SlideShare a Scribd company logo
1 of 24
Download to read offline
Next-gen Flash-based
MySQL and NoSQL
Solutions
Real World Case Studies of Extreme
Performance, Scalability, and Availability


Darpan Dinker
Vice President, Database Technologies




                                                               Partnership Power >
© 2010 Schooner Information Technology. All rights reserved.
MySQL
Conference &
Expo, 2010                   Agenda


       • Datacenter trends and challenges

       • Next-gen flash-based solutions

       • MySQL case studies

       • NoSQL case studies




                                                                Partnership Power >
 © 2010 Schooner Information Technology. All rights reserved.
                                                                                      2
MySQL
Conference &                 Too Much Rack, Power, Pipe, and
Expo, 2010                   Complexity




                                                                                                                  For every 100
  U.S. data-                                                    The number of                                     units of energy
                                     Datacenter                 installed servers      From 2003 to 2008          piped into a data
  centers use                        equipment is
  more energy                                                   in the U.S. will       the data size of the       center, only
                                     only utilized              increase from 2.2      average web page has       three are used
  than the entire                    6% to 10%.
  nation of                                                     million in 2007 to     more than tripled.         for actual
  Sweden.                            - William Forrest          6.8 million in 2010.   –websiteoptimization.com   computing.
                                       Forbes                   - Frost & Sullivan
  - EE Times                                                                                                      - U.S. Department
                                                                                                                    of Energy




 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                                      3
MySQL
Conference &
Expo, 2010                   Typical Datacenter Deployment
                                                                                    Data Access Tier


                                                    Web/App Tier      Caching Tier                         Database Tier
                                                         PHP, Perl,      Memcached                             MySQL
                                                         Ruby, Java
                                                                                                                       Slaves




                                                                                        POOL 1
                                                                                                             Master




                                                                                        POOL 2
                                 Ensure                                                           Scale
   End                                                                                                                          Minimize
   User                         Quality of                                                       to Meet
                                                                                                                                 Costs
                                 Service                                NoSQL Tier               Demand
                                                                       Key-Value Store,
                                                                      Document Store, etc.




                                                                                        POOL3




                                                                                                                                  4
 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                                           4
MySQL
Conference &
Expo, 2010                  Key Challenges

                                                         Pain of sharding and re-sharding

                    Scale                               Complexity of adding new servers
                   to Meet
                   Demand                              Headache of managing server sprawl


                                                        Poor response time and availability

                   Ensure                                Trade-offs in consistency models
                  Quality of
                   Service                             Complex, defensive app development


                                                         Too much underutilized hardware

                                                         Wasted power, pipe, and cooling
                   Minimize
                    Costs                               Integration & management burden
© 2009 Schooner Information Technology. Confidential                                          5
MySQL
Conference &
                            Vision: Tightly Coupled, Scalable MySQL
Expo, 2010                  and NoSQL Building Blocks

   Integrated, optimized, scalable MySQL & NoSQL solutions:
    Effectively leverage flash memory, multi-core processors, high-
     speed networking, scalable data access software
    Incorporate highly optimized, balanced hardware platform,
     operating environment, integrated MySQL and NoSQL
    Provide efficient, higher level scalable building blocks
    Eliminate complex integration projects and leverage out of the box
     performance, scalability and availability
    Deliver enterprise class reliability




 © 2010 Schooner Information Technology. All rights reserved.
                                                                          6
MySQL
Conference &
                             Tightly Coupled Software
Expo, 2010                   Architecture

                                                                          Networked Clients

                                 MySQL                                                                               NoSQL

                                                           Operating Environment
               Intelligent Caching                         Optimized Flash                    Multi-Core                     Transparent
                    Hierarchy                              Memory Access                      Scalability                       HA/DR

