SlideShare una empresa de Scribd logo
1 de 21
Why I/O Is Strategic
for Big Data

Presented by: Emulex and
Evaluator Group



                           1
Webcast Housekeeping


1.   All attendees will be on mute during the presentation
2.   Please submit your questions via the text/chat feature
3.   We will do all Q&A at the end of the presentation




                                                              2
Why I/O Is Strategic



Katherine Lane
Director of Corporate
Communications


                        3
Why I/O Is Strategic?




          Building a Virtual Panel of Experts!

                                                 4
Topics for the Virtual Panel




    Server         Cloud       Big      Network
Virtualization   Computing     Data   Convergence

                                                5
Moving the Elephant
                 Through the Pipes
                                John Webster
                                Senior Partner
                               Evaluator Group



© 2012 Evaluator Group, Inc.
Overview
 “Big data” can mean two different things
       — Storage for large amounts of data
       — Analytics against very large amounts of data
       — I/O is critical for both
 Big Data Apps
       — Personalized Healthcare
       — Online-style shopping for bricks-and-mortar retailers
       — Fraud detection
 Marketing Needs it Now
       — Correlate customer data with social media data feeds
       — Understand the buyer as an individual


                                                                 12/11/2012   7
© 2012 Evaluator Group, Inc.
Customer
                         Data Analytics Model for Individualized Marketing
    Profiles

NoSQL DB                            High Scale Data
 HDFS                                                                      BI and
                                      Reductions
                                                                          Analytics
     Logs,                                            Predictions
    Tweets
   Location                                           on Buying
                                                       Behavior

                                                                                         4) Real-time:
                                                                        Expert System   Determine Best
                                                                                         Offer For This
  Low                                            3) Input Into
                                                                                          Customer
Latency

                                                                                          1) Identify
                                    2b) Lookup    NoSQL DB                                   User
                                     Location
                                                                    2a)Lookup
                                                                    User Profile
                                                                                          12/11/2012      8
     © 2012 Evaluator Group, Inc.
Distributed, Shared-Nothing
    Architectures for Big Data Analytics
                                            1            2       3            4   5                6   7              8            Console

    Network
                                                Link                 Link                 Link                 Link       Pwr




                               B8GMR3
                                                Active               Active               Active            Active        Active

     Layer

                                        C                    N                        N                    N                                   N
                                        O                    O                        O                    O                                   O
                                        N
                                                             D                        D                    D                                   D
     Compute                            T
                                                             E                        E                    E                                   E
                                        R
      Layer                             O
                                        L                    1                        2                    3                                   n




       Storage
        Layer

                                 DAS                         DAS                  DAS                      DAS                               DAS

                                                                                                                                             12/11/2012   9
© 2012 Evaluator Group, Inc.
CAP theorem
           It is impossible for a distributed computer system
           to simultaneously provide all three of the
           following guarantees:
            Consistency (all nodes see the same data at the same
             time)
            Availability (a guarantee that every request receives a
             response about whether it was successful or failed)
            Partition tolerance (the system continues to operate
             despite arbitrary message loss or failure of part of the
             system)
           A distributed system can satisfy any two of these
           guarantees at the same time, but not all three


© 2012 Evaluator Group, Inc.
The Impact of Network and I/O Performance

 The impacts of internal analytics system
  network performance—both positive and
  negative—are experienced at the level of
  analytics application users.
 The rate at which data flows between storage
  and processors within a Hadoop cluster has a
  direct effect on cluster performance and
  scalability.
 Getting data into and out of distributed
  computing clusters impacts how quickly query
  results are delivered to users.



                                                 12/11/2012   11
© 2012 Evaluator Group, Inc.
Internal Network Throughput 1GbE




© 2012 Evaluator Group, Inc.
Internal Network Throughput 10GbE




© 2012 Evaluator Group, Inc.
Load/Unload Throughput




© 2012 Evaluator Group, Inc.
Why Enterprise IT is Now Involved

 Distributed computing for analytics (Hadoop, for example) is
  moving from science experiment to mission-critical
 Emerging Enterprise Hadoop use cases include:
       — Hadoop for very large data sets that can’t be analyzed economically
         by the data warehouse
       — Hadoop on the front-end of the data warehouse
       — Hadoop as data convergence engine – combine new unstructured
         data sources with structured data warehouse data
       — Hadoop as the back-end to the data warehouse
 Also emerging in the need to bring Hadoop under the data
  governance umbrella
       — Use case for NAS/SAN attached to Hadoop clusters?
       — At what cost?

                                                                    12/11/2012   15
© 2012 Evaluator Group, Inc.
Is Hadoop Ready for Prime Time?
 Hadoop was not born and raised in the highly
  risk averse, enterprise data center

 Hadoop puts forward a different and
  inefficient operational model from the
  standpoint of enterprise IT

 Hadoop introduces enterprise security and
  data governance issues




                                                 12/11/2012   16
© 2012 Evaluator Group, Inc.
Shared Storage as Secondary Storage

                      Network                1   Link     2   3   Link     4   5       Link     6   7   Link     8   Pwr      Console




                                B8GMR3
                                                 Active           Active               Active           Active       Active



                       Layer
                                         C                    N                    N                    N                               N
                                         O
                                         N                    O                    O                    O                               O
                     Compute             T
                                         R                    D                    D                    D                               D
                      Layer              O
                                         L
                                                              E                    E                    E                               E

                                                              1                    2                    3                               n

                      Storage
                       Layer

                                                                               SAN/NAS



© 2012 Evaluator Group, Inc.
Shared Storage as Primary Storage

                      Network                1   Link     2   3    Link    4   5       Link     6   7   Link     8   Pwr      Console




                                B8GMR3
                                                 Active           Active               Active           Active       Active



                       Layer
                                         C                    N                    N                    N                               N
                                         O
                                         N                    O                    O                    O                               O
                     Compute             T
                                         R                    D                    D                    D                               D
                      Layer              O
                                         L
                                                              E                    E                    E                               E

                                                              1                    2                    3                               n

                      Storage                                     SAN and Scale-out NAS
                       Layer




© 2012 Evaluator Group, Inc.
Evaluating Hadoop as a Storage Device

                              Single Points of Failure Eliminated?
                              SSD and automated tiering?
                              Dedupe?
                              Snapshots?
                              Insert your hot-button storage feature here:
                                    __________




© 2012 Evaluator Group, Inc.
Enterprise IT and Big Data Analytics

 There will be Big Data—Storage and Apps
 The traditional data warehouse will continue to evolve
 Distributed computing clusters (XxSQL, Hadoop) will achieve
  prominence in enterprise data centers
 Shared storage, while controversial within some circles, can
  be applied
 Communications bandwidth is as important a resource as
  compute and storage




                                                        12/11/2012   20
© 2012 Evaluator Group, Inc.
© 2011 Emulex Corporation   21

Más contenido relacionado

Similar a Emulex and the Evaluator Group Present Why I/O is Strategic for Big Data

Ebs architecture con9036_pdf_9036_0001
Ebs architecture con9036_pdf_9036_0001Ebs architecture con9036_pdf_9036_0001
Ebs architecture con9036_pdf_9036_0001jucaab
 
Cloud Computing through FCAPS Managed Services in a Virtualized Data Center
Cloud Computing through FCAPS Managed Services in a Virtualized Data CenterCloud Computing through FCAPS Managed Services in a Virtualized Data Center
Cloud Computing through FCAPS Managed Services in a Virtualized Data Centervsarathy
 
Kuldeep presentation ppt
Kuldeep presentation pptKuldeep presentation ppt
Kuldeep presentation pptkuldeep khichar
 
Accel Partners New Data Workshop 7-14-10
Accel Partners New Data Workshop 7-14-10Accel Partners New Data Workshop 7-14-10
Accel Partners New Data Workshop 7-14-10keirdo1
 
Net App Scores 100% For Midrange Storage Market Solutions
Net App Scores 100% For Midrange Storage Market SolutionsNet App Scores 100% For Midrange Storage Market Solutions
Net App Scores 100% For Midrange Storage Market SolutionsMichael Hudak
 
The Synergy Between the Object Database, Graph Database, Cloud Computing and ...
The Synergy Between the Object Database, Graph Database, Cloud Computing and ...The Synergy Between the Object Database, Graph Database, Cloud Computing and ...
The Synergy Between the Object Database, Graph Database, Cloud Computing and ...InfiniteGraph
 
