Abstract
Traditional Virtual Machine Monitor (VMM) virtualizes some devices and instructions, which induces performance overhead to guest operating systems. Furthermore, the virtualization contributes a large amount of codes to VMM, which makes a VMM prone to bugs and vulnerabilities.
On the other hand, in cloud computing, cloud service provider configures virtual machines based on requirements which are specified by customers in advance. As resources in a multi-core server increase to more than adequate in the future, virtualization is not necessary although it provides convenience for cloud computing. Based on the above observations, this paper presents an alternative way for constructing a VMM: configuring a booting interface instead of virtualization technology. A lightweight virtual machine monitor - OSV is proposed based on this idea. OSV can host multiple full functional Linux kernels with little performance overhead. There are only 6 hyper-calls in OSV. The Linux running on top of OSV is intercepted only for the inter-processor interrupts. The resource isolation is implemented with hardware-assist virtualization. The resource sharing is controlled by distributed protocols embedded in current operating systems.
We implement a prototype of OSV on AMD Opteron processor based 32-core servers with SVM and cache-coherent NUMA architectures. OSV can host up to 8 Linux kernels on the server with less than 10 lines of code modifications to Linux kernel. OSV has about 8000 lines of code which can be easily tuned and debugged. The experiment results show that OSV VMM has 23.7% performance improvement compared with Xen VMM.
- CVE-2010-0633. http://cve.mitre.org/cgibin/cvename.cgi?name=CVE-2010-0633, 2010.Google Scholar
- CVE-2010-4255. http://cve.mitre.org/cgibin/cvename.cgi?name=CVE-2010-4255, 2010.Google Scholar
- CVE-2010-4247. http://cve.mitre.org/cgibin/cvename.cgi?name=CVE-2010-4247, 2010.Google Scholar
- CVE-2012-0217: SYSRET 64-bit operating system privilege escalation vulnerability on Intel CPU hardware. http://cve.mitre.org/cgibin/cvename.cgi?name=CVE-2012-0217, 2012.Google Scholar
- HP ProLiant DL980 G7 Server Data Sheet. http://h20195.www2.hp.com/V2/GetPDF.aspx/4AA1-5671ENW.pdf, 2012.Google Scholar
- AMD. Amd64 architecture programmer's manual volume 2: System programming. Publication No. 24593, September 2007.Google Scholar
- J. Appavoo, D. Silva, O. Krieger, M. Auslander, M. Ostrowski, B. Rosenburg, A. Waterland, R. Wisniewski, J. Xenidis, M. Stumm, et al. Experience distributing objects in an SMMP OS. ACM Transactions on Computer Systems (TOCS), 25(3):6--es, 2007. ISSN 0734-2071. Google Scholar
Digital Library
- P. Barham, B. Dragovic, K. Fraser, S. Hand, T. Harris, A. Ho, R. Neugebauer, I. Pratt, and A. Warfield. Xen and the Art of Virtualization. Proceedings of the 19th ACM symposium on Operating systems principles, pages 164--177, 2003. Google Scholar
Digital Library
- A. Baumann, P. Barham, P. Dagand, T. Harris, R. Isaacs, S. Peter, T. Roscoe, A. Schüpbach, and A. Singhania. The multikernel: a new OS architecture for scalable multicore systems. In Proceedings of the ACM SIGOPS 22nd symposium on Operating Systems Principles, pages 29--44. ACM, 2009. Google Scholar
Digital Library
- S. Boyd-Wickizer, H. Chen, R. Chen, Y. Mao, F. Kaashoek, R. Morris, A. Pesterev, L. Stein, M.Wu, Y. Dai, et al. Corey: An operating system for many cores. In Proceedings of the 8th USENIX conference on Operating systems design and implementation, pages 43--57. USENIX Association, 2008. Google Scholar
Digital Library
- S. Boyd-Wickizer, A. Clements, O. Mao, A. Pesterev, M. Kaashoek, R. Morris, and N. Zeldovich. An analysis of Linux scalability to many cores. In Proceedings of the 9th USENIX conference on Operating systems design and implementation. USENIX Association, 2010. Google Scholar
Digital Library
- E. Bugnion, S. Devine, and M. Rosenblum. Disco: running commodity operating systems on scalable multiprocessors. ACM SIGOPS Operating Systems Review, 31(5):143--156, 1997. ISSN 0163-5980. Google Scholar
Digital Library
- D. Engler, M. Kaashoek, et al. Exokernel: An operating system architecture for application-level resource management. ACM SIGOPS Operating Systems Review, 29(5):251--266, 1995. Google Scholar
Digital Library
- B. Gamsa, O. Krieger, J. Appavoo, and M. Stumm. Tornado: Maximizing locality and concurrency in a shared memory multiprocessor operating system. Operating systems review, 33:87--100, 1998. ISSN 0163-5980.Google Scholar
