摘要
With cloud computing technology becoming more mature, it is essential to combine the big data processing tool Hadoop with the Infrastructure as a Service(Iaa S) cloud platform. In this study, we first propose a new Dynamic Hadoop Cluster on Iaa S(DHCI) architecture, which includes four key modules: monitoring,scheduling, Virtual Machine(VM) management, and VM migration modules. The load of both physical hosts and VMs is collected by the monitoring module and can be used to design resource scheduling and data locality solutions. Second, we present a simple load feedback-based resource scheduling scheme. The resource allocation can be avoided on overburdened physical hosts or the strong scalability of virtual cluster can be achieved by fluctuating the number of VMs. To improve the flexibility, we adopt the separated deployment of the computation and storage VMs in the DHCI architecture, which negatively impacts the data locality. Third, we reuse the method of VM migration and propose a dynamic migration-based data locality scheme using parallel computing entropy. We migrate the computation nodes to different host(s) or rack(s) where the corresponding storage nodes are deployed to satisfy the requirement of data locality. We evaluate our solutions in a realistic scenario based on Open Stack.Substantial experimental results demonstrate the effectiveness of our solutions that contribute to balance the workload and performance improvement, even under heavy-loaded cloud system conditions.
With cloud computing technology becoming more mature, it is essential to combine the big data processing tool Hadoop with the Infrastructure as a Service(Iaa S) cloud platform. In this study, we first propose a new Dynamic Hadoop Cluster on Iaa S(DHCI) architecture, which includes four key modules: monitoring,scheduling, Virtual Machine(VM) management, and VM migration modules. The load of both physical hosts and VMs is collected by the monitoring module and can be used to design resource scheduling and data locality solutions. Second, we present a simple load feedback-based resource scheduling scheme. The resource allocation can be avoided on overburdened physical hosts or the strong scalability of virtual cluster can be achieved by fluctuating the number of VMs. To improve the flexibility, we adopt the separated deployment of the computation and storage VMs in the DHCI architecture, which negatively impacts the data locality. Third, we reuse the method of VM migration and propose a dynamic migration-based data locality scheme using parallel computing entropy. We migrate the computation nodes to different host(s) or rack(s) where the corresponding storage nodes are deployed to satisfy the requirement of data locality. We evaluate our solutions in a realistic scenario based on Open Stack.Substantial experimental results demonstrate the effectiveness of our solutions that contribute to balance the workload and performance improvement, even under heavy-loaded cloud system conditions.
基金
supported by the Open Project Program of Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks(No.WSNLBKF201503)
the Fundamental Research Funds for the Central Universities(No.2016JBM011)
Fundamental Research Funds for the Central Universities(No.2014ZD03-03)
the Priority Academic Program Development of Jiangsu Higher Education Institutions
Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology