Mukil Kesavan
ABSTRACT
This paper investigates what it entails to provide I/O service differentiation and performance isolation for virtual machines on individual multicore nodes in cloud platforms. Sharing I/O between VMs is fundamentally different from sharing I/O between processes because guest VM operating systems use adaptive resource management mechanisms like TCP congestion avoidance, disk I/O schedulers, etc. The problem is that these mechanisms are generally sensitive to the magnitude and rate of change of service latencies, where failing to address these latency concerns while designing a service differentiation framework for I/O results in undue performance degradation and hence, insufficient isolation between VMs. This problem is addressed by the notion of Differential Virtual Time (DVT), which can provide service differentiation with performance isolation for VM guest OS resource management mechanisms. DVT is realized within a proportional share I/O scheduling framework for the Xen hypervisor, and its use requires no changes to guest OSs. DVT is applied to message-based I/O, but is also applicable to subsystems like disk I/O. Experimental results with DVT-based I/O scheduling for representative applications demonstrate the utility and effectiveness of the approach.
- Amazon CloudFront. http://aws.amazon.com/cloudfront/.Google Scholar
- M. Armbrust et al. Above the Clouds: A Berkeley View of Cloud Computing. Technical report, University of California, Berkeley, Feb 2009.Google Scholar
- P. Barham et al. Xen and the Art of Virtualization. In SOSP '03, 2003. Google ScholarDigital Library
- J. C. R. Bennett and H. Zhang. Hierarchical Packet Fair Queueing Algorithms. In SIGCOMM '96, 1996. Google ScholarDigital Library
- D. Boutcher and A. Chandra. Does Virtualization Make Disk Scheduling Passe? In HotStorage '09, October 2009.Google Scholar
- L. S. Brakmo, S. W. O'Malley, and L .L. Peterson. TCP Vegas: New Techniques for Congestion Detection and Avoidance. In SIGCOMM '94, 1994. Google ScholarDigital Library
- H. M. Chaskar and U. Madhow. Fair Scheduling with Tunable Latency: A Round-Robin Approach. IEEE/ACM Trans. Netw., 2003. Google ScholarDigital Library
- L. Cherkasova and R. Gardner. Measuring CPU Overhead for I/O Processing in the Xen Virtual Machine Monitor. In ATEC '05, 2005. Google ScholarDigital Library
- K. J. Duda and D .R. Cheriton. Borrowed-Virtual-Time (BVT) scheduling: Supporting Latency-Sensitive Threads in a General-Purpose Scheduler. SIGOPS Oper. Syst. Rev., 2000. Google ScholarDigital Library
- S. Govindan et al. Xen and Co.: Communication-Aware CPU Scheduling for Consolidated Xen-based Hosting Platforms. In VEE '07, 2007. Google ScholarDigital Library
- A. Gulati, I. Ahmad, and C. A. Waldspurger. PARDA: Proportional Allocation of Resources for Distributed Storage Access. In FAST '09, 2009. Google ScholarDigital Library
- A. Gulati, A. Merchant, and P. J. Varman. Clock: An Arrival Curve Based Approach for QoS Guarantees in Shared Storage Systems. SIGMETRICS Perform. Eval. Rev., 2007. Google ScholarDigital Library
- D. Gupta et al. Enforcing Performance Isolation Across Virtual Machines in Xen. In Middleware '06, 2006. Google ScholarDigital Library
- D. Hilley. Cloud Computing: A Taxonomy of Platform and Infrastructure-level Offerings. Technical report, 2009.Google Scholar
- S.Iyer and P. Druschel. Anticipatory Scheduling: A Disk Scheduling Framework to Overcome Deceptive Idleness in Synchronous I/O. In SOSP '01, 2001. Google ScholarDigital Library
- M. B. Jones et al. An overview of the Rialto real-time architecture. In EW7: Proceedings of the 7th workshop on ACM SIGOPS European workshop, 1996. Google ScholarDigital Library
- M. B. Jones and J. Regehr. CPU Reservations and Time Constraints: Implementation Experience on Windows NT. In WINSYM '99, 1999. Google ScholarDigital Library