Framework Engineering
Framework EngineeringFramework Engineering
Framework EngineeringYoungSu Son
 
Datacenter Design Guide UNIQUE Panduit-Cisco
Datacenter Design Guide UNIQUE Panduit-Cisco Datacenter Design Guide UNIQUE Panduit-Cisco
Datacenter Design Guide UNIQUE Panduit-Cisco jpjobard
 
Intel And Big Data: An Open Platform for Next-Gen Analytics
Intel And Big Data: An Open Platform for Next-Gen AnalyticsIntel And Big Data: An Open Platform for Next-Gen Analytics
Intel And Big Data: An Open Platform for Next-Gen AnalyticsIntel IT Center
 
Design Verification: The Past, Present and Futurere
Design Verification: The Past, Present and FuturereDesign Verification: The Past, Present and Futurere
Design Verification: The Past, Present and FuturereDVClub
 
Intel open stack v1
Intel open stack v1Intel open stack v1
Intel open stack v1benbenhappy
 
Application Logging for Forensics
Application Logging for ForensicsApplication Logging for Forensics
Application Logging for ForensicsRaffael Marty
 
SISO LSA AND OMG DDS
SISO LSA AND OMG DDSSISO LSA AND OMG DDS
SISO LSA AND OMG DDSSimware
 

Similar a Emulex and the Evaluator Group Present Why I/O is Strategic for Big Data (20)

Ebs architecture con9036_pdf_9036_0001
Ebs architecture con9036_pdf_9036_0001Ebs architecture con9036_pdf_9036_0001
Ebs architecture con9036_pdf_9036_0001
 
Cloud Computing through FCAPS Managed Services in a Virtualized Data Center
Cloud Computing through FCAPS Managed Services in a Virtualized Data CenterCloud Computing through FCAPS Managed Services in a Virtualized Data Center
Cloud Computing through FCAPS Managed Services in a Virtualized Data Center
 
Kuldeep presentation ppt
Kuldeep presentation pptKuldeep presentation ppt
Kuldeep presentation ppt
 
Accel Partners New Data Workshop 7-14-10
Accel Partners New Data Workshop 7-14-10Accel Partners New Data Workshop 7-14-10
Accel Partners New Data Workshop 7-14-10
 
An Hour of DB2 Tips
An Hour of DB2 TipsAn Hour of DB2 Tips
An Hour of DB2 Tips
 
Net App Scores 100% For Midrange Storage Market Solutions
Net App Scores 100% For Midrange Storage Market SolutionsNet App Scores 100% For Midrange Storage Market Solutions
Net App Scores 100% For Midrange Storage Market Solutions
 
Big Data on AWS
Big Data on AWSBig Data on AWS
Big Data on AWS
 
The Synergy Between the Object Database, Graph Database, Cloud Computing and ...
The Synergy Between the Object Database, Graph Database, Cloud Computing and ...The Synergy Between the Object Database, Graph Database, Cloud Computing and ...
The Synergy Between the Object Database, Graph Database, Cloud Computing and ...
 
16h30 p duff-big-data-final
16h30   p duff-big-data-final16h30   p duff-big-data-final
16h30 p duff-big-data-final
 
Framework Engineering
Framework EngineeringFramework Engineering
Framework Engineering
 
Datacenter Design Guide UNIQUE Panduit-Cisco
Datacenter Design Guide UNIQUE Panduit-Cisco Datacenter Design Guide UNIQUE Panduit-Cisco
Datacenter Design Guide UNIQUE Panduit-Cisco
 
Intel And Big Data: An Open Platform for Next-Gen Analytics
Intel And Big Data: An Open Platform for Next-Gen AnalyticsIntel And Big Data: An Open Platform for Next-Gen Analytics
Intel And Big Data: An Open Platform for Next-Gen Analytics
 
Design Verification: The Past, Present and Futurere
Design Verification: The Past, Present and FuturereDesign Verification: The Past, Present and Futurere
Design Verification: The Past, Present and Futurere
 
Intel open stack v1
Intel open stack v1Intel open stack v1
Intel open stack v1
 
Intel open stack v1
Intel open stack v1Intel open stack v1
Intel open stack v1
 
Big Data & The Cloud
Big Data & The CloudBig Data & The Cloud
Big Data & The Cloud
 
Application Logging for Forensics
Application Logging for ForensicsApplication Logging for Forensics
Application Logging for Forensics
 
05 architectural design
05 architectural design05 architectural design
05 architectural design
 
Netflix in the cloud 2011
Netflix in the cloud 2011Netflix in the cloud 2011
Netflix in the cloud 2011
 
SISO LSA AND OMG DDS
SISO LSA AND OMG DDSSISO LSA AND OMG DDS
SISO LSA AND OMG DDS
 

Más de Emulex Corporation

Acronym Soup – NFV, SDN, OVN and VNF
Acronym Soup – NFV, SDN, OVN and VNFAcronym Soup – NFV, SDN, OVN and VNF
Acronym Soup – NFV, SDN, OVN and VNFEmulex Corporation
 
Improving Incident Response: Building a More Efficient IT Infrastructure
Improving Incident Response: Building a More Efficient IT InfrastructureImproving Incident Response: Building a More Efficient IT Infrastructure
Improving Incident Response: Building a More Efficient IT InfrastructureEmulex Corporation
 
Using NetFlow to Streamline Security Analysis and Response to Cyber Threats
Using NetFlow to Streamline Security Analysis and Response to Cyber ThreatsUsing NetFlow to Streamline Security Analysis and Response to Cyber Threats
Using NetFlow to Streamline Security Analysis and Response to Cyber ThreatsEmulex Corporation
 
Network Forensics for Splunk, an Emulex presentation
Network Forensics for Splunk, an Emulex presentationNetwork Forensics for Splunk, an Emulex presentation
Network Forensics for Splunk, an Emulex presentationEmulex Corporation
 
Using NetFlow to Improve Network Visibility and Application Performance
Using NetFlow to Improve Network Visibility and Application PerformanceUsing NetFlow to Improve Network Visibility and Application Performance
Using NetFlow to Improve Network Visibility and Application PerformanceEmulex Corporation
 
Using Network Recording and Search to Improve IT Service Delivery
Using Network Recording and Search to Improve IT Service DeliveryUsing Network Recording and Search to Improve IT Service Delivery
Using Network Recording and Search to Improve IT Service DeliveryEmulex Corporation
 
Introducing Endace Packets - EndaceVision™ with Protocol Decodes
Introducing Endace Packets - EndaceVision™ with Protocol DecodesIntroducing Endace Packets - EndaceVision™ with Protocol Decodes
Introducing Endace Packets - EndaceVision™ with Protocol DecodesEmulex Corporation
 
Linked in Twitter Facebook Google+ Email Embed Share Flash Across Virtualized...
Linked in Twitter Facebook Google+ Email Embed Share Flash Across Virtualized...Linked in Twitter Facebook Google+ Email Embed Share Flash Across Virtualized...
Linked in Twitter Facebook Google+ Email Embed Share Flash Across Virtualized...Emulex Corporation
 
Tap DANZing - Arista Networks Redefining the Cost of Accessing Network Traffic
Tap DANZing - Arista Networks Redefining the Cost of Accessing Network TrafficTap DANZing - Arista Networks Redefining the Cost of Accessing Network Traffic
Tap DANZing - Arista Networks Redefining the Cost of Accessing Network TrafficEmulex Corporation
 
First Look Webcast: OneCore Storage SDK 3.6 Roll-out and Walkthrough
First Look Webcast: OneCore Storage SDK 3.6 Roll-out and WalkthroughFirst Look Webcast: OneCore Storage SDK 3.6 Roll-out and Walkthrough
First Look Webcast: OneCore Storage SDK 3.6 Roll-out and WalkthroughEmulex Corporation
 
Why I/O is Strategic for Convergence - with 451 Research
Why I/O is Strategic for Convergence - with 451 ResearchWhy I/O is Strategic for Convergence - with 451 Research
Why I/O is Strategic for Convergence - with 451 ResearchEmulex Corporation
 
Emulex and IDC Present Why I/O is Strategic for the Cloud
Emulex and IDC Present Why I/O is Strategic for the Cloud Emulex and IDC Present Why I/O is Strategic for the Cloud
Emulex and IDC Present Why I/O is Strategic for the Cloud Emulex Corporation
 
