Become a fan of Slashdot on Facebook


Forgot your password?
DEAL: For $25 - Add A Second Phone Number To Your Smartphone for life! Use promo code SLASHDOT25. Also, Slashdot's Facebook page has a chat bot now. Message it for stories and more. Check out the new SourceForge HTML5 Internet speed test! ×

Submission + - Among Servers, Apple's Mac Mini Quietly Gains Ground (

Nerval's Lobster writes: "In 2005, the first business to offer colocated Mac Minis inside a data center made its debut, provoking criticism on Slashdot of everything from how the Mini was cooled to the underlying business model. But nowadays, more than half a dozen facilities are either hosting their own Mac Minis for rent, or offering colocation services for individual consumers and businesses. While some vendors declined to give out reliability information, those who did claimed a surprisingly small number of failures. “If Dell makes a small little machine, you don’t know that they’ll be making that, in that form factor, six months down the road, or what they’re going to do, or how they’re going to refresh it,” Jon Schwenn, a network engineer for CyberLynk Networks (which owns Macminivault) said in an interview. “We’ve had three model years of Minis that have stayed externally, physically identical.” Customers are using Minis for all sorts of things: providing Mail, iCal, and the Websites for small businesses; databases, like Filemaker or Daylite; as a VPN server for those who want an IP address in the United States; build servers for Xcode; and general personal servers for Plex media streaming and other fun projects. Some are even using it for Windows."

Submission + - Amazon's Christmas Eve Outage Teaches Recovery Lessons (

Nerval's Lobster writes: "Amazon’s explanation for the problem that took down Netflix and other sites on Christmas Eve: human error. The Web giant blamed an unnamed developer who ran a maintenance process against state data used by the company’s Elastic Load Balancers, or ELBs. That mistake cascaded into other areas. At its peak, 6.8 percent of the company’s ELBs were affected—which might not sound like a lot, but they were balancing loads across multiple servers. Netflix was forced to apologize for the outage, publicly pinning the blame on AWS infrastructure. Amazon’s mea culpa highlights two areas in which the company can improve: access to its infrastructure, and disaster recovery (even if that disaster was self-inflicted)."
Open Source

Submission + - How to Use a Linux Virtual Private Server (

Nerval's Lobster writes: "Game developer David Bolton writes: "For my development of Web games, I’ve hit a point where I need a Virtual Private Server. (For more on this see My Search for Game Hosting Begins.) I initially chose a Windows VPS because I know Windows best. A VPS is just an Internet-connected computer. “Virtual” means it may not be an actual physical computer, but a virtualized host, one of many, each running as if it were a real computer. Recently, though, I’ve run into a dead end, as it turns out that Couchbase doesn’t support PHP on Windows. So I switched to a Linux VPS running Ubuntu server LTS 12-04. Since my main desktop PC runs Windows 7, the options to access the VPS are initially quite limited, and there’s no remote desktop with a Linux server. My VPS is specified as 2 GB of ram, 2 CPUs and 80 GB of disk storage. The main problem with a VPS is that you have to self-manage it. It’s maybe 90% set up for you, but you need the remaining 10%. You may have to install some software, edit a config file or two and occasionally bounce (stop then restart) daemons (Linux services), after editing their config files.""

Submission + - How Peer1 Survived Sandy (

Nerval's Lobster writes: "When hurricane Sandy knocked out the electricity in lower Manhattan, data-center operator Peer1 took extreme measures to keep its servers humming, assembling a bucket brigade that carried diesel fuel up several flights of stairs. For this installment of our “Surviving Sandy” interview series (we previously talked to CoreSite and IPR), we sat down with Ted Smith, senior vice president of operations for Peer1, who talked about the decisions made as the floodwaters rose, the main generators went offline, and the changes his company’s made in the aftermath of the storm."

Submission + - Syrian Malware Servers Survive, Then Die (

Nerval's Lobster writes: "A massive outage knocked Syria’s Internet offline Nov. 29—with the exception of five servers implicated in serving malware earlier this year. But the next day, those five servers went dark as well. Internet analytics firm Renesys suggested late Nov. 29 that those five servers were likely offshore. “Now, there are a few Syrian networks that are still connected to the Internet, still reachable by traceroutes, and indeed still hosting Syrian content,” the company wrote in a blog post. “These are five networks that use Syrian-registered IP space, but the originator of the routes is actually Tata Communications. These are potentially offshore, rather than domestic, and perhaps not subject to whatever killswitch was thrown today within Syria.” By the morning of Nov. 30, those five servers went offline. “The last 5 networks belonging to Syria, a set of smaller netblocks previously advertised by Tata Communications, have been torn down and are no longer routed,” Renesys wrote."