- S. T. Jones et al. Antfarm: Tracking Processes in a Virtual Machine Environment. In ATEC '06, 2006. Google ScholarDigital Library
- S. Kandula et al. The Nature of Data Center Traffic: Measurements & Analysis. In IMC '09, 2009. Google ScholarDigital Library
- K. Kant. Towards a Virtualized Data Center Transport Protocol. In INFOCOM Workshops 2008, IEEE, April 2008.Google ScholarCross Ref
- M. Kesavan, A. Gavrilovska, and K. Schwan. On Disk I/O Scheduling in Virtual Machines. In WIOV '10, March 2010. Google ScholarDigital Library
- J. Martin, A. Nilsson, and I. Rhee. Delay-based Congestion Avoidance for TCP. IEEE/ACM Trans. Netw., 2003. Google ScholarDigital Library
- C. W. Mercer, S. Savage, and H. Tokuda. Processor Capacity Reserves for Multimedia Operating Systems. Technical report, 1993. Google ScholarDigital Library
- D. Mosberger and T. Jin. httperf - A Tool for Measuring Web Server Performance. SIGMETRICS Perform. Eval. Rev., 1998. Google ScholarDigital Library
- R.Nathuji and K. Schwan. VirtualPower: Coordinated Power Management in Virtualized Enterprise Systems. In SOSP '07, 2007. Google ScholarDigital Library
- J. Nieh and M. S. Lam. A SMART Scheduler for Multimedia Applications. ACM Trans. Comput. Syst., 2003. Google ScholarDigital Library
- D. Ongaro, A. L. Cox, and S. Rixner. Scheduling I/O in Virtual Machine Monitors. In VEE '08, 2008. Google ScholarDigital Library
- Iperf. http://sourceforge.net/projects/iperf/.Google Scholar
- Lighttpd. http://www.lighttpd.net/.Google Scholar
- The VMWare ESX Server. http://www.vmware.com/products/esx/.Google Scholar
- A. K. Parekh and R. G. Gallagher. A Generalized Processor Sharing Approach to Flow Control in Integrated Services Networks: The Multiple Node Case. IEEE/ACM Trans.Netw., 1994. Google ScholarDigital Library
- S. Pratt and D. Heger. Workload Dependent Performance Evaluation of the Linux 2.6 I/O Schedulers. In OLS '04. Ottawa Linux Symposium, 2004.Google Scholar
- S. R. Seelamand P. J. Teller. Virtual I/O Scheduler: A Scheduler of Schedulers for Performance Virtualization. In VEE '07, 2007. Google ScholarDigital Library
- J. A. Stankovic and K. Ramamritham. The Spring Kernel: A New Paradigm for Real-Time Systems. IEEE Softw., 1991. Google ScholarDigital Library
- D. Stiliadis and A. Varma. Latency-Rate Servers: A General Model for Analysis of Traffic Scheduling Algorithms. IEEE/ACM Trans. Netw., 6(5), 1998. Google ScholarDigital Library
- K. Tan and J. Song. A Compound TCP Approach for High-Speed and Long Distance Networks. In Proc. IEEE INFOCOM, 2006.Google ScholarCross Ref
- C. A. Waldspurger. Memory Resource Management in VMware ESX Server. In OSDI '02. Google ScholarDigital Library
- D. X. Wei, C. Jin, S. H. Low, and S. Hegde. FASTTCP: Motivation, Architecture, Algorithms, Performance. IEEE/ACM Trans. Netw., 2006. Google ScholarDigital Library
- H. Yamada and K. Kono. FoxyTechnique: Tricking Operating System Policies with a Virtual Machine Monitor. In VEE '07, 2007. Google ScholarDigital Library
- J. Zhang et al. Storage Performance Virtualization via Throughput and Latency Control. In MASCOTS '05, 2005. Google ScholarDigital Library
Index Terms
- Differential virtual time (DVT): rethinking I/O service differentiation for virtual machines
Recommendations
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 ...
A Technical Review for Efficient Virtual Machine Migration
CUBE '13: Proceedings of the 2013 International Conference on Cloud & Ubiquitous Computing & Emerging TechnologiesThis paper presents the recent technical research survey on the efficient live migration of virtual machines. Virtual machine migration is required for many reasons like load balancing, energy reduction, dynamic resizing, and to increase availability. ...
Comments