              •   Optimized buffer mgmt &              •   Highly parallel read and   •   Fine grain locking           •   Synchronous and async
                  scan resistant algorithms                write access                                                    replication
                                                                                      •   Scalable and concurrent
              •   Write-through and write-             •   Intelligent flash wear         data structures              •   Failure detection and
                  back caching flexibility                 algorithms                                                      automated VIP failover
                                                                                      •   Optimized thread to core
              •   Adaptive , fine-grained              •   Durability with high-          allocation                   •   Fast, incremental data
                  memory management                        performance                                                     recovery
                                                                                      •   Efficient handling of
              •   Efficient object meta-               •   High-performance,              network interrupts           •   Incremental,/full online
                  data for persistence                     integrated RAID                                                 backup and restore




                                         Optimized, Balanced Hardware Platform
 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                                                      7
MySQL
Conference &                 Schooner MySQL and
Expo, 2010                   NoSQL Solutions

• Integrated, turnkey appliance                                 1       The Schooner Appliance for
                                                                      MySQL EnterpriseTM with InnoDB
          – Integrated hardware and software

          – Enterprise-class support

          – 100% compatibility, fully certified

• High performance                                                                   +
          – 8x performance improvement

          – 1/8x the power and rack space

          – 50% lower TCO over 3 years                          2         The Schooner Appliance for
                                                                            Memcached / NoSQL
• High availability
          – Complete data & service availability

          – Transparent and fully integrated                          High         Persistent
                                                                                                     100%
          – 90% higher availability
                                                                    Capacity
                                                                     Cache
                                                                               +   Key-Value
                                                                                     Store
                                                                                                +   Memcapable




 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                 8
MySQL
Conference &
Expo, 2010                   Schooner Powered Datacenter
                                                                                    Data Access Tier


                                                    Web/App Tier       Caching Tier
                                                                      Caching Tier                        Database Tier
                                                                                                          Database Tier
                                                         PHP, Perl,       Memcached
                                                                         Memcached                            MySQL
                                                                                                              MySQL
                                                         Ruby, Java
                                                                                                                      Slaves




                                                                                       POOL 1
                                                                                                            Master




                                                                                       POOL 2
                                 Ensure                                                          Scale                         Minimize
   End                                                                  NoSQL Tier
   User                         Quality of                                                      to Meet                         Costs
                                 Service                                Key-Value Store,
                                                                        NoSQL Tier              Demand
                                                                      Document Store, etc.
                                                                       Key-Value Store,
                                                                      Document Store, etc.




                                                                                       POOL3




                                                                                                                                 9
 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                                          9
MySQL
Conference &
                               Schooner Appliance for
Expo, 2010                     MySQL Enterprise™ with InnoDB
       High Performance                                                     High Availability                                                        Turnkey Appliance
    • Highly parallel, optimized                                       • Fully ACID-compliant with                                                  • Multi-instance consolidation
      flash memory access                                                data durability                                                              on single appliance
    • Advanced buffer pool                                             • Integrated replication and                                                 • Web-based GUI/CLI for
      caching algorithms                                                 automated failover                                                           centralized management
    • Multi-core scalability with fine                                 • Integrated, high-performance                                               • Integration with 3rd party
      grained locking                                                    backup and restore                                                           mgmt & monitoring tools
    • Delivered on proven IBM                                          • RAID across SSDs and                                                       • 100% compatible and fully
      server with up to 1TB of flash                                     HDDs                                                                         certified by Sun/MySQL


                       DBT2 Performance (TPM)                                                                                                Connection Scalability
          75000
                                                                                                                                     40000



                                                                                                                 Master Server TPS
          60000
                                                                                                                                     30000
          45000
                                                                                                                                     20000
          30000                                                                                                                      10000
          15000                                                                                                                         0
                                                                                                                                               64       256    1024   4096   16384
                0
                                                                                                                                                         Legacy MySQL
                     Legacy MySQL with SSDs                   Schooner Appliance
                                                                                                                                                         Schooner MySQL
        Measured DBT2 throughput at 1000 warehouses,32 connections, 8 SSDs/HDDS with RAID 5. All databases configured for durability and consistency. Legacy results were
        on MySQL version 5.1.44 (most commonly used today). Schooner MySQL Appliance results were on Schooner-optimized 5.1.44
 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                                                                                     10
MySQL
Conference &
                                   MySQL
Expo, 2010                         Consolidation and Cost Savings
                                 TCO: $832,000                  TCO: $282,000



