Capacity Utilization as a C-Suite Shocker

Are C-suite executives really comparing efficiency metrics like Power Usage Effectiveness (PUE) in evaluating their data center performance? The Uptime Institute says it sees this happening, but industry observers are skeptical. “I think it’s a bit of a stretch to assume C-Level execs are even aware of PUE (let alone calling data center staff out on the carpet about it),” writes Matt Stansberry.

Other industry veterans say executives are indeed pressuring data center managers, but the metric that has been a real shocker is capacity utilization - how much mileage the company is getting out of the hardware it has already bought.

“We’re going to see the C-suite pushing back down on asset utilization and asset management,” said Jack Pouchet, Direct of Energy Initiatives at Emerson Network Power’s Liebert unit. Pouchet said there is low executive awareness of server utilization rates, which are often cited as averaging between 10 and 30 percent. “You’re going to start seeing aggressive policies coming down to change that.”

Closer Look: Brocade’s Deal for Foundry

Catching up: Earlier this week Brocade Communications Systems (BRCD) announced plans to acquire Foundry Networks for $3 billion. This deal figures to be significant in the evolving battle for market share and mindshare in converged data center networks. Here’s a roundup of analysis from major tech sites:

• PC World describest Brocade’s move as “a major strategic move in a brewing war over the future of data-center connectivity” that would “combine a maker of Fibre Channel SAN (storage area network) switches for data centers and a specialist in enterprise Ethernet LANs, two technologies that are headed toward a merger themselves.”
• Search Networking examines whether the acquisition allows brocade to gain ground on Cisco Systems (CSCO), with one analyst opining that it “is likely to help Brocade remain a viable competitor in a two-company battle, but it’s not likely to dramatically change the balance of power in that battle.”

Maintenance Key to Maximizing Battery Life

Maintenance and monitoring are important steps in ensuring that your data center batteries operate at peak reliability. Charles O’Donnell, vice president of Monitoring and Professional Services for the Liebert Services business of Emerson Network Power, discusses the importance of battery maintenance and the company’s remote monitoring services. This video runs approximately 2 minutes, 45 seconds.

For additional video, check out our DCK video archive and the Data Center Videos channel on YouTube.

Have You Checked Your Data Center Batteries?

Batteries have emerged as significant contributors in several recent data center outages, underscoring the need to monitor and maintain battery banks. Here’s a recap:

• Battery failure was cited as the root cause of a May 23 outage at HostDime and Surpass Hosting. “The diagnosis conducted revealed there was a fault within a battery string which is connected to the UPS. It is this fault that disabled the UPS from being able to fully sustain continuous power to the load. … While the age of the battery supply being employed was well within the manufacturer’s life span expectancy, the entire battery supply was replaced with a new set.”
• Battery issues were also noted in a June 21 downtime event at AdHost in Seattle. “Very early indications suggest that the underlying nature of this failure was a significant drop in amperage from the battery strings which might have caused, for an as yet unknown reason, the (UPS) unit to go into an uncontrolled over-voltage situation to compensate. The end result was significant heat and smoke damage to the UPS unit.”

Advocates of flywheel (rotary UPS) technology say they are preferable to batteries, contending that repeated brief “bumps” to grid power can affect the life expectancy of the battery.

Harden Those Servers, Then Chain Them Down

Pingdom takes a look at data center security and the threat posed by physical break-ins, as opposed to the cyber threats that enter through the network. The post reviews the growing list of recent incidents involving hardware thefts at colocation facilities (many of which we’ve written about here), but also looks at some of the massive data breaches that have occurred on company premises (and those are only the ones that made it into the headlines).

Scaling Flickr, and Other Huge Databases

Microsoft’s James Hamilton has been collecting scaling stories for a while, and has shared a list of resources providing insider accounts of how the Web’s largest sites have managed their scalability challenges. The post focuses on Flickr’s database architecture, but also provides links to similar accounts for Amazon, LinkedIn, Second Life, CraigsList and MySpace. Readers focused on scalability may also be interested in Breakthrough Failures That Help Sites Scale.

As we noted in that story, many of the toughest scaling challenges involve databases. This week Jeff Atwood at Coding Horror wrote about database normalization, sparking a conversation that Todd Hoff at High Scalability has dubbed “the mother of all database normalization debates.”

SysAdmin Controls SanFran Computer Network

A disgruntled network administrator has been jailed after locking down a key computer network for the city of San Francisco by creating a password that gave him exclusive access to the system, according to city officials. San Francisco police arrested Terry Childs Sunday after he refused to provide them with working access codes for the city’s new multi-million dollar FiberWAN network, which stores e-mails, city payroll files, confidential law enforcement documents and jail inmates’ booking records.

Childs is a network administrator in the city’s Department of Technology. City officials reported late Monday that the system remained online and said they “made some headway” in overcoming the access controls implemented by Childs, who reportedly had been disciplined in recent months.

Lee Technologies Announces Global Expansion

Citing growing demand for global infrastructure for cloud computing, Lee Technologies today announced a global expansion that includes a new international business unit based in Dublin, Ireland and an alliance with an IT solutions specialist with an existing global network of offices. Lee provides data center design, construction and staffing services for government agencies and corporate customers, including Microsoft. Today’s expansion announcement featured two components:

• The launch of Lee Technologies International Services, Ltd. (LTSI), a Dublin-based operation that will deliver mission-critical solutions to global enterprises located throughout Europe, Asia and the Middle East.
• The formation of LZ Technologies, Ltd., a Dublin-based joint venture with Zenith Technologies that will integrates mission-critical facility and IT data center management services into a powerful single source solution. Zenith Technologies provides IT and automation solutions and is headquartered in Cork, Ireland, with offices in Dublin, UK, Germany, the U.S., Singapore and India.

“Surging fiber and infrastructure build-out required to deliver cloud computing is driving demand for mission-critical solutions providers with the capability to design, build and operate data centers and other mission-critical facilities on a global scale,” said Lee Kirby, Vice President & GM, Lee Technologies, and the new head of LTSI, who said LTSI “represents a tremendous opportunity to extend our capabilities overseas.”