- C. Gough, S. Siddha, and K. Chen. Kernel scalability--expanding the horizon beyond fine grain locks. In Proceedings of the Linux Symposium, pages 153--165, 2007.Google Scholar
- K. Govil, D. Teodosiu, Y. Huang, and M. Rosenblum. Cellular Disco: Resource management using virtual clusters on shared-memory multiprocessors. In Proceedings of the seventeenth ACM symposium on Operating systems principles, pages 154--169. ACM, 1999. ISBN 1581131402. Google Scholar
Digital Library
- J. Held, J. Bautista, and S. Koehl. White paper from a few cores to many: A tera-scale computing research review.Google Scholar
- Intel. The MultiProcessor Specification Version 1.4. http://download.intel.com/design/archives/processors/pro/docs/24201606.pdf, 1997.Google Scholar
- E. Keller, J. Szefer, J. Rexford, and R. B. Lee. Nohype: virtualized cloud infrastructure without the virtualization. In Proceedings of the 37th annual international symposium on Computer architecture, ISCA '10, pages 350--361, New York, NY, USA, 2010. ACM. ISBN 978-1-4503-0053-7. doi: 10.1145/1815961.1816010. URL http://doi.acm.org/10.1145/1815961.1816010. Google Scholar
Digital Library
- A. Klein. An NUMA API for Linux. http://www.firstfloor.org/andi/numa.html, August 2004.Google Scholar
- L. McVoy and C. Staelin. lmbench: Portable tools for performance analysis. In Proceedings of the 1996 annual conference on USENIX Annual Technical Conference, page 23. Usenix Association, 1996. Google Scholar
Digital Library
- E. Nightingale, O. Hodson, R. McIlroy, C. Hawblitzel, and G. Hunt. Helios: heterogeneous multiprocessing with satellite kernels. In Proceedings of the ACM SIGOPS 22nd symposium on Operating systems principles, pages 221--234. ACM, 2009. Google Scholar
Digital Library
- B. Saha, A. Adl-Tabatabai, A. Ghuloum, M. Rajagopalan, R. Hudson, L. Petersen, V. Menon, B. Murphy, T. Shpeisman, E. Sprangle, et al. Enabling scalability and performance in a large scale CMP environment. In ACM SIGOPS Operating Systems Review, volume 41, pages 73--86. ACM, 2007. Google Scholar
Digital Library
- J. Szefer, E. Keller, R. B. Lee, and J. Rexford. Eliminating the hypervisor attack surface for a more secure cloud. In Proceedings of the 18th ACM conference on Computer and communications security, CCS '11, pages 401--412, New York, NY, USA, 2011. ACM. ISBN 978-1-4503-0948-6. doi: 10.1145/2046707.2046754. URL http://doi.acm.org/10.1145/2046707.2046754. Google Scholar
Digital Library
- B. Veal and A. Foong. Performance scalability of a multi-core web server. In Proceedings of the 3rd ACM/IEEE Symposium on Architecture for networking and communications systems, pages 57--66. ACM, 2007. Google Scholar
Digital Library
- B. Verghese, S. Devine, A. Gupta, and M. Rosenblum. Operating system support for improving data locality on CC-NUMA compute servers, volume 31. ACM, 1996. ISBN 0897917677. Google Scholar
Digital Library
- C. Waldspurger. Memory resource management in VMware ESX server. ACM SIGOPS Operating Systems Review, 36(SI):194, 2002. Google Scholar
Digital Library
Index Terms
A lightweight VMM on many core for high performance computing
Recommendations
A lightweight VMM on many core for high performance computing
VEE '13: Proceedings of the 9th ACM SIGPLAN/SIGOPS international conference on Virtual execution environmentsTraditional Virtual Machine Monitor (VMM) virtualizes some devices and instructions, which induces performance overhead to guest operating systems. Furthermore, the virtualization contributes a large amount of codes to VMM, which makes a VMM prone to ...
Enabling Instantaneous Relocation of Virtual Machines with a Lightweight VMM Extension
CCGRID '10: Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid ComputingWe are developing an efficient resource management system with aggressive virtual machine (VM) relocation among physical nodes in a data center. Existing live migration technology, however, requires a long time to change the execution host of a VM, it ...
Performance Analysis for Pareto-Optimal Green Consolidation Based on Virtual Machines Live Migration
Huge energy requirement of cloud data centers is prime concern. Dynamic Virtual Machine VM consolidation based on VM live migration to switched-off or put some of the under-loaded host Physical Machines PMs into a low power consumption mode can ...







Comments