                                                                TCO SAVINGS:
                                                                $550,000
       3 Year TCO (2 TB MySQL)




                                        OpEx



                                                                     OpEx
                                                                                     THE BOTTOM LINE
                                     CapEx: 32
                                      Servers                      CapEx: 4          • Immediate capex savings
                                                                  Appliances
                                                                                     • 66 % TCO savings ($550,000)
                                 Without Schooner               With Schooner          over 3 years
                                 32 servers, 17.9 kW               4 Schooner        • Power & space reductions
                                                                appliances, 1.8 kW
                                                                                       enable green datacenter




 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                     11
MySQL
Conference &
Expo, 2010
MySQL
                            What Can I Do With It?
                   Reduce sharding and                                                  Scale performance and
                    consolidate slaves                                                  process queries faster
    Apps          Masters    Slaves                    Apps       Schooner


                                                                                                             70K TPM (DBT2)
                                                                                                             20K Connections

                                                                                                                          ½ TB or
                                                                                                                         1TB Flash
                     …

                               …




                    Reduce planned and                                               Eliminate integration and
                    unplanned downtime                                               optimization headaches

                                                                                                                       • Software
                     MySQL
                    Replication        +       MMM
                                              Failover
                                                                             Install/Config                            • Hardware
                                                                                              HA Tools
                                                                                                                       • Support
       SSD RAID &                SSD RAID &                SSD RAID &
      Data Durability           Data Durability           Data Durability                                              • Certified

                                                                                 Tuning
                                                                                                  Services             • Complete

© 2009 Schooner Information Technology. Confidential                                                                                 12
MySQL
Conference &
Expo, 2010                   Case Study: Financial Services

                    Scale Performance and Process Queries Faster

                                                                         High-performance, out-of-the-box
                                                                                100% compatible




               "Our ad-hoc MySQL queries run at least five times faster after installing the Schooner
               Appliances. They deliver a huge performance benefit and are a breeze to install and manage.“

                                   – Darryl Weatherspoon, VP of Eng at Xoom.



 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                              13
MySQL
Conference &
Expo, 2010                   Case Study: Social Networking

                                                                Consolidate Slaves
                Apps                     Masters                Slaves      Apps     Masters   Schooner




  "In our business, website performance and efficiency is key to the success of our web properties. The
  Schooner MySQL Appliances have significantly helped GuteFrage improve their overall website response
  time while at the same time allowing them to consolidate their database slaves onto a single Schooner
  appliance, dramatically reducing the time necessary for database administration.“

                     – Frank Penning, CTO of Holzbrinck Digital

 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                          14
MySQL
Conference &                 Schooner Appliance for Memcached
Expo, 2010
                             / NoSQL
       High Performance                                           High Availability                      Easy Appliance
    • Highly parallel, optimized                                • Persistent key-value store          • Dynamic containers for
      flash memory access                                         mode and cache mode                   consolidation & multi-tenancy
    • Fast, efficient DRAM-to-                                  • Transparent replication and         • Web-based GUI/CLI for
      Flash caching algorithms                                    automated failover                    centralized management
    • Multi-core scalability with                               • Non-disruptive, rolling             • Integration with 3rd party
      parallel thread allocation                                  upgrades                              mgmt & monitoring tools
    • Delivered on a proven IBM                                 • RAID & high-performance             • 100% compatible and fully
      server with a ½ TB of flash                                 backup and restore                    memcapable compliant




                                                                                       Key-Value Store Service
                                 Memcached Caching Service                        •   350GB capacity, 150K TPS
                               • 150GB capacity, 250K TPS                         •   Replication & Failover
                               • Replication & Failover                           •   Persistence, RAID, and Backup
                               • 100% Memcapable                                  •   Memcached-based key-value API


 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                                        15
MySQL
Conference &
                             Schooner Memcached / NoSQL:
Expo, 2010                   Capacity and Availability


                 Cache Capacity per Node (GB)                                        Reduction in Downtime (%)
        600                                                                 100

        500
                                                                            80

        400
                                                                            60
        300
                                                                            40
        200

