Thursday, March 24th, 2016

Time	Event
4:00p	LinkedIn Adopting the Hyperscale Data Center Way LinkedIn’s need for scale has never been higher than today, and the social networking company is adopting a lot of the same approaches to building hyperscale data center infrastructure companies like Google, Facebook, and Microsoft have been using. Those approaches include designing custom hardware, software, and data center infrastructure, and sourcing hardware directly from design manufacturers, bypassing the leading big IT vendors, such as HP, Dell, or Cisco. “We took our data center through a transformation,” Yuval Bachar, LinkedIn’s principal engineer of global infrastructure architecture and strategy, said. “We have been working on this for the last eight months.” The first place where the company is applying the new infrastructure strategy is its new data center outside of Portland. The facility, which LinkedIn is leasing from Infomart Data Centers, features custom electrical and mechanical design, as well as custom network switches. It is the first data center designed to enable the company to go from running on tens of thousands of servers to running on hundreds of thousands of servers. The other LinkedIn data centers, located in California, Texas, Virginia, and Singapore, will transition to the new hyperscale infrastructure gradually, Bachar said. Infomart’s Portland data center in Hillsboro, Oregon (Photo: Infomart Data Centers) Homebaked 100G Switches and Fabric The biggest part of the transformation was rethinking the way the company does networking inside its data centers. It has designed its own 100 Gigabit switches and a scale-out data center network fabric. The plan is to use the same kind of switch in all LinkedIn data centers. Today, the company has a mix of whitebox switches designed to its spec and regular switches by the big well-known vendors. LinkedIn went with 100G as the baseline networking technology because it will eventually need that kind of bandwidth (it doesn’t today) and because the technology enables it to get 10G, 25G, or 50G switching meanwhile, Bachar explained. Using the PSM4 optical interface standard, LinkedIn engineers split 100G into two 50G ports. This enabled them to use the latest switching technology a lot cheaper than 40G optical interconnect, according to Bachar. “It’s the most cost-effective solution today to connect with such high bandwidth,” he said. You can read more on LinkedIn’s network fabric in a blog post by Bachar. Mega Scale at High Power Density At this point, LinkedIn has not started designing its own servers the way other hyperscale data center operators do. It does, however, buy servers from the same original design manufacturers, picking what they have on the menu, with some configuration modifications. For the next generation, LinkedIn is “definitely considering” having servers designed to its own specs for better cost efficiency, Bachar said. The new fabric enables the company to switch to a high-density data center design – the one thing that is radically different from the low-density, highly distributed model Facebook and Microsoft use. The data center in Oregon will have 96 servers per cabinet. It is slightly below 18kW per cabinet today, he said, but the cooling design allows densities up to 32 kW per rack. For comparison, the average power density in Facebook’s data centers is about 5.5kW, according to Jason Taylor, VP of infrastructure at Facebook. One other internet giant that has gone the high-density route is eBay. To cool this kind of density, LinkedIn is using heat-conducting doors on every cabinet, and every cabinet is its own contained ecosystem. There are no hot and cold aisles like you would find in a typical data center. “Everything is cold aisle,” Bachar said. “The hot aisle is contained within the rack itself.” The decision to use a high-density design was made after a detailed analysis of server, power, and space costs. It turned out high density was the most optimal route for LinkedIn, he said. The main reason it was the most optimal is that the company uses leased data center space, so it has space and power restriction the likes of Facebook or Google, who design and build their own data centers, don’t have, Bachar explained. On Board with Open Innovation It is also the reason LinkedIn decided against using Open Compute Project hardware, which is not designed for standard data centers and data center racks. Bachar said LinkedIn didn’t have any immediate plans to join OCP, the Facebook-led open source hardware and data center design effort, which lists Apple, Microsoft, and now also Google as members. But the company does share the ideals of openness that underpin OCP, he said. LinkedIn will make some of the infrastructure innovation it’s done internally publicly available, be it through OCP or another avenue. “We will share our hardware development and some of our software development,” Bachar said. (Comment on this)
