In collaboration with Intel®

Unleashing IT Seize innovation, accelerate business, drive outcomes.

Volume 2, Issue 5

• Identifying $40 million in sales opportunities. Page 6

• Transforming product and service delivery. Page 8

Big Data Special EditionStrategies, experiences, and solutions for maximizing the value of enterprise data.

facebook twitter

Unleashing IT is published by Cisco Systems, Inc. To receive future editions of Unleashing IT and provide feedback on the articles in this edition, visit: www.UnleashingIT.com

Intel and the Intel Inside logo are trademarks of Intel Corporation in the U.S. and/or other countries.

©2013 Cisco and/or its affiliates. All rights reserved. Cisco, the Cisco logo, Cisco Unified Computing System, Cisco UCS, and Cisco Nexus are trademarks or registered trademarks of Cisco and/or its affiliates in the U.S. and other countries. To view a list of Cisco trademarks, go to this URL: www.cisco.com/go/trademarks. Third party trademarks mentioned are the property of their respective owners. The use of the word partner does not imply a partnership relationship between Cisco and any other company. (1310)

Strategies

03 Big data, big changes Why organizations must embrace change and adapt to new opportunities and paradigms.

04 The currency of “everything” With the Internet of Everything, $14.4 trillion is “up for grabs” in the next decade.

05 Big data versus fast data Why speed is just as important as volume when it comes to data analytics.

Experiences

06 The start of a journey Cisco’s first big data use case uncovered $40 million in new business opportunities.

08 Solutionary bets heavily on big data The managed security services provider is changing the way it protects its customers.

10 Saving brick and mortar retail How sensors and analytics are helping retailers enhance the customer experience in real time.

Solutions

12 The underpinnings of big data success Intel and Cisco team up to deliver an integrated foundation for big data workloads.

14 Tuning Cisco® UCSTM and Nexus for big data Optimizing server, storage, and network environments for big data tasks.

15 Cisco® Tidal Enterprise Scheduler An easy-to-use workload automation and orchestration tool.

Unleashing IT Seize innovation, accelerate business, drive outcomes.

Volume 2, Issue 5

Priceless grains of sand

Imagine standing on a beach. Now imagine if a few dozen grains of sand—buried within miles of coastline—could dramatically change your perspective on the present, allow you to peer into the future, and change your fortunes forever. How would you find them?

This special edition of Unleashing IT is all about big data, which is often described in the simplest of terms: A linear distillation of many (data sources) to a few (insights and actions). But as every beachcomber knows, there is nothing simple or linear about big data.

Organizations must rethink the realm of possibility. They must openly embrace change (page 3). And they must consider new tools and technologies (pages 12, 14, and 15). Doing so can help transform product and service delivery (page 8), identify business opportunities representing tens of millions of dollars (page 6), and save entire industries (page 10).

With big data experience and foundational technologies, Cisco and Intel are ready to help you unearth those priceless grains of sand.

For more information, follow the links inside or contact Cisco at 1-800-553-6387 and select option 1 to speak with a representative. We welcome your feedback on the articles in this publication at www.UnleashingIT.com

Sincerely,

Boyd Davis Vice President and General ManagerIntel Corporation

David YenSenior Vice President and General Manager Cisco Systems, Inc.

In collaboration with Intel®

Strategies

More sensors and devices. Faster and more economical processing, networking, and storage. And intelligent connections among them. All are converging to create a host of data-driven business opportunities.

“The industry has been talking about the unrealized value within data for more than a decade,” says David Yen, Senior Vice President and General Manager of Cisco’s Data Center Business Group. “We just haven’t seen a lot of activity or action until recently.”

More than visionary ideas and hype-inducing promises, big data has become a reality. But there is no distinct path for pursuing the needles of value within the haystacks of enterprise data. No silver bullet for success.

“Big data is here to stay because there is real value in it,” says Yen. “But we are still in the early stages. We must all adapt to these new opportunities and paradigms. Where to invest and how to reap value will be different for every organization.”

In many ways, big data means big changes for those seeking to capitalize. It requires new platforms, new processes, new skill sets, and new software capabilities. While they have similar components and attributes, Yen says big data environments are fundamentally different than standard data center systems.

