Lei Cui
ABSTRACT
Virtual machine (VM) snapshot enhances the system availability by saving the running state into stable storage during failure-free execution and rolling back to the snapshot point upon failures. Unfortunately, the snapshot state may be lost due to disk failures, so that the VM fails to be recovered. The popular distributed file systems employ replication technique to tolerate disk failures by placing redundant copies across disperse disks. However, unless user-specific personalization is provided, these systems consider the data in the file as of same importance and create identical copies of the entire file, leading to non-trivial additional storage overhead.
This paper proposes a page-aware replication system (PARS) to store VM snapshots efficiently. PARS employs VM introspection technique to explore how a page is used by guest, and classifies the pages by their importance to system execution. If a page is critical, PARS replicates it multiple copies to ensure high availability and long-term durability. Otherwise, the loss of this page causes no harm for system to work properly, PARS therefore saves only one copy of the page. Consequently, PARS improves storage efficiency without compromising availability. We have implemented PARS to justify its practicality. The experimental results demonstrate that PARS achieves 53.9% space saving compared to the native replication approach in HDFS which replicates the whole snapshot file fully and identically.
- National center for biotechnology information. ftp://ftp.ncbi.nih.gov.Google Scholar
- Elasticsearch. http://www.elasticsearch.org/.Google Scholar
- Hdfs. http://hadoop.apache.org/.Google Scholar
- Mummer. http://mummer.sourceforge.net/.Google Scholar
- Mysql. http://www.mysql.com/.Google Scholar
- Sysbench. http://sysbench.sourceforge.net/.Google Scholar
- Weibo. http://weibo.com.Google Scholar
- libhdfs. http://hadoop.apache.org/docs/r1.2.1/libhdfs.html.Google Scholar
- Salesforce, 1999. http://www.salesforce.com.Google Scholar
- Using the snapshot, 2003. https://www.vmware.com/support/ws4/doc/preserve_snapshot_ws.html.Google Scholar
- readahead, 2005. https://lwn.net/Articles/155510/.Google Scholar
- Amazon ec2, 2006. http://aws.amazon.com/ec2/.Google Scholar
- Superfetch, 2007. http://en.wikipedia.org/wiki/Windows_Vista_I/O_technologies.Google Scholar
- S. Akiyama, T. Hirofuchi, R. Takano, and S. Honiden. Fast wide area live migration with a low overhead through page cache teleportation. In Proceedings of CCGrid, pages 78--82, 2013.Google ScholarDigital Library
- N. Amit, D. Tsafrir, and A. Schuster. Vswapper: A memory swapper for virtualized environments. In Proceedings of ASPLOS, pages 349--366, 2014. Google ScholarDigital Library
- B. Calder, J. Wang, A. Ogus, and N. N. et al. Windows azure storage: A highly available cloud storage service with strong consistency. In Proceedings of SOSP, pages 143--157, 2011. Google ScholarDigital Library
- J.-H. Chiang, H.-L. Li, and T. cker Chiueh. Introspectionbased memory de-duplication and migration. In Proceedings of VEE, pages 51--62, 2013. Google ScholarDigital Library
- M. Christodorescu, R. Sailer, D. L. Schales, D. Sgandurra, and D. Zamboni. Cloud security is not (just) virtualization security: A short paper. In Proceedings of the ACM Workshop on Cloud Computing Security, pages 97--102, 2009. Google ScholarDigital Library
- J. C. Corbett, J. Dean, and M. E. et al. Spanner: Google's globally-distributed database. In Proceedings of OSDI, pages 251--264, 2012. Google ScholarDigital Library
- L. Cui, B. Li, Y. Zhang, and J. Li. Hotsnap: A hot distributed snapshot system for virtual machine cluster. In Proceedings of USENIX LISA, pages 59--73, 2013. Google ScholarDigital Library
