优化方法[J]. 计算机应用, 2019, 39(3): 858-863.
[11]	王志伟, 杨超. 基于流量控制的Docker容器网络带宽控制机制[J]. 计算机应用, 2019, 39(12): 3628-3632.
[12]	乔永卫, 张宇翔, 肖春景. 基于会话时序相似性的矩阵分解数据填充[J]. 计算机应用, 2018, 38(8): 2236-2242.
[13]	向敏, 陈诚. 基于改进Dijkstra算法的配用电通信网流量调度策略[J]. 计算机应用, 2018, 38(6): 1715-1720.
[14]	彭丽苹, 吕晓丹, 蒋朝惠, 彭成辉. 基于Docker的云资源弹性调度策略[J]. 计算机应用, 2018, 38(2): 557-562.
[15]	喻德旷, 杨谊, 钱俊. 云计算资源的动态随机扰动的粒子群优化策略[J]. 计算机应用, 2018, 38(12): 3490-3495.

基于Docker swarm集群的动态加权调度策略

Dynamic weighted scheduling strategy based on Docker swarm cluster

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics