The Experts below are selected from a list of 660 Experts worldwide ranked by ideXlab platform

Wanyu Zang - One of the best experts on this subject based on the ideXlab platform.

  • incentive compatible moving target defense against vm colocation attacks in clouds
    Information Security Conference, 2012
    Co-Authors: Yulong Zhang, Kun Bai, Wanyu Zang
    Abstract:

    Cloud computing has changed how services are provided and supported through the computing infrastructure. However, recent work [11] reveals that virtual machine (VM) colocation based side-channel attack can leak users privacy. Techniques have been developed against side-channel attacks. Some of them like NoHype remove the Hypervisor Layer, which suggests radically changes of the current cloud architecture. While some other techniques may require new processor design that is not immediately available to the cloud providers.

Cl Wang - One of the best experts on this subject based on the ideXlab platform.

  • PVTCP: Towards practical and effective congestion control in virtualized datacenters
    'United States Sports Academy', 2013
    Co-Authors: Lau Fcm, Cheng L, Cl Wang
    Abstract:

    While modern datacenters are increasingly adopting virtual machines (VMs) to provide elastic cloud services, they still rely on traditional TCP for congestion control. In virtualized datacenters, TCP endpoints are separated by a virtualization Layer and subject to the intervention of the Hypervisor’s scheduling. Most previous attempts focused on tuning the Hypervisor Layer to try to improve the VMs’ I/O performance, and there is very little work on how a VM’s guest OS may help the transport Layer to adapt to the virtualized environment. In this paper, we find that VM scheduling delays can heavily contaminate RTTs as sensed by VM senders, preventing TCP from correctly learning the physical network condition. After giving an account of the source of the problem, we propose PVTCP, a ParaVirtualized TCP to counter the distorted congestion information caused by VM scheduling on the sender side. PVTCP is self-contained, requiring no modification to the Hypervisor. Experiments show that PVTCP is much more effective in addressing incast congestion in virtualized datacenters than standard TCP.published_or_final_versio

  • vBalance: using interrupt load balance to improve I/O performance for SMP virtual machines
    'Association for Computing Machinery (ACM)', 2012
    Co-Authors: Cheng L, Cl Wang
    Abstract:

    A Symmetric MultiProcessing (SMP) virtual machine (VM) enables users to take advantage of a multiprocessor infrastructure in supporting scalable job throughput and request responsiveness. It is known that Hypervisor scheduling activities can heavily degrade a VM’s I/O performance, as the scheduling latencies of the virtual CPU (vCPU) eventually translates into the processing delays of the VM’s I/O events. As for a UniProcessor (UP) VM, since all its interrupts are bound to the only vCPU, it completely relies on the Hypervisor’s help to shorten I/O processing delays, making the Hypervisor increasingly complicated. Regarding SMP-VMs, most researches ignore the fact that the problem can be greatly mitigated at the level of guest OS, instead of imposing all scheduling pressure on the Hypervisor. In this paper, we present vBalance, a cross-Layer software solution to substantially improve the I/O performance for SMP-VMs. Under the principle of keeping Hypervisor scheduler’s simplicity and efficiency, vBalance only requires very limited help in the Hypervisor Layer. In the guest OS, vBalance can dynamically and adaptively migrate the interrupts from a preempted vCPU to a running one, and hence avoids interrupt processing delays. The prototype of vBalance is implemented in Xen 4.1.2 Hypervisor, with Linux 3.2.2 as the guest. The evaluation results of both micro-level and application-level benchmarks prove the effectiveness and lightweightness of our solution.link_to_OA_fulltex

Yulong Zhang - One of the best experts on this subject based on the ideXlab platform.

  • incentive compatible moving target defense against vm colocation attacks in clouds
    Information Security Conference, 2012
    Co-Authors: Yulong Zhang, Kun Bai, Wanyu Zang
    Abstract:

    Cloud computing has changed how services are provided and supported through the computing infrastructure. However, recent work [11] reveals that virtual machine (VM) colocation based side-channel attack can leak users privacy. Techniques have been developed against side-channel attacks. Some of them like NoHype remove the Hypervisor Layer, which suggests radically changes of the current cloud architecture. While some other techniques may require new processor design that is not immediately available to the cloud providers.

Cho-li Wang - One of the best experts on this subject based on the ideXlab platform.