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...Emulex Corporation
 
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...Emulex Corporation
 
Emulex and Enterprise Strategy Group Present Why I/O is Strategic for Virtual...
Emulex and Enterprise Strategy Group Present Why I/O is Strategic for Virtual...Emulex and Enterprise Strategy Group Present Why I/O is Strategic for Virtual...
Emulex and Enterprise Strategy Group Present Why I/O is Strategic for Virtual...Emulex Corporation
 
Introducing OneCommand Vision 3.0, I/O management that gives your application...
Introducing OneCommand Vision 3.0, I/O management that gives your application...Introducing OneCommand Vision 3.0, I/O management that gives your application...
Introducing OneCommand Vision 3.0, I/O management that gives your application...Emulex Corporation
 
Emulex Presents Why I/O is Strategic Global Survey Results
Emulex Presents Why I/O is Strategic Global Survey ResultsEmulex Presents Why I/O is Strategic Global Survey Results
Emulex Presents Why I/O is Strategic Global Survey ResultsEmulex Corporation
 
Integrating and Optimizing Suricata with FastStack™ Sniffer10G™
Integrating and Optimizing Suricata with FastStack™ Sniffer10G™Integrating and Optimizing Suricata with FastStack™ Sniffer10G™
Integrating and Optimizing Suricata with FastStack™ Sniffer10G™Emulex Corporation
 

Más de Emulex Corporation (20)

Acronym Soup – NFV, SDN, OVN and VNF
Acronym Soup – NFV, SDN, OVN and VNFAcronym Soup – NFV, SDN, OVN and VNF
Acronym Soup – NFV, SDN, OVN and VNF
 
Improving Incident Response: Building a More Efficient IT Infrastructure
Improving Incident Response: Building a More Efficient IT InfrastructureImproving Incident Response: Building a More Efficient IT Infrastructure
Improving Incident Response: Building a More Efficient IT Infrastructure
 
SC Magazine eSymposium: SIEM
SC Magazine eSymposium: SIEMSC Magazine eSymposium: SIEM
SC Magazine eSymposium: SIEM
 
Using NetFlow to Streamline Security Analysis and Response to Cyber Threats
Using NetFlow to Streamline Security Analysis and Response to Cyber ThreatsUsing NetFlow to Streamline Security Analysis and Response to Cyber Threats
Using NetFlow to Streamline Security Analysis and Response to Cyber Threats
 
Network Forensics for Splunk, an Emulex presentation
Network Forensics for Splunk, an Emulex presentationNetwork Forensics for Splunk, an Emulex presentation
Network Forensics for Splunk, an Emulex presentation
 
Using NetFlow to Improve Network Visibility and Application Performance
Using NetFlow to Improve Network Visibility and Application PerformanceUsing NetFlow to Improve Network Visibility and Application Performance
Using NetFlow to Improve Network Visibility and Application Performance
 
The Great IT Migration
The Great IT MigrationThe Great IT Migration
The Great IT Migration
 
Using Network Recording and Search to Improve IT Service Delivery
Using Network Recording and Search to Improve IT Service DeliveryUsing Network Recording and Search to Improve IT Service Delivery
Using Network Recording and Search to Improve IT Service Delivery
 
Introducing Endace Packets - EndaceVision™ with Protocol Decodes
Introducing Endace Packets - EndaceVision™ with Protocol DecodesIntroducing Endace Packets - EndaceVision™ with Protocol Decodes
Introducing Endace Packets - EndaceVision™ with Protocol Decodes
 
Linked in Twitter Facebook Google+ Email Embed Share Flash Across Virtualized...
Linked in Twitter Facebook Google+ Email Embed Share Flash Across Virtualized...Linked in Twitter Facebook Google+ Email Embed Share Flash Across Virtualized...
Linked in Twitter Facebook Google+ Email Embed Share Flash Across Virtualized...
 