4:36p	HPE and Microsoft Back Data Center Startup Mesosphere Mesosphere, the data center startup commercializing open source technology that powers data centers for some of the most popular tech companies, including Apple, Netflix, Twitter, eBay, and Uber, has scored official backing from two giants in the enterprise data center space: Hewlett Packard Enterprise and Microsoft. HPE and Microsoft joined Mesosphere’s latest funding round, a $73.5 million Series C, which also included among others the startup’s previous backers, Silicon Valley venture capital heavyweights Andreessen Horowitz and Khosla Ventures. Mesosphere announced the round, which HPE led, in a blog post Thursday. Investment by the two big vendors is “strategic,” which usually means the investors plan to take advantage of the startup’s technology in a big way. In Mesosphere’s case, it could mean package deals with enterprise customers, where its product is integrated with other technology the giants sell. Microsoft and HPE sell into most enterprise data center users and have long and deep relationships in that enormous IT market. For a startup like Mesosphere, the ability to leverage those relationships is a big advantage. Last year, Microsoft reportedly indicated interest in acquiring Mesosphere. Put simply, the startup’s product, called the Datacenter Operating System, or DCOS, abstracts whatever mix of computing resources an IT organization has, be they bare-metal servers, virtual machines, or cloud VMs, presenting them all as a single virtual pool of compute. This simplifies IT management and deployment of applications. Mesosphere has also expanded its technology set to provide a full solution for automating data center infrastructure to enable continuous software integration and development process using Docker containers. At the heart of DCOS is Apache Mesos, the open source software for managing clusters of servers. Mesos was the result of a research project by computer science students at the University of California, Berkeley, which started in the late 2000s. Mesosphere’s product is a platform that makes Mesos easier to use for enterprise IT shops. The startup combines and integrates it with other proprietary and open source technologies, such as Docker containers, Apache Cassandra (the distributed database management system), HDFS (the file system for storing data on large server clusters), Apache Spark (the processing framework for real-time data analytics), and Marathon (Mesosphere’s own open source Docker container orchestration platform). The announcement is a step up in Mesosphere’s already existing relationship with Microsoft. DCOS has been available as a beta service on the giant’s Azure cloud since last year, and Microsoft’s cloud container orchestration service, Azure Container Service, was built together with Mesosphere using Mesos and Marathon. Read more: Mesosphere’s Data Center OS Comes to Azure and AWS Also on Thursday, Mesosphere announced the release of production-ready Marathon 1.0. (Comment on this)
4:54p	No Country for Legacy BI Brad Peters is Chairman and Chief Product Officer for Birst. If money talks, then CIOs’ spending habits have a lot to say about the state of Business Intelligence (BI). For the past decade, BI and analytics have been a top investment priority for businesses, but the technology has yet to meet business needs and live up to the promise of BI. Enterprises are struggling to solve today’s data analytics problems with yesterday’s tools and strategies. When asked which technologies will have the most significant impact on business over the next two years, CIOs named analytics, business intelligence, digital and cloud, according to Deloitte’s 2015 Global CIO Survey. In 2006, BI and analytics was the number one investment priority for global CIOs. Today, it still remains the number one priority. While IT leaders’ historical investments in BI reinforce the fundamental importance of data analytics, it also signals a larger problem. To date, these investments have failed to solve BI issues, forcing companies to continue to make BI and data analytics technology their top spending concern for the past 10 years. Why have investments in BI and analytics not lived up to their expected value? Ensuring success with analytics requires meeting end-user demand for self-service capabilities without sacrificing governance and trust in the data. CIOs must break away from legacy solutions and create a model that bridges the gap between centralized BI teams supporting enterprise requirements and user-led decentralized teams looking for greater autonomy. Doing so requires embracing a new architecture. Yesterday’s BI Technology Can’t Solve Today’s Challenges The most fundamental issue with existing BI and data analytics technology and approaches is that they create silos everywhere — data silos, analytics silos and tools silos. Twenty years ago, businesses invested heavily in legacy BI and analytics tools. While these tools boasted strong governance and scale, they were slow, expensive and