        100                                                                 20


           0                                                                 0
                        Traditional                    Schooner Appliance          Traditional Persistent   Storage   Replication
                        Memcached                                                 Memcached Caching          RAID     & Failover




 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                                    16
MySQL
Conference &
                                       Memcached / NoSQL Consolidation
Expo, 2010                             and Cost Savings
                                     TCO: $610,000              TCO: $282,000



                                                                TCO SAVINGS:
       3 Year TCO (2 TB Memcached)




                                            OpEx
                                                                $328,000

                                                                     OpEx
                                                                                      THE BOTTOM LINE
                                         CapEx: 32                 CapEx: 4
                                          Servers                 Appliances          • Immediate capex savings
                                                                                      • 54% TCO savings ($328,000)
                                     Without Schooner           With Schooner           over 3 years
                                     32 servers, 17.9 kW            4 Schooner        • Power & space reductions
                                                                 appliances, 1.8 kW
                                                                                        enable green datacenter




 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                     17
MySQL
Conference &
Expo, 2010                   What Can I Do With It?
                 Consolidate and reduce                                                             Reduce planned and
                     server sprawl                                                                  unplanned downtime
          Traditional Memcached                                 Schooner
                                                                                                           Application Transparent
                                   POOL 1



                                                                                               Synchronous
                                                                                                Replication                +   Automated
                                                                                                                                Failover
                                   POOL 2




                                                                                                    SSD RAID &                 SSD RAID &
                                                                                                    Persistence                Persistence



               Scale cache capacity and                                                          Reduce application
                process requests faster                                                        development complexity
                                                                                          Application Tier                                Application Tier
                                                                               Failure Detection          Replication

                                                                                Group Delete             Data Durability
                                                 250K TPS




                                                                                                                                                   M$D
                                                                                                                                                   API
                                                                       ½ TB                        M$D
                                                                                                   API
                                                                       Flash
                                                                                                                               Failure Detection          Replication

                                                                                                                                Group Delete             Data Durability

                                                                                     Traditional Memcached                                   Schooner
 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                                                                           18
MySQL
Conference &
Expo, 2010                   Case Study: Social Networking
                                 Consolidate and Reduce Server Sprawl
                                           Traditional Memcached




                                                                POOL 1
                                                                         Schooner




                                                                POOL 2




       Scaling with 12:1 Consolidation using Persistence, Multi-Get, Replication and Recovery

       Scaling the data tier is a common challenge, and Schooner is helping us do just that. Power is the big
       constraint right now, so anything we can do to reduce that footprint right now is helpful. From an
       administrative perspective, fewer machines is always better, from a monitoring and scripting
       standpoint, and it also means reductions in potential failures due to fewer boxes.“

                           – Saran Chari, CTO and Founder at Flixster

 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                                19
MySQL
Conference &
Expo, 2010                   Case Study: Media

                            Reduce Planned and Unplanned Downtime
                                                                        Application Transparent

                                                          Synchronous
                                                           Replication          +          Automated
                                                                                            Failover




                                                                SSD RAID &                 SSD RAID &
                                                                Persistence                Persistence



     40 Million Users Address Books in Key Value Store with 8:1 Consolidation

     In the wonderful Schooner world, failovers go away. Schooner replication means that you’re sure that
     what you have on one node will also be on the other. Our developers don’t have to worry about cache
     coherency. They can plan on the data being available so they don’t have to program defensively.

                         – Ethan Erchinger, Director of Ops at Plaxo


 © 2010 Schooner Information Technology. All rights reserved.
                                                                                                            20
MySQL
Conference &
Expo, 2010                   Market Segments

                        Social Networking

                        Business Analytics

                        Gaming

                        Cloud

                        Media

                        Telco

                        Finance
 © 2010 Schooner Information Technology. All rights reserved.
                                                                21
MySQL
Conference &
Expo, 2010                   The Schooner Advantage

