Scalability of VM provisioning systems

@article{Jones2016ScalabilityOV,
  title={Scalability of VM provisioning systems},
  author={Mike Jones and Bill Arcand and Bill Bergeron and David Bestor and Chansup Byun and Lauren Milechin and Vijay N. Gadepally and Matthew Hubbell and Jeremy Kepner and Peter Michaleas and Julie Mullen and Andrew Prout and Tony Rosa and Siddharth Samsi and Charles Yee and A. Reuther},
  journal={2016 IEEE High Performance Extreme Computing Conference (HPEC)},
  year={2016},
  pages={1-5}
}
Virtual machines and virtualized hardware have been around for over half a century. [] Key Method The startup performance overhead of three of the most mature, widely deployed cloud management frameworks (OpenStack, OpenNebula, and Eucalyptus) is measured to determine their suitability for workloads typically seen in an HPC environment. A 10x performance difference is observed between the fastest (Eucalyptus) and the slowest (OpenNebula) framework. This time difference is primarily due to delays in waiting…

Figures and Tables from this paper

A Performance Survey of Lightweight Virtualization Techniques
TLDR
This work provides a comprehensive performance comparison covering containers, unikernels, whole-system virtualization, native hardware, and combinations thereof, representing common workloads in microservice-based applications.
Resource-sharing Policy in Multi-tenant Scientific Workflow as a Service Platform
TLDR
An Elastic Budget-constrained resource Provisioning and Scheduling algorithm for Multiple workflows that can reduce the computational overhead by encouraging resource sharing to minimize workflows' makespan while meeting a user-defined budget is proposed.
Topology-Aware Prediction of Virtual Network Function Resource Requirements
TLDR
This paper proposes a graph neural network-based algorithm which exploits VNF forwarding graph topology information to predict future resource requirements for each VNF component (VNFC).
Best of Both Worlds: High Performance Interactive and Batch Launching
TLDR
A novel preemptive approach to implement “spot” jobs on MIT SuperCloud systems allowing the resources to be fully utilized for both long running batch jobs while still providing fast launch for interactive jobs.
Interactive Launch of 16,000 Microsoft Windows Instances on a Supercomputer
TLDR
This paper describes a unique approach using the Lincoln Laboratory LLMapReduce technology in combination with the Wine Windows compatibility layer to rapidly and simultaneously launch and run Microsoft Windows applications on thousands of cores on a supercomputer.
Node-Based Job Scheduling for Large Scale Simulations of Short Running Jobs
TLDR
This paper presents a novel node-based scheduling approach for large scale simulations of short running jobs on MIT SuperCloud systems, that allows the resources to be fully utilized for both long running batch jobs while simultaneously providing fast launch and release of large-scale shortRunning jobs.
3D Real-Time Supercomputer Monitoring
TLDR
This system allows operators to quickly assess how the supercomputer is being used, gives users visibility into the resources they are consuming, and provides instructors new ways to interactively teach the computing architecture concepts necessary for efficient computing.
The technique of locking memory on Linux operating system - Application in checkpointing
TLDR
This paper aims to present two main memory lock techniques working in both kernel and user space and a performance comparison when applying them in checkpointing for the Checkpointing Aided Parallel Execution (CAPE).
Multiple Workflows Scheduling in Multi-tenant Distributed Systems
TLDR
A detailed taxonomy and a comprehensive survey of the current literature are presented and future directions to foster research in the field of multiple workflow scheduling in multi-tenant distributed computing systems are identified.
Lessons Learned from a Decade of Providing Interactive, On-Demand High Performance Computing to Scientists and Engineers
TLDR
An overview of current needs and the technical solutions the MIT Lincoln Laboratory is building to lower the barrier to entry for new users from the humanities, social, and biological sciences are presented.
...
1
2
...

References

SHOWING 1-10 OF 25 REFERENCES
HPC-VMs: Virtual machines in high performance computing systems
TLDR
This paper analyzes the effectiveness of using virtual machines in a high performance computing (HPC) environment, and proposes adding some virtual machine capability to already robust HPC environments for specific scenarios where the productivity gained outweighs the performance lost for usingvirtual machines.
Xen and the art of virtualization
TLDR
Xen, an x86 virtual machine monitor which allows multiple commodity operating systems to share conventional hardware in a safe and resource managed fashion, but without sacrificing either performance or functionality, considerably outperform competing commercial and freely available solutions.
A comparison of software and hardware techniques for x86 virtualization
TLDR
It is found that the hardware support for Virtual Machine Monitors for x86 fails to provide an unambiguous performance advantage for two primary reasons: first, it offers no support for MMU virtualization; second, it fails to co-exist with existing software techniques for MM U virtualization.
Managing Performance Overhead of Virtual Machines in Cloud Computing: A Survey, State of the Art, and Future Directions
TLDR
The causes of VM performance overhead are unveiled by illustrating representative scenarios, the performance modeling methods with a particular focus on their accuracy and cost are discussed, and the overhead mitigation techniques are compared by identifying their effectiveness and implementation complexity.
Evaluation of the HPC Challenge Benchmarks in Virtualized Environments
TLDR
The HPC Challenge benchmarks had some overhead in all the virtual environments, with the overhead becoming less significant with larger problem sizes, and the RandomAccess results show drastically different behavior and the cause of variability of performance results is shown.
The Eucalyptus Open-Source Cloud-Computing System
TLDR
This work presents Eucalyptus -- an open-source software framework for cloud computing that implements what is commonly referred to as Infrastructure as a Service (IaaS); systems that give users the ability to run and control entire virtual machine instances deployed across a variety physical resources.
kvm : the Linux Virtual Machine Monitor
TLDR
The Kernel-based Virtual Machine, or kvm, is a new Linux subsystem which leverages virtualization extensions to add a virtual machine monitor (or hypervisor) capability to Linux.
Enabling on-demand database computing with MIT SuperCloud database management system
TLDR
The MIT SuperCloud database management system allows for rapid creation and flexible execution of a variety of the latest scientific databases, including Apache Accumulo and SciDB, and permits snapshotting of databases to allow researchers to experiment and push the limits of the technology without concerns for data or productivity loss.
Introduction and overview of the multics system
TLDR
Multics (Multiplexed Information and Computing Service) is a comprehensive, general-purpose programming system which is being developed as a research project and will be implemented on the GE 645 computer.
QEMU, a Fast and Portable Dynamic Translator
  • Fabrice Bellard
  • Computer Science
    USENIX Annual Technical Conference, FREENIX Track
  • 2005
TLDR
QEMU supports full system emulation in which a complete and unmodified operating system is run in a virtual machine and Linux user mode emulation where a Linux process compiled for one target CPU can be run on another CPU.
...
1
2
3
...