Big Data. Big Decisions
InformationWeek
Special Coverage Series


Joyent Tools Cut Data Center Power Consumption

IaaS provider says it can help to reduce power used in older data centers by 25% by using big data analytics.

New tools are appearing in the ongoing battle to reduce energy consumption in a data center, and some of these tools are also designed to boost a data center's power usage effectiveness (PUE) rating. Google, Facebook, Yahoo, and Microsoft compete to get to the lowest possible PUE measure in their newest data centers.

PUE compares how much total electricity a data center imports to get a unit of computing done. Most older enterprise data centers have a PUE of 1.9- 2.0; they consume almost twice as much power as what's actually devoted to computing. The extra power is needed for heating/cooling, lights, and auxiliary systems, with cooling being the biggest culprit.

More Insights

Webcasts

More >>

White Papers

More >>

Reports

More >>

Instead of that average 2.0 PUE, advanced data centers get ratings such as 1.22 or 1.16, achieved on Google's last two publicly announced data centers. Yahoo operates a data center in Lockport, N.Y., with a PUE of 1.07, while Facebook's Prineville, Ore., center has a 1.06 rating.

But doing something about electrical gluttony in older data centers can get awkward. "Operating for efficiency and failing will get you yelled at. Operating for availability and failing will get you fired," summed up Steve Hassell, president of the Avocent business unit of Emerson Network Power, which specializes in producing power management devices.

Aiming for reliable availability in the data center usually means sacrificing some efficiency by building in extra memory buffers, surplus CPU cycles, and extra-large network bandwidth. Surpluses usually also include power to guard against any failure triggered by a shortage. But eliminating surplus power may mean eliminating your margin for error, in some cases, unless you can get a view into what devices are using and what are the real-time needs.

[ Want to learn more about the competition to build power-efficient data centers? See Data Centers May Not Gobble The Earth After All. ]

San Francisco-based Joyent provides infrastructure-as-a-service (IaaS) from a dozen data centers. CEO Jason Hoffman has tried during the company's eight years to get on top of the issue. He knew if he could reduce power consumption, his infrastructure would be more competitive with bigger names, such as Google and Amazon. And if it worked for him, then it could be an added feature on the server racks that Joyent also ships for private cloud installations at its enterprise customers.

In an interview, Hoffman noted that he opted for an appliance with an odd-sounding name that can amass and perform analytics on data from the many devices in the data center. The Avocent Universal Management Gateway accepts information spewed out by such components as the service processor on a server's motherboard, a microcontroller that collects temperature, voltage, and fan speed data and sends it to the gateway appliance. Network interface cards, switches, and other devices on the server rack and in the data center do the same thing, describing their states in component-specific languages.

In many cases, no one is interested in what the devices are reporting and the information "is dumped into a black hole," said Hoffman. But the Universal Management Gateway understands what each device is saying and it can capture, store, and analyze the information. Emerson acquired Avocent three years ago because it had developed what Hassell described as "a universal translator" for device languages, he said.

Information from the gateway is delivered to Emerson's Trellis data center management software, where it goes into applications seeking to accomplish specific goals, including managing power consumption in the data center. It includes four modules:

-- Inventory Manager is a device discovery and mapping system that detects one device talking to another and records its location and characteristics to build a blueprint of the data center, or data centers.

-- Site Manager reports to data center operators on the health of the running systems. Is the temperature going up on a certain server? Is that because the voltage has increased, it's engaged in particularly intensive, multi-CPU calculations, or perhaps the fan has slowed and is about to fail? It has intelligence to collect information from many devices to report on their health.

-- Change Planner can capture device additions, moves, or decommissions and update Inventory Manager with fresh information. It helps plan device changes and tracks them as they occur.

-- Energy Insight calculates total data center energy consumption and electricity costs, as well as individual device consumption. Are three servers clustered together working exceptionally hard, heating up and prompting the cooling system to overcool the whole data center? Perhaps their workload could be spread around. Energy Insight can also be used to calculate the PUE of the data center, said Hassel. Instead of an annual audit, the module can give you a PUE value on a real-time basis, he noted.

Trellis software and the Universal Management Gateway provide "big data and big data analytics for the data center," said Hoffman.

Joyent has gained enough experience with the combination that it's become a secondary business to its IaaS, offered as a feature on a server rack of Joyent infrastructure destined for installation on a customer's premises. It's added as a 5%-10% premium on the price of the rack.

Emerson says in information on its website that the Gateway-Trellis combination can save 25% of a data center's energy consumption. Hoffman claims that savings is borne out by Joyent's own experience. "We think we can do better than that," he added.