      •       Vastly Higher Performance and Scalability: 8x compared to traditional
              servers
      •       Significantly Lower TCO: Replacing 8 traditional
              servers with 1 reduces TCO by more than 50%
      •       Quick Deployment: Easy plug-and-play
              installation and configuration
      •       Seamless Operation: 100% compatible with
              existing client applications and management tools
      •       Higher Reliability: Delivers enterprise-class reliability by
              leveraging persistence, replication, and recovery software
      •       Easy Management: Simple but powerful centralized
              management and reporting with integrated CLI and GUI
      •       More Revenue: Powers new revenue-producing applications
              enabled by fast access to terabyte-scale data
      •       World-Class Support: IBM provides 24/7/365, single-point-of-contact
              service and support for every Schooner appliance, worldwide


 © 2010 Schooner Information Technology. All rights reserved.
                                                                                      22
MySQL
Conference &
Expo, 2010




                                                                Q&A




 © 2010 Schooner Information Technology. All rights reserved.
                                                                      23
MySQL
Conference &
Expo, 2010
                                                                Abstract


           Scale out data centers are realizing order of magnitude improvements in
           performance, scalability, and availability while reducing TCO with
           innovative MySQL and NoSQL solutions. These architectures tightly couple
           MySQL and NoSQL with flash memory, multi-core processors and high
           performance networking into balanced, highly available, scalable solutions .


           In this presentation, Darpan Dinker, Vice President of Database Technologies,
           Schooner Information Technology, will discuss:
               business and technology challenges
               tightly coupled MySQL and NoSQL scale out architectures
               case studies of large scale web site deployments in premier web 2.0,
                enterprise, and cloud companies, discussing their realized order of
                magnitude improvements in performance, scalability, downtime and TCO.




 © 2010 Schooner Information Technology. All rights reserved.
                                                                                           24

More Related Content

What's hot

Presentación Data Center Cablevisión Day 2010
Presentación Data Center Cablevisión Day 2010Presentación Data Center Cablevisión Day 2010
Presentación Data Center Cablevisión Day 2010Logicalis Latam
 
Business Infrastructure & IT Pain points
Business Infrastructure & IT Pain pointsBusiness Infrastructure & IT Pain points
Business Infrastructure & IT Pain pointsRichardson Eyres
 
Nevmug Amd January 2009
Nevmug   Amd January 2009 Nevmug   Amd January 2009
Nevmug Amd January 2009 csharney
 
Mas 90 Top 10 Reasons To Upgrade
Mas 90 Top 10 Reasons To UpgradeMas 90 Top 10 Reasons To Upgrade
Mas 90 Top 10 Reasons To Upgradekbalonier
 
CloudBees PaaS Presentation at Oakland JUG
CloudBees PaaS Presentation at Oakland JUGCloudBees PaaS Presentation at Oakland JUG
CloudBees PaaS Presentation at Oakland JUGCloudBees
 
Dell high density GPU solution
Dell high density GPU solutionDell high density GPU solution
Dell high density GPU solutionClayton Li
 
Leon IT Setup Case Study
Leon IT Setup Case StudyLeon IT Setup Case Study
Leon IT Setup Case Studyrahulmeher
 
Java ee 7 platform developing for the cloud kshitiz saxena
Java ee 7 platform developing for the cloud   kshitiz saxenaJava ee 7 platform developing for the cloud   kshitiz saxena
Java ee 7 platform developing for the cloud kshitiz saxenaIndicThreads
 
Spring, Java Web Apps to the cloud
Spring, Java Web Apps to the cloudSpring, Java Web Apps to the cloud
Spring, Java Web Apps to the cloudCloudBees
 
Microsoft Unified Communications - Outlook/Exchange Better Together Presentation
Microsoft Unified Communications - Outlook/Exchange Better Together PresentationMicrosoft Unified Communications - Outlook/Exchange Better Together Presentation
Microsoft Unified Communications - Outlook/Exchange Better Together PresentationMicrosoft Private Cloud
 
3 junhua-experience show unified communication
3 junhua-experience show unified communication3 junhua-experience show unified communication
3 junhua-experience show unified communicationITband
 
IBM System z - zEnterprise a future platform for enterprise systems
IBM System z - zEnterprise a future platform for enterprise systemsIBM System z - zEnterprise a future platform for enterprise systems
IBM System z - zEnterprise a future platform for enterprise systemsIBM Sverige
 