“You can’t shove a large volume of unstructured data into traditional systems and expect good results,” he explains. “And you can’t piece together a bunch of off-the-shelf servers for big data analytics without running into administration and networking problems.”

According to Yen, Cisco and Intel are well positioned to help organizations step into the big data waters, minimizing startup challenges

and expediting ROI. The Cisco® Unified Computing System™ (UCS) can form the foundation for big data success. Based on Intel® Xeon® processors, Cisco UCS™ brings together compute, storage, networking, and management resources and can be fine-tuned for big data workloads (see related article on page 14). And the Intel Distribution for Apache Hadoop software is the only distribution built from silicon up to enable the widest range of data analyses on Apache Hadoop (see related article on page 12).

“We don’t want to duplicate or replace existing environments and solutions, we want to complement them,” says Yen. “[Cisco] UCS bridges the gaps between traditional systems, enterprise networks, and big data processing—with one management interface.”

Cisco and Intel also collaborate with independent software vendors such as MapR, Cloudera, Pivotal, Hortonworks, and Oracle to make sure their software works seamlessly on Cisco and Intel platforms.

“There are different approaches for big data depending on the use case, the type of data and analytics involved, and how they are consumed,” Yen explains. “We have reference architectures, roadmaps, and partners for all of them.”

Organizations seeking to mine value from big data have two options. They can piece together their own systems and navigate uncharted waters on their own. Or they can lean on bundled infrastructure solutions from industry leaders that have a wealth of big data expertise.

“We have the right experience, the right platforms, and the right partners,” says Yen. “We can help our customers get the most out of their big data investments.”

Leaning on bundled solutions and proven expertise to achieve big data success.

Big data, big changes

3Seize innovation, accelerate business, drive outcomes.

Unleashing IT4

As soon as the Internet was developed, there was a desire to connect more “things” to it. Desire led to action and progress, with the Internet now connecting anywhere from 10 to 15 billion devices. Even so, less than 1 percent of things are connected to the Internet today.1

This is changing. As additional networked connections are made between physical objects—and capabilities such as context-awareness and increased processing power are applied—organizations are beginning to embrace the Internet of Everything (IoE).

“IoE brings together people, process, data, and things to make networked connections more relevant and valuable than ever before,” says Dave Evans, Chief Futurist at Cisco. “It turns information into actions that create new capabilities,

richer experiences, and unprecedented economic opportunities.”

As billions, or even trillions, of connections form the arteries of IoE, big data will be the blood that flows through them.

“IoE and big data are reliant on one another, and are evolving together,” Evans explains. “Data is the currency of IoE. Without data going back and forth, the engine stalls.”

Connections are merely the first step, he adds. To realize the value within and among the connections, organizations must apply processing and analytics.

“More connections mean more data that can be extrapolated and analyzed,” Evans says. “Doing so increases knowledge and wisdom, which lead to action and value.”

What’s the upshot? Cisco predicts that the IoE Value at Stake will be $14.4 trillion for companies and industries worldwide in the next decade. More specifically, over the next 10 years, the Value at Stake will present global enterprises with an opportunity to increase profits by nearly 21 percent. In other words, between 2013 and 2022, $14.4 trillion of value (net profit) will be “up for grabs”—driven by IoE.2

1 “The Internet of Everything: How More Relevant and Valuable Connections Will Change the World,” Cisco, 2012. 2 “Embracing the Internet of Everything To Capture Your Share of $14.4 Trillion,” Cisco, 2013.

Get the white papers

To learn more about the Internet of Everything and the $14.4 trillion of value therein, get the white papers at: www.UnleashingIT.com

Estimates show 99.4 percent of physical objects are still unconnected. Conversely, this means that only about 10 billion of the 1.5 trillion things globally are connected. At a more personal level, there are approximately 200 connectable things per person in the world today. These facts highlight the vast potential of connecting the unconnected.

The currency of “everything”

Strategies

Big data versus fast dataThe power of Data in Motion is not in the analysis of the stored data or examination of historical data. The real power of Data in Motion lies in the capability to create tools and interactions that matter here and now, in real time.

When it comes to extrapolating value from data, size doesn’t always matter. Sometimes speed is more important than volume.

As organizations rush to take advantage of big data, they shouldn’t ignore the prospects of data in motion, says David Orain, a Senior Consultant focused on emerging technologies at Cisco.

