Samsung SDS will present a case study on using OpenStack to support its massive mobile ecosystem.
Topics will include:
1. Cloud services based on smart devices and ecosystem
2. Hybrid Architecture and its solutions
3. Collaboration with Rightscale and Canonical partners
4. Lessons Learned
Re-launched in 2002, BestBuy.com has grown to be the third most visited retail e-commerce site for the US holiday season. Facing increasing traffic and continued growth, BestBuy.com has engaged in an effort to re-architect and re-platform the site. A key component of these re-platform efforts is the hyper-scale CDC (Continuous Delivery Cloud). The CDC, based on the Openstack Essex release powers 40+ development teams today and is an innovation catalyst which enables thousands of automated tests running each day, early integration, and R&D for cloud deployments.
In this session we'll cover:
When someone hears that Rackspace deploys from OpenStack trunk into a production cloud environment, there are generally lots of questions (and sideways glances at the perceived insanity.) In this session, we'll address both the business strategy behind this approach and begin a deeper conversation with the OpenStack Community.
Talk Outline:
Business Strategy
- What does an trunk deployment look like (branch management, merge conflicts, etc)? Why does Rackspace deploy OpenStack from trunk into production?
- What are the benefits gained going this route vs using an official release candidate? What makes keeping up with trunk difficult?
Community Engagement
- What does having the largest OpenStack deployment running within weeks of trunk give back to the Community?
- How can embracing this strategy help make OpenStack a better project for all deployers? What innovation and collaboration will we be able to foster in the next release cycle? We'll address these questions and others!
This session is a panel discussion of OpenStack users having experience deploying Quantum in production environments, backed by network virtualization technology from a variety of vendor solutions and open source projects. Moderated by independent industry analyst Brad Casemore of IDC, the panel will be asked to discuss specific networking challenges faced before and after deploying Quantum and network virtualization; the impact it’s had on their production cloud deployments, and their sense of where the technology is at today and where it needs to evolve in the short and long term.
Panel will include Quantum users from eBay and HP clouds, among others.
PayPal is the world's most successful e-commerce payment platform.
In Fall of 2012 PayPal embarked on a pilot OpenStack project aimed at transforming its global infrastructure into an agile, open and robust cloud platform.
Today the first PayPal production applications are running on OpenStack. By end of fall 2013, we expect several thousand instances in production supporting web and mid-tier applications. Along the way, PayPal solved several technical challenges making OpenStack high available, scalable and easy to operate at scale.
In this case study, MercadoLibre, the e-commerce leader in Latin America, will show you how they developed a solution based on OpenStack Swift.
They will share a brief story about how they are moving away from NFS to a highly scalable and durable Object Storage solution, using a Flexible RESTful HTTP API, and commodity hardware to store large amounts of data.
This presentation will walk you through the different stages of their implementation, sharing experiences and tips of how it was pushed into production.
The CMS and ATLAS online clusters consist of more than 3000 computers each. They have been exclusively used for the data acquisition that led to the Higgs particle discovery, handling 100Gbytes/s data flows and archiving 20Tbytes of data per day.
An openstack cloud layer has been deployed on the newest part of the clusters (totalling 1300 hypervisors and more than 13000 cores in CMS alone) as a minimal overlay so as to leave the primary role of the computers untouched while allowing an opportunistic usage of the cluster.
This presentation will show how to share resources with a minimal impact on the existing infrastructure. We will present the architectural choices made to deploy an unusual, as opposed to dedicated, "overlaid cloud infrastructure". These architectural choices ensured a minimal impact on the running cluster configuration while giving a maximal segregation of the overlaid virtual computer infrastructure. The use of openvswitch to avoid changes on the network infrastructure and encapsulate the virtual machines traffic will be illustrated, as well as the networking configuration adopted due to the nature of our private network. The design and performance of the openstack cloud controlling layer will be presented. We will also show the integration carried out to allow the cluster to be used in an opportunistic way while giving full control to the CMS online run control.
By the summit, the NeCTAR Research Cloud will have been operating in production for more than a year.
