Hadoop In The Real World


Published on

Many organizations are struggling to understand Big Data, what it is, and how to best harness it. Generated by mobile devices, social media, click streams, machines, applications, and more, data is exploding at an exponential rate from sources that are increasingly complex and varied.

How do you manage and leverage both structured and unstructured data? How do you use advanced analytics to gain new insights, find anomalies, correlations, and answers that can transform the business?

Learn how enterprises are implementing Hadoop to get the answers to these questions and more.

Published in: Technology, Business
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide
  • Thank you for the opportunity
  • Thank you for your time today. Today we’ll walk through a brief presentation to give you an overview of MapR. The high level summary of what we’ll talk about can be summarized in 3 points.

    Hadoop is the leading technology for Big Data platform with the power to transform customer’s business
    MapR gives you the most technologically advanced distribution for Hadoop
    MapR has the product, services, and partner network to ensure production success and continued success.
  • Hadoop is making CIO’s rethink their data architecture. It is a fundamental shift in the economics of data storage/processing/analytics, and is opening up entirely new business opportunities. Let’s talk about 3 key trends we are seeing, as well as 3 realities or implications on your business and “readiness” to harness the power of big data and Hadoop.
  • The first trend is that the industry leaders have shown how to use big data to compete and win in their markets. It’s no longer a nice to have – you need big data to compete

    Google pioneered MapReduce processing on commodity hardware and used that to catapult themselves to into the leading search engine even though they were 19th in the market

    Yahoo! Leveraged these ideas to create Hadoop to keep up with Google and many mainstream companies have followed with new data-driven applications such as “people you may know” (started by LinkedIN and now used by Facebook, Twitter, and every social application), product recommendation engines, contextual and personalized music services (beats), measuring digital media effectiveness (comScore), serving more relevant/targeted ads(Comcast, rubicon project), fraud and risk detection, healthcare efficacy, and more

    What makes the difference? A lot of attention is given to data science and developing sophisticated new algorithms, but in many cases just having more data beats better algorithms. (make point on collecting more consumer interaction as well as transaction data, as an example).

    In addition, competitive advantage is decided by very small percentages. Just 1% improvement in fraud can mean hundreds $millions in savings. A ½% lift in advertising effectiveness means millions in new product sales and profitability. The same can be applied to customer churn, disease diagnosis, and more.

  • A second trend in enterprise architecture has been big data overwhelming the existing workload-specific systems which are in production. (list of requirements for each of these on the side in text)
    People started with mainframes or operational systems which run ERP, finance, CRM and other mission-critical applications. They require… (pick out attributes you want to stress on the left)
    You also have data warehouses, marts, data mining, and other analytical systems which pull data from these operational and other systems for providing insights to the business for decision making
    The amount/variety of data has been overloading these systems. You reach a certain point as you try to ingest new types of data when these systems are not cost-effective to scale to terabytes or petabytes of data

  • Hadoop has become the defacto big data platform which allows organizations to keep up with big data and feed data-driven applications and processes
    This chart shows the percentage growth of jobs from Indeed.com.
    Compared to other popular technologies such as MongoDB and Cassandra, Hadoop is not only the fastest growing big data technology it’s one of the fastest growing technologies period.
    Hadoop has the most robust ecosystem and momentum and is the big data platform of choice for industry-leading, data-driven companies

    (Also of interest is that Indeed.com (which is a subsidiary of a Japanese-owned company) is a customer of MapR – they harness and analyze all of the job trends data using MapR)

  • The first reality is that as people put Hadoop into production, to relieve the pressure from other systems in their enterprise architecture it needs to reliable . Hadoop needs to be held to the same enterprise standards as your Oracle, SAP, Teradata, NetApp storage, or any other enterprise system.
    Many organizations are putting Hadoop into their data center to provide (list of use cases underneath) … it can do all of this and more, but
    For Hadoop to act as a system of record , it must provide the same guarantees for SLA’s, performance, data protection, and more
    Most importantly, Hadoop has the potential for both analytics AND operations. It can be used to optimize the data warehouse provide batch data refining or storage. But Hadoop can provide many operational analytics or database operations/jobs when done right.
  • In a recent article by Tom Davenport (http://www.cmswire.com/cms/big-data/5-things-to-lessen-your-anxiety-about-big-data-024382.php) – he says
    “Big data’s biggest wins come from making many small decisions vs. one that’s huge. The majority of big data driven decisions will be recurring, made at speed (in milliseconds), and at scale; actions will be taken automatically (vs. reviewed and approved by an individual). Examples include ad platforms making many constant adjustments, fraud detection on millions of transactions that are based on individual patterns, fleet management and routing taking into account current conditions….

    This requires a Hadoop platform that can go beyond batch and support streaming writes so data can be constantly writing to the system while analysis is being conducted. High performance to meet the business needs and real-time operations the ability to perform online database operations to react to the business situation and impact business as it happens not report on it one week, month or quarter later.

    To do this requires THE RIGHT ARCHITECTURE
  • 96% of US internet traffic
    Formerly used 2 other distros
    Went to MapR to meet very high SLA’s and performance
  • Push messaging. Starbucks or ESPN applications, and others.
    MapR is the only software that they pay for. Have HBase committers on staff.
    Taken 8 applications clusters and moved into 1 MapR cluster; have 1 cluster with 8 sub-clusters running on different sets of nodes. Data placement control enables this.
    Went from 12 CDH servers and cut it down to 6. Just for HBase tables. (They won’t use M7 since they are HBase committers. )
  • Verizon Teradata example
    Less than 10% of CDR’s analyzed
  • More relevant local example Experian
  • Solutionary is a Managed Security Services provider with services that include network intrusion detection

  • ----- Meeting Notes (3/27/14 11:12) -----
    Zions Bank
    Video - Phishing Attack
  • http://www.datanami.com/datanami/2014-02-21/a_peek_inside_cisco_s_hadoop_security_machine.html
  • 20 TB per day; 60 nodes, 1000 cores
  • MapR is the Hadoop technology leader with over 500 paying customers and the largest production deployments in the world.

    People like to think of Yahoo, Facebook, and LinkedIn as big Hadoop users, and they are, but you would expect this because of their deep engineering heritage. Mainstream organizations who want to leverage Hadoop without hiring armies of engineers turn to MapR. We have the largest retailer, largest financial services deployment, largest media, healthcare, and government agencies

    Through a combination of Apache Hadoop community participation and a differentiated data platform, MapR lets organizations do more with Hadoop in both operational and analytical use cases that are expensive or impossible with other Hadoop distributions.
  • Again,

    Hadoop is the leading technology for Big Data platform with the power to transform customer’s business
    MapR gives you the most technologically advanced distribution for Hadoop
    MapR has the product, services, and partner network to ensure production success and continued success.