Mobile App Assurance: Yesterday, Today, and Tomorrow.
Mobile App Assurance: Yesterday, Today, and Tomorrow.Mobile App Assurance: Yesterday, Today, and Tomorrow.
Mobile App Assurance: Yesterday, Today, and Tomorrow.Bob Binder
 
Advancing the Traditional Enterprise: An EA Story
Advancing the Traditional Enterprise: An EA Story Advancing the Traditional Enterprise: An EA Story
Advancing the Traditional Enterprise: An EA Story InnoTech
 
Share Point 2010 Deployment
Share Point 2010 DeploymentShare Point 2010 Deployment
Share Point 2010 DeploymentKamol Sagwan
 
Couchbase Server and IBM BigInsights: One + One = Three
Couchbase Server and IBM BigInsights: One + One = ThreeCouchbase Server and IBM BigInsights: One + One = Three
Couchbase Server and IBM BigInsights: One + One = ThreeDipti Borkar
 
Upgrade services share_pointserver
Upgrade services share_pointserverUpgrade services share_pointserver
Upgrade services share_pointserverArd van Someren
 

What's hot (20)

Presentación Data Center Cablevisión Day 2010
Presentación Data Center Cablevisión Day 2010Presentación Data Center Cablevisión Day 2010
Presentación Data Center Cablevisión Day 2010
 
Business Infrastructure & IT Pain points
Business Infrastructure & IT Pain pointsBusiness Infrastructure & IT Pain points
Business Infrastructure & IT Pain points
 
Ps Data Center Dal
Ps Data Center DalPs Data Center Dal
Ps Data Center Dal
 
Nevmug Amd January 2009
Nevmug   Amd January 2009 Nevmug   Amd January 2009
Nevmug Amd January 2009
 
Mas 90 Top 10 Reasons To Upgrade
Mas 90 Top 10 Reasons To UpgradeMas 90 Top 10 Reasons To Upgrade
Mas 90 Top 10 Reasons To Upgrade
 
CloudBees PaaS Presentation at Oakland JUG
CloudBees PaaS Presentation at Oakland JUGCloudBees PaaS Presentation at Oakland JUG
CloudBees PaaS Presentation at Oakland JUG
 
Dell high density GPU solution
Dell high density GPU solutionDell high density GPU solution
Dell high density GPU solution
 
Leon IT Setup Case Study
Leon IT Setup Case StudyLeon IT Setup Case Study
Leon IT Setup Case Study
 
Java ee 7 platform developing for the cloud kshitiz saxena
Java ee 7 platform developing for the cloud   kshitiz saxenaJava ee 7 platform developing for the cloud   kshitiz saxena
Java ee 7 platform developing for the cloud kshitiz saxena
 
Spring, Java Web Apps to the cloud
Spring, Java Web Apps to the cloudSpring, Java Web Apps to the cloud
Spring, Java Web Apps to the cloud
 
102 1600-1630
102 1600-1630102 1600-1630
102 1600-1630
 
Microsoft Unified Communications - Outlook/Exchange Better Together Presentation
Microsoft Unified Communications - Outlook/Exchange Better Together PresentationMicrosoft Unified Communications - Outlook/Exchange Better Together Presentation
Microsoft Unified Communications - Outlook/Exchange Better Together Presentation
 
3 junhua-experience show unified communication
3 junhua-experience show unified communication3 junhua-experience show unified communication
3 junhua-experience show unified communication
 
IBM System z - zEnterprise a future platform for enterprise systems
IBM System z - zEnterprise a future platform for enterprise systemsIBM System z - zEnterprise a future platform for enterprise systems
IBM System z - zEnterprise a future platform for enterprise systems
 
Mobile App Assurance: Yesterday, Today, and Tomorrow.
Mobile App Assurance: Yesterday, Today, and Tomorrow.Mobile App Assurance: Yesterday, Today, and Tomorrow.
Mobile App Assurance: Yesterday, Today, and Tomorrow.
 
