Icehouse, the 9th release of OpenStack, is out! Thanks to the 1200+ contributors. OpenStack Icehouse
October 15, 16, 17, 18
Thanks for attending! The OpenStack Summit was a four-day conference for developers, users, and administrators of OpenStack Cloud Software.
Zorawar 'Biri' Singh
Enterprises have been steadily embracing private cloud environments and are increasingly finding use cases for the public cloud. We are past the point of the cloud being limited to shadow IT and startups. We are now entering the next wave of innovation and adoption which will drive the migration of production workloads to a cloud model and will require seamless public to private interoperability.
This move will create a greater demand for cloud platforms that provide innovative, open services in a secure environment, backed by business level SLAs, and supported by quality service. Adopting a hybrid delivery model to ensure flexibility and scale will no longer be an option but rather a necessity.
Zorawar 'Biri' Singh, SVP & GM, HP Cloud Services, will share how HP's customers are currently taking advantage of this hybrid delivery capability through HP's Converged Cloud vision and strategy. He'll discuss the untapped opportunities and benefits to moving production workloads to the cloud and the potential for OpenStack to lead this next wave of adoption.
WebEx is a leader in on-demand collaboration and the second largest vendor of SaaS for business applications in the world. Earlier this year, the company placed a strategic bet on OpenStack to build a private cloud platform for many of its mission-critical apps. In collaboration with Mirantis, WebEx was able to successfully traverse the implementation path and is currently onboarding a number of production workloads onto its OpenStack cloud. In this talk, WebEx will share more about the project, rationale behind choosing OpenStack, some of the key road-blocks on the path to production and touch upon the future roadmap.
DreamHost is launching several public cloud offerings, and along the way
we have learned a lot of information. The goal of this talk is to share
some of the lessons, tips, and tricks we have learned while designing
public cloud architectures.
Talk Outline and Notes:
The problems: Scale, Speed, Monitoring, Uptime, Security, Cost.
The domains: Networking, Storage, Hypervisors.
Scale: The pervasive problem. There are obvious issues (Data Center
Size, Network Switching Architecture, etc), but there are also the
not-so-obvious problems: DNS zone sizes and rebuild times, ARP/ND table
sizes, growing beyond Ethernet VLANs, and multiplication factor on small
delays. IPv6 is a requirement, not a nice to have, because we're out of
Speed: Disk I/O, Memory I/O, Network I/O, and CPU time all matter.
Performance cannot be cloud washed any longer. Beyond the user focused
problems there are pressing concerns inside the provider as well: how
fast can you expand? Automation is a requirement here that may cause
some initial delays will pay off long term.
Monitoring: Start with simple service monitoring via Nagios, then go
deeper. Agents on every everything. "Graph all the things"" (we use
Uptime: Decouple everything. Have multiple paths. Maintenance windows
are a thing of the past. HA is no longer an option
In a little over two years, OpenStack has shattered adoption benchmarks set by previous open source projects and gained acceptance as the future of the data center but has your career kept up with its blistering pace? Come join Niki Acosta, Cloud Evangelist at Rackspace in an engaging panel session to learn about the career paths of OpenStack heavyweights and how you can accelerate your career with OpenStack. Panelists will include John Purrier, CTO at AppFog; Gretchen Curtis, Co-Founder and Chief Strategy Officer at Piston Cloud Computing; Mike Metral, formerly of Sandia Labs and current Enterprise Architect at Rackspace; and John Dickinson, Director of Technology at SwiftStack and PTL for OpenStack Swift.
Did you know that VMware is a top-10 code and bugfix contributor to OpenStack and that VMware has helped customers with Openstack production deployments? In this session, learn howcustomers are using OpenStack with VMware offerings like ESX, CloudFoundry and RabbitMQ. Walk away with a better understanding of VMwares plans with OpenStack and the software-defined data center as well as VMwares efforts around expanding Niciras contributions to Quantum and Open vSwitch.
Randy Bias, Dan Sneddon
While traditional HA and clustering techniques work for many cases, they are also frequently at the root of catastrophic failures. In this presentation we will cover other well understood and proven approaches to providing greater uptime. Load balancing and service distribution patterns provide an alternative that allows for better horizontal scaling, greater aggregate throughput, and have failure characteristics that reduce the chance of cascading failures. In addition, these alternative approaches are typically simpler to implement and have fewer moving parts, which means they are less prone to failures and have significantly less operational overhead. In this session we'll discuss general principles around using equal-cost multi-pathing (ECMP) for IP flow load balancing, using routing protocols judiciously for managing ECMP flows, and show what happens in various failure conditions and how this is different from traditional load balancers, HA pairs, or clustering.