  • Hadoop In The Real World

    1. 1. © 2014 MapR Technologies 1© 2014 MapR Technologies
    2. 2. © 2014 MapR Technologies 2 MapR Overview BIG DATA BEST PRODUCT BUSINESS IMPACT Hadoop Top Ranked Production Success
    3. 3. © 2014 MapR Technologies 3© 2014 MapR Technologies 3 Trends Forcing a revolution in enterprise architecture
    4. 4. © 2014 MapR Technologies 4 Industry Leaders Compete and Win with Data1TREND More Data Beats Better Algorithms Collecting interaction data from ecommerce, social media, offline, and call centers enables a “customer 360 view” and consumer intimacy Competitive Advantage is Decided by 0.5% Consumer financial services: 1% improvement in fraud means hundreds of millions of dollars Advertising and retail: 0.5% improvement in lift means millions of dollars increase in profitability
    5. 5. © 2014 MapR Technologies 5 Big Data is Overwhelming Traditional Systems • Mission-critical reliability • Transaction guarantees • Deep security • Real-time performance • Backup and recovery • Interactive SQL • Rich analytics • Workload management • Data governance • Backup and recovery Enterprise Data Architecture 2TREND ENTERPRISE USERS OPERATIONAL SYSTEMS ANALYTICAL SYSTEMS PRODUCTION REQUIREMENTS PRODUCTION REQUIREMENTS OUTSIDE SOURCES
    6. 6. © 2014 MapR Technologies 6 Hadoop: The Disruptive Technology at the Core of Big Data3TREND JOB TRENDS FROM INDEED.COM Jan ‘06 Jan ‘12 Jan ‘14Jan ‘07 Jan ‘08 Jan ‘09 Jan ‘10 Jan ‘11 Jan ‘13
    7. 7. © 2014 MapR Technologies 7© 2014 MapR Technologies And 3 Realities
    8. 8. © 2014 MapR Technologies 8 OPERATIONAL SYSTEMS ANALYTICAL SYSTEMS ENTERPRISE USERS 1REALITY • Data staging • Archive • Data transformation • Data exploration • Streaming, interactions Hadoop Relieves the Pressure from Enterprise Systems 2 Interoperability 1 Reliability and DR 4 Supports operations and analytics 3 High performance Keys for Production Success
    9. 9. © 2014 MapR Technologies 9 Hadoop is Being Used to Drive Small, Rapid Decisions2REALITY High Arrival Rate Data • Clickstream • Social media • Sensor data, … Business Impact • Revenue optimization • Risk mitigation • Operational efficiency
    10. 10. © 2014 MapR Technologies 10 Architecture Matters for Success3REALITY FOUNDATION
    11. 11. © 2014 MapR Technologies 11 FOUNDATION Architecture Matters for Success3REALITY Data protection & security High performance Multi-tenancy Workload management Open standards for integration NEW APPLICATIONS SLAs TRUSTEDINFORMATION LOWERTCO
    12. 12. © 2014 MapR Technologies 12 World-Record Performance on Cisco UCS PREVIOUS RECORD: 1.6 TB with 2200 nodes 1.65 TBIN 1 MINUTE 298 NODES NEW MINUTESORT WORLD RECORD MapR: With a Fraction of the Hardware Previous Record Get the most out of your hardware infrastructure
    13. 13. © 2014 MapR Technologies 13© 2014 MapR Technologies MapR: Hadoop Real World Examples
    14. 14. © 2014 MapR Technologies 14 Largest Biometric Database in the World PEOPLE 20 BILLION BIOMETRICS National identification system in India for all citizens Fingerprint and retinal scan images and citizen data 1 trillion+ ID verifications per week, geographically dispersed across 8 data centers About 600m “residents” enrolled Requires 100ms response times; zero data loss and cross-datacenter replication
    15. 15. © 2014 MapR Technologies 15 Helping Farmers: Software and Insurance • Help farmers protect and improve their farming operations • Use machine learning to predict weather & other agribusiness elements • Combine hyper-local weather monitoring, agronomic data modeling, and high-resolution weather simulations • Project weather for 2.5 years at every 20x20 plot across the US • Climatology simulations need to quickly experiment at small scale and then scale reliably • MapR Hadoop to analyze >10 trillion data points from 2.5million sensors • Faster machine learning performance enables more/faster simulations • MapR M7 enables geospatial database backed by Amazon S3 OBJECTIVES CHALLENGES SOLUTION Lower risk with new insurance products through better data analytics Business Impact “85% of farmer risk is weather-related. MapR has enabled us to provide a class of weather insurance that was not available before, helping farmers protect their operations.” IT Director, Climate Corporation
    16. 16. © 2014 MapR Technologies 16 Cisco was able to analyze service sales opportunities in 1/10 the time, at 1/10 the cost, and generated $40 million in incremental service bookings in the first year. Cisco: 360° Customer View Cisco uses integrated customer data to increase revenues • Create shared view of customer & operations across 75,000 employees • Increase revenue opportunities with sales partners • Customer information was siloed in different divisions • Customer interactions were inconsistent and not satisfying • Missed opportunities for upselling/cross selling • Use MapR to collect customer information across touch points • Integrate billing, support, manufacturing, social media, websites, dial-in data • Generate new sales leads internally and for partners OBJECTIVES CHALLENGES SOLUTION Architecture for Sales Partner Opportunities Business Impact