- L. Cui, J. Li, B. Li, and et al. Vmscatter: Migrate virtual machines to many hosts. In Proceedings of VEE, pages 63--72, 2013. Google ScholarDigital Library
- U. Deshpande, X. Wang, and K. Gopalan. Live gang migration of virtual machines. In Proceedings of HPDC, pages 135--146, 2011. Google ScholarDigital Library
- C. Dubnicki, L. Gryz, L. Heldt, and M. Kaczmarczyk. Hydrastor: A scalable secondary storage. In Proceedings of FAST, pages 197--210, 2009. Google ScholarDigital Library
- D. Ford, F. Labelle, F. I. Popovici, M. Stokely, V.-A. Truong, L. Barroso, C. Grimes, and S.Quinlan. Availability in globally distributed storage systems. In Proceedings of OSDI, pages 1--14, 2010. Google ScholarDigital Library
- T. Garfinkel and M. Rosenblum. A virtual machine introspection based architecture for intrusion detection. In Proceedings of NDSS, pages 191--206, 2003.Google Scholar
- S. Ghemawat, H. Gobioff, and S.-T. Leung. The google file system. In Proceedings of SOSP, pages 29--43, 2003. Google ScholarDigital Library
- D. Harnik, O. Margalit, D. Naor, D. Sotnikov, and G. Vernik. Estimation of deduplication ratios in large data sets. In Proceedings of MSST, pages 1--11, 2012.Google ScholarCross Ref
- M. Hibler, R. Ricci, L. Stoller, J. Duerig, S. Guruprasad, T. Stack, K. Webb, and J. Lepreau. Large-scale virtualization in the emulab network testbed. In USENIX Annual Technical Conference, pages 113--128, 2008. Google ScholarDigital Library
- X. Jiang and D. Xu. Violin: Virtual internetworking on overlay infrastructure. In Parallel and Distributed Processing and Applications, pages 937--946, 2005. Google ScholarDigital Library
- H. Jin, L. Deng, and S. Wu. Live virtual machine migration with adaptive memory compression. In Proceedings of CLUSTER, pages 1--10, 2009.Google ScholarCross Ref
- S. T. Jones, A. C. Arpaci-Dusseau, and R. H. Arpaci-Dusseau. Geiger: Monitoring the buffer cache in a virtual machine environment. In Proceedings of ASPLOS, pages 14--24, 2006. Google ScholarDigital Library
- A. Kangarlou, P. Eugster, and D. Xu. Vnsnap: Taking snapshots of virtual networked environments with minimal downtime. In Proceedings of DSN, pages 87--98, 2011.Google Scholar
- A. Kivity, Y. Kamay, D. Laor, U. Lublin, and A. Liguori. Kvm: the linux virtual machine monitor. In Proceedings of the Linux Symposium, pages 225--230, 2007.Google Scholar
- J. F. Kloster, J. Kristensen, and A.Mejlholm. Determining the use of interdomain shareable pages using kernel introspection. Technical report, Aalborg University, 2007.Google Scholar
- G. Kola, T. Kosar, and M. Livny. Faults in large distributed systems and what we can do about them. In Proceedings of Euro-Par, pages 442--453, 2005. Google ScholarDigital Library
- R. Kotla, L. Alvisi, and M. Dahlin. Safestore: A durable and practical storage system. In Proceedings of ATC, pages 127--142, 2007. Google ScholarDigital Library
- A. Koto, H. Yamada, K. Ohmura, and K. Kono. Towards unobtrusive vm live migration for cloud computing platforms. In Proceedings of APSys, pages 1--6, 2012. Google ScholarDigital Library
- J. Kubiatowicz, D. Bindel, Y. Chen, and S. C. et al. Oceanstore: An architecture for global-scale persistent storage. In Proceedings of ASPLOS, pages 190--201, 2000. Google ScholarDigital Library
- X. Li, M. Lillibridge, and M. Uysal. Reliability analysis of deduplicated and erasure-coded storage. Proceedings of SIGMETRICS Performance Evaluation Review, 38(3):4--9, 2010. Google ScholarDigital Library
- C. Liu, D. Ju, Y. Gu, Y. Zhang, D. Wang, and D. H. Du. Semantic data de-duplication for archival storage systems. In Proceedings of ACSAC, pages 1--9, 2008.Google ScholarCross Ref