Rackspaces Enterprise Business Intelligence group (EBI) was seeking a way to move away from their current Data Warehouse solution. They were looking for a cost effective way to scale out new infrastructure in order to meet the increasing business demands of users, house increasing amounts of data, and customize the collection of data. For this, they utilized Hadoop, Cassandra and PostgreSQL with an OpenStack cloud and build the Analytical Compute Grid (ACG).
Analytical Compute Grid(ACG) is solution that enables Rackspace to:
The team selected OpenStack to be the heart of the Analytic Compute Grid for the following reasons:
OpenStack allow us to configure images with different data stores:
As the result, ACG enables users to select optimal data store for information collected. ACG provides SQL like syntax for data retrieval via standard JDBC interface regardless of the underlying data store type.
Come hear about how Rackspace is using OpenStack to help manage it's data.
Startups and enterprises alike have placed their strategic bets to monetize the OpenStack wave in various ways. As an ecosystem insider and board memeber of the OpenStack Foundation, in his talk, Boris Renski will offer his views on how various organizations in the OpenStack ecosystem are trying to monetize it today. He will also share his perspective on what works and what doesnt, based on his experience helping grow Mirantis OpenStack business to 60+ people in just under 18 months.
Everyone loves it when things are fast, and that statement holds true whether you're visiting http://www.livingsocial.com or whether you're hitting the OpenStack Nova API and requesting, "Please show me all the instances which I've got running"". Nobody ever writes in asking for support and saying
With the rapid growth of Sina Weibo, which now has over 350 million registered users around the world, and its affiliated services such as Weibo open API and the WeiGame platform which are now the most popular social and online gaming platform in China, we needed a robust and flexible infrastructure to host those applications and platforms.
In the early 2011, we initiated Sina Web Services (SWS), the first public IaaS cloud based on OpenStack in China. Thanks to the extensible architecture of OpenStack and the help of the OpenStack community, we were able to build up our IaaS platform and push it into production in a very short time.
We have accumulated much experience over 1.5 years of developing and operating an OpenStack public cloud. Since OpenStack now is far away from a 'turnkey' solution, in order to put it to production use, we must develop some necessary services in addition to the current projects of OpenStack. In this presentation, I will dive into the actual deployment and network topology of our production environment. I will also share about the extensions that we have made to OpenStack, such as Keystone integration to our existing identity system, OpenStack security enhancement, Swift performance optimization. I will also make public the design and architecture of our own service, such as LBaaS implementation; user & admin console, whose UI and underlying components are designed by ourselves that is now completely different from Horizon; Dough and Kanyun, which are now community project addressing metering and billing issue of OpenStack.
Regarding the operation of OpenStack, I will also talk about how we manage the internal branch and official code base of OpenStack, and how we build our CI system to archive highly automatic operation.
Sanjiva Nath, Stefano Maffulli
The OpenStack project consists of dozens of sub-projects and each of those are managed via a number of email lists and forums as well as software engineering tools such as issue trackers, version control, continuous integration, etc. Achieving a coherent view of all the information is tedious and immensely difficult. In this session, you will learn how the OpenStack Community team is piloting the Wikidsmart platform from zAgile to integrate information across different systems for a unified view in real-time dashboards. Instant questions can now be answered with faceted search of concepts across all the different repositories. And people and artifacts can be traced across different repositories in order to reconcile people and corresponding contributions.
Ken Pepple, Gavin Pratt, Dan Mihai Dumitriu, Mike Cohen
With the Nicira acquisition, the spotlight is on network virtualization. The Folsom release will introduce OpenStacks networking component for the first time. And indeed, networking may turn out to be the most strategic component in OpenStack, and the key to realizing a vision of the software-defined data center. Its a big opportunity and in addition to Nicira, there are many start-ups already tackling the challenges to network virtualization. This panel will include representatives from a few of these companies: Midokura, BigSwitch and 1-2 others, in a space that is quickly becoming more strategic to OpenStack success. Topics will include VMwares acquisition of Nicira, estimated market opportunity for network virtualization (or SDN), realities of enterprise adoption, challenges to standard OpenStack networking (automation, scale, security etc.) and different technical approaches. The panel will conclude with predictions from the panel and an interactive Q&A with the audience.