rigid. Consequently, business users became disgruntled with long wait times and lack of access to data, so they turned to a variety of desktop data discovery tools. Unfortunately, the proliferation of data discovery tools brought about its own problems. Popular data discovery solutions lack the enterprise features that centralized BI teams need to ensure governance, administration and scalability. With data discovery tools, data is frequently copied and moved between enterprise data warehouses and desktops, making it even more fragmented and leaving teams arguing about who has the right numbers instead of having meaningful business conversations. Finally, while the introduction of Apache Hadoop brought about the potential to aggregate data, it also added yet another silo that enterprises must figure out how to break down. The more decentralized teams adopt these tools inside an organization, the greater the risk of analytical silos and reporting chaos that impact both the business and IT. Business users can’t trust the data because the snapshots of data they get are outdated, incomplete and out of sync across tools. Traditional IT problems persist or worsen with long backlogs and rogue data analytics projects, forcing IT to stay in maintenance mode rather than establishing themselves as a valuable asset for strategic data and analytics projects. The New Analytics Gold Standard Businesses don’t operate like a collection of disconnected silos, so why should this be the case for data and BI blueprints? Enterprises have to shift architectures to solve these problems. Thus far, enterprises have seen that trying to port legacy architectures to the cloud is a dead end. Smart CIOs know that legacy technology with a browser pasted on top is not a real cloud BI solution. They must adopt an architecture that is designed to support mash ups of local data, maintain a unified view of data across the business, and fit with the existing tools and platforms. CIOs then can begin to break down the silos and realize the business value of data analytics. With a modern, multi-tenant cloud architecture, CIOs can achieve both rapid deployment and easy access to robust BI capabilities through a shared data fabric that is accessible by multiple users. This enables organizations to expand the use of BI across multiple regions, departments and customers in a more agile way, and empowers these decentralized groups to augment the global analytical fabric with their own local data. The result is enterprise-grade scalability at unprecedented speed and end-user freedom with self-service data preparation capabilities and transparent governance. By bringing analytics to the virtual world and creating a single, networked view of data, CIOs can eliminate data silos once and for all and dramatically accelerate the delivery of BI across the enterprise. Only when enterprises embrace new BI architectures will they be able to meet their data needs and see technology investments pay off. Industry Perspectives is a content channel at Data Center Knowledge highlighting thought leadership in the data center arena. See our guidelines and submission process for information on participating. View previously published Industry Perspectives in our Knowledge Library. (Comment on this)
8:28p	Why Google Doesn’t Outsource Data Center Operations Human error is the root cause of most data center outages. It is the data center industry’s maxim backed by data, collected and published by companies that study it. At Google data centers, however, it simply doesn’t apply. Why? Because Google data centers are operated by the one percent. “On the infrastructure side, the industry norm is that human error still accounts for the overwhelming majority of incidents,” Joe Kava, Google’s top data center operations exec, said. “Because of our designs and our highly qualified people, only a very small fraction of our incidents were related to human error, and none of them caused downtime.” A one-percenter at Google is different than a one-percenter the way Bernie Sanders or Occupy Wall Street mean it, however. Very few Google employees are allowed to visit the company’s data centers. “In fact, less than 1 percent of all Googlers ever set foot in a data center at Google,” Kava said, while speaking at Google’s big cloud event in San Francisco Thursday. The only way to get in is to have a specific business reason to be there, and Googlers that work in these facilities are some of the most experienced and brightest people with diverse backgrounds in engineering and mission critical operations, who all have a common trait. “They are systems thinkers,” he said. “They understand how systems interact and how they work together.” Go on a Virtual 360-Degree Google Data Center Tour About 70 percent of data center reliability incidents are caused by human error on average, Kava said, citing data by the Uptime Institute, an industry organization owned by the 451 Group. Only 15.4 percent of incidents at Google data centers were caused