期刊
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
卷 22, 期 -, 页码 S10219-S10227出版社
SPRINGER
DOI: 10.1007/s10586-017-1245-1
关键词
Cloud computing; Dominant resource fairness; Multi-resource fair allocation; Dynamic fair
资金
- Chinese Natural Science Foundation [11361048]
- Yunnan Natural Science Foundation
- Qujing Normal University Natural Science Foundation [ZDKC2016002]
The fast-developing of cloud computing causes the resource management to the hot and heat research. Some researcher have studied the resource allocation and proposed some resource allocation mechanisms in the cloud computing, such as max-min fairness that is used in the data center. In order to satisfy the demand of cloud computing, we need to design a efficient and fair resource allocation mechanism. Wang et al. (Proceedings of the USENIX Conference on File and Storage Technologies (FAST), 229-242, 2014) proposed a new resource allocation mechanism, called balancing fairness and efficiency with bottleneck-aware allocation (BAA). BAA aims to find the fair between the users and maximize the resource utilization. However, BAA only consider the two resource types and the resource pool may have multiple resource types such as CPU, memory and storage. In addition, BAA consider the static allocation and do not take into account the dynamic allocation of users join the system one by one. To over this drawback, we propose the bottleneck-aware allocation of multiple resources (MRBAA) and dynamic bottleneck-aware allocation (DBBA) fair allocation mechanism. MRBAA and DBBA have lots of good properties. In addition, we characterizes the properties of our proposed mechanisms. Furthermore, our proposed mechanisms achieves the multiple resources fair and dynamic allocation to become more adaptable the real-world scenarios. Compared with the existing popular mechanism dominant resource fairness (DRF) from the literature, the simulation results show that our proposed mechanisms can efficient use of heterogeneous resources, increase multiple resources utilization, and schedule more tasks to benefit users.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据