Tap DANZing - Arista Networks Redefining the Cost of Accessing Network Traffic
Tap DANZing - Arista Networks Redefining the Cost of Accessing Network TrafficTap DANZing - Arista Networks Redefining the Cost of Accessing Network Traffic
Tap DANZing - Arista Networks Redefining the Cost of Accessing Network Traffic
 
First Look Webcast: OneCore Storage SDK 3.6 Roll-out and Walkthrough
First Look Webcast: OneCore Storage SDK 3.6 Roll-out and WalkthroughFirst Look Webcast: OneCore Storage SDK 3.6 Roll-out and Walkthrough
First Look Webcast: OneCore Storage SDK 3.6 Roll-out and Walkthrough
 
Why I/O is Strategic for Convergence - with 451 Research
Why I/O is Strategic for Convergence - with 451 ResearchWhy I/O is Strategic for Convergence - with 451 Research
Why I/O is Strategic for Convergence - with 451 Research
 
Emulex and IDC Present Why I/O is Strategic for the Cloud
Emulex and IDC Present Why I/O is Strategic for the Cloud Emulex and IDC Present Why I/O is Strategic for the Cloud
Emulex and IDC Present Why I/O is Strategic for the Cloud
 
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
 
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
Get Better I/O Performance in VMware vSphere 5.1 Environments with Emulex 16G...
 
Emulex and Enterprise Strategy Group Present Why I/O is Strategic for Virtual...
Emulex and Enterprise Strategy Group Present Why I/O is Strategic for Virtual...Emulex and Enterprise Strategy Group Present Why I/O is Strategic for Virtual...
Emulex and Enterprise Strategy Group Present Why I/O is Strategic for Virtual...
 
Introducing OneCommand Vision 3.0, I/O management that gives your application...
Introducing OneCommand Vision 3.0, I/O management that gives your application...Introducing OneCommand Vision 3.0, I/O management that gives your application...
Introducing OneCommand Vision 3.0, I/O management that gives your application...
 
Emulex Presents Why I/O is Strategic Global Survey Results
Emulex Presents Why I/O is Strategic Global Survey ResultsEmulex Presents Why I/O is Strategic Global Survey Results
Emulex Presents Why I/O is Strategic Global Survey Results
 
Integrating and Optimizing Suricata with FastStack™ Sniffer10G™
Integrating and Optimizing Suricata with FastStack™ Sniffer10G™Integrating and Optimizing Suricata with FastStack™ Sniffer10G™
Integrating and Optimizing Suricata with FastStack™ Sniffer10G™
 