The default Nova configuration works well for many use cases, but there are a myriad of options (many underused) that can help Nova better suit your needs. This talk will discuss some of these options, with a focus on new options in Folsom.
Novas configuration options:
At the beginning of 2012, eBay decided to overhaul its technology platform to support an increased focus on rapid innovation, and developer efficiency. To support this effort we built a developer cloud as an extension to our production cloud to give developers maximum flexibility and freedom while protecting business critical infrastructure.
This talk will present the challenges of designing a network infrastructure for both scale, and isolation, and how by using Software Defined Networks we were able to accommodate these two dimensions. We will also go through the automation aspects, presenting how the combination of openstack and quantum, allowed the rapid deployment of our developer cloud.
Sean Roberts, Kamesh Pemmaraju
Openstack has started what will be a complete rebuild of the enterprise data center. It will take time and wont be a straight path but this shift represents one of the most fundamental changes to enterprise infrastructure. Many existing companies will adapt and thrive - many more will fail. The massive disruption in the enterprise IT market will create enormous opportunities for startups in the years ahead. My talk will go over some of my observations as a venture investor and why this is the time to think about openstack as a foundation for your startup.
The default Essex Nova scheduler is slow when it comes to scheduling multiple VMs. Taking about 26 seconds to schedule 100 VMs in our lab environment. This talk will cover the process we took to identify the bottlenecks in the scheduler, in both the Essex and Folsom schedulers. Covering:
CERN, the European Laboratory for particle physics, supports over 10,000 scientists world wide in their quest to find out what the Universe is made of and how it works. As part of a multi-year project to modernise and streamline its tools and processes, CERN is using OpenStack and other leading open source tools to double the computing resources available for physicists to around 15,000 servers by 2015.
This talk will review the current state of OpenStack at CERN, the early experiences of deployment such as LDAP integration and configuring with Puppet along with the plans for production.
Learn more about Red Hat's cloud strategy and how OpenStack is becoming a big part of it. From delivering the core open source building blocks that power today's leading clouds to collaborating with the OpenStack community in building tomorrow's open source cloud platform - Red Hat offers a comprehensive set of products for customers to build an Open Hybrid Cloud.
Eileen Evans, Alice King
At the OpenStack Design Summit and Conference in October 2011, Rackspace announced that it would be moving the OpenStack open source project to a separate foundation. Following that, OpenStack invited community participation to help guide the process of moving to a foundation. There have been a number of lessons learned during this process and a couple of members of the OpenStack Drafting Committee would like to share those with you. This session will be led by Alice King, Vice President & Associate General Counsel, Rackspace, and Eileen Evans, Vice President & Associate General Counsel, Hewlett-Packard Company.
When Morplabs created mCloud - cloud software intended to allow service providers and enterprises to create EC2-like private clouds - Eucalyptus was the only open source compute cloud project in the game.
That all changed in July 2010 with the launch of OpenStack.
With multiple production deployments of Eucalyptus-based mCloud, find out how Morphlabs moved from Eucalyptus to OpenStack in 6 weeks.
Christopher Aedo will go into detail around pain points and challenges the team faced.
Somik Behera, Jacob Cherkas
Nicira runs its Worldwide(WW) Field and Sales Engineering team's customer-facing demo and evaluation infrastructure as well as Engineering DevTest, Build and QA automation infrastructure on an internal private OpenStack Cloud that is built using OpenStack Essex components, OpenStack Quantum and a front-end UI that lets users deploy complex, multi-tier Enterprise application with multiple private networks, with just a click of a button!
In this presentation, we will provide user's with an overview of Nicira OpenStack Cloud, our complex enterprise customer use-cases for an OpenStack Cloud and how we have on-boarded following applications to the cloud:
Since its creation, OpenStack has enabled developers to build easy-to-use, massively scalable public and private clouds. This session will look at a new use for OpenStack that is helping organizations of all sizes thrive in a changing IT environment: cloud-hosted virtual desktops.
