Guest Blog by Jack Norris
Jack is responsible for worldwide marketing for MapR Technologies, the leading provider of a enterprise grade Hadoop platform. He has over 20 years of enterprise software marketing experience and has demonstrated success from defining new markets for small companies to increasing sales of new products for large public companies. Jack’s broad experience includes launching and establishing analytic, virtualization, and storage companies and leading marketing and business development for an early-stage cloud storage software provider.
Big Data use cases are changing the competitive dynamics for organizations with a range of operational use cases. Operational intelligence refers to applications that combine real-time, dynamic, analytics that deliver insights to business operations. Operational intelligence requires high performance. “Performance” is a word that is used quite liberally and means different things to different people. Everyone wants something faster. When was the last time you said, “No, give me the slow one”?
When it comes to operations, performance is about the ability to take advantage of market opportunities as they arise. To do this requires the ability to quickly monitor what is happening. It requires both real-time data feeds and the ability to quickly react. The beauty of Apache Hadoop, and specifically MapR’s platform, is that data can be ingested as a real-time stream; analysis can be performed directly on the data, and automated responses can be executed. This is true for a range of applications across organizations, from advertising platforms, to on-line retail recommendation engines, to fraud and security detection.
When looking at harnessing Big Data, organizations need to realize that multiple applications will need to be supported. Regardless of which application you introduce first, more will quickly follow. Not all Hadoop distributions are created equal. Or more precisely, most Hadoop distributions are very similar with only minor value-added services separating them. The exception is MapR. With the best of the Hadoop community updates coupled with MapR’s innovations, the broadest set of applications can be supported including mission-critical applications that require a depth and breadth of enterprise-grade Hadoop features.
Read More »
Tags: Big Data, enterprise scheduler, Hadoop, informatica, job scheduling, MapR, Tidal Enterprise Scheduler, UCS, workload automation
The Transaction Processing Performance Council today announced its fifth international Conference on Performance Evaluation and Benchmarking (TPCTC 2013). I’ve the great privilege of chairing TPCTC series since 2009. This year’s conference will be collocated with the 39th International Conference on Very Large Data Bases (VLDB 2013) on August 26, 2013 in Riva del Garda, Italy. With this conference we are encouraging researchers and industry experts to submit ideas and methodologies in performance evaluation, measurement and characterization. Additional information on TPCTC 2013 is available online at http://www.tpc.org/tpctc/tpctc2013/.
Tags: Big Data, Big Data Benchmarks, bigdatatop100, Hadoop, TPCTC, WBDB, WBDB 2012, wbdb2012-in
Cisco and NetApp have been partners for over a decade, and in January we announced the planned expansion of our partnership. We are always looking to work with our partners in new ways to offer customers greater choice, and Cisco and NetApp are working toward delivering a complete platform for enterprises in data-intensive industries with business-critical SLAs. The solution will offer pre-sized storage, networking, and compute in a highly reliable, ready-to-deploy Hadoop stack, and it is planned to be generally available summer 2013. But, who can wait until summer?! I know we can’t, so we’re going to offer a demo of the joint reference architecture at Cisco Live! Melbourne March 5-8, and we hope you’ll stop by to check it out!
To give you more information on the solution — it will be pre-validated for enterprise Hadoop deployments built using 6296 Fabric Interconnects (connectivity and management), a pair of Nexus 2232s, C220 M3 Servers (compute) and NetApp E5400 and FAS 2240 series storage arrays. Following the – highly successful – FlexPod model of pre-sized rack level configurations, this solution will be made available through the well-established FlexPod sales engagement and channel. Field sales and partners from both companies will resell the solution upon general availability.
Tags: Big Data, Cisco UCS CPA, CPA, Hadoop, netapp
This has been an exciting week. Further expanding its Big Data portfolio, Cisco has announced collaboration with Intel, its long term partner, for the next generation of open platform for data management and analytics. The joint solution combines Intel® Distribution for Apache Hadoop Software with Cisco’s Common Platform Architecture (CPA) to deliver performance, capacity, and security for enterprise-class Hadoop deployments.
As described in my blog posting, the CPA is highly scalable architecture designed to meet variety of scale-out application demands that includes compute, storage, connectivity and unified management, already being deployed in a range of industries including finance, retail, service provider, content management and government. Unique to this architecture is the seamless data integration and management integration capabilities between big data applications and enterprise applications such as Oracle Database, Microsoft SQL Server, SAP and others, as shown below:
The current version of the CPA offers two options depending on use case: Performance optimized – offers balanced compute power with I/O bandwidth optimized for price/performance, and Capacity optimized – for low cost per terabyte. The Intel® Distribution is supported for both performance optimized and capacity optimized options, and is available in single rack and multiple rack scale.
The Intel® Distribution is a controlled distribution based on the Apache Hadoop, with feature enhancements, performance optimizations, and security options that are responsible for the solution’s enterprise quality. The combination of the Intel® Distribution and Cisco UCS joins the power of big data with a dependable deployment model that can be implemented rapidly and scaled to meet performance and capacity of demanding workloads. Enterprise-class services from Cisco and Intel can help with design, deployment, and testing, and organizations can continue to rely on these services through controlled and supported releases.
A performance optimized CPA rack running Intel® Distribution will be demonstrated at the Intel Booth at O’Reilly Strata Conference 2013 this week.
Tags: Big Data, Cisco UCS CPA, CPA, Hadoop, HBase, Intel, NoSQL
Today Paul Perez, Vice President and CTO of Cisco’s Data Center Group joined on stage downtown San Francisco Boyd A. Davis, Intel Architecture Group Vice President and GM, Data Center Software Division to announce a proposed extension of the alliance between Cisco and Intel into Big Data .
Over the past months, our readers had the opportunity to appreciate the growing investment of Cisco in this market frequently articulated by our experts Raghunath Nambiar and Jacob Rapp through blog postings and speaking at industry events.
Cisco and Intel have worked together for years to deliver enterprise solutions that improve performance and enable organizations to deliver new services. As we have stated several times recently , Intel has been a critical partner and significant contributor to the phenomenal success of the Cisco UCS. So it will not come as a surprise to anybody that Cisco and Intel are looking to partner again to offer you a leading Big Data solution.
In this video, Cisco Paul Perez and Intel Boyd Davis explained how Cisco will support the Intel distribution of Apache Hadoop on UCS, and how both companies intend to collaborate to address the growing Big Data needs of our joint customers.
Please read the Intel announcement and stay tuned for a more detailed and technical blog by Raghunath Nambiar.
Tags: Big Data, Cisco, data center, Hadoop, Intel, UCS