Welcome!

Cloud Expo Authors: Kevin Jackson, Walter Hinton, Maureen O'Gara, Esmeralda Swartz, Paul Ressler

Related Topics: Cloud Expo, Open Source, Apache

Cloud Expo: Article

Hadoop and Realtime Cloud Computing

Architectures such as MapReduce and Hadoop are good for batch processing of big data, but bad for realtime processing

Big data is creating a massive disruption for the IT industry. Faced with exponentially growing data volumes in every area of business and the web, companies around the world are looking beyond their current databases and data warehouses for new ways to handle this data deluge.

Taking a lead from Google, a number of organizations have been exploring the potential of MapReduce, and its open source clone Hadoop, for big data processing. The MapReduce/Hadoop approach is based around the idea that what's needed is not database processing with SQL queries, but rather dataflow computing with simple parallel programming primitives such as map and reduce.

As Google and others have shown, this kind of basic dataflow programming model can be implemented as a coarse-grain set of parallel tasks that can be run across hundreds or thousands of machines, to carry out large-scale batch processing on massive data sets.

Google themselves have been using MapReduce for batch processing for over six years, and others, such as Facebook, eBay and Yahoo have been using Hadoop for the same kind of batch processing for several years now. So today, parallel dataflow is firmly established as an alternative to databases and data warehouses for offline batch processing of big data. But now the game is changing again...

In recent months, Google has realized that the web is now entering a new era, the realtime era, and that batch processing systems such as MapReduce and Hadoop cannot deliver performance anywhere near the speed required for new realtime services such as Google Instant. Google noted that

  • "MapReduce isn't suited to calculations that need to occur in near real-time"

and that

  • "You can't do anything with it that takes a relatively short amount of time, so we got rid of it"

Other industry leaders, such as Jeff Jonas, Chief Scientist for Analytics at IBM, have made similar remarks in recent weeks. In his recent video "Big Thoughts on Big Data", Jonas notes that with only batch processing tools to handle it, organizations grappling with a relentless avalanche of realtime data will get dumber over time rather than getting smarter.

  • "The idea of waiting for a batch job to run doesn't cut it. Instead, how can an organization make sense of what it knows, as a transaction is happening, so that it can do something about it right then"
  • "I'm not a big fan of batch processes... I've never seen a batch system grow up an become a realtime streaming system, but you can take a realtime streaming system and make it eat batches all day long"
  • "I like Hadoop but it's meant for batch activities. That's not the kind of back-end you would use for realtime sense-making systems"

So coarse-grain dataflow architectures such as Hadoop are good for batch, but bad for realtime.

To power realtime big data apps we need a completely new type of fine-grain dataflow architecture. An architecture that can, for example, continuously analyze a stream of events at a rate of say one million events per second per server, and deliver results with a maximum latency of five seconds between data in and analytics out. At Cloudscale we set out to crack this major technical problem, and to build the world's first "realtime data warehouse". The linearly scalable Cloudscale parallel dataflow architecture not only delivers game-changing realtime performance on commodity hardware, but also, as Jeff Jonas notes above "can eat batches all day long" like a traditional MapReduce or Hadoop architecture. There isn't really an established name yet for such a system. I guess we could call it a "Redoop" architecture (Realtime Dataflow on Ordinary Processors, or Realtime Hadoop).

More Stories By Bill McColl

Bill McColl left Oxford University to found Cloudscale. At Oxford he was Professor of Computer Science, Head of the Parallel Computing Research Center, and Chairman of the Computer Science Faculty. Along with Les Valiant of Harvard, he developed the BSP approach to parallel programming. He has led research, product, and business teams, in a number of areas: massively parallel algorithms and architectures, parallel programming languages and tools, datacenter virtualization, realtime stream processing, big data analytics, and cloud computing. He lives in Palo Alto, CA.