“Sensors, networks, and smart devices are everywhere, providing a torrent of streaming data,” he explains. “This data has tremendous potential, but it retains its highest value for only a short period of time.”

This is different from big data, where the value derived is typically proportional to the quantity of information being analyzed. With data in motion, value is relative to the speed with which information can be processed and acted upon.

“To reap the most value, organizations must master both,” says Orain. “Big data provides context, data in motion provides real-time insight.”

While both are important, Orain says data in motion is often easier and less expensive to exploit. Because real-time processing is applied to data that is already flowing, organizations don’t have to do the heavy lifting—such as consolidation, storage, and analytics—associated with big data.

“With data in motion, you’re not looking for a needle in the haystack like big data,” Orain says. “It’s all about creating new experiences, services, and efficiencies in real time.”

Retailers, for example, can tap video data to understand and interact with customers better and faster. Some have created smart mirrors that combine live video feeds with virtual clothing to let customers “try on” outfits—mixing styles, colors, patterns, and accessories instantaneously.

Healthcare is another industry utilizing data in motion. Several providers are using medical sensors to remotely monitor the progress of patients in their homes. Others are sending real-time patient data from ambulances to the emergency room so the hospital can be better prepared for their arrival.

The manufacturing industry is taking advantage of “fast” data to improve monitoring and control. For example, video analysis can be used to track the movement of machines, products, and people. This allows operational efficiency to be continually fine-tuned, and problems can be identified and addressed before they become severe.

“With an intelligent network and a secure architectural approach,” says Orain, “forward-thinking organizations can capture and act on the most relevant data while it is still in motion, and while it retains its maximum value.”

Get the white paper

To learn more about data in motion, download the white paper at: www.UnleashingIT.com

5Seize innovation, accelerate business, drive outcomes.

Strategies

Unleashing IT6

How Cisco built a big data analytics platform and identified $40 million in new service opportunities.The journey started two years ago with an open-ended objective: data innovation. Cisco wanted to find new ways of creating and unearthing value from the information scattered across the company and its various technology systems. Not just structured data about customers, products, and network activity, but unstructured data found in web logs, videos, emails, documents, and images.

At the time, the big data movement was in its infancy. There were no answers, no roadmaps. Only possibilities and hypothetical outcomes.

“We needed to come up with a use case that marries IT opportunity with business opportunity,” says Piyush Bhargava, a Cisco IT Distinguished Engineer who focuses on big data programs. “At the same time, we wanted the platform to support any number of use cases, so

it needed to be broad, horizontal, and enterprise ready.”

Building the platform

To unlock the business intelligence hidden in globally distributed big data, Cisco IT turned to Hadoop, an open-source software framework that supports data-intensive, distributed applications.

“Hadoop behaves like an affordable supercomputing platform,” Bhargava explains. “It moves compute resources to where the data is stored, which mitigates the disk I/O bottleneck and provides almost linear scalability. Hadoop enabled us to consolidate the islands of data scattered throughout the company.”

If data consolidation is the first step, analytics are the second. Before it could be achieved, however, Cisco IT needed to design and implement an enterprise platform that could support appropriate service-level agreements (SLAs) for availability and performance.

“Our challenge,” says Bhargava, “was adapting the open-source Hadoop platform for the enterprise.”

The start of a journey Experiences

Cisco IT built a Hadoop big data analytics platform using the Cisco® Common Platform Architecture (CPA) for Big Data, which is based on the Cisco Unified Computing System™ and Intel® Xeon® processors. The platform provides high performance in a multitenant environment, anticipating that internal users will continually find more use cases for big data analytics. It also takes advantage of the Cisco Tidal Enterprise Scheduler (TES) to facilitate job scheduling and workload automation. With built-in connectors to Hadoop, TES minimizes programming and debugging tasks and saves hours on each job.

Putting the first use case into production

The first big data analytics program in production at Cisco helps increase revenue by identifying hidden opportunities for partners to sell services.

“Previously, we used traditional data warehousing techniques to analyze the install base and identify opportunities for the next four quarters,” says Srini Nagapuri, Cisco IT project manager. “But analysis took 50 hours, so we could only generate reports once a week.”

