Funktionen

Print[PRINT]
.  Home  .  Lehre  .  Seminare  .  Sommersemester 2018  .  Hauptseminar virtualisierte Systeme  .  Themen

Im Folgenden finden Sie eine Aufstellung der zur Verfügung stehenden Themen. Die angegebene Literatur versteht sich als Startlektüre und weitere Literatur sollte selbstständig recherchiert wertden.

Introduction

1. Challenges and Opportunities of Virtualization

The gap between the deployment costs for the new services, apps and hosting machines with the expected revenue forces the operators to think in the virtualization concept although the heterogeneity in virtualization techniques solutions. This paper shall present the emerging opportunities corresponding to the FCAPS model, as well as actual and future challenges.
  1. Bouali, Lyes, et al. "Virtualization Techniques: Challenges and Opportunities." International Conference on Mobile, Secure and Programmable Networking. Springer, Cham, 2016. [LINK]
  2. Danciu, Vitalian A. "Host Virtualization: A Taxonomy of Management Challenges." GI Jahrestagung. 2009. [LINK]

Host Vitualization

2. Types of Host-Virtualization

The virtualization layer manages the hardware resources between the different VMs. The guest OS is the OS that is running within a VM. There exist several virtualization techniques for host virtualization, which shall be presented within this paper.
  1. Bouali, Lyes, et al. "Virtualization Techniques: Challenges and Opportunities." International Conference on Mobile, Secure and Programmable Networking. Springer, Cham, 2016. [LINK]
  2. Crosby, Simon, and David Brown. "The virtualization reality." Queue 4.10 (2006): 34-41. [LINK]

3. Hypervisor in HPC

High Performance Computing (HPC) has special needs. Therefore, virtualization technologies need to be applied to its tasks without losing performance. Current virtualization methods exploit a combination of hardware and software mechanisms. This paper should determine the possibilities and challenges of actual approaches.
  1. Kudryavtsev, Alexander, et al. "Virtualizing HPC applications using modern hypervisors." Proceedings of the 2012 workshop on Cloud services, federation, and the 8th open cirrus summit. ACM, 2012. [LINK]
  2. Gavrilovska, Ada, et al. "High-performance hypervisor architectures: Virtualization in hpc systems." Workshop on System-level Virtualization for HPC (HPCVirt). 2007. [LINK]

4. Virtualization of Accelerators

Virtualization can help to efficiently use shared hardware by high performance applications. Unfortunately, virtualization also prevents efficient access to accelerators, such as Graphics Processing Units (GPUs). This paper shall investigate up-to-date solutions and compare their efficiency.
  1. Gupta, Vishakha, et al. "GViM: GPU-accelerated virtual machines." Proceedings of the 3rd ACM Workshop on System-level Virtualization for High Performance Computing. ACM, 2009. [LINK]
  2. Morishima, Shin, Masahiro Okazaki, and Hiroki Matsutani. "A Case for Remote GPUs over 10GbE Network for VR Applications." Proceedings of the 8th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies. ACM, 2017. [LINK]
  3. Xiao, Shucai, et al. "Transparent accelerator migration in a virtualized GPU environment." Proceedings of the 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012). IEEE Computer Society, 2012. [LINK]
  4. Montella, Raffaele, et al. "On the virtualization of CUDA based GPU remoting on ARM and X86 machines in the GVirtuS framework." International Journal of Parallel Programming 45.5 (2017): 1142-1163. [LINK]

5. Nested Virtualization strategies

Nested virtualization, the ability to run a virtual machine inside another virtual machine, is increasingly important. In classical machine virtualization, a hypervisor runs multiple operating systems simultaneously. In nested virtualization, a hypervisor can run multiple other hypervisors with their associated virtual machines. For different architectures different approaches exist. This paper shall present and compare the most promising ones.
  1. Lim, Jin Tack, et al. "NEVE: Nested Virtualization Extensions for ARM." Proceedings of the 26th Symposium on Operating Systems Principles. ACM, 2017. [LINK]
  2. Ben-Yehuda, Muli, et al. "The Turtles Project: Design and Implementation of Nested Virtualization." OSDI. Vol. 10. 2010. [LINK]

