Improving fairness of network bandwidth allocation for virtual machines in cloud environment

With the rapid development of cloud computing, data center's resource management has become a critical component in its business model. CPU, memory and network in a data center have many effective partitioning methods among the virtual machines that could offer high-efficiency, enhanced fairness and performance guarantee. However, in existing software based virtualization architecture (e.g., Xen), the network bandwidth is always decided by the number of connections, and no effective proportional share mechanism exists for the concurrently running virtual machines (VMs). Therefore, existing mechanism of network sharing will cause unfairness between VMs. In case that VMs should be given the same network bandwidth, there will be no such guarantee, especially when they establish different number of connections to outside world, even when the VMs are assigned with equal weight. In this paper, we present a mechanism that can improve the fairness of network bandwidth allocation in Xen para-virtualization in dynamic network environment. The experiment results demonstrate that every VM could share the network bandwidth almost according to its share even under real-world fluctuating network conditions.

[1]  William E. Weihl,et al.  Lottery scheduling: flexible proportional-share resource management , 1994, OSDI '94.

[2]  J. Manyika Big data: The next frontier for innovation, competition, and productivity , 2011 .

[3]  Hai Jin,et al.  VMStore: Distributed storage system for multiple virtual machines , 2011, Science China Information Sciences.

[4]  Amin Vahdat,et al.  Dynamic Scheduling of Virtual Machines Running HPC Workloads in Scientific Grids , 2007, 2009 3rd International Conference on New Technologies, Mobility and Security.

[5]  Sally Floyd,et al.  TCP and explicit congestion notification , 1994, CCRV.

[6]  William Hunt What Is Google Apps for Business , 2013 .

[7]  Dorgival O. Guedes,et al.  Gatekeeper: Supporting Bandwidth Guarantees for Multi-tenant Datacenter Networks , 2011, WIOV.

[8]  Helen J. Wang,et al.  SecondNet: a data center network virtualization architecture with bandwidth guarantees , 2010, CoNEXT.

[9]  Randy H. Katz,et al.  A view of cloud computing , 2010, CACM.

[10]  R. Shreedhar,et al.  Efficient Fair Queuing Using Deficit Round - , 1997 .

[11]  Miltos Petridis,et al.  Dynamic Scheduling of Virtual Machines Running HPC Workloads in Scientific Grids , 2009, 2009 3rd International Conference on New Technologies, Mobility and Security.

[12]  Lisandro Zambenedetti Granville,et al.  Data Center Network Virtualization: A Survey , 2013, IEEE Communications Surveys & Tutorials.

[13]  George Varghese,et al.  Efficient fair queueing using deficit round-robin , 1996, TNET.

[14]  Albert G. Greenberg,et al.  Seawall: Performance Isolation for Cloud Datacenter Networks , 2010, HotCloud.