ACM Transactions on Computer Systems (TOCS)
Xen and the art of virtualization
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
Diagnosing performance overheads in the xen virtual machine environment
Proceedings of the 1st ACM/USENIX international conference on Virtual execution environments
Optimizing network virtualization in Xen
ATEC '06 Proceedings of the annual conference on USENIX '06 Annual Technical Conference
Characterization of network processing overheads in Xen
VTDC '06 Proceedings of the 2nd International Workshop on Virtualization Technology in Distributed Computing
Concurrent Direct Network Access for Virtual Machine Monitors
HPCA '07 Proceedings of the 2007 IEEE 13th International Symposium on High Performance Computer Architecture
Scheduling I/O in virtual machine monitors
Proceedings of the fourth ACM SIGPLAN/SIGOPS international conference on Virtual execution environments
Network Virtualization: Breaking the Performance Barrier
Queue - Virtualization
Bridging the gap between software and hardware techniques for I/O virtualization
ATC'08 USENIX 2008 Annual Technical Conference on Annual Technical Conference
The definitive guide to the xen hypervisor
The definitive guide to the xen hypervisor
Towards high performance virtual routers on commodity hardware
CoNEXT '08 Proceedings of the 2008 ACM CoNEXT Conference
Evaluating and enhancing xen-based virtual routers to support real-time applications
CCNC'10 Proceedings of the 7th IEEE conference on Consumer communications and networking conference
VOLTAIC: volume optimization layer to assign cloud resources
Proceedings of the 3rd International Conference on Information and Communication Systems
Hi-index | 0.01 |
With resurgent interest in virtualisation, router virtualisation seems the next step to servers virtualisation. It is also a key in deploying flexible and isolated virtual networks. In this paper, we evaluate Xen-based virtual routers on top of commodity hardware. Forwarding being achieved through the driver domain networking model, we identify and analyse the throughput limitation through profiling the CPU usage and the memory accesses. In multi-core systems, the memory access latencies are then the bottleneck. Then, we propose in this context a mechanism reducing packets waiting time to be delivered to the virtual router, which guarantees throughput and ensures minimal latency and jitter to delay-sensitive flows, based on the priority they are assigned.