    17. 17. © 2014 MapR Technologies 17 Financial Services: Recommendation Engine & Real-time Targeting Making personalized real-time offers to credit card customers • Increase revenue and customer loyalty with real-time personalized offers • Increases revenue and improves customer experience through real-time targeting • A more flexible, scalable platform that’s a fraction of the cost of traditional technologies • Ensures reliability with MapR’s high availability and disaster recovery features • Many different CRM tools and siloed targeting engines • Developers and analysts are unable to access all customer data • Want to increase speed and relevance of recommendations • MapR M7 centralizes analytics and operational apps on one platform • Integrates all customer online and offline data into HBase in real-time: card member spend graph, merchant data, location, and feedback • Centralized customer data repository provides more accurate insights • Uses Mahout machine learning to provide real-time personalized offers OBJECTIVES CHALLENGES SOLUTION Business Impact GLOBAL FINANCIAL SERVICES CORPORATION
    18. 18. © 2014 MapR Technologies 18 Rubicon Project: Ad Optimization Rubicon Project runs a real-time automated advertising platform • Create open ad platform for over 100K global advertising brands and over 500 of the world’s premium publishers • To keep up with their rapid growth, they needed to move to a fault-tolerant, high-availability Hadoop production system • Hadoop had become central to their operations but they were having problems with instability • Their 330-node Hadoop cluster processes 1M records/second • They chose MapR for enterprise features such as high availability, data protection and recoverability, disaster recovery, redundancy, and support OBJECTIVES CHALLENGES SOLUTION “Our company cannot run without Hadoop and MapR. We rely on MapR’s self-healing HA, disaster recovery and advanced monitoring features to conduct 90 billion real-time auctions on our global transaction platform.” Jan Gelin, VP of Engineering, Rubicon Project Business Impact
    19. 19. © 2014 MapR Technologies 19 Operational Apps: Push Messaging Platform MapR: Enabling the “smartest, most aware, precise, easy-to-use, scalable, secure and powerful push messaging platform on the planet" • Enable organizations to build one-on-one brand relationships • Push messaging and geo-location targeting that • Support large numbers of customers in a multi-tenant platform • Target specific consumers in real time with relevant offers • Increase reliability of push messaging while lowering data center costs OBJECTIVES CHALLENGES SOLUTION • Increasing engagement and customer loyalty for 100’s of leading brands • Reduced hardware footprint by 50% • Consolidated 8 Hadoop clusters into 1 MapR cluster Business Impact • MapR Distribution for Hadoop with Apache HBase for operational workloads • Data placement control enables efficient cluster resource management
    20. 20. © 2014 MapR Technologies 20© 2014 MapR Technologies Enterprise Data Hub Case Studies
    21. 21. © 2014 MapR Technologies 21 Data Warehouse Optimization Improve data services to customers while reducing enterprise architecture costs • Provide cloud, security, managed services, data center, & comms • Report on customer usage, profiles, billing, and sales metrics • Improve service: Measure service quality and repair metrics • Reduce customer churn – identify and address IP network hotspots • Cost of ETL & DW storage for growing IP and clickstream data; >3 months • Reliability & cost of Hadoop alternatives limited ETL & storage offload • MapR Data Platform for data staging, ETL, and storage at 1/10th the cost • MapR provided smallest datacenter footprint with best DR solution • Enterprise-grade: NFS file management, consistent snapshots & mirroring OBJECTIVES CHALLENGES SOLUTION • Increased scale to handle network IP and clickstream data • Reduced workload on DW to maintain reporting SLA’s to business • Unlocked new insights into network usage and customer preferences Business Impact FORTUNE 100 TELCO
    22. 22. © 2014 MapR Technologies 22 Mainframe Offload & Optimization Free up MIPS with Hadoop to Lower Cost and Modernize Data Architecture • Reduce costs: defer expensive mainframe upgrades and reduce MIPS • Maintain business SLA’s • Open standards: convert gradually to next-gen data architecture (Hadoop) • Connect and transform unique data formats (EBCDIC vs. ASCII) • Skills shortage: Hadoop and mainframe (COBOL & JCL) • Reliability and flexibility of alternate systems • Syncsort connectivity and data conversions on MapR • MapR uniquely handle small files without additional ETL steps to meet SLA • MapR only Hadoop distribution with reliability mainframe customers expect OBJECTIVES CHALLENGES SOLUTION  Reduce storage costs: Go from $100K/TB to $1K/TB by migrating data to Hadoop  Use MIPS wisely: Save average of $7K per MIPS by offloading batch jobs to Hadoop  Deliver powerful new insights: combine mainframe data with big data for deep insights Business Impact