6. Memory Ballooning

Minimizing the total amount of physical memory consumption of a set of virtual machines improves the maximum number of VMs that can run on a server without performance degradation. Memory Ballooning, the ability to increase/decrease the memory size of a running VM is fully supported in almost all current versions of hypervisors, to give each VM just enough physical memory needed. This concept should be presented with this paper.
  1. Moltó, Germán, et al. "Elastic memory management of virtualized infrastructures for applications with dynamic memory requirements." Procedia Computer Science 18 (2013): 159-168. [LINK]
  2. Chiang, Jui-Hao, Han-Lin Li, and Tzi-cker Chiueh. "Working Set-based Physical Memory Ballooning." ICAC. 2013. [LINK]

7. Challenges of embedded virtualization in IoT

Embedded virtualization has emerged as a valuable way to reduce costs, improve software quality, and decrease design time. This paper shall present the key features for embedded virtualization and their challenges.
  1. Moratelli, Carlos, et al. "Embedded virtualization for the design of secure IoT applications." Proceedings of the 27th International Symposium on Rapid System Prototyping: Shortening the Path from Specification to Prototype. ACM, 2016. [LINK]
  2. Celesti, Antonio, et al. "Exploring container virtualization in IoT clouds." Smart Computing (SMARTCOMP), 2016 IEEE International Conference on. IEEE, 2016. [LINK]
  3. Moratelli, Carlos, Sergio Johann, and Fabiano Hessel. "Exploring embedded systems virtualization using MIPS virtualization module." Proceedings of the ACM International Conference on Computing Frontiers. ACM, 2016. [LINK]

8. Virtual Machine communication

Computer systems have many components that need to exchange data, but timescales span from nanoseconds for onchip hardware, to hundreds of nanosecond or microseconds for processes or Virtual Machines and their hypervisors, up to milliseconds or more for peripherals with moving parts, or long distance communication. This paper shall investigate efficient possibilities of inter- and intra-VM-communication.
  1. Chen J., Xu S., Zhang H., Wang Z. (2016) A Virtual Machine Data Communication Mechanism on Openstack. In: Zu Q., Hu B. (eds) Human Centered Computing. HCC 2016. Lecture Notes in Computer Science, vol 9567. Springer, Cham [LINK]
  2. Rizzo, Luigi, et al. "A study of speed mismatches between communicating Virtual Machines." Proceedings of the 2016 Symposium on Architectures for Networking and Communications Systems. ACM, 2016. [LINK]
  3. Machado, Rui, and Carsten Lojewski. "The Fraunhofer virtual machine: a communication library and runtime system based on the RDMA model." Computer Science-Research and Development 23.3-4 (2009): 125-132. [LINK]

Storage Virtualization

9. Virtualization of Databases

Flexible and scalable management of data is often realized by database management systems (DMBSs) on virtualized resources. However, there are several techniques to realize a virtualized database. This paper shall present different approaches.
  1. Kiefer, Tim, and Wolfgang Lehner. "Private table database virtualization for dbaas." Utility and Cloud Computing (UCC), 2011 Fourth IEEE International Conference on. IEEE, 2011. [LINK]
  2. Soror, Ahmed A., et al. "Automatic virtual machine configuration for database workloads." ACM Transactions on Database Systems (TODS) 35.1 (2010): 7. [LINK]
  3. Pham, Quan, et al. "LDV: light-weight database virtualization." Data Engineering (ICDE), 2015 IEEE 31st International Conference on. IEEE, 2015. [LINK]