Emulex and the Evaluator Group Present Why I/O is Strategic for Big Data

  • 1. Why I/O Is Strategic for Big Data Presented by: Emulex and Evaluator Group 1
  • 2. Webcast Housekeeping 1. All attendees will be on mute during the presentation 2. Please submit your questions via the text/chat feature 3. We will do all Q&A at the end of the presentation 2
  • 3. Why I/O Is Strategic Katherine Lane Director of Corporate Communications 3
  • 4. Why I/O Is Strategic? Building a Virtual Panel of Experts! 4
  • 5. Topics for the Virtual Panel Server Cloud Big Network Virtualization Computing Data Convergence 5
  • 6. Moving the Elephant Through the Pipes John Webster Senior Partner Evaluator Group © 2012 Evaluator Group, Inc.
  • 7. Overview  “Big data” can mean two different things — Storage for large amounts of data — Analytics against very large amounts of data — I/O is critical for both  Big Data Apps — Personalized Healthcare — Online-style shopping for bricks-and-mortar retailers — Fraud detection  Marketing Needs it Now — Correlate customer data with social media data feeds — Understand the buyer as an individual 12/11/2012 7 © 2012 Evaluator Group, Inc.
  • 8. Customer Data Analytics Model for Individualized Marketing Profiles NoSQL DB High Scale Data HDFS BI and Reductions Analytics Logs, Predictions Tweets Location on Buying Behavior 4) Real-time: Expert System Determine Best Offer For This Low 3) Input Into Customer Latency 1) Identify 2b) Lookup NoSQL DB User Location 2a)Lookup User Profile 12/11/2012 8 © 2012 Evaluator Group, Inc.
  • 9. Distributed, Shared-Nothing Architectures for Big Data Analytics 1 2 3 4 5 6 7 8 Console Network Link Link Link Link Pwr B8GMR3 Active Active Active Active Active Layer C N N N N O O O O O N D D D D Compute T E E E E R Layer O L 1 2 3 n Storage Layer DAS DAS DAS DAS DAS 12/11/2012 9 © 2012 Evaluator Group, Inc.
  • 10. CAP theorem It is impossible for a distributed computer system to simultaneously provide all three of the following guarantees:  Consistency (all nodes see the same data at the same time)  Availability (a guarantee that every request receives a response about whether it was successful or failed)  Partition tolerance (the system continues to operate despite arbitrary message loss or failure of part of the system) A distributed system can satisfy any two of these guarantees at the same time, but not all three © 2012 Evaluator Group, Inc.
  • 11. The Impact of Network and I/O Performance  The impacts of internal analytics system network performance—both positive and negative—are experienced at the level of analytics application users.  The rate at which data flows between storage and processors within a Hadoop cluster has a direct effect on cluster performance and scalability.  Getting data into and out of distributed computing clusters impacts how quickly query results are delivered to users. 12/11/2012 11 © 2012 Evaluator Group, Inc.
  • 12. Internal Network Throughput 1GbE © 2012 Evaluator Group, Inc.
  • 13. Internal Network Throughput 10GbE © 2012 Evaluator Group, Inc.
  • 14. Load/Unload Throughput © 2012 Evaluator Group, Inc.
  • 15. Why Enterprise IT is Now Involved  Distributed computing for analytics (Hadoop, for example) is moving from science experiment to mission-critical  Emerging Enterprise Hadoop use cases include: — Hadoop for very large data sets that can’t be analyzed economically by the data warehouse — Hadoop on the front-end of the data warehouse — Hadoop as data convergence engine – combine new unstructured data sources with structured data warehouse data — Hadoop as the back-end to the data warehouse  Also emerging in the need to bring Hadoop under the data governance umbrella — Use case for NAS/SAN attached to Hadoop clusters? — At what cost? 12/11/2012 15 © 2012 Evaluator Group, Inc.
  • 16. Is Hadoop Ready for Prime Time?  Hadoop was not born and raised in the highly risk averse, enterprise data center  Hadoop puts forward a different and inefficient operational model from the standpoint of enterprise IT  Hadoop introduces enterprise security and data governance issues 12/11/2012 16 © 2012 Evaluator Group, Inc.
  • 17. Shared Storage as Secondary Storage Network 1 Link 2 3 Link 4 5 Link 6 7 Link 8 Pwr Console B8GMR3 Active Active Active Active Active Layer C N N N N O N O O O O Compute T R D D D D Layer O L E E E E 1 2 3 n Storage Layer SAN/NAS © 2012 Evaluator Group, Inc.
  • 18. Shared Storage as Primary Storage Network 1 Link 2 3 Link 4 5 Link 6 7 Link 8 Pwr Console B8GMR3 Active Active Active Active Active Layer C N N N N O N O O O O Compute T R D D D D Layer O L E E E E 1 2 3 n Storage SAN and Scale-out NAS Layer © 2012 Evaluator Group, Inc.
  • 19. Evaluating Hadoop as a Storage Device  Single Points of Failure Eliminated?  SSD and automated tiering?  Dedupe?  Snapshots?  Insert your hot-button storage feature here: __________ © 2012 Evaluator Group, Inc.
  • 20. Enterprise IT and Big Data Analytics  There will be Big Data—Storage and Apps  The traditional data warehouse will continue to evolve  Distributed computing clusters (XxSQL, Hadoop) will achieve prominence in enterprise data centers  Shared storage, while controversial within some circles, can be applied  Communications bandwidth is as important a resource as compute and storage 12/11/2012 20 © 2012 Evaluator Group, Inc.
  • 21. © 2011 Emulex Corporation 21

Notas del editor

  1. Emulex Branding Americas - Focus On Top OEM & DMR GroupsAPAC and EMEA – 10Gb VAR MediaEmulex = Ethernet#1 for Web SearchesGoogle, Yahoo, Bing, BaiduDMR Search Engine PlacementSocial Media Community BuildingIO Blender.com & Linked In Convergence CommunityECE – Emulex Connected Experience – End User Loyalty ProgramCustomized Content DeliveryMYEMULEX.com, iPhone App - Connected CardsTargeted Push (iSCSI, VMware, Oracle, MSFT, FC, Convergence)SF.com lead and community maturation