Data Center Knowledge | News and analysis for the data center industry - Industr's Journal
 
[Most Recent Entries] [Calendar View]

Friday, March 20th, 2015

    Time Event
    12:00p
    Making Your Own Servers Wasn’t Always Sexy

    Initiatives like Facebook’s Open Compute Project and IBM’s OpenPOWER Foundation are perceived as ecosystems comprised of people that do some of the most cutting-edge thinking about computing on a massive scale. DIY server design is what cool kids like Google and Facebook do, but it hasn’t always been that way.

    “It wasn’t sexy,” Rackspace CTO John Engates says, remembering the company’s early years. “Today it’s sexy to build your own servers. Back then it was cheap and scrappy to build your own servers.”

    Like for many other tech-startup entrepreneurs in the late 90s and early 2000s (Google included), the local PC shop that sold cheap computer parts was Rackspace’s primary “server” vendor. “And what we were really building was PCs that we were using as servers,” Engates recalls. “You build a PC and slap Linux on it and call it a server. That was how we started our company.”

    The reason they went the DIY server route was that it was simply cheaper that way. Once the company started growing and talking to enterprise customers who understood what a real server looked like, it started buying off-the-shelf enterprise-class servers. Dell was its first real server vendor – a relationship that started around 2002. Around the same time Rackspace also started buying “grown-up” storage systems from the likes of NetApp and EMC.

    Matching Hardware to Workload

    Today, the company is back to building its own servers, but its staff don’t actually put them together, and it’s doing it for very different reasons. There are still cost advantages to it, but it’s more about matching your computing needs with your infrastructure better. It’s more about shaping the roadmap of a server platform so that you don’t have to simply adapt to whatever the latest enterprise server vendors put on the market. “You want to be able to design it,” Engates explains.

    Best hardware for a particular workload is the reason so many companies are looking into Open Compute, OpenPOWER, or ARM server technologies, he says. Having multiple suppliers compete for a contract to supply the same server – the server the customer needs – also doesn’t hurt.

    Rackspace has bought its version of Open Compute servers from Taiwanese manufacturer Quanta, as well as from HP and Dell, Engates says. Other vendors have been in the mix too.

    First Worthy Challenger to x86

    The company got involved with OpenPOWER last December for similar reasons. “OpenPOWER represents more opportunity to have a supply-chain advantage and to have economics that are potentially better than what you get off the shelf today,” he says.

    OpenPOWER and Open Compute are very different beasts, however. Open Compute is literally open source. The specs and designs available through the project can be used by anyone for any purpose. OpenPOWER provides a way for companies to license the POWER processor architecture from IBM to do development on it.

    In the world of processor intellectual property, that’s as open as it gets today. U.K.’s ARM Holdings also licenses its architecture to chip makers. But IBM’s consortium has some heavyweight members, including Google, NVIDIA, Samsung, and Hitachi, among others. Google has already designed its own server based on POWER.

    Rackspace’s participation is starting to bear fruit too. Earlier this week the company announced a server spec that for the first time combines OpenPOWER and Open Compute. The design is optimized to run OpenStack, the open source cloud architecture nearly all of Rackspace’s cloud offerings are built on. The company was one of the key forces behind OpenStack’s birth and development.

    POWER is a different alternative to Intel’s x86 architecture than ARM is. With ARM, users have to accept lower performance in return for energy efficiency. That’s not the case with POWER, which is competitive with x86 in terms of both performance and price, Engates says. “It’s the first thing that’s shown a lot of promise as an alternative to x86.”

    Not Swearing Off ‘Incumbent’ Gear

    To be sure, Rackspace-designed Open Compute servers are not the only kind of hardware running in the company’s data centers. They support its public cloud and bare-metal services. Many of its other more traditional services (things like VMware virtual machines) run on traditional enterprise infrastructure.

    One reason is the legacy of cross-certification among incumbent vendors. If you want EMC, Oracle, and Cisco to cooperate with each other in supporting an enterprise IT environment running in your data center, that environment better consist of components the vendors have certified to work together.