by human error over the past two years, he said. One of the biggest reasons Google is so far ahead of the industry average is that it doesn’t outsource data center operations. “You see, the norm in the industry is for the design-build contractor to hand over a set of drawings and a set of owner’s manuals and the keys to the front door and wish the data center operator good luck,” Kava said. “And all too often, frankly, those operations teams, they’re not employed by the owner; they’re outsourced to the lowest-cost bidder.” The result is not only does the data center’s actual user have no control over the quality of professionals running their facility, they also can’t be sure those people will go over and above when things do go wrong. “If there’s one certainly in data center operations, it’s that problems and faults are going to happen in the middle of the night, typically on Sundays, when no-one else is available to help out,” he said. Googlers responsible for data center operations work side by side with Googlers who design and build the facilities. There is a constant feedback loop between these teams, and every data center that gets built is better than the previous one. “This gives us an unparalleled level of ownership, end-to-end, of our infrastructure,” Kava said. (Comment on this)
9:33p	IT Innovators: Bolstering the Hybrid Cloud Through Analytics By WindowsITPro About 100 years ago, as electrical power became more widespread, many large companies and factories opted to build their own power-generation plants. This meant that electrical systems were generally small and localized, serving only those who could afford to construct and maintain one themselves. Over time, a gridded system of electricity was developed across America, allowing all households and businesses to tap into the wider system with a small investment and pay only for the electricity they used. In the same way, the hybrid cloud can provide powerful storage and tools to businesses of all sizes for a relatively low cost of entry, says Kevin Petrie, tech evangelist at Attunity, a data-management software provider. “It’s the same philosophy that you have for cloud computing—shared resources that are part of a public infrastructure can be more cost effective and help companies focus on what they do best,” Petrie says. “I think the cloud can benefit most any organization, in one way or another.” Increasingly companies are discovering that they can use the cloud for at least some of their business functions, Petrie says. And, that they don’t have to move all of their data or operations to a cloud-based model if that’s not what makes sense for their business needs. Companies often struggle to add a new platform to their IT suite, Petrie says. But innovations in data mobility and security mean that there are a myriad ways to do so without taking on exhorbitant costs or adding too much complexity. And those platforms increasingly come with the option of storing data conventionally, in the cloud–or both, depending on the firm’s needs for that data. “There are exciting new platforms that work very well for certain types of workplaces,” Petrie says. “No single platform is going to replace the others.” And what makes sense is, for many companies, a solution that involves both private and public clouds for data storage and access. “There’s been a big shift in the industry,” Petrie says, “from private clouds to hybrid clouds.” Companies can now have both public and private clouds, for different needs. Petrie gives the example of his company’s work with a healthcare provider. Of course, dealing with healthcare data requires a high degree of security and sensitivity. It also requires that patient data be stored, potentially without being accessed for long periods of time–but easily accessible when required. “They used us to move data to and from data warehouses,” Petrie says of the healthcare provider. “They’re not moving data to one place and leaving it there for all time, but actually moving it as needed.” That’s where a cloud solution for storing that data can provide a significant advantage to an organization. Of course, it’s important for that data to be securely stored. Healthcare organizations told Modern Healthcare, in a survey released last month, that the threat of cybersecurity breaches will have some (51 percent) or considerable (42 percent) impact on their IT security spending in 2016. That underlines the importance of security for data storage solutions, cloud or otherwise. “The public cloud itself can be relatively secure,” Petrie says. Even the CIA uses a public cloud—the data is so distributed that it’s an advantage, he says. “It would be hard for a bad guy to reassemble the bits into any sort of readable format,” Petrie says. That ability to both encrypt data and to know where it is when, and who is accessing it, is a key feature of a good cloud storage solution, Petrie says. “I think one of the misconceptions about the cloud is that data can be moved to one place on