The consumerization of IT is changing the way the workforce operates, with mobility, remote workers and BYOD presenting tough challenges for IT administrators. Since introduction, virtual desktop infrastructure (VDI) looked to be a promising solution, but fell short due to high CapEx costs and complicated on-site infrastructure requirements. Solution providers such as Dell, NaviSite, Rackspace and NetApp are instead turning to the cloud to host virtual desktops that are affordable, quick to provision and easy to manage. With OpenStack as the foundation for cloud-hosted virtual desktops, service providers can reduce operational costs while deploying Windows desktops that are secure, scalable and accessible on any device.
In this session, Desktone Vice President of Engineering Ken Ringdahl will discuss how OpenStack can simplify virtual desktop deployments. The discussion will include:
In this talk the patent context of open source and Linux will be outlined including the evolution from the SCO litigation through to the Mobile Patent Wars. As part of this history the formation and operational evolution of OIN from passive to active deterrent will be discussed with an eye toward providing OpenStack Foundation members the benefit of OIN's experience as well as offering a set of considerations designed to aid in shaping the Foundation's IP policy. This session will be presented by Keith Bergelt, CEO of Open Invention Network, in the hope of ensuring the Foundation's IP policy advances the OpenStack project's goals and is coherent with OIN's community-based approach to the preservation of freedom from patent aggression.
As enterprises grow to adopt OpenStack, use cases around resillient storage and the vendors they already have procurement relationships with keep popping up. There are two foundational functions that need to be supported within OpenStack in order as foundations to build a rich storage system that meets the demands of the enterprise. I'd like to focus on what the community wants to see in these features and how they should be built.
Enterprise IT is increasingly challenged to not only reduce costs but also respond to business imperatives with agility and innovation. Intel IT has addressed this challenge since 2010 by deploying a private cloud and continuously evolving its infrastructure. To improve the speed and availability with which we deploy new cloud services, we recently augmented our private cloud with OpenStack along with our own internal code. Das Kamhout, Intel IT Principal Engineer, will map the journey Intel took to integrate OpenStack into our enterprise environment and what enterprise IT needs from OpenStack. Join this session to discuss how I ntel and the OpenStack community can work together to catalyze this transformation in the datacenter.
Cloud computing workloads are increasingly sophisticated and specialized. End users continue to recognize the value of choice of their computing infrastructure (i.e. being able to select the 'right tool for the job' in their data centers). Why is computational architectural diversity important? How do you work with a relatively new community on enabling choice? Is it possible to do so in a manner that is viewed as a "win-win"" for everyone? Please join us for an overview of how IBM is working with the OpenStack Community to expand the choices available to our customers which enables them to optimize their workloads
The past five years have been a time of significant transformation in the legal and policy side of open source, particularly concerning expectations around relationships between open source community projects and corporate participants. This talk will discuss these developments and explain how they are illustrated by the launch of the OpenStack project and the licensing, contribution and governance models it has adopted.
In recent times, there has been a growing interest in evaluating the feasibility of running High Performance Computing (HPC) applications on cloud computing environments. Flexibility, scalability, and dynamic provisioning capabilities provided by a cloud infrastructure make it an attractive platform for running HPC applications. One important requirement of running today's data-intensive HPC applications is the availability of a parallel high performance storage system. Scalability and high bandwidth from the storage system are critical for HPC applications. Researchers have studied the I/O performance obtained from the traditional cloud storage options such as the persistent and ephemeral block storage. However there has not been any comprehensive studies about how a parallel file system (PFS) can be effectively integrated and provided as a service to cloud users running HPC applications and what would be the performance and security implications of such systems.
The objectives of our work to integrate a PFS in a cloud environment are two-fold: first, to determine the most efficient way to access a PFS from virtual-machine instances in the cloud, and second, to design a framework to provide the PFS as a service through the OpenStack platform.
We have identified and implemented three ways in which a high-performance file system can be used in HPC-cloud environment using Lustre:
A. PFS as a back-end to persistent volume storage
B. Accessing the PFS directly through file-system clients running inside the virtual machine instances
C. Accessing the PFS mounted on the virtual machine hosts through file-system pass-through from the instances. We are in the process of evaluating in detail the performance characteristics and security implications of each of these methods.
We are also looking at incorporating a file-system service inside the OpenStack framework that would allow users to provision and configure PFS storage dynamically and securely, in much the same way they can provision instances and volumes. The challenges involve ensuring security and isolation in allocating storage to the cloud users, and determining the file-system configuration options that should be exposed to the users through the file-system service APIs.