LinkedIn Leads Standardized Cloud Gear Alliance
A group of major backers has formed the Project19 Foundation to support standardized gear and networking across cloud data centers.
![](https://eu-images.contentstack.com/v3/assets/blt69509c9116440be8/blt0de326d1a5de7939/64cb18b06dc3881c6f5c4293/CloudFromPlane.jpg?width=850&auto=webp&quality=95&format=jpg&disable=upscale)
LinkedIn is leading a project with muscular industry backers to produce componentized and standardized data center hardware that will be useful in small and medium-sized enterprise data centers as well as large cloud centers.
LinkedIn announced the Open19 Project in July last year. Yesterday it announced that HPE, GE Digital, Flexj and Vapor IO have said they're backing the Open19 Project and forming a foundation to support it. Vapor IO is a firm with products to manage edge computing, hybrid cloud computing and decentralized data centers collecting device data and sensor information flow. Flex supplies customizable manufacturing of electronics equipment.
Open19 data center gear includes a data center switch and is expected to include standardized storage options. Curt Belusar, senior director of hyper-scale engineering at HPE, said in a blog yesterday, "Open19 community members can 'mix and match” components in the way that best meets their data center needs to increase operational efficiency and reduce cost." The Open19 project gets its name from its reliance on a standard 19-inch wide rack for mounting servers and other devices.
Want to learn more about open source hardware? See Battle Intensifies To Become Cloud Hardware Leader.
Open19 is as much about having a standard networking environment in multiple cloud data centers as it is about gear. In a blog May 23, Darren Haas, senior VP, cloud and data for GE Digital, said it was difficult to implement Predix when cloud environments constantly varied in their hardware and networking: "The ability to use an open network stack with a mix of simple interchangeable solutions sharing the same standard will help allow us to deliver racks quickly, reduce deployment costs and have a wider inventory..."
Open 19 has several smaller backers, such as Inspur and Cumulus Networks, who were already part of the open source hardware project. Cumulus joined in April. Inspur is a 19-inch rack and "brick" supplier with ties to the Chinese technology companies Baidu, Alibaba and Tencent.
Open19 is a younger project than Open Compute, which was founded by Facebook in 2009 and was the first to apply the principles of open source code sharing and development to hardware design. Open Compute's first task was to popularize a standardize server and server switch design originated by Facebook and used in its hyper-scale data centers.
With Open19, the emphasis is more on useful components that can be assembled in large or small data processing centers, including some at the edge of the network or aggregators on the Internet of Things. Both projects share the goal of coming up with industry standard designs that can be stamped out by a number of low name recognition producers to minimize costs and maximize their usefulness in the data center.
In a blog on July 19 last year, Yuval Bachar, a veteran of engineering organizations at Cisco and Facebook and then the principal engineer for global infrastructure architecture at Linked in, wrote: "This new project aims to establish a new open standard for servers based on a common form factor. The goals of Open19 are to provide lower cost per rack, lower cost per server, optimized power utilization, and (eventually) an open standard that everyone can contribute to and participate in."
LinkedIn, of course, was acquired by Microsoft, so Open19 designs and products may find a future in Azure data centers as well as in LinkedIn's. But Microsoft is also a backer of Open Compute. For now, the initiative lies with LinkedIn engineers such as Bachar to make something distinctive of the project and allow it to serve complementary objectives.
About the Author(s)
You May Also Like
How to Amplify DevOps with DevSecOps
May 22, 2024Generative AI: Use Cases and Risks in 2024
May 29, 2024Smart Service Management
June 4, 2024