The other limitation of the old architecture was the lack of a “single source of truth” for opportunity data. Instead, service opportunity information was spread out across multiple data stores, causing

confusion for partners and the Cisco partner support organization.

Cisco’s new big data platform has removed such limitations. Not only does it bring disparate data sets together for analytical purposes, but it processes 25 percent more data in 10 percent of the time. Analyses are now completed in six hours instead of 50, and opportunities are identified for the next five calendar quarters instead of four. Partners and Cisco employees can also dynamically change the criteria for identifying opportunities.

And the business outcome?

“The solution processes 1.5 billion records daily, and we identified new service opportunities the same day we placed the system in production,” says Nagapuri. These opportunities, he adds, are expected to generate $40 million in incremental revenue from partners in fiscal year 2013.

Advice for others

While Cisco’s initial results are certainly desirable, Bhargava acknowledges others are still wrestling with the newness, uncertainty, and investment required for big data.

“There is always resistance to change, and big data architectures are still very new, very different,” he says. “Getting executive sponsorship, having a strong

change management strategy, and building momentum are essential. It’s also important to get a handle on internal data before incorporating external data from partners, industry sources, and consumer channels like social media.”

Being successful also requires the right technology infrastructure, proactive education so stakeholders and users have a full understanding of the capabilities, and a clear definition of timeline, costs, and benefits.

“The challenge is often justifying the upfront cost. Start with a small investment focused on a defined use case that brings together technology opportunity with business opportunity,” Bhargava recommends. “But make sure you have a big vision and a platform to support it, or there’s a good chance you will end up with small data silos. Once you exhibit the value of big data analytics, other business units will invariably start thinking of additional use cases. That’s when the value of big data gets bigger.”

Speak to a Cisco big data expert

You have questions, we have answers. For a complimentary consultation with a Cisco big data expert about your challenges and opportunities, request a meeting at: www.UnleashingIT.com

7Seize innovation, accelerate business, drive outcomes.

Unleashing IT8

Security breaches and events are often like cold cases. Some linger for long stretches of time before anyone notices. Once identified, it can be difficult to determine where, when, and how the problem occurred, and who or what is responsible. Many security breaches and events are never detected at all.

Solutionary, a wholly owned subsidiary of NTT Group, works to prevent such problems. The managed security services provider (MSSP) actively monitors its clients’ technology systems—including applications, servers, databases, firewalls, and network gear—to spot and throttle security events before they can have a negative impact.

“We’re not looking for viruses and malware,” says Dave Caplinger, Director of Systems for Solutionary. “We’re looking for behaviors—from devices or their users—that might signal a virus, malware, or other security event.”

But there is a major shift underway in how the company protects its customers.

Solutionary is transitioning its flagship ActiveGuard® service platform from a traditional server infrastructure to a big data environment.

“Our other system was having trouble scaling and supporting more in-depth analyses,” Caplinger explains. “Data mining was painful and licensing costs were prohibitive.”

In response, Solutionary turned to MapR enterprise Hadoop software running on the Cisco® Unified Computing System™ (UCS), which utilizes Intel® Xeon® processors. The cloud-based system has been live since spring 2013 for internal testing, and will go into production in early 2014.

“We’ve been very happy with the combination of MapR and UCS,” Caplinger reports. “We’ve configured the entire system as if it’s a network element, which makes it easier to configure, deploy, and manage. And because UCS blurs the line between the server world and the network

Solutionary bets heavily on big data

Experiences

With a big data analytics platform in place, the managed security services provider is transforming the value it delivers to customers.

“We are betting heavily on this system and these capabilities. We think it has big potential, and we’re not taking it lightly.” Don Gray, Chief Security Strategist, Solutionary

world, we can do it with one team instead of separate server and network teams.”

“We are betting heavily on this system and these capabilities,” adds Don Gray, Solutionary’s Chief Security Strategist. “We think it has big potential, and we’re not taking it lightly.”

Broader, deeper analytics

Built and tuned for big data analytics, the new Solutionary environment has opened up an entirely new realm of possibilities—both with the volume of data processed and the type of investigations performed.

“We can do deeper analytics than ever before,” says Gray. “We can do real-time analyses as logs flow into our system, with pre-processing to enrich the data and analyzers in memory. We can also do extremely large batch analytics.”

