LinuxCon Japan is the premiere Linux conference in Asia that brings together a unique blend of core developers, administrators, users, community managers and industry experts.
CloudOpen Japan is a conference celebrating and exploring the open source projects, technologies and companies who make up the cloud. It’s built on a belief that open works: for users, for industry and for technology.
KVM has brought Linux to the forefront of data center virtualization and cloud computing. The KVM project evolves rapidly to meet the challenges of these computing environments. Come learn about the advances KVM has made over the past year, and what new developments are on the horizon for KVM. The session will discuss the major new developments in KVM/QEMU in the last year, and in particular those targeting data centers and cloud management.The audience should be familiar with server virtualization technology, general data center and cloud computing concepts.
Nested Virtualization was once considered as a research project, but we are seeing real demands for it, even in the cloud. Without nested virtualization, hardware virtualization is not enabled in the cloud. As Linux is required to run in virtualization as the default deployment for IT and the cloud, the virtualization feature such as KVM or Xen is required to be available and optimized in guests as well. For example, the Android emulator wouldnât provide practical performance on a Linux VM without nested virtualization. In this talk, we discuss use cases, characteristics of nested virtualization, and optimizations using new hardware virtualization features, such as
"VMCS shadowing".
The expected audience is developers interested in new technologies for virtualization and the cloud. They will learn about use cases, latest status, and how nested virtualization is becoming real.
Linux container(LXC) is known as one of the operating system level virtualization solution, who has better performance because all the Guests share the same kernel with Host, using namespace to isolate each Guest. People can use LXC to implement application containers and operation system containers. An application container provides a partial virtualization. An operating system container provides the whole virtualization. In this topic, the LXC related technologies, such as namespace and related API will be introduced, and the main contribution of Fujitsu and the problems and challenges we are facing. Audience: All the LXC developers, users, and whoever is interested in LXC.
In a virtualization system, problems like I/O and scheduling delay sometimes occur on guests because those operations of guests and the host will compete by sharing I/O devices or CPU cores. But if you just look into only guest's trace data, it will be difficult to analyze the problems. So, we are developing "Integrated trace" system which allows us to analyze trace data of all guests and a host by merging data in chronological order. Our proposal is to use TSC for merging and the concept was reviewed by the community, and we found that there are two problems: TSC offset changing and difference of TSC between multiple CPUs.
In this presentation, we report current status of Integrated trace, share the problems using TSC in detail, and explain how to approach for that. This presentation will be a help for troubleshooting on virtualized mission-critical systems or cloud systems.
In virtual environment, many guests are running on one hypervisor and reliability of KVM hypervisor is really important. One of the key features is "hardware error handling." In order to minimize area of influence when hardware error, such as Machine Check, is detected, isolating hardware with a failure, shutting down only affected guest, are required. As for hardware error handling of Linux, there are three key features: pre-failure detection, failure isolation, continuity after isolation. These features are generally implemented in upstream kernel, however some important issues are still unresolved.
This presentation will show the current implementation of the three key features, detail of unresolved issues, and current activities to solve those issues will be explained. Target audience is kernel developers who are interested in reliability of virtual environment.
On this talk we are going to discuss what has changed on KVM migration since LinuxCon2012.
Migration thread
We discuss the work of moving the execution of outgoing live migration to a separate dedicated thread. Using a separate thread for live migration reduces contention with the IO thread and vcpus: higher throughput and more reliable downtime. Move migration to use synchronous IO.
Block Migration
Now we can migrate storage, independently of how we are handling migration itself.
Migration performance on large guests
What is on the pipeline?
QEMU serves as the core device model for both KVM and Xen making it a solid foundation for the Open Cloud. This talk will focus on the features and function QEMU offers that make Open Virtualization a compelling alternative to proprietary technologies. I will cover the current state of the community and present a roadmap for version 2.0 and beyond.
This talk is intended for virtualization developers and IT professionals evaluating virtualization software. Attendees can expect to learn about the benefits of Open Virtualization, the future roadmap of QEMU, and how to participate in its development.