the cloud, and that’s where it will reside in perpetuity,” Petrie says. Data needs to keep moving to meet different needs for workload and analytical objectives, he says. That means encryption is a popular and critical measure when transferring data. “In addition, usage-tracking software of a variety of types is really helpful to make sure that your data is only being used in appropriate ways, by appropriate people,” Petrie says. Automation is another cloud benefit that can help companies manage data effectively, whether it resides in the cloud or not. This can often be accomplished through software that helps organizations integrate data and move it in an automated way across platforms. The software also helps organizations understand how data is being used. That involves making decisions on things like cloud solutions, data platforms and warehouses. It also means helping companies understand how data is stored, which can improve performance and reduce costs. “The final piece is helping companies prepare data for analytics by creating data warehouses and managing them in an automated fashion,” Petrie says. When it comes to data management, automation is key. “We find the most successful companies use automation tools,” Petrie says. Aside from managing the data itself, those tools can also give companies powerful analytic abilities–ensuring that businesses don’t just know where their data is and who is accessing it, but are able to use it to learn more about their business operations. “The key value of analytics is more precise and more meaningful data points or incorporating new data points in order to arrive at better conclusions,” Petrie says. It allows companies to make business decisions more accurately and effectively, he says. To bring it back to power companies, a 2014 PwC survey found that 73 percent of power and utilities executives had changed their organizations’ approach to big decision-making because of what they learn through data and analytics. And 50 percent of Canadian executives described decision-making at their organizations as highly data driven. The benefits are clear to Petrie. “There’s no company that wants fewer insights about their companies, about their market. You can always use more information,” he says. “Analytics is designed to help you use that information in a meaningful way, to help you make meaningful decisions.” Terri Coles is a freelance writer based in St. John’s, NL. Her work covers topics as diverse as food, health and business. If you have a story you would like profiled, contact her at coles.terri@gmail.com. The IT Innovators series of articles is underwritten by Microsoft, and is editorially independent. This first ran at http://windowsitpro.com/it-innovators/it-innovators-bolstering-hybrid-cloud-through-analytics (Comment on this)
9:47p	Oracle Pitches On-Premise Enterprise Cloud it Will Manage By The WHIR Oracle introduced a new way for organizations to get the benefits of on-premises deployments from Oracle Public Cloud Services on Thursday – by running them in their own data centers. Oracle Cloud at Customer is a family of offerings the company said enable enterprise workloads to be moved to the cloud despite business, regulatory, and compliance restraints. Oracle said the service provides the agility, simplicity, performance, elastic scaling, and subscription pricing of Oracle Cloud, but in the organization’s data center. It provides a “natural path” to move critical applications from on-premises to the (actual) cloud. The difference between Oracle Cloud at Customer and hybrid cloud computing is that Oracle is responsible for the operation and maintenance of servers in the client organization’s data center. “We are committed to helping our customers move to the cloud to help speed their innovation, fuel their business growth, and drive business transformation,” Oracle president Thomas Kurian said in a statement. “Today’s news is unprecedented. We announced a number of new cloud services and we are now the first public cloud vendor to offer organizations the ultimate in choice on where and how they want to run their Oracle Cloud.” The company said the 100-percent Oracle Cloud-compatible stack makes it seamless enough for disaster recovery, elastic bursting, dev/test, lift-and-shift workload migration, and DevOps with a single API and scripting toolkit. The new service suite includes infrastructure, data management, application development (starting with Oracle Java Cloud and eventually including polyglot development in Java SE, Node.Js, Ruby, and PHP), enterprise integration, and management. Concerns about compliance, security, and governance of corporate data are persistent barriers preventing some organizations from adopting cloud computing, and Oracle is pitching its on-premises cloud services to them. This first ran at http://www.thewhir.com/web-hosting-news/oracle-pitches-on-prem-cloud-for-compliance-conscious-enterprises (Comment on this)

<< Previous Day

2016/03/24 [Calendar]

Next Day >>