    Another reason is there are lots of enterprises that simply prefer the traditional hardware route. Enterprise customers tend to be more inclined to “buy off-the-shelf enterprise-class gear, because it’s already completely qualified, optimized, and tuned, pre-integrated and ready to go,” Engates says. They know that equipment and want their service provider to offer it to them.

    This is a telling dynamic. The “incumbent” gear Rackspace does buy is purchased to satisfy enterprise customers who aren’t in the custom, DIY mindset the service provider itself is in. As an end user buying hardware for its own needs (infrastructure it uses to support its cloud services), it has chosen Open Compute because it makes better sense.

    As Open Compute matures, however, and more enterprise data center users get comfortable with it — and there are signs that this has started to happen — it is a real possibility that companies like Rackspace will find themselves buying fewer and fewer off-the-shelf boxes, replacing them with custom-designed commodity infrastructure optimized for their specific requirements. After all, DIY servers are now sexy.

    3:00p
    Modern Data Management Startup Reltio Raises $10M

    Modern Data Management company Reltio’s flagship product Reltio cloud has entered wide availability, and the company has raised a $10 million Series A from Crosslink Capital and .406 Ventures.

    Reltio’s MDM helps uncover data relationships to improve productivity. Similar to Business Intelligence, MDM provides wider, multi-domain insights, with BI as a subset of MDM. While BI is largely the domain of data scientists, MDM provides insights to more general business users such as sales, marketing, and compliance professionals.

    Founded by the team behind Informatica’s MDM, the company claims it is profitable and will use the venture capital to accelerate product development and expand sales and marketing.

    Reltio consists of data-driven applications and a modern data management platform.

    It uncovers relationships through combining operational and analytical capabilities to manage and act on a complete view of relationships between people, products, places, and activities. It fuses multiple data types such multi-domain master data, transaction and interaction data, third-party assets, and public and social data.

    Reltio is an example of the commercialization influence on business IT. It said in a statement that it is designed for users accustomed to the ease of LinkedIn and Facebook.

    This influence is seen in Reltio Commercial Graph, the core piece of its MDM platform. A columnar-graph hybrid repository combines, connects and stores a large number of attributes and relationships. The company includes data-as-a-service, which provides real-time delivery of third-party, social and public data sources directly into each application.

    Data is growing, and our ability to analyze and act on that data is beginning to catch up. The bigger trend in BI and MDM is making data analysis available beyond data scientists. BI provider Looker recently raised funding citing a similar mission.

    “The data-driven applications and data management market is exploding, and Reltio is poised to play a major role,” said Jim Feuille, partner at Crosslink Capital in a press release. “Reltio is the first company in this arena to put tailored data-driven applications into the hands of business users, with the data management compliance and discipline that IT requires.”

    Data-driven applications are available for specific verticals such as retail and distribution, oil and gas, and healthcare. They are available either through Reltio or its partners.

    3:30p
    Strategies for Evaluating Data Center Aisle Containment, Part Two

    Todd Boucher is the Principal and Founder of Leading Edge Design Group (@ledesigngroup), a critical infrastructure firm that specializes in designing, building, and maintaining Data Center, LED Lighting, and Information and Communications Technology systems.

    In the first part of this blog, we reviewed common data center challenges that are creating a need for aisle containment, how an aisle containment solution can help an owner gain back capacity in their data center, and some vendor-neutral strategies for evaluating containment solutions. Here, we will review peripheral project costs that have the potential to impact the project budget and strategy of an aisle containment solution.

    Review Peripheral Project Costs

    For most retrofit projects, there are typically required costs outside of the aisle containment system itself that will impact your overall implementation budget. It is important to review your existing data center to determine how these peripheral items will add to your project budget.

    Fire Protection

    Creating a fully encapsulated cold or hot aisle containment system may require modifications to your fire protection system, which could include additional detection and suppression inside of your containment area. Even if you are only implementing partial containment (like a vertical wall from the top of your racks to the ceiling) the quantity placement of your fire suppression nozzles may need to be augmented. This is a cost that impacts most aisle containment implementations and should be considered when creating a budget for the project.