Network virtualization and software defined networking present new opportunities for data center design. However, they also impose new requirements to fully realize that vision such as greater levels of visibility, remote control, and programmability. Open vSwitch takes advantage of its unique position on the edge of the network to bring together the power and flexibility of software with the rich information available to the hypervisor.
Starting with an overview of the Open vSwitch design and features, the presentation will also cover uses, the broader ecosystem, and future directions.
This tutorial will include:
The target audience should have a background in devops, with a basic working knowledge of Linux and Python. Attendees can expect to walk away with a good grasp of the OpenStack cloud and cloud architectures.
Since last year we have introduced many new features. The biggest one is dropping the Big Libvirt Lock which speeds up domain starting by 200%. Then, we have introduced support for external disk snapshots and block jobs for better control of restoring points. In area of disk locking, our own implementation has been released so users are not locked down with just sanlock. Support for yet another hypervisor has been added. This time it's Parallels Cloud Server. Speaking of drivers, ESX driver has been completely rewritten and gained new functionality. Since last year, we have taught libvirt to utilize qemu guest agent so now it's possible to run some operations from inside the guest. And many other important features that will be more detailed in the talk.
The talk is aimed mostly at developers, especially those working in virtualization.
In 2013, the Xen Hypervisor will be 10 years old: when Xen was designed, we anticipated a world, which now is known as cloud computing. Today, Xen powers the largest clouds in production and is the basis for several commercial virtualization products. In this talk we will give on overview of Xen and related projects, cover hot developments in the Xen community and outline what comes next.
The talk is intended for users and developers that are familiar with virtualization: no deep knowledge is required. We will start with an architectural overview and cover topics such as: Xen and Linux, how to secure your cloud using disaggregation, SELinux and XSM/FLASK, the evolution of Paravirtualization, Xen on ARM and common challenges for open source hypervisors. We will explore the potential of Open Mirage for testing hypervisors. The talk will conclude with an outlook to the future of Xen.
OpenStack is one of the most popular Open Source IaaS infrastructure software. Commercial use of OpenStack is already started including large scale environments. By the large number of developer participation, features of OpenStack is evolving with six month release cycle. Increasing number of features itself is great, but for user's viewpoint, it is necessary to consider compatibility between newer and older version to safely upgrade and continue to operate the cloud infrastructure.
This talk will discuss the compatibility issues such as databases, APIs, configuration files, and possible solutions such as compatibility tests, increasing API test coverage and so on. This talk will be intended for developers/users who are interested in developing and using OpenStack.
Open vSwtich is a multi-layer software switch and MPLS is a mechanism to allow direction of data based on labels which are attached to frames. Although MPLS is conceptually simple at the frame-level, a stack of one or more 4 byte entries inserted into a frame, adding support to Open vSwtich has proved challenging. This presentation will explore those challenges and discuss the approaches that are being taken to address them.
Ryu is an open-sourced network operating system licensed under Apache License v2. The project URL is http://osrg.github.com/ryu/ . Ryu aims to provide logically centralized control and well defined API that makes it easy for cloud operators to implement network management applications on top of the Ryu. Currently, Ryu supports OpenFlow protocol to control the network devices. Ryu plugin for OpenStack was merged into Quantum. You can create tens of thousands of isolated virtual networks without using VLAN. The project goal is to develop an OSS network operating system that has high quality enough for use in large production environment in code qualify/functionality/usability. This talk is intended for cloud operators and developers. Audience
members will learn Ryu desgin and how to manage network with Ryu. We expect that the audience is familiar with network.
OpenStack is the open source cloud platform. The OpenStack community releases a new version every six months, and the OpenStack APIs are increasing version by version. Now OpenStack has hundreds of its API.
In each API, it should be checked out all parameters of API in terms of acceptable types, minimum and maximum length and ranges. However, not all the parameters are completely checked out. By such situation, many API operations run without parameter check.
For this problem, I'd like to propose the API validation framework. The framework requires the definition of all API parameters, and it checks parameters by the definition before each API operation runs. If parameters are invalid, the framework will return errors on unified manner.
The purpose of this talk is to introduce the API validation framework. This talk is targeted for people who is interested in developing OpenStack.