Beyond one-off analyses, the system is helping Solutionary continually learn and build upon its knowledge base. By taking new data and insights, applying them to historical data, and re-analyzing the batch, Solutionary not only pinpoints current security events, but also the precursors

and catalysts that led to them.

“In the past, we couldn’t perform longer term analyses. It was much more difficult and complex to correlate current findings with historical data,” explains Caplinger. “We now have a much clearer picture of what is happening, why, and for how long.”

In addition to actively monitoring and analyzing each customer’s data, Solutionary will also perform broader level trend analyses across its entire client base. Both deep and broad, these analyses will allow Solutionary to identify “slow and low” activity—like long-term surveillance—that would otherwise be difficult or impossible to detect.

“We have the ability to look for truly global activity that is impacting multiple clients,” says Gray. “The knowledge can be used to improve our services and client protection, and we can also modify and add to the analytics for new insights and value. We think it will be a big growth area for us.”

Benefits beyond security

According to Gray, one of the most significant benefits of the new platform is data accessibility—for both Solutionary and its customers.

“Many companies have avoided MSSPs because they don’t want to give up access to or control of their data,” he explains. “And in the past, we had to pull information for our customers upon request, which took effort and time. Because the new platform is cloud-based, clients will have their data at their fingertips.”

This means Solutionary customers will soon get more than security monitoring and protection. They will get additional use and value out of their data—for audits and investigations, IT management and service delivery, operational performance, and business intelligence.

“We are a security provider first and foremost,” says Gray. “But big data allows us to broaden the value and services we deliver to our customers. And it helps us innovate and adapt faster than ever before.”

Speak to a Cisco big data expert

You have questions, we have answers. For a complimentary consultation with a Cisco big data expert about your challenges and opportunities, request a meeting at: www.UnleashingIT.com

9Seize innovation, accelerate business, drive outcomes.

Unleashing IT10

“Big data will save brick and mortar retail,” claims Paul Schottmiller, a Senior Partner for Cisco Consulting Services’ retail practice.

It’s a bold statement, but industry experts are bullish on the transformative prospects of in-store and online data. Retail success has always been achieved by getting the right product to the right customer at the right time, location, and price. And yet, retail has historically been a time-delayed business, with critical decisions made from outdated information.

“Retailers have always been forced to evaluate the past to inform the present and future. Last month’s inventory levels, last quarter’s marketing campaigns, last year’s holiday season. Even coupons are based on previous shopping trips,” Schottmiller explains. “But the industry is evolving. More than ever, retailers have the ability to gather information in real time, and influence the in-store experience as it is happening.”

What does this mean in dollars and cents? According to Cisco Consulting Services, retailers can realize an estimated 54

percent after-tax profit gain once big data analytics are adopted.1

The rise of sensors

The increase in retail opportunities is directly aligned with an increase in data sources. From in-store sensors—such as video cameras, Wi-Fi, and weight-sensing shelves—to location-based applications on smartphones to social media and website data, retailers have more information about their operations and customers than in the past.

“Big data is helping retailers shift from a review-and-revise model to a real-time, sense-and-respond model,” says Shaun Kirby, Director of Innovations Architecture for Cisco Consulting Services. “But that’s only the first step. Once their capabilities become more sophisticated, they will be able to predict customers’ needs and desires as well as market and operating conditions, and prepare in advance.”

Sensors, in particular, are speeding up retail analyses and decision making. Video

Saving brick and mortar retail Experiences

The opportunities for retailers to tap big data are vast, as long as they avoid notable pitfalls.

11Seize innovation, accelerate business, drive outcomes.

cameras can give a wealth of information—especially when combined with other sensors, such as Wi-Fi—about foot traffic, behavioral patterns, inventory levels, safety incidents, and theft. More advanced video analytics can detect a consumer’s demographics and biometrics, even hand gestures, eyeball movement, and emotions.

“Sensors are everywhere, but they are mostly siloed,” says Kirby. “The greatest value is found when multiple data sources are combined and analyzed, also known as ‘sensor fusion.’ This is when limited data sets of limited value can become truly transformative.”

With more data and better analyses, retailers can eliminate long lines and out-of-stock situations. They can interact with consumers in real time, delivering targeted coupons, incentives, and expertise at the critical moment when a purchase is being considered. And they can make adjustments—to inventory levels, product placement, labor resources, and customer services—with greater speed and precision. Whatever the use case, big data is helping retailers close traditional latency gaps, allowing them to improve their operations and enhance the customer experience faster than ever before.