- C. Marshall. Efficient and safe data backup with arrow. Technical report, 2008.Google Scholar
- P. Nath, M. A. Kozuch, D. R. OHallaron, and J. Harkes. Design tradeoffs in applying content addressable storage to enterprise-scale systems based on virtual machines. In Proceedings of ATC, pages 71--84, 2006. Google ScholarDigital Library
- E. Park, B. Egger, and J. Lee. Fast and space-efficient virtual machine checkpointing. In Proceedings of VEE, pages 75--85, 2011. Google ScholarDigital Library
- M. R, Hines, and K. Gopalan. Post-copy based live virtual machine migration using adaptive pre-paging and dynamic self-ballooning. In Proceedings of VEE, pages 51--60, 2009. Google ScholarDigital Library
- R. Rodrigues and B. Liskov. High availability in dht erasureerasure code vs replication. In Proceedings of IPTPS, pages 226--239, 2005. Google ScholarDigital Library
- B. Schroeder and G. A. Gibson. Understanding failures in petascale computers. Journal of Physics, 78:1--11, 2007.Google ScholarCross Ref
- B. Schroeder and G. A. Gibson. Disk failures in the real world what does an mttf of 1,000,000 hours mean to you. In Proceedings of FAST, pages 1--16, 2007. Google ScholarDigital Library
- P. Stuedi, B.Metzler, and A. Trivedi. jverbs: Ultra-low latency for data center applications. In Proceedings of ACM SoCC, 2013. Google ScholarDigital Library
- M. H. Sun and D. M. Blough. Fast, lightweight virtual machine checkpointing. Technical report, 2010.Google Scholar
- Y. Xu, M. Bailey, B. Noble, and F. Jahanian. Small is better: Avoiding latency traps in virtualized data. In Proceedings of ACM SoCC, 2013. Google ScholarDigital Library
- L. L. You, K. T. Pollack, and D. D. E. Long. Deep store: An archival storage system architecture. In Proceedings of ICDE, pages 804--815, 2005. Google ScholarDigital Library
- I. Zhang, A. Garthwaite, Y. Baskakov, and K. C. Barr. Fast restore of checkpointed memory using working set estimation. In Proceedings of VEE, pages 534--533, 2009. Google ScholarDigital Library
- I. Zhang, T. Denniston, Y. Baskakov, and A. Garthwaite. Optimizing vm checkpointing for restore performance in VMware esxi. In Proceedings of USENIX ATC, pages 1--12, 2013. Google ScholarDigital Library
- W. Zhang, H. Tang, H. Jiang, T. Yang, X. Li, and Y. Zeng. Multi-level selective deduplication for vm snapshots in cloud storage. In Proceedings of Cloud, pages 550--557, 2012. Google ScholarDigital Library
- B. Zhu, K. Li, and H. Patterson. Avoiding the disk bottleneck in the data domain deduplication file system. In Proceedings of FAST, pages 1--14, 2008. Google ScholarDigital Library
Index Terms
- PARS: A Page-Aware Replication System for Efficiently Storing Virtual Machine Snapshots
Recommendations
PARS: A Page-Aware Replication System for Efficiently Storing Virtual Machine Snapshots
VEE '15Virtual machine (VM) snapshot enhances the system availability by saving the running state into stable storage during failure-free execution and rolling back to the snapshot point upon failures. Unfortunately, the snapshot state may be lost due to disk ...
Introspection-Based Memory Pruning for Live VM Migration
Virtual Machine (VM) migration is an appealing technique on nowadays cloud platforms to achieve high availability, load balancing and power saving. Unfortunately, migration of VM involves transferring a large amount of data, thereby imposing high ...
Consistent and automatic replica regeneration
Reducing management costs and improving the availability of large-scale distributed systems require automatic replica regeneration, that is, creating new replicas in response to replica failures. A major challenge to regeneration is maintaining ...
Comments