Submission + - NYC Data Center Needs Focus on Fuel (

Nerval's Lobster writes: "Who knew that the most critical element of operating a data center in New York City was ensuring a steady supply of diesel fuel? In the wake of Hurricane Sandy, the challenges facing data center operators in the affected zones include pumping water from basements, waiting for utility power to be restored, and managing fuel-truck deliveries. And it’s become increasingly clear which companies had the resources and foresight to plan for a disaster like Sandy, and which are simply reacting. Here’s the latest on providers around the New York area."

Submission + - NYC Data Centers Struggle to Recover After Sandy (

Nerval's Lobster writes: "Problems in New York’s data centers persisted through Wednesday morning, with hosting companies and other facilities racing against time to keep generators humming as water was pumped out of their facility basements. The fight now is to keep those generators fueled while pumps clear the basement areas, allowing the standard backup generators to begin operating. It’s also unclear whether the critical elements of infrastructure (power and communications) will both be up and running in time to restore services. The following is a list of some of the data centers and services in the area, and how they’re faring:"

Submission + - AMD to Build ARM-Based Opterons (

Nerval's Lobster writes: "In a shocking but not totally unexpected development, Advanced Micro Devices announced Oct. 29 that it would license a future 64-bit core from ARM and develop it for use as a microprocessor for the data center.

Instead of taking a license to the ARM architecture itself, AMD will license a single, undisclosed 64-bit ARM core and surround it with its existing intellectual property. The exact core will be disclosed by ARM Oct. 30, when the company will make the announcement at its developer conference in Silicon Valley.

“I think that this is a key moment in the industry,” said Rory Read, the chief executive of AMD, at an Oct. 29 press conference in San Francisco. “I don’t think that there is any doubt about it. Today is about what AMD is about at its core, and it’s in our DNA to innovate, and to think about what’s next we look to disrupt the status quo, we look to drive the industry to where it needs to go.”

The question, of course, is the potential significance of ARM architecture in the data center. Analyst firms such as Gartner have termed the potential of low-power servers “minuscule.” Nonetheless, AMD and ARM convinced Dell and Facebook to join them onstage, and both endorsed the future of ARM servers.

Read, in response to a question from SlashDataCenter, said the potential for low-power serves in the data center was “well into a double-digit percentage” in three to five years."

Submission + - Green Grid Argues That Data Centers Can Lose the Chillers (

Nerval's Lobster writes: "The Green Grid, a nonprofit organization dedicated to making IT infrastructures and data centers more energy-efficient, is making the case that data center operators are operating their facilities in too conservative a fashion. Rather than rely on mechanical chillers, it argues in a new white paper, data centers can reduce power consumption via a higher inlet temperature of 20 degrees C.

Green Grid originally recommended that data center operators build to the ASHRAE A2 specifications: 10 to 35 degrees C (dry-bulb temperature) and between 20 to 80 percent humidity. But the paper also presented data that a range of between 20 and 35 degrees C was acceptable.

Data centers have traditionally included chillers, mechanical cooling devices designed to lower the inlet temperature. Cooling the air, according to what the paper originally called anecdotal evidence, lowered the number of server failures that a data center experienced each year. But chilling the air also added additional costs, and PUE numbers would go up as a result."

Red Hat Software

Submission + - ARM, AMCC Team on Server (

Nerval's Lobster writes: "Red Hat announced Oct. 25 that it had teamed up with both ARM and ARM licensee Applied Micro Circuits Corp. to develop a 64-bit server design based on the ARM architecture, a day after another ARM server partnership was struck.

ARM and AMCC said that they planned to develop a server that would be based on the AppliedMicro X-Gene “server on a chip” design. It wasn’t immediately clear if the two companies would be developing the server design themselves, or if they would need to partner with a third company.

For its part, Red Hat said that it was interested in the work, and planned to have a “Fedora 19 [Linux] remix” out in time for the 64-bit designs, expected later in 2014."


Submission + - Russian Website Selling Hacked Servers: Report (

Nerval's Lobster writes: "Here’s one way to create your own cloud-based data center: buy access into a network of hacked corporate PCs.