Avoiding the “creepy factor”

While big data spells big opportunity, it can also present risk. As retailers learn more about consumers and collect personal details—including who and where they are, and how they behave—they must straddle a fine line between insight and privacy, value and intrusion.

“Retailers need to avoid the ‘creepy factor’ at all costs,” warns Schottmiller. “Location matters and price matters, but brand image is huge. Once that image is tarnished or becomes untrustworthy, it can be a long recovery process.”

To stay on the right side of the fine line, retailers need to deliver two things: transparency and value.

“Transparency promotes trust, value promotes desire. Retailers must do both,” says Schottmiller. “Being secretive may allow retailers to fly under the radar for a while, but if those secrets are exposed, retailers will lose brand equity and customers.”

Being open and honest about the data being collected and how it is being used can help allay consumer fears over privacy. Many banks and big

box retailers, for example, show their surveillance feeds at the front door, helping customers be aware of the feeds and understand their primary purpose is security related.

Retailers must also deliver value if they want consumers to readily accept their big data tactics. Having customers opt-in to programs—through location-based applications on smartphones, for example—is one way to foster transparency and deliver value.

“Customers will give up a measure of privacy if they get something in return,” Schottmiller explains. “But they don’t like too much noise, so the offers and services must be truly valuable. It’s a give-and-take proposition.”

1 “Surfing the Data Deluge: How Retailers Can Turn Big Data into Big Profits,” Cisco Internet Business Solutions Group, August 2012.

More information

For additional perspective on big data in retail and an Intel “Future of Shopping” video, visit: www.UnleashingIT.com

Unleashing IT12

CIO Eric Slavinsky works with Cisco and LG&E and KU operations personnel to drive change

The underpinnings of big data success

Intel and Cisco team up to deliver an integrated technology foundation that supports a number of big data workloads. When most people consider big data, they think of the end game: analytics. But according to industry experts, the precursor to successful analytics is an integrated technology foundation that is tuned for a variety of big data workloads.

“To maximize the use and results of any enterprise technology implementation, both hardware and software must work well together,” says Boyd Davis, Vice President and General Manager of Data Center Software at Intel. “Big data is no different. Companies need a foundational layer that provides top-notch manageability and security in support of application-level software and services.”

Intel and Cisco are working together to deliver this foundational layer. The Intel® Distribution for Apache Hadoop software (Intel® Distribution) is being integrated with the Cisco Common Platform Architecture (CPA) for Big Data—a configuration of

the Cisco® Unified Computing System™ (UCS), which is based on Intel® Xeon® processors. The result is a comprehensive Hadoop platform that delivers exceptional performance, management, and capacity while reducing risk and accelerating deployment.

Creating an enterprise-ready platform

Big data technology—and Apache Hadoop in particular—is finding use in an enormous number of applications and is being evaluated and adopted by enterprises of all sizes. While the technology helps transform large volumes of data into actionable information, many organizations are struggling to deploy effective and reliable Hadoop infrastructure that is appropriate for mission-critical applications.

“Cisco and Intel enjoy a close technology partnership, and we’re extending this relationship to create next generation big data solutions,” says Paul Perez, Vice President and General Manager of Computing Systems at Cisco. “We share a vision for a data analytics platform that is seamlessly integrated into an enterprise environment. One that takes advantage of the storage, networking, and built-in automation of Cisco

Solutions

13Seize innovation, accelerate business, drive outcomes.

(From left) Senior Systems Analyst Bryon Fowler, Network Analyst Mark Davis, CIO Jeff Brooks, and Senior IT Manager Kim Sanders bring resiliency and flexibility to Muscogee (Creek) Nation Casinos

UCS and Intel’s processor and management technologies, making it easy to plan, provision, execute, and scale.”

Supporting a variety of workloads

The combination of Intel Distribution and Cisco UCS™ is being tuned to support a variety of workloads and investigations, including batch-mode analysis, massive parallel processing (MPP) queries, machine-learning, and streaming analytics.

Currently the most common big data investigation, batch-mode analysis includes direct MapReduce jobs or Hive queries involving very large data sets. According to Davis, the typical response time is one to several minutes.