Related Reading




Currently we allow the following HTML tags in comments:

Single tags

These tags can be used alone and don't need an ending tag.

<br> Defines a single line break

<hr> Defines a horizontal line

Matching tags

These require an ending tag - e.g. <i>italic text</i>

<a> Defines an anchor

<b> Defines bold text

<big> Defines big text

<blockquote> Defines a long quotation

<caption> Defines a table caption

<cite> Defines a citation

<code> Defines computer code text

<em> Defines emphasized text

<fieldset> Defines a border around elements in a form

<h1> This is heading 1

<h2> This is heading 2

<h3> This is heading 3

<h4> This is heading 4

<h5> This is heading 5

<h6> This is heading 6

<i> Defines italic text

<p> Defines a paragraph

<pre> Defines preformatted text

<q> Defines a short quotation

<samp> Defines sample computer code text

<small> Defines small text

<span> Defines a section in a document

<s> Defines strikethrough text

<strike> Defines strikethrough text

<strong> Defines strong text

<sub> Defines subscripted text

<sup> Defines superscripted text

<u> Defines underlined text

BYTE encourages readers to engage in spirited, healthy debate, including taking us to task. However, BYTE moderates all comments posted to our site, and reserves the right to modify or remove any content that it determines to be derogatory, offensive, inflammatory, vulgar, irrelevant/off-topic, racist or obvious marketing/SPAM. BYTE further reserves the right to disable the profile of any commenter participating in said activities.

Disqus Tips To upload an avatar photo, first complete your Disqus profile. | View the list of supported HTML tags you can use to style comments. | Please read our commenting policy.

Follow InformationWeek

By The Numbers

What Are Your Primary Concerns About Using Big Data Software?

Base: 417 respondents at organizations using or planning to deploy data analytics, BI or statistical analysis software
Data: InformationWeek 2013 Analytics, Business Intelligence and Information Management Survey of 541 business technology professionals, October 2012

What Do You Think?

What's your attitude about SQL analysis on top of Hadoop?
We want fast, standard SQL analysis capabilities on Hadoop ASAP
Hadoop is for unstructured data; SQL is for relational databases
We'll give SQL on Hadoop a try, but relational DBs will remain the mainstay
Given strong SQL support on Hadoop, we'd nix the data warehouse
We're not interested in Hadoop
No opinion



Related Content

From Our Sponsor

Five Big Data Challenges and How to Overcome Them with Visual Analytics

Five Big Data Challenges and How to Overcome Them with Visual Analytics

Business leaders often need a visual snapshot of data to quickly grasp and use it. This paper identifies five challenges in presenting data and how visual analytics can resolve them. Solutions are suggested to overcome the challenges of: speed, data clarity, data quality, displaying meaningful results, and dealing with outliers.

Game-Changing Analytics: How IT Executives Can Use Analytics to Create Innovation and Business Success

Game-Changing Analytics: How IT Executives Can Use Analytics to Create Innovation and Business Success

Today's competitive advantage requires a deeper understanding of your business, your market and your customers. As an IT executive, you can drive that knowledge transformation. In this white paper, learn how to make decisions as a strategic business leader and three steps to begin an analytics initiative within your enterprise.

Data Visualization Techniques: From Basics to Big Data with SAS Visual Analytics

Data Visualization Techniques: From Basics to Big Data with SAS Visual Analytics

High-performance data visualization turns sophisticated analyses into meaningful graphics, leading to faster and smarter decision making. In this white paper, learn how visual analytics can transform big data, with additional features such as real-time functionality, mobile compatibility, robust applications for technical groups and accessibility for nontechnical users.

Big Data: Lessons from the Leaders

Big Data: Lessons from the Leaders

Financial performance, competitive advantage, operational efficiency, strategic decision making - every business goal can extract value from big data, and the time for doubt or inaction has long passed. In this Economist Intelligence Unit report, in-depth interviews with data pioneers reveal the link between the effective use of big data and the bottom line among other results.

Decision-Driven Data Management: A Strategy for Better Decisions with Better Data

Decision-Driven Data Management: A Strategy for Better Decisions with Better Data

Which came first, the data or the decision? This white paper makes the case for having a decision in mind, then tailoring big data's volume, variety and velocity to achieve business results such as overcoming customer dissatisfaction or creating well-informed strategies in real time.

Informationweek Reports

Research: The Big Data Management Challenge

Research: The Big Data Management Challenge

The challenge of big data is real, but most organizations don't differentiate 'big data' from traditional data, and nearly 90% of respondents to our survey use conventional databases as the primary means of handling data. We'll help you understand what constitutes big data (it's not just size) and the numerous management challenges it poses.