    Real-Time Data Collection

    There are several energy efficiency gains that can be realized through the implementation of aisle containment systems. Most notably, the supply air temperature being delivered from your CRAC units to the server inlet can often be increased. Energy Star states that data centers can save 4-5 percent in energy costs for every 1°F increase in server inlet temperature. However, prior to making server inlet temperature adjustments, it is important that you have the ability to capture relevant data from your data center to understand the real-time environmental impacts of a temperature increase.

    Temperature (or combination temperature/relative humidity) sensors should be installed in the cold aisle at the server inlet location (front of the IT equipment racks) to collect real-time server inlet temperature information. These should be installed prior to aisle containment so a baseline and/or trend can be created for your cold aisle. After implementing aisle containment, most data centers will see a decrease in the server inlet temperature due to the reduced air mixing between supply and exhaust air. Once your environment has stabilized, it is recommended that you increase supply temperature incrementally (1°F or 2°F at a time) while actively monitoring the server inlet temperature through your sensors.

    Sensors can be installed cost effectively either through your Data Center Infrastructure Management (DCIM) system or through an independent monitoring system.

    CRAC Unit Controls

    In most legacy data centers with multiple Computer Room Air Conditioners (CRACs), the units operate independently, controlling temperature and humidity based on their individual setpoints. This leads to a common data center cooling problem of ‘dueling’ CRAC units, where one CRAC unit is in reheat mode while another adjacent unit is in cooling mode. When implementing aisle containment to an existing data center with perimeter CRAC units, it is important to understand the manner in which the CRAC units are controlled. If the units operate independently, a centralized control system should be considered. This will enable the CRAC units to work together as a group and help prevent the inefficiency created by ‘dueling’ units.

    Because this strategy and cost are not typically included in aisle containment proposals, it is important that data center operators understand the configuration of their existing CRAC units and integrate the review of the controls system into their evaluation of an aisle containment solution.

    Blanking Panels and Sealed Openings

    The effectiveness of aisle containment systems is significantly reduced if blanking panels are not installed in IT enclosures and raised floor openings are not sealed. Any open spaces in the IT racks or openings for cable cutouts in the raised floor increase air mixing and prohibits a proper segregation of cool supply air from hot exhaust air. Implementing blanking panels and sealing raised floor openings is a simple, cost effective initiative that should be completed prior to implementing any aisle containment solution.

    Completing a thorough review of your own data center, determining what modifications you are willing to make (if any) as part of a containment project, and understanding what peripheral costs may impact your project budget will enable you to complete a vendor-neutral review of aisle containment solutions and effectively determine which is best for your unique data center.

    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.

    4:00p
    Friday Funny: Pick the Best Caption for Unicorn

    Spring has sprung around the U.S. and it brought more than warm temps to Kip and Gary! Help us celebrate the season’s arrival with our Friday Funny Caption Contest.

    Here’s how it works: Diane Alber, the Arizona artist who created Kip and Gary, creates a cartoon and we challenge our readers to submit a humorous and clever caption that fits the comedic situation. Then we ask our readers to vote for the best submission and the winner receives a signed print of the cartoon.

    Several great submissions came in for last week’s cartoon – now all we need is a winner. Help us out by submitting your vote below!

    Take Our Poll
    For previous cartoons on DCK, see our Humor Channel. And for more of Diane’s work, visit Kip and Gary’s website!

    4:30p
    VIDEO: How to Reduce Noise in Your Data Center

    From server fans to UPS flywheels, there are lots of noisy neighbors in every data center. Noise volume level in a typical data hall can go as high as 80 decibels.

    In this video, Cisco’s IT architect Doug Alger goes over the biggest sources of noise in one of the company’s data centers and recommends things you can do to make a mission critical facility quieter.

    4:57p
    Fujitsu Opens Third Singapore Data Center

    Fujitsu has opened a data center location within Equinix Singapore. The company will offer cloud services out of the location, and plans to add cloud connectivity services to other clouds via Equinix’s Cloud Exchange.