10. Storage Virtualization in SAN

Storage area network (SAN) is a technology to efficiently manage the ever-increasing amount of data. Extending SANs over large distances becomes essential to facilitate data protection and sharing storage resources over large geographic distances. This paper shall introduce SANs and give an overview of actual trends.
  1. Li, Bigang, Jiwu Shu, and Weimin Zheng. "Design and implementation of a storage virtualization system based on SCSI target simulator in SAN." Tsinghua Science & Technology 10.1 (2005): 122-127. [LINK]
  2. Narayan, Ganesh, and K. Gopinath. "iSAN–An Intelligent Storage Area Network Architecture." International Conference on High-Performance Computing. Springer, Berlin, Heidelberg, 2004. [LINK]
  3. El-Gorashi, Taisir EH, and Jaafar MH Elmirghani. "Optical Storage Area Networks." Towards Digital Optical Networks. Springer, Berlin, Heidelberg, 2009. 285-302. [LINK]

Network Virtualization

11. Network virtualization in Software-defined Networks: applications and challenges.

Infrastructure providers are increasingly looking towards network virtualization using SDN to better utilize their networking resources. In particular, network virtualization enabled by SDN allows infrastructure owners to lower the management complexity of their networks, while customizing their tenants’ network to better serve their needs. This paper shall present applications and challenges of SDN.
  1. Jain R, Paul S. Network virtualization and software defined networking for cloud computing: a survey. IEEE Communications Magazine. 2013 Nov;51(11):24-31. [LINK]
  2. Drutskoy D, Keller E, Rexford J. Scalable network virtualization in software-defined networks. IEEE Internet Computing. 2013 Mar;17(2):20-7. [LINK]
  3. Al-Shabibi A, De Leenheer M, Gerola M, Koshibe A, Parulkar G, Salvadori E, Snow B. OpenVirteX: Make your virtual SDNs programmable. InProceedings of the third workshop on Hot topics in software defined networking 2014 Aug 22 (pp. 25-30). ACM. [LINK]
  4. Nunes RV, Pontes RL, Guedes D. Virtualized network isolation using software defined networks. InLocal Computer Networks (LCN), 2013 IEEE 38th Conference on 2013 Oct 21 (pp. 683-686). IEEE. [LINK]

12. Network Function Virtualization: applications and future trends

Network function virtualization was proposed to improve the flexibility of network service provisioning. By leveraging virtualization technologies and commercial off-the-shelf programmable hardware, NFV decouples the software implementation of network functions from the underlying hardware. This paper shall investigate this emerging technology and present future trends.
  1. Han B, Gopalakrishnan V, Ji L, Lee S. Network function virtualization: Challenges and opportunities for innovations. IEEE Communications Magazine. 2015 Feb;53(2):90-7. [LINK]
  2. Mijumbi R, Serrat J, Gorricho JL, Bouten N, De Turck F, Boutaba R. Network function virtualization: State-of-the-art and research challenges. IEEE Communications Surveys & Tutorials. 2016 Jan 1;18(1):236-62. [LINK]
  3. Mehraghdam S, Keller M, Karl H. Specifying and placing chains of virtual network functions. InCloud Networking (CloudNet), 2014 IEEE 3rd International Conference on 2014 Oct 8 (pp. 7-13). IEEE. [LINK]
  4. Ledjiar A, Sampin E, Talhi C, Cheriet M. Network Function Virtualization as a Service for multi-tenant software defined networks. InSoftware Defined Systems (SDS), 2017 Fourth International Conference on 2017 May 8 (pp. 168-173). IEEE. [LINK]

Applications

13. Singularity container in HPC

Singularity is a container solution created by necessity for scientific application driven workloads. This paper shall present its architecture and possibilities for any usage in HPC, for example with MPI.
  1. Kurtzer, Gregory M., Vanessa Sochat, and Michael W. Bauer. "Singularity: Scientific containers for mobility of compute." PloS one 12.5 (2017): e0177459. [LINK]
  2. Zhang, Jie, Xiaoyi Lu, and Dhabaleswar K. Panda. "Is Singularity-based Container Technology Ready for Running MPI Applications on HPC Clouds?." Proceedings of the10th International Conference on Utility and Cloud Computing. ACM, 2017. [LINK]