“An example of batch-mode analysis would be a job that tries to find anomalies in trading transactions that happened over a period of a month or a year,” he explains. “This would be accomplished by combining trading data with other large reference data sets.”

MPP queries typically involve data warehouse applications like Hive, with an expectation of browser response time or better. In these

queries, the reference data sets are generally smaller than batch-mode analytics.

“MPP queries are often performed to analyze and segment the purchase patterns of customers in a retail chain over short periods of time—using up to a week of data—in order to set prices,” says Davis. “Another example is a pipeline set of queries, used for tasks like malware detection, where an automated job takes output of one query and uses it as input for another. The shorter response time for each query speeds up detection, and therefore improves prevention and response measures.”

Machine-learning includes both predictive analytics and data mining. Using Bayesian classifiers, neural networks, and other algorithms, machines can automatically improve their modeling and prediction capabilities. With data mining, unknown relationships within data sets can be discovered.

“We can use predictive analytics to anticipate machine failures,” Davis explains. “And data mining can be used to discover interesting dependencies in, say, social networking data or telecom call records.”

Streaming analytics involve immediate investigations as data flows into a cluster, rather than being pulled from a static repository. This type of analysis is becoming increasingly important when dealing with sensor data—compiled by smart meters, security systems, and the like—allowing discoveries and decisions to be made in real time.

“We are optimizing our Hadoop software so it works seamlessly on Cisco UCS, regardless of the workload or application,” says Davis. “It will be as close to plug-and-play as possible, so enterprises can focus on application-level software and services and not worry about the foundational layer.”

“Cisco is committed to big data, open source, and our work with Intel,” says Perez, “to optimize data-intensive computing for on-premise enterprise and hosted as-a-service environments.”

Speak to a Cisco big data expert

You have questions, we have answers. For a complimentary consultation with a Cisco big data expert about your challenges and opportunities, request a meeting at: www.UnleashingIT.com

Unleashing IT14

As organizations race to unearth value within big data, many are finding traditional server environments are not up to the task.

“Big data requires a fundamentally different architecture,” says Raghunath Nambiar, Distinguished Engineer and Chief Architect of Big Data Solutions at Cisco, who was recently elected by the Transaction Processing Performance Council (TPC) to lead the development of big data benchmark standards. “To get the most out of big data, companies need an infrastructure that is tuned for big data workloads, with better performance and scalability than traditional environments.”

To meet these requirements, Cisco designed a comprehensive solution: Cisco® Common Platform Architecture (CPA) for Big Data. The architecture takes advantage of the Cisco® Unified Computing System™ (UCS), which utilizes Intel® Xeon® processors, and Cisco Nexus® switches. The comprehensive stack is designed specifically for big data, and includes compute, storage, connectivity, and unified management:

• Cisco UCS 6200 Series Fabric Interconnects, which provide high-speed, low-latency connectivity for servers and integrated, unified management for all connected devices.

• Cisco UCS 2200 Series Fabric Extenders, which provide highly scalable and extremely cost-effective connectivity for a large number of nodes.

• Cisco UCS C240 M3 Rack Servers, which are two-rack-unit (2RU) servers designed for a wide range of compute, I/O, and storage capacity demands.

• Cisco Nexus switches, the foundation of Cisco® Unified Fabric, delivering exceptional availability and outstanding scalability to meet the requirements of mission-critical data centers.

“Our core strength in networking technologies combined with Cisco UCS enables us to offer big data clusters with hundreds of servers and petabytes of storage,” says Nambiar. “And all of it can be managed from a single pane using UCS Manager and UCS Central, either in a data center or distributed globally.”

Sometimes forgotten in big data discussions and decisions is the network, which plays a crucial role within the cluster and between the cluster and data sources. By combining compute and networking technologies, Cisco CPA offers predictable performance and network programmability to meet big data requirements. It also seamlessly integrates with Oracle databases, SAP HANA, and other workloads in the data center on a common fabric and management platform to simplify the infrastructure and minimize cost.

“If interest and adoption are any indication, Cisco CPA for Big Data is very much needed in the marketplace,” says Nambiar. “Within a few months after it became available, it was already being deployed in a range of industries, including finance, retail, service provider, content management, and government.”