Cloud Expo Breaking News
“I believe it is incumbent on the Cloud Service Providers (CSPs) and/or System Integrators (SIs) to understand the regulatory and compliance-related issues that their customers face,” noted Manjula Talreja, VP of Global Cloud Business Development at Cisco, in this exclusive Q&A with Cloud Expo Conference Chair Jeremy Geelan. “Of course these issues are different in each industry and in each country.” Cloud Computing Journal: The move to cloud isn't about saving money, it is about saving time - ...
“Regulations and compliance are key trust topics with regards to cloud solutions and technology,” noted Sven Denecken, Vice President, Strategy and Co-Innovation Cloud Solutions, SAP AG, in this exclusive Q&A with Cloud Expo Conference Chair Jeremy Geelan. “But it is also more than security of access – it is portability of data and a clear definition of where the data resides.” Cloud Computing Journal: The move to cloud isn't about saving money, it is about saving time – agree or disagree? Sve...
Many organizations want to expand upon the IaaS foundation to deliver cloud services in all forms – software, mobility, infrastructure and IT. Understanding the strategy, planning process and tools for this transformation will help catalyze changes in the way the business operates and deliver real value.
WSO2 on Thursday announced that WSO2 Vice President of Technology Evangelism Chris Haddad and SUSE Business Development Manager Frank Rego will lead a joint presentation at 12 International Cloud Expo. The session, "Bridging IaaS and PaaS to Deliver the Service-Oriented Data Center," is part of the event's Enterprise Cloud Computing Track on Thursday, June 13, 2013. The Cloud Expo conference is being held June 10-13, 2013 at the Javits Center in New York City. Bridging IaaS and PaaS to Deliver ...
IT has more opportunities than ever before with the growth in users, devices, data and secure cloud services. This creates not only a more enriching experience for users, but more opportunities for businesses. The key to capitalizing on these opportunities is to have the right tools in place to help scale operations. In his Day 3 Keynote at 12th Cloud Expo | Cloud Expo New York [June 10-13, 2013], Intel's Rob Crooke will describe the range of products that Intel provides to support different usa...
Quantum Corp., a proven global expert in data protection and Big Data management, has announced that Senior Vice President of Cloud Solutions Henrik Rosendahl will present a session exploring the future of cloud data protection and the impact of data reduction technologies on cloud storage at the 12th International Cloud Expo. The conference takes place June 10-13 at the Javits Center in New York City. Rosendahl will explore trends in cloud-based backup and disaster recovery (DR) and how curre...
One of the cloud’s biggest draws is the capability to virtualize computing resources, allowing it to be consumed with the click of a mouse. But behind that simple click is an enormous infrastructure challenge that has recently been cited as a major cause for slower enterprise adoption. Enterprises can better prepare for this shift and take full advantage of future computing benefits. Between architecture design and migration planning, the road can be long, so what do you do with your talent? I...
In the old world of IT, if you didn't have hardware capacity or the budget to buy more, your project was dead in the water. Budget constraints can leave some of the best, most creative and most ingenious innovations on the cutting room floor. It’s a true dilemma for developers and innovators – why spend the time creating, when a project could be abandoned in a blink? That was the old world. In the new world of IT, developers rule. They have access to resources they can spin up instantly. A hyb...
INetU, the industry's experts in complex hosting and a global provider of business-centric managed cloud and application hosting, has announced that Cloud Architect Rich Hand will be presenting "Private Cloud, Public Cloud - Is There a Third Option?" at the 12th International Cloud Expo taking place June 10-13, 2013 in New York City. As more enterprise IT departments move into the cloud, many executives are evaluating whether to adopt a Public or Private cloud. The cost benefits of the Public ...
“I’m careful when using terms like Big Data, because it can mean so many things to different people,” explained Eric Hanselman, Chief Analyst at 451 Research, in this exclusive Q&A with Cloud Expo Conference Chair Jeremy Geelan. “There is huge value in analytics that companies can use to pull intelligence from a collection of data sources that are available in their businesses. The inexpensive storage that cloud services can offer make a great environment to pull together siloed data.” Cloud Co...