archive-com.com » COM » X » XENSOURCE.COM

Total: 333

Choose link from "Titles, links and description words view":

Or switch to "Titles and links view".
  • Xen Summit
    and Apache CloudStack Apache CloudStack has already proven its abilities to scale to tens of thousands of physical XenServer nodes but a number of traditional networking schemes don t work VLANs max out at 4096 Layer3 isolation aka Security Groups helps scale to a degree but you lose a lot of flexibility in the process XCP and XS6 0 have the ability to make use of openvswitch to build software

    Original URL path: http://xen.xensource.com/xensummit/xs12na_talks/T6b.html (2016-02-13)
    Open archived version from archive


  • Xen Summit
    power consumption optimization inside the cluster and host maintenance etc Being able to do VM live migration as quickly as possible with no service interruption is regarded as a key competitiveness of the virtualization platform Xen has supported live migration for many years However our recent study shows that Xen still has lots of room to improve in the aspects of live migration elapsed time service downtime and concurrency instance number Several experimental enhancements have been added and the initial result looks pretty good For instance merely using memory comparison before migration can speed up the elapsed time by 2X in some cases per our evaluation The policy to balance the CPU utilization and the compression ratio is also considered Xiaowei Yang Huawei Xiaowei is an architect of Huawei Virtualzation Platform He is responsible for the technical development of virutalization projects He started working on opensource Xen project in 2005 Xiaowei has extensive background in processor architectures and operating system internals Prior to joining Huawei Xiaowei worked for Intel Open Source Tech Center for more than 6 years Xiaowei received his Master degree of CS from Shanghai Jiatong University Tao Hong Huawei Tao is an architect of Huawei Virtualzation Platform

    Original URL path: http://xen.xensource.com/xensummit/xs12na_talks/T7.html (2016-02-13)
    Open archived version from archive

  • Xen Summit
    scalability of the cloud environment since bottlenecks can quickly develop along the centralized I O point as the number of hypervisor nodes scales out In this session Julian Chesterfield former XenServer storage architect and current OnApp Storage and Virtualization Architect will advocate the deployment of a new cloud scale approach to storage Through decentralized storage management and exposure of direct attached storage located within hypervisors a dynamic and scalable distributed block store can be composed As the number of hosting end points scales up to accommodate the virtualization workload demand so too can the storage capacity and I O processing capacity Using a distributed block storage approach in the cloud companies and service providers can decentralize their I O paths to avoid any points of contention or I O bottlenecks By distributing them over the entire platform each I O path is independently optimized to deliver far greater performance and scalability the same scalability one would expect to accompany an open Xen based hypervisor platform What s more the latest cloud storage innovations allow this distributed approach to be implemented using commodity Ethernet and storage hardware thereby creating an inherently scalable and cost effective approach to storage in the cloud with a far more consistent level of performance over vast ranges in the number of end points Such a decentralized distributed storage approach is especially valuable for service providers who typically start out with a small number of servers and then often find themselves quickly scaling up as their user base grows With traditional storage solutions requirements for such rapid scalability cannot be met or easily provisioned for as it s very difficult to predict growth or demand A distributed block storage model however can easily accommodate the scalability such providers need as they grow their business This session will

    Original URL path: http://xen.xensource.com/xensummit/xs12na_talks/T7b.html (2016-02-13)
    Open archived version from archive

  • Xen Summit
    of discussions You can find presentations on slideshare and videos on vimeo We will also embedded both in the agenda The slides are also available for download as zip file Hybrid Future of PV PV guest in HVM container is needed for 64bit performance The system call overhead is eliminated when running in HVM container as the kernel can run in ring 0 Mukesh Rathor Oracle Download original News Press

    Original URL path: http://xen.xensource.com/xensummit/xs12na_talks/M9.html (2016-02-13)
    Open archived version from archive