A federated Infrastructure-as-a-Service cloud for use in any discipline across the Australian research community has provided virtual machines and object storage to researchers around the country. Within the next eight months, it will expand to 30,000 cores over 8 sites distributed over an area comparable to the USA, using OpenStack Compute Cells.
Using this as a platform, the sector is moving to build an array of services and software solutions to enhance research ability and collaboration. This presentation builds on the existing case study (http://www.openstack.org/user-stories/nectar/collaborative-research/) to introducing the design, and address the challenges encountered in operating a multi-site cloud for researchers from Archaeology to Wine.
For the technical: we'll dive into cells, list real hardware specifications, talk about HA, puppet, and more For the manager: ask us about how few people we need to run a cloud of this scale, and how we build up the stack.
This session will feature Mark Muehl, SVP, Product Engineering at Comcast who will present an overview of their OpenStack strategy and deployment plans followed by a Q&A session with OpenStack Foundation Vice-chair Lew Tucker.
Comcast Cable is the nation's largest video, high-speed Internet and phone provider to residential customers under the XFINITY brand and also provides these services to businesses. Comcast has invested in technology to build an advanced network that delivers among the fastest broadband speeds, and brings customers personalized video, communications and home management offerings.
Whether it's regulatory issues, early cloud market questions, licensing uncertainty, or competitive pressures, cloud service providers around the world are facing unique challenges in their markets to build a business and gain traction. In this session, we'll hear from service providers across four continents that have chosen OpenStack as their cloud platform. We'll learn the unique technology and market drivers that led them to OpenStack, how OpenStack is enabling them to compete in the global IaaS market and where they think OpenStack should go next.
Companies large and small are utilizing the agility and ease of use found in the public cloud. However for large enterprises the public cloud is expensive at scale and availability is not guaranteed For smaller SME's experiencing rapid growth, every day is one step closer to a call from the CFO regarding another rapid growth... cost.
In my presentation I will go over two use cases, one will feature a very large Fortune 100 company experiencing an increasing internal customer base moving to Amazon AWS for rapid provisioning of new infrastructure and how we used OpenStack to provide feature parity, ease of use and self-provisioning to move those customers back into an on-premise private cloud. My second use case will cover a rapidly growing and large consumer of Amazon AWS who was feeling the pain/costs associated with running entirely in the public cloud and found economies of scale in an OpenStack based private cloud.
Both cases illustrate big wins for OpenStack, and the ability to provide massive value to both Fortune 1000's and rapid growth SME's.
Two years ago, Rackspace set out on a quest to build a public cloud in the open, powered by OpenStack. Building the Open Cloud from an idea to a viable deployment of thousands of servers has come with lots of growing pains. We've also gained a little bit of wisdom along the way and are ready to keep pushing for great things. In this case study, we will talk about the various deployment strategies we have used, our experience with them, and how what worked for 200 nodes didn't always work for 1,000 nodes. We'll end by look at how we will get to the first 10,000+ node deployment and stay continuous.
EIG/Bluehost is one of the largest hosting companies in the world. The scale of our systems at Bluehost have been rapidly increasing. We are challenged with respect to how to manage such large server farms distributed across multiple data centers that are geographically distant. Although the main stream products at BlueHost still reside on traditional hosting platforms that have their own idiosyncratic requirements, we have been seeking an ideal cloud-based solution for an efficient management system in a highly scalable environment. We chose to leverage Openstack in provisioning tens of thousands of servers while meeting customers’ availability requirements.
In this talk, we will present our use case of Openstack in a traditional hosting environment. Although it can be considered odd or appear to be a conflict between 'traditional hosting' and 'cloud,' Openstack has been a good decision with which we could successfully launch our cloud-based traditional hosting products for dedicated servers and virtual private servers (VPS). We also plan on utilizing other benefits that exist in Cloud technologies so as to improve our hosting products as much as possible. We have learned many useful lessons from our unique experience, including the scalability issues that we faced while operating tens of thousands of servers and the stability issues that each OpenStack subcomponent currently has, as well as the architectural design considerations while using OpenStack. We are interested in sharing with the OpenStack community our experiences and code for some new features that we have added to OpenStack. We would like to obtain feedback from the community and also contribute our experiences back to the community.