    The data center is Fujitsu and Fujitsu Asia’s third in Singapore. The first was opened in 2002 followed by another in 2009. The company already has an established customer base in the region and said the data center was opened in response to cloud demand. The company offers a range of cloud services across software, platform and infrastructure.

    The data centers offer both private and public cloud, dubbed Fujitsu Cloud IaaS Private Hosted service and Cloud IaaS Trusted Public S5. Other public cloud Fujitsu data centers are located in Australia, the US, the UK and Germany, in addition to an existing Singapore location.

    Fujitsu cited familiar reasons for choosing to expand in Singapore, such as low-level of natural disaster related risks, and the country’s role as a network hub in the region. Singapore is strategically important for multi-national companies because of its location and connectivity. In-country needs are also growing, particularly in the financial services and government sectors.

    The Equinix Platform is centered on cloud and network connectivity, and will help Fujitsu expand in this regard. Equinix has also received accreditation by the BCA Green Mark Scheme.

    Data center activity in Singapore continues unabated. This week, Equinix opened a new facility as part of a wider global expansion, and CenturyLink opened a cloud data center.

    Fujitsu has over one hundred data centers globally dispersed with well over 1.5 million square feet of space.

    “The new datacenter will offer not only the current lineup of cloud and other datacenter services, but also new cloud service functionality which is now under development,” said the company in a release. “Furthermore, by enabling inter-database connectivity to the cloud services of other major companies, Fujitsu will answer the needs of its diverse clientele.”

    5:18p
    The Fourth Annual Greater New York Data Center Summit

    The Fourth Annual Greater New York Data Center Summit will be held April 13-14, 2015 at Convene in New York, New York.

    Join data center colleagues and develop new relationships while hearing from 40+ speakers in various panel discussions and workshops.

    The summit will feature an opening night reception on April 13, and full-day conference at Convene in Lower Manhattan on April 14.

     

    For more information about this event, visit The Fourth Annual Greater New York Data Center Summit website.

    To view additional events, return to the Data Center Knowledge Events Calendar.

    6:47p
    Missouri Taking Another Stab At Data Center Tax Incentives

    Legislators in Missouri are looking to attract data centers, reports the Kansas City Business Journal. A bill that would exempt new or expanding data centers from tax on equipment, utilities or materials passed both the House and the Senate.

    While it has passed the House and Senate, it’s not quite across the finish line. The measure has been sent to Governor Jay Nixon.

    Nixon was in a nixin’ mood when he vetoed a similar measure last year. The bill was one of 10 passed on the final day of session, all of which offered tax breaks to businesses. Nixon called the bills “Friday favors,” a commentary on last-minute lobbyist appeasement, and vetoed all 10.

    The new measure would require $25 million investment and 10 jobs for new data centers, and investment of $5 million and five new jobs for expansions. Jobs must pay 150 percent over the county average wage to qualify. Benefits given have a ceiling based on an economic model.

    The Midwest is a somewhat burgeoning data center location. Several different areas are collectively called “The Silicon Prairie.” In terms of multi-tenant data centers, St. Louis is home to data centers from 365 Data Centers, midwest-focused player Cosentry, and Ascent calls it headquarters, to name a few.

    Missouri is one of several states looking to attract data center business through incentives. States are offering increasingly aggressive tax breaks to attract the business making for a competitive landscape, often tipping the scales.

    Tax incentives are only a small part of provider considerations, though they certainly help. The debate on the part of the states has been on evaluating the return on these breaks.

    The difficulty is assessing the benefits of data centers since most benefit comes indirectly. Often job creation is tossed out as a determining metric because data centers themselves aren’t always big direct employers if an office doesn’t come in tow.

    The big effect and benefit is how they stimulate the area, the tech scene and local businesses, as well as their ability to potentially attract out of state business.

    For multi-tenant providers, these tax breaks are often a way to extend savings to customers as well. Multiple customers in a facility means multiple businesses in the area taking that space. Big enterprise data centers provide good publicity, and can trigger a clustering effect.

    << Previous Day 2015/03/20
    [Calendar]
    Next Day >>

Data Center Knowledge | News and analysis for the data center industry - Industry News and Analysis About Data Centers   About LJ.Rossia.org