  • Xen Summit
    The slides are also available for download as zip file Evaluation of X32 ABI for Virtualization and Cloud As the Linux 3 4 has x32 ABI support we think it s the right time for us to evaluate x32 ABI for virtualization and the cloud The x32 ABI provides a model in x86 64 psABI with 32 bit address space with 16 64 bit integer registers 8 additional integer registers 8 additional SSE registers etc compared to the conventional x86 32 bit ABI We look at performance improvements and memory saving gained by x32 applications and discuss how x32 can be helpful for Xen and the clouds Jun Nakajima Principal Engineer Intel Jun Nakajima is a Principal Engineer leading open source virtualization projects such as Xen and KVM at the Intel Open Source Technology Center He is recognized as one of the key contributors to Xen and he presented a number of times at technical conferences including Xen Summit OLS KVM Forum and USENIX He has over 20 years of experience with operating system internals and an extensive background in processor architectures Prior to joining Intel he worked on various projects in the industry such as AT T USL Unix

    Original URL path: http://xen.xensource.com/xensummit/xs12na_talks/T8b.html (2016-02-13)
    Open archived version from archive

  • Xen Summit
    case of Xen Having to deal with NUMA machines is becoming more and more common and will likely continue to do so Running typical virtualization workloads on such systems is particularly challenging as Virtual Machines VMs are long lived processes with large memory footprints This means one might incur really bad performance if the specific characteristics of the platform are not properly accounted for Extensive benchmarks are being performed running memory intensive workloads inside Linux VMs hosted on NUMA hardware of different kinds and size This is driving the design and development of a suite of new VM placement scheduling and memory allocation policies for the Xen hypervisor and its toolstack The subset of such changes that has been implemented so far is already proving to be effective in yielding performance improvements and the talk will illustrate these early results It will also offer the chance for the Xen community to discuss about all the various aspects of this challenging problem and of drawing a roadmap for how to put together the best NUMA support ever Dario Faggioli Citrix Dario Faggioli has interacted with the Linux kernel community in the domain of scheduling during his PhD on real time systems

    Original URL path: http://xen.xensource.com/xensummit/xs12na_talks/T9.html (2016-02-13)
    Open archived version from archive

  • Xen Summit
    as zip file Block Storage For VMs With Ceph Ceph is an open source distributed object store network block device and file system What began as a research project at the University of California Santa Cruz has become an increasingly viable option for scalable cloud storage Ceph can be used for object storage through its S3 compatible REST interface It can also provide storage for network block devices with the thin provisioning and copy on write cloning features necessary to support large scale virtualization This talk will begin with a brief overview of Ceph s architecture and a review of its current status and future plans Then it will conclude with a discussion about the current state of interoperability between Xen and Ceph the possible approaches that can be taken to enrich it and ways the Xen community can participate Sage Weil Chief Architect Inktank Sage Weil is the creator of Ceph Sage originally designed Ceph as part of his PhD research in Storage Systems at the University of California Santa Cruz Since graduating he has continued to refine the system with the goal of providing a stable next generation distributed storage system for Linux Sage is a co founder

    Original URL path: http://xen.xensource.com/xensummit/xs12na_talks/T9b.html (2016-02-13)
    Open archived version from archive

  • Xen Summit
    we review the existing hardware features that are not used by Xen today showing examples for use cases 1 For example The descriptor table exiting should be useful for the guest kernels or security agent to enhance security features 2 The VMX preemption timer allows the hypervisor to preempt guest VM execution after a specified amount of time which is useful to implement fair scheduling The hardware can save the timer value on each successive VMexit after setting the initial VM quantum 3 VMFUNC is an operation provided by the processor that can be invoked from VMX non root operation without a VM exit Today EPTP switching is available and we discuss how we can use the feature Second we talk about new hardware features especially for interrupt optimizations Jun Nakajima Principal Engineer Intel Jun Nakajima is a Principal Engineer leading open source virtualization projects such as Xen and KVM at the Intel Open Source Technology Center He is recognized as one of the key contributors to Xen and he presented a number of times at technical conferences including Xen Summit OLS KVM Forum and USENIX He has over 20 years of experience with operating system internals and an extensive

    Original URL path: http://xen.xensource.com/xensummit/xs12na_talks/T10.html (2016-02-13)
    Open archived version from archive



  •