    23. 23. © 2014 MapR Technologies 23© 2014 MapR Technologies Security and Risk Mgmt. Case Studies
    24. 24. © 2014 MapR Technologies 24 Solutionary: Managed Security Services Provider Threat detection on real-time streaming data via platform as a service (PaaS) • To address their growing customer base by processing trillions of messages (petabyte) per year while continuing to provide reliable security services • To improve data analytics by leveraging newer, more granular unstructured data sources ”MapR has taken Apache Hadoop to a new level of performance and manageability. It integrates into our systems seamlessly to help us boost the speed and capacity of data analytics for our clients.” - Dave Caplinger, Director of Architecture, Solutionary • Expanding existing database solution to meet demand was cost prohibitive • The existing technology could not process unstructured data at scale • Replaced RDBMS with MapR M7 to scale while retaining reliability requirements • Reduced time needed to investigate security events for relevance and impact • Improved data analytics, enabling new services and security analytics • 2x faster performance compared to competing solutions OBJECTIVES CHALLENGES SOLUTION Business Impact Leader in Magic Quadrant
    25. 25. © 2014 MapR Technologies 25 Zions Bank: From SIEM to Fraud Detection Cost effective security analytics and fraud detection on one platform • To operationalize big data fraud detection: Fraud Operations and Security Analytics team at Zions maintains data stores, builds statistical models to detect fraud, and then uses these models to data mine and evaluate suspicious activity • (Global bank fraud costs $200B annually) “We initially got into centralizing all of our data from an information security perspective. We then saw that we could use this same environment to help with fraud detection” Michael Fowkes - SVP Fraud Operations and Security Analytics • Existing technology infrastructure could not scale • Timeliness of reports degraded over the last several years • Chose MapR and cut storage costs by 50% • Gained huge performance advantage – Querying time reduced from 24 hours to 30 min on 1.2 PB of data • Leverage MapR scale for increased model accuracy and deeper insights OBJECTIVES CHALLENGES SOLUTION Business Impact
    26. 26. © 2014 MapR Technologies 26 Cisco: Global Security Intelligence Operations (MSSP) Operational and analytical security applications on one platform • To protect customer networks through early-warning intelligence & vulnerability analysis • To better react to evolving security threats in real-time • Collect additional telemetry data from customers' firewalls, intrusion prevention systems • Different analytical teams derived security intelligence in silos and lacked synergy • Inability to scale with existing infrastructure to a million events per second from nearly 100 different channels over tens of thousands of distributed sensors OBJECTIVES CHALLENGES SOLUTION Business Impact • All analytic teams leverage a common platform leading to operational efficiencies • Capability to scale - aggregating and analyzing millions of data points in real time • Update customer networks with new threat footprints within a 2 to 5 minute window • MapR M7: Central hub for all of the security analytics teams • Stream, interactive, graph and batch processing on MapR with the flexibility to perform closed-loop analytics across these functions in real time • Key Features: Scale, enterprise-grade, operational efficiency and high performance
    27. 27. © 2014 MapR Technologies 27 Cisco SIO Hadoop Stack SENSOR DATA FIREWALL LOGS INTRUSION PROTECTION SYSTEM LOGS Globally Dispersed Datacenters SECURITY APPLIANCE LOGS SQL Queries and Reporting Batch Processing Graph Processing New Threat Footprint within 2-5 min Closed-Loop Operations Benefits: Unified platform for Analytics  Low Operational Costs  Faster Response Times  Better Algorithms MapR M7 Distribution for Hadoop 1 million events/sec. Over 100 channels Spark Streamin g for known threats & aggregation Mahout, MLLib Shark, Impala GraphX & TitanDB
    28. 28. © 2014 MapR Technologies 28 MapR is the Hadoop Technology Leader BIG DATA HADOOP
    29. 29. © 2014 MapR Technologies 29 MapR Distribution for Hadoop MapR Data Platform (Random Read/Write) Data HubEnterprise Grade Operational MapR-FS (POSIX) MapR-DB (High-Performance NoSQL) Security YARN Pig Cascading Spark Batch Spark Streaming Storm* Streaming HBase Solr NoSQL & Search Juju Provisioning & Coordination Savannah* Mahout MLLib ML, Graph GraphX MapReduc e v1 & v2 APACHE HADOOP AND OSS ECOSYSTEM EXECUTION ENGINES DATA GOVERNANCE AND OPERATIONS Workflow & Data GovernanceTez* Accumulo* Hive Impala Shark Drill* SQL Sentry* Oozie ZooKeeperSqoop Knox* WhirrFalcon*Flume Data Integration & Access HttpFS Hue NFS HDFS API HBase API JSON API
    30. 30. © 2014 MapR Technologies 30 MapR Summary BIG DATA BEST PRODUCT BUSINESS IMPACT Hadoop Top Ranked Production Success
    31. 31. © 2014 MapR Technologies 31 Q&A @mapr maprtech nitin@mapr.com Engage with us! MapR maprtech mapr-technologies