Does that sound illegal? Of course it is. But one firm is apparently shopping those services on the open market, according to security researcher and reporter Brian Krebs. On his blog, Krebs notes that advertised access to about 17,000 corporate PCs that were improperly secured. We’ll have to take his word for it, of course, since whoever owned the site has since pulled it down. If it existed—and we believe Mr. Krebs when he says that it did—the site has obviously been moved to another server or service.

The site promised access to any number of the compromised PCs, all apparently combining weak username and passwords to the Remote Desktop Protocol, which allows for remote access. Each PC shopped to the site had a representative or salesperson (of sorts). And the prices were low, low, low: Krebs said he found (with a screenshot to prove it) a hacked Windows Server 2003 system at an Internet address space assigned to Cisco Systems being sold for $4.55."


Submission + - Gartner: Low-Power Server Sales Will Be Minuscule (

Nerval's Lobster writes: "Despite the hype attached to low-power servers, research firm Gartner believes the format will occupy a low percentage of the actual server market.

That’s according to an Oct. 4 research note identifying three key areas of growth for the relatively low-margin server market.

Key server segments include hyperscale data centers, hosted virtual desktop workloads and extreme low-energy servers. Gartner suggested vendors would embrace the latter, driven by a need to escape the relatively low profit margins of the general-purpose server market.

“Currently, the server market is highly competitive, and despite its size, offers only small profit margins,” Jeffrey Hewitt, research vice president at Gartner, wrote in a statement. “The prevalence of standardized (x86) platforms also makes it hard for companies to differentiate their products.”

That desire for higher profit margins has driven server providers to make more of an effort to create fabric-based infrastructure and converge around integrated systems. “To succeed in the server market in the next few years,” Hewitt added, “companies must innovate and respond quickly to shifts in demand.”"


Submission + - Open Compute Project Publishes Final Open Rack Spec (

Nerval's Lobster writes: "The Open Compute Project has published the final specification of the Open Rack Specification, which widens the traditional server rack to more than 23 inches.

Specifically, the rack is 600 mm wide (versus the 482.6 mm of a 19-inch rack), with the chassis guidelines calling for a width of 537 mm. All told, that’s slightly wider than the 580 mm used by the Western Electric or ETSI rack.

The Open Compute Project said that changes in the new 1.0 specification include a new focus on a single-column rack design. The new dimensions now accommodate hotter inlet temperatures of between 18 to 35 degrees Celsius and up to 90 percent humidity, which reflects other Open Compute designs and real-world data center temperatures, according to project documents.

Facebook has led the implementation of the Open Compute Project, which publicly shares the designs it uses in data centers, including its Prineville, Ore. facility. As the spec clearly shows, however, the new designs deviate from the traditional configurations and specifications, which means data center operators will need to find and then source racks from third-party vendors (or, in the case of Facebook, design their own)."


Submission + - HP, Intel to Power World's Greenest Data Center (

Nerval's Lobster writes: "Hewlett-Packard and Intel have been selected to power a new petascale HPC system, designed to be the world’s most energy efficient, which will reside at the U.S. Department of Energy’s National Renewable Energy Laboratory (NREL).

And there’s a nifty energy-saving twist, too: Like the SuperMUC—Europe’s most powerful supercomputer—the NREL HPC system will use warm water to cool the servers. That water will then be transported to the ESIF offices and lab space, where it will serve as the primary heat source. Excess heat can also be exported to adjacent buildings and other areas of the NREL campus.

The $10 million HPC system will reside at the Energy Systems Integration Facility (ESIF), currently under construction on the Golden, Colorado, campus. The Alliance for Sustainable Energy operates NREL on behalf of the Department of Energy."

Data Storage

Submission + - Will Baidu's Data Center Be the World's Largest? (

Nerval's Lobster writes: "Chinese social networking giant Baidu said this week that it will spend a massive 10 billion yuan ($1.6 billion) on a cloud-computing center in China, potentially one of the largest investments ever for a data center.

Baidu is essentially is the Google of China, enhanced even further with the Wikipedia-like Baidu Baike online encyclopedia. In September 2011, Baidu ranked 6th overall in the Alexa Internet rankings, according to Wikipedia. All that traffic requires a massive infrastructure investment, and the Chinese company appears ready to make it.

Baidu touted the investment at a conference this week at its Baidu Technology Innovation Forum in Beijing, without disclosing specifics such as an estimated date of completion. It also announced a mobile browser and a version of the Android operating system."

Slashdot Top Deals

backups: always in season, never out of style.