Xen and the art of virtualization
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
Measuring CPU overhead for I/O processing in the Xen virtual machine monitor
ATEC '05 Proceedings of the annual conference on USENIX Annual Technical Conference
A unified framework for max-min and min-max fairness with applications
IEEE/ACM Transactions on Networking (TON)
Crossbow: from hardware virtualized NICs to virtualized networks
Proceedings of the 1st ACM workshop on Virtualized infrastructure systems and architectures
Hedera: dynamic flow scheduling for data center networks
NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
SR-IOV networking in Xen: architecture, design and implementation
WIOV'08 Proceedings of the First conference on I/O virtualization
Seawall: performance isolation for cloud datacenter networks
HotCloud'10 Proceedings of the 2nd USENIX conference on Hot topics in cloud computing
SecondNet: a data center network virtualization architecture with bandwidth guarantees
Proceedings of the 6th International COnference
Sharing the data center network
Proceedings of the 8th USENIX conference on Networked systems design and implementation
Gatekeeper: supporting bandwidth guarantees for multi-tenant datacenter networks
WIOV'11 Proceedings of the 3rd conference on I/O virtualization
NetLord: a scalable multi-tenant network architecture for virtualized datacenters
Proceedings of the ACM SIGCOMM 2011 conference
FairCloud: sharing the network in cloud computing
Proceedings of the ACM SIGCOMM 2012 conference on Applications, technologies, architectures, and protocols for computer communication
| Hi-index | 0.00 |
The network, similar to the CPU and memory, is a critical and shared resource in Cloud. However, unlike the CPU and memory division strategy, virtual network bandwidth should be allocated according to the payment and needs of tenants. Different tenants may have different network demands for VM. This paper proposed a receive side network allocation mechanism under NIC hardware virtualization environment. We use two bandwidth control methods - (1) Control the Interrupt Throttle Rate (maximum interrupt number per second) of each VM. (2) Control the packet fetching rate using the TBF (Token Bucket Filtering) algorithm. As SR-IOV has become an industry standard of network sharing with a lot of advantages, It reduces the unnecessary context switch overhead and efficiently improves the bandwidth utilization on the basis of providing the sharing of I/O devices. We implement our algorithm on SR-IOV based environment. We evaluate the network performance of our algorithm. The result shows that the algorithm proportionally divides VM bandwidth according to what we specify without reducing the network efficiency largely.