There is something for everybody on the Internet.  The landscape on the Web is a diverse and complex place.  For a data center this is reflected in usage.  Niche sites may plateau anywhere from 500-3000 hits a day.  But sites with accelerating popularity may generate a figure that is astounding.  Example?  2010 startup Pinterest currently gets around 1.5 million users a day.  That’s a lot of movement.  For a data center that means a lot of energy.

Data centers are starting to rethink how they manage their billing structure. Most data centers do charge for things like storage and network bandwidth.  However, the energy and heat produced by frequently engaged servers leads to a lot of extra costs for data center operators.  Consider all of the extra power consumption.  Cooling becomes more costly— not solely because of the energy cost, but also because of the ongoing maintenance needed for a constantly blowing HVAC.

Many businesses have usage-based billing structures that take in consideration the consumption of their company’s billable resources.  The most obvious example is a phone company. Usage charges range from time-of-day based rates to minutes used.  Many Internet providers are exploring a similar course, billing their customers if they exceed a defined limit of bandwidth.

For the data center there is a clear advantage to usage based billing.  Offsetting the costs of busy servers has to come from somewhere.  If 5% of a data center operator’s clients are responsible for 85% of energy usage, is it fair to pass the costs on to everyone? Raising prices on every client risks scaring away loyal customers and hurting the bottom line.  The answer is to pass the costs to the clients responsible for the excessive energy.

How does a data center operator pinpoint which of the client’s servers are consuming the most power?  Submetering.  Intelligent power submetering is an effective way to measure where the costs are coming from.  By providing an accurate picture of where the energy costs are coming from, a data center operator can confidently translate where the excessive energy is produced into hard figures.  Over time, daily readings can give a good overall picture, thereby allowing a business to determine their billable resources.  The result is a profitable billing structure that stabilizes the growing costs of a business’ energy.

For more information on how Uptime Devices’ Intelligent Power Meters can help your business implement a more profitable billing structure, please visit our site: www.uptimedevices.com/products , or email: sales@uptimedevices.com

The Growing Importance of Intelligent Power Submetering

Rising energy costs have created more discussion on the need for accurate energy use monitoring. At Uptime Devices, we made sure our newest infrastructure monitoring solution, the RPM Console Manager, came equipped to host ANSI billing class power meters.

Uptime Devices is based out of Austin, Texas, and, the problem of rising energy prices has been illustrated perfectly in our own backyard. Currently, City of Austin Electricity is negotiating with Austin City Council on sizeable electric bill hikes from small businesses to homeowners. While schools get a deserved break on the proposed new rates, unfortunately, according to the Austin-American Statesman, “businesses such as hospitals and data centers would see rates rise as much as 20 percent”.

With the upward trajectory of green energy, many electric utilities are seeing their profits diminished as more businesses switch to alternative solutions for their power. As a result, electric companies are increasing bills. There are several arguments for accurate power metering.

Load Profiling and Benchmarking

Monitoring your energy enables a business to see if the load profiling they are getting from the electric company is accurate. It also allows for pinpointing where excessive energy might be cut and makes for more efficient energy use.

Data Center Tenant Cost Allocation

Accurately monitoring power in a data center means being able to assess which users are using the lion’s share of resources. For example, if one customer is utilizing 25% off all resources with busy servers, action can be taken to minimize costs.

Continue Reading…

For upper management, data center maintenance is viewed as an unfortunate, yet necessary, write-off. It is akin to having one’s automobile breakdown and taken to the shop. The repair is an expenditure that is inevitable by virtue of the large investment that was initially made. With DCIM implementation it is possible to extend the life of your servers, thereby minimizing costly replacement and repair.

The truth is, there is a tremendous business value in proactively implementing data center infrastructure management (DCIM). With the right monitoring tools, the need for maintenance can be minimized. Moreover, staff can be equipped with accurate symptoms that can prevent costly breakdowns.

As old data center architectures are getting deteriorate, inefficiencies are surfacing that reveal an ongoing extraneous cost. As upper management become more informed on the benefits of DCIM technology, they are progressively setting aside budget dollars for DCIM. Instead of another cost, it is seen as a significant cost-saver.

Here are a handful of facts and data that support DCIM and the modernization of data centers.

Continue Reading…

Bill Kleyman, Data Center News

The data center environment is growing, and it has become even more important to properly manage server logs. Keeping an eye on servers, firewalls, appliances and even switching infrastructure event logs can help IT administrators do much more than just check for reactive issues – when log management is kept accurate, engineers are actually creating a proactive environment capable of spotting and controlling problems before they even come up. Let’s review some tips to help you make the most of server log data.

With effective log management, administrators are able to accomplish the following tasks:

•Create an audit trail for forensics analysis. There are times when an intrusion is suspected or a data loss event has occurred. A good audit trail allows forensic data center engineers to retrace the steps taken by anyone who has entered the environment recently, and then correlate that data into usable information.

•Manage and monitor intrusion. Active server log monitoring can help prevent both accidental and malicious intrusion into the system. When logs are setup properly, all vital systems are monitored and an immediate red flag can be raised if unauthorized activities occur.

Continue Reading…

YYN9T7C2DYJU

Stephen J. Bigelow, Senior Technology Editor, DataCenter News

It’s just not enough to install new servers, set them up, install applications and then walk away. Servers need regular performance monitoring to ensure that your hardware investment will deliver the service you expect – and provide ample early warning of impending trouble, such as resource shortages or hardware issues. Performance monitoring tools can provide a wealth of useful information, but only when those tools are set up and running properly. Fortunately, a few important insights will help any administrator get the best results from performance monitoring.

Achieving accuracy in performance monitoring
Monitoring is useless if it delivers erroneous information, so ensuring accurate data should be one of your first considerations. There are several aspects to accuracy, including interoperability, sampling window, tool architecture, virtualization awareness and calibration.

Interoperability. For this discussion, interoperability is basically the ability of a performance monitoring tool to access and read data points from the various pieces of hardware within your data center environment. Homogeneous environments focused on a single vendor’s product line can take advantage of performance monitoring tools that use hooks deliberately integrated into the hardware. These hooks can deliver detailed information to the tool.

The situation can be far more challenging for heterogeneous environments, where tools and hardware don’t mesh. A vendor’s tool may look for data that certain pieces of hardware simply cannot provide with the required level of consistency (if at all). It’s a similar problem for third-party performance monitoring tools that often cannot detect every sensor or hardware nuance on every possible device, and instead rely more on operating system-level data, which usually lacks granularity. In either case, the result is missing data or inaccurate data points that reduce the insight gained from performance monitoring.

Continue Reading…