Rob Gardner

Hewlett-Packard, Palo Alto, California, United States

Are you Rob Gardner?

Claim your profile

Publications (4)0 Total impact

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a high level overview of a virtual machine placement system in which an autonomic controller dynamically manages the mapping of virtual machines onto physical hosts in accordance with policies specified by the user. By closely monitoring virtual machine activity and employing advanced policies for dynamic workload placement, such an autonomic solution can achieve substantial cost savings from better utilization of computing resources and less frequent overload situations. Abstract We present a high level overview of a virtual machine placement system in which an autonomic controller dynamically manages the mapping of virtual machines onto physical hosts in accordance with policies specified by the user. By closely monitoring virtual machine activity and employing advanced policies for dynamic workload placement, such an autonomic solution can achieve substantial cost savings from better utilization of computing resources and less frequent overload situations.
    03/2008;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Virtual machines (VMs) have recently emerged as the basis for allo- cating resources in enterprise settings and hosting centers. One benefit of VMs in these environments is the ability to multiplex several operating systems on hardware based on dynamically changing system characteristics. However, such multiplexing must often be done while observing per-VM performance guaran- tees or service level agreements. Thus, one important requirement in this envi- ronment is effective performance isolation among VMs. In this paper, we address performance isolation across virtual machines in Xen (1). For instance, while Xen can allocate fixed shares of CPU among competing VMs, it does not curr ently account for work done on behalf of individual VMs in device drivers. Thus, the behavior of one VM can negatively impact resources available to other VMs even if appropriate per-VM resource limits are in place. In this paper, we present the design and evaluation of a set of primitives im- plemented in Xen to address this issue. First, XenMon accurately measures per- VM resource consumption, including work done on behalf of a particular VM in Xen's driver domains. Next, our SEDF-DC scheduler accounts for aggregate VM resource consumption in allocating CPU. Finally, ShareGuard limits the total amount of resources consumed in privileged and driver domains based on administrator-specified limits. Our performance evaluation indicates that o ur mech- anisms effectively enforce performance isolation for a variety of workloads and configurations.
    Middleware 2006, ACM/IFIP/USENIX 7th International Middleware Conference, Melbourne, Australia, November 27-December 1, 2006, Proceedings; 01/2006
  • Source
    Ludmila Cherkasova, Rob Gardner
    [Show abstract] [Hide abstract]
    ABSTRACT: Virtual Machine Monitors (VMMs) are gaining popularity in enterprise environments as a software-based solution for building shared hardware infrastructures via virtualization. In this work, using the Xen VMM, we present a light weight monitoring system for measuring the CPU usage of different virtual machines including the CPU overhead in the device driver domain caused by I/O processing on behalf of a particular virtual machine. Our performance study attempts to quantify and analyze this overhead for a set of I/O intensive workloads.
    Proceedings of the 2005 USENIX Annual Technical Conference, April 10-15, 2005, Anaheim, CA, USA; 01/2005
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The goal of this short paper is twofold: 1) it briefly describes a new performance monitoring tool, XenMon, that we built for the Xen-based virtual environment, and 2) it presents a performance case study that demonstrates and explains how different metrics re- ported by XenMon can be used in gaining insight into an application's performance and its resource usage/requirements, especially in the case of I/O intensive applications.