14. Classical Virtualization on x86 and ARM Architecture

The x86 and ARM architecture have not supported classical virtualization by Design. Therefore, architectural extensions to support virtualization were introduced. This paper shall describe the actual virtualization possibilities of both and compare them.
  1. Bugnion, Edouard, et al. "Bringing virtualization to the x86 architecture with the original vmware workstation." ACM Transactions on Computer Systems (TOCS) 30.4 (2012): 12. [LINK]
  2. Varanasi, Prashant, and Gernot Heiser. "Hardware-supported virtualization on ARM." Proceedings of the Second Asia-Pacific Workshop on Systems. ACM, 2011. [LINK]
  3. Vasudevan, Amit, et al. "Requirements for an integrity-protected hypervisor on the x86 hardware virtualized architecture." International Conference on Trust and Trustworthy Computing. Springer, Berlin, Heidelberg, 2010. [LINK]

15. Docker containers in dynamic, heterogeneous environments

Docker containers are gaining wide traction due to the fact that they allow deploying applications in any environment faster and more efficiently than using virtual machines. However, Docker-based container deployment solutions are aimed at managing containers in a single-site, which limits their capabilities. This paper shall investigate current possibilities of the usage of Docker-container in dynamic, heterogeneous environments.
  1. Chen, Yi-Wei, et al. "Virtual Hadoop: MapReduce over Docker Containers with an Auto-Scaling Mechanism for Heterogeneous Environments." Proceedings of the International Conference on Research in Adaptive and Convergent Systems. ACM, 2016. [LINK]
  2. Abdelbaky, Moustafa, et al. "Docker containers across multiple clouds and data centers." Utility and Cloud Computing (UCC), 2015 IEEE/ACM 8th International Conference on. IEEE, 2015. [LINK]

16. OpenStack services enabling modern Cloud Computing

The OpenStack project is an open source cloud computing platform for all types of clouds. OpenStack provides an Infrastructure-as-a-Service (IaaS) solution through a set of interrelated services. Each service offers an API that facilitates this integration. This paper shall give an overview of these services and evaluate their possibilities to modern cloud computing.
  1. OpenStack Documentation: Conceptual architecture [LINK]
  2. Rosado, Tiago, and Jorge Bernardino. "An overview of openstack architecture." Proceedings of the 18th International Database Engineering & Applications Symposium. ACM, 2014. [LINK]

17. Windows Subsystem for Linux

The Windows Subsystem for Linux (WSL) is a new Windows 10 feature that enables running native Linux command-line tools directly on Windows. This paper shall investigate its architecture and implementation within Windows 10 and evaluate possible missing features of other common Linux virtualizations.
  1. Microsoft Developer: Windows Subsystem for Linux [LINK]
  2. Microsoft Developer: Windows Subsystem for Linux Blog [LINK]

Security

18. Meltdown and Spectre: vulnerabilities on speculative execution of VMs

With the "Meltdown" and "Spectre" vulnerabilities on speculative execution paths within CPUs it is possible to maliciously leverage the speculative execution capabilities of modern CPUs to read memory typically restricted to kernel space. On a single, bare-metal machine, this allows a user space process to access and read kernel space memory. On a machine running as a hypervisor with one or more virtual machines, the situation is more complex. This paper shall present the two vulnerabilities and investigate the threat on virtualized Hosts.
  1. Kocher, Paul, et al. "Spectre Attacks: Exploiting Speculative Execution." arXiv preprint arXiv:1801.01203 (2018). [LINK]
  2. Lipp, Moritz, et al. "Meltdown." arXiv preprint arXiv:1801.01207 (2018). [LINK]
  3. Horn, Jann. "Reading privileged memory with a side-channel." (2018). [LINK]

19. Selected vulnerabilities and exploits of Virtualization

Virtualized computing enables resource utilization among hardware, operating system and software. The virtual machines can be managed user friendly. However, all this flexibility leads to security challenges and possible exploits, which should be investigated in this paper.
  1. Hanqian Wu, Yi Ding, C. Winer and Li Yao, "Network security for virtual machine in cloud computing," 5th International Conference on Computer Sciences and Convergence Information Technology, Seoul, 2010, pp. 18-21. [LINK]
  2. Joao Carlos Carvalho dos Santos Ramos. "SECURITY CHALLENGES WITH VIRTUALIZATION". (2009) [LINK]