  • PVTCP: Towards Practical and Effective Congestion Control in Virtualized Datacenters
    2014
    Co-Authors: Luwei Cheng, Cho-li Wang, Francis C. M. Lau
    Abstract:

    Abstract—While modern datacenters are increasingly adopting virtual machines (VMs) to provide elastic cloud services, they still rely on traditional TCP for congestion control. In virtualized datacenters, TCP endpoints are separated by a virtualization Layer and subject to the intervention of the Hypervisor’s scheduling. Most previous attempts focused on tuning the Hypervisor Layer to try to improve the VMs ’ I/O performance, and there is very little work on how a VM’s guest OS may help the transport Layer to adapt to the virtualized environment. In this paper, we find that VM scheduling delays can heavily contaminate RTTs as sensed by VM senders, preventing TCP from correctly learning the physical network condition. After giving an account of the source of the problem, we propose PVTCP, a ParaVirtualized TCP to counter the distorted congestion information caused by VM scheduling on the sender side. PVTCP is self-contained, requiring no modification to the Hypervisor. Experiments show that PVTCP is much more effective in addressing incast congestion in virtualized datacenters than standard TCP. I

  • vBalance: Using Interrupt Load Balance to Improve I/O Performance for SMP Virtual Machines
    2013
    Co-Authors: Luwei Cheng, Cho-li Wang
    Abstract:

    A Symmetric MultiProcessing (SMP) virtual machine (VM) enables users to take advantage of a multiprocessor infrastructure in supporting scalable job throughput and request responsiveness. It is known that Hypervisor scheduling activities can heavily degrade a VM’s I/O performance, as the scheduling latencies of the virtual CPU (vCPU) eventually translates into the processing delays of the VM’s I/O events. As for a UniProcessor (UP) VM, since all its interrupts are bound to the only vCPU, it completely relies on the Hypervisor’s help to shorten I/O processing delays, making the Hypervisor increasingly complicated. Regarding SMP-VMs, most researches ignore the fact that the problem can be greatly mitigated at the level of guest OS, instead of imposing all scheduling pressure on the Hypervisor. In this paper, we present vBalance, a cross-Layer software solution to substantially improve the I/O performance for SMP-VMs. Under the principle of keeping Hypervisor scheduler’s simplicity and efficiency, vBalance only requires very limited help in the Hypervisor Layer. In the guest OS, vBalance can dynamically and adaptively migrate the interrupts from a preempted vCPU to a running one, and hence avoids interrupt processing delays. The prototype of vBalance is implemented in Xen 4.1.2 Hypervisor, with Linux 3.2.2 as the guest. The evaluation results of both micro-level and application-level benchmarks prove the effectiveness and lightweightness of our solution

Luwei Cheng - One of the best experts on this subject based on the ideXlab platform.

  • PVTCP: Towards Practical and Effective Congestion Control in Virtualized Datacenters
    2014
    Co-Authors: Luwei Cheng, Cho-li Wang, Francis C. M. Lau
    Abstract:

    Abstract—While modern datacenters are increasingly adopting virtual machines (VMs) to provide elastic cloud services, they still rely on traditional TCP for congestion control. In virtualized datacenters, TCP endpoints are separated by a virtualization Layer and subject to the intervention of the Hypervisor’s scheduling. Most previous attempts focused on tuning the Hypervisor Layer to try to improve the VMs ’ I/O performance, and there is very little work on how a VM’s guest OS may help the transport Layer to adapt to the virtualized environment. In this paper, we find that VM scheduling delays can heavily contaminate RTTs as sensed by VM senders, preventing TCP from correctly learning the physical network condition. After giving an account of the source of the problem, we propose PVTCP, a ParaVirtualized TCP to counter the distorted congestion information caused by VM scheduling on the sender side. PVTCP is self-contained, requiring no modification to the Hypervisor. Experiments show that PVTCP is much more effective in addressing incast congestion in virtualized datacenters than standard TCP. I

  • vBalance: Using Interrupt Load Balance to Improve I/O Performance for SMP Virtual Machines
    2013
    Co-Authors: Luwei Cheng, Cho-li Wang
    Abstract:

    A Symmetric MultiProcessing (SMP) virtual machine (VM) enables users to take advantage of a multiprocessor infrastructure in supporting scalable job throughput and request responsiveness. It is known that Hypervisor scheduling activities can heavily degrade a VM’s I/O performance, as the scheduling latencies of the virtual CPU (vCPU) eventually translates into the processing delays of the VM’s I/O events. As for a UniProcessor (UP) VM, since all its interrupts are bound to the only vCPU, it completely relies on the Hypervisor’s help to shorten I/O processing delays, making the Hypervisor increasingly complicated. Regarding SMP-VMs, most researches ignore the fact that the problem can be greatly mitigated at the level of guest OS, instead of imposing all scheduling pressure on the Hypervisor. In this paper, we present vBalance, a cross-Layer software solution to substantially improve the I/O performance for SMP-VMs. Under the principle of keeping Hypervisor scheduler’s simplicity and efficiency, vBalance only requires very limited help in the Hypervisor Layer. In the guest OS, vBalance can dynamically and adaptively migrate the interrupts from a preempted vCPU to a running one, and hence avoids interrupt processing delays. The prototype of vBalance is implemented in Xen 4.1.2 Hypervisor, with Linux 3.2.2 as the guest. The evaluation results of both micro-level and application-level benchmarks prove the effectiveness and lightweightness of our solution