Concurrent Direct Network Access for Virtual Machine Monitors

Willmann, Paul; Shafer, Jeffrey; Carr, Dominic; Menon, Aravind; Rixner, Scott; Cox, Alan L.; Zwaenepoel, Willy

doi:10.1109/hpca.2007.346208

Cited by 89 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [11], the authors analyze and compare the CPU schedulers in the Xen virtual machine monitor (VMM) [12] in the context of traditional workload managers. They use the open source Xen virtual machine monitor to perform a comparative evaluation of three different CPU schedulers for virtual machines and analyze the impact of the CPU scheduler and resource allocation on application performance.…”

Section: Related Workmentioning

confidence: 99%

A Real-Time Scheduling Mechanism of Resource for Multiple Virtual Machine System

Wan

et al. 2010

2010 Fifth Annual ChinaGrid Conference

View full text Add to dashboard Cite

With the growth of hardware and software resources, the management of virtual machine system is becoming more and more difficult. It has become a very difficult problem that how to schedule the system resource in real time and improve the service performance of resource in a multiple virtual machine system. In order to solve this problem, the authors propose a real-time scheduling mechanism of resource for multiple virtual machine system. In the real-time scheduling mechanism of resource, the authors first describe the architecture of multiple virtual machine system. Then, the authors present a real-time scheduling strategy of resource. In order to justify the feasibility and the availability of this resource scheduling mechanism, a series of experiments have been done. The results show that it is feasible to schedule the system resources for tasks in multiple virtual machine system.

show abstract

Section: Related Workmentioning

confidence: 99%

A Real-Time Scheduling Mechanism of Resource for Multiple Virtual Machine System

Wan

et al. 2010

2010 Fifth Annual ChinaGrid Conference

View full text Add to dashboard Cite

show abstract

“…The hypervisor verifies the address of guest buffers specified in the guest DMA descriptors so that the address does not point to the hypervisor regions. This technique is similar to that used in a software-based IOMMU [26]. To prevent attacks using DMA that do not need to be intercepted, we can use IOMMU hardware.…”

Section: Dmamentioning

confidence: 99%

“…Shafer et al [26] proposed a software-based IOMMU that intercepts and verifies the DMA descriptor to allow direct access to the NIC device from a guest OS. This technique is similar to the shadow DMA descriptor used in BitVisor.…”

Section: Related Workmentioning

confidence: 99%

BitVisor

Shinagawa

Eiraku

Tanimoto

et al. 2009

Proceedings of the 2009 ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments

129

View full text Add to dashboard Cite

Virtual machine monitors (VMMs), including hypervisors, are a popular platform for implementing various security functionalities. However, traditional VMMs require numerous components for providing virtual hardware devices and for sharing and protecting system resources among virtual machines (VMs), enlarging the code size of and reducing the reliability of the VMMs. This paper introduces a hypervisor architecture, called parapassthrough, designed to minimize the code size of hypervisors by allowing most of the I/O access from the guest operating system (OS) to pass-through the hypervisor, while the minimum access necessary to implement security functionalities is completely mediated by the hypervisor. This architecture uses device drivers of the guest OS to handle devices, thereby reducing the size of components in the hypervisor to provide virtual devices. This architecture also allows to run only single VM on it, eliminating the components for sharing and protecting system resources among VMs.We implemented a hypervisor called BitVisor and a parapassthrough driver for enforcing storage encryption of ATA devices based on the parapass-through architecture. The experimental result reveals that the hypervisor and ATA driver require approximately 20 kilo lines of code (KLOC) and 1.4 KLOC respectively.

show abstract

“…More details of the Xen architecture can be found in [7]. The 'hosted' driver architecture incurs a significant performance overhead for guest domains, which has been studied in [15,21,12]. The biggest overhead is incurred due to the frequent context switches between the driver domain and guest domains for driver invocation and interrupt handling, which results in increased TLB and cache misses [12].…”

Section: Background On Xen I/omentioning

confidence: 99%

TwinDrivers

Menon

Schubert

Zwaenepoel

2009

Proceedings of the 14th International Conference on Architectural Support for Programming Languages and Operating Systems

Self Cite

View full text Add to dashboard Cite

In a virtualized environment, device drivers are often run inside a virtual machine (VM) rather than in the hypervisor, for reasons of safety and reduction in software engineering effort. Unfortunately, this approach results in poor performance for I/O-intensive devices such as network cards. The alternative approach of running device drivers directly in the hypervisor yields better performance, but results in the loss of safety guarantees for the hypervisor and incurs additional software engineering costs.In this paper we present TwinDrivers, a framework which allows us to semi-automatically create safe and efficient hypervisor drivers from guest OS drivers. The hypervisor driver runs directly in the hypervisor, but its data resides completely in the driver VM address space. A Software Virtual Memory mechanism allows the driver to access its VM data efficiently from the hypervisor running in any guest context, and also protects the hypervisor from invalid memory accesses from the driver. An upcall mechanism allows the hypervisor to largely reuse the driver support infrastructure present in the VM. The TwinDriver system thus combines most of the performance benefits of hypervisor-based driver approaches with the safety and software engineering benefits of VM-based driver approaches.Using the TwinDrivers hypervisor driver, we are able to improve the guest domain networking throughput in Xen by a factor of 2.4 for transmit workloads, and 2.1 for receive workloads, both in CPU-scaled units, and achieve close to 64-67% of native Linux throughput.

show abstract

Concurrent Direct Network Access for Virtual Machine Monitors

Abstract: Abstract

Cited by 89 publications

References 12 publications

A Real-Time Scheduling Mechanism of Resource for Multiple Virtual Machine System

A Real-Time Scheduling Mechanism of Resource for Multiple Virtual Machine System

BitVisor

TwinDrivers

Contact Info

Product

Resources

About