Get the solution briefs

For Cisco UCS and Nexus solution briefs, highlighting big data optimization and software integration, visit: www.UnleashingIT.com

Combining data center and network technologies, the new Cisco® UCSTM Common Platform Architecture for Big Data is built for demanding tasks.

Tuning Cisco® UCSTM and Cisco Nexus® for big data

Solutions

To keep up with growing demand for the exploration of large data sets, organizations need an easy-to-use workload automation solution. Depending on the company’s infrastructure and business needs, the tool needs to orchestrate processes involving a variety of technologies and workloads.

The Cisco Tidal Enterprise Scheduler (TES) fits the bill. An end-to-end workload automation solution, TES offers built-in adapters to Hadoop, Sqoop, and Hive as well as leading enterprise resource planning (ERP), database, data warehouse, data integration, and business intelligence applications.

“TES is used to schedule processes that move data in and out of big data file systems, run data feeds from inside and outside the firewall, and execute big data

workloads,” says Andrew Blaisdell, a Cisco Product Marketing Manager specializing in workload automation for big data services.

Along with complex, time-based batch scheduling, Cisco TES automates workloads by initiating event-based actions. An event such as the creation of a new customer record might trigger an action such as moving a set of records into a data warehouse. Events can also include running self-service ad hoc reports for end users or watching FTP folders for changes.

“Cisco IT specialists have validated and run proof of concept testing on the TES API integration points for loading data and running Hive queries, Sqoop ETL processes, and MapReduce workloads,” Blaisdell says. “They love the deep integration and ease-of-use of TES, and

see a faster time to market for their big data services.”

TES runs jobs and events from a single, centralized server and can manage many thousands of jobs per day. All big data jobs are managed from a single instance, lowering the burden of having to mange a distributed environment. TES’s end-to-end coverage also allows administrators both inside and outside the data center to connect and manage workloads from any data source in the enterprise.

More information

To learn more about end-to-end workload automation, get the white paper and solution briefs at:www.UnleashingIT.com

An easy-to-use automation and orchestration tool for big data workloads.

Cisco® Tidal Enterprise Scheduler Solutions

15Seize innovation, accelerate business, drive outcomes.

34%

Industry-Leading Database Performance

34% Faster 2

For more performance information, visit cisco.com/go/ucsbenchmarks. 1. Based on SPECjbb2005 benchmark on Cisco UCS C220 M3 server at 1,584,567 BOPS, 792,284 BOPS/JVM. 2. Based on TPC Benchmark C Results on 2 Processor Systems. Cisco UCS C240 M3 High-Density Rack Server with Oracle Database 11g Release 2 Standard Edition One, 1,609,186.39 tpmC, $0.47/tpmC, available 9/27/12 compared to IBM Power 780 Server Model 9179-MHB with IBM DB2 9.5, 1,200,011.00 tpmC, $0.69/tpmC, available 10/13/10. 3. Based on SPECjEnterprise2010 benchmark with 8 total Java EE Server processors on Cisco UCS B440 M2 servers at 26,118.67 EjOPS compared to RISC-based IBM Power 780 at 16,646.34 EjOPS. SPEC®, SPECjbb®, and SPECjEnterprise® are registered trademarks of Standard Performance Evaluation Corporation. TPC Benchmark C® is a trademark of the Transaction Performance Processing Council (TPC). The performance results described here are derived from detailed benchmark results available at http://www.spec.org and http://www.tpc.org as of 1-15-2013. ©2013 Cisco and/or its a� liates. All rights reserved. All third-party products belong to the companies that own them. Cisco, the Cisco logo, and Cisco UCS are trademarks or registered trademarks of Cisco. Intel, the Intel logo, Xeon and Xeon Inside are trademarks or registered trademarks of Intel Corporation in the U.S. and/or other countries. All other trademarks are the property of their respective owners.

Unparalleled Application Performance with Cisco Servers.

1,584,567

Find out more at cisco.com/servers

Cisco Uni� ed Computing System

Outperforms RISC by

On Java Applications3

Business Operations Per Second:Unparalleled Cisco Server Performance. 1

57%With Intel® Xeon® processors

Cisco-UCS_App-Q3-7.75x10.5.indd 1 1/28/13 3:52 PM