Advancing the Traditional Enterprise: An EA Story
Advancing the Traditional Enterprise: An EA Story Advancing the Traditional Enterprise: An EA Story
Advancing the Traditional Enterprise: An EA Story
 
Share Point 2010 Deployment
Share Point 2010 DeploymentShare Point 2010 Deployment
Share Point 2010 Deployment
 
Software as a Service
Software as a ServiceSoftware as a Service
Software as a Service
 
Couchbase Server and IBM BigInsights: One + One = Three
Couchbase Server and IBM BigInsights: One + One = ThreeCouchbase Server and IBM BigInsights: One + One = Three
Couchbase Server and IBM BigInsights: One + One = Three
 
Upgrade services share_pointserver
Upgrade services share_pointserverUpgrade services share_pointserver
Upgrade services share_pointserver
 

Viewers also liked

Spike Free Low Latency
Spike Free Low LatencySpike Free Low Latency
Spike Free Low LatencyJack O'Brien
 
Violin Memory DOAG (German Oracle User Group) Nov 2012
Violin Memory DOAG (German Oracle User Group) Nov 2012Violin Memory DOAG (German Oracle User Group) Nov 2012
Violin Memory DOAG (German Oracle User Group) Nov 2012Jack O'Brien
 
MariaDB 10 and what's new with the project
MariaDB 10 and what's new with the projectMariaDB 10 and what's new with the project
MariaDB 10 and what's new with the projectColin Charles
 
Nvmfs benchmark
Nvmfs benchmarkNvmfs benchmark
Nvmfs benchmarkLouis liu
 
My SQL and Ceph: Head-to-Head Performance Lab
My SQL and Ceph: Head-to-Head Performance LabMy SQL and Ceph: Head-to-Head Performance Lab
My SQL and Ceph: Head-to-Head Performance LabRed_Hat_Storage
 
PostgreSQL - Ups, DevOps..., Алексей Лесовский (PostgreSQL-Consulting)
PostgreSQL - Ups, DevOps..., Алексей Лесовский (PostgreSQL-Consulting)PostgreSQL - Ups, DevOps..., Алексей Лесовский (PostgreSQL-Consulting)
PostgreSQL - Ups, DevOps..., Алексей Лесовский (PostgreSQL-Consulting)Ontico
 
ICDE2014 Session 14 Data Warehousing
ICDE2014 Session 14 Data WarehousingICDE2014 Session 14 Data Warehousing
ICDE2014 Session 14 Data WarehousingTakuma Wakamori
 
VLDB2013 Session 1 Emerging Hardware
VLDB2013 Session 1 Emerging HardwareVLDB2013 Session 1 Emerging Hardware
VLDB2013 Session 1 Emerging HardwareTakuma Wakamori
 
Webinar: Capacity Planning
Webinar: Capacity PlanningWebinar: Capacity Planning
Webinar: Capacity PlanningMongoDB
 
SSD для вашей базы данных, Петр Зайцев (Percona)
SSD для вашей базы данных, Петр Зайцев (Percona)SSD для вашей базы данных, Петр Зайцев (Percona)
SSD для вашей базы данных, Петр Зайцев (Percona)Ontico
 
Infiniflash benchmark
Infiniflash benchmarkInfiniflash benchmark
Infiniflash benchmarkLouis liu
 
(BDT323) Amazon EBS & Cassandra: 1 Million Writes Per Second
(BDT323) Amazon EBS & Cassandra: 1 Million Writes Per Second(BDT323) Amazon EBS & Cassandra: 1 Million Writes Per Second
(BDT323) Amazon EBS & Cassandra: 1 Million Writes Per SecondAmazon Web Services
 
MongoDB on EC2 and EBS
MongoDB on EC2 and EBSMongoDB on EC2 and EBS
MongoDB on EC2 and EBSJared Rosoff
 
VMware Performance for Gurus - A Tutorial
VMware Performance for Gurus - A TutorialVMware Performance for Gurus - A Tutorial
VMware Performance for Gurus - A TutorialRichard McDougall
 

Viewers also liked (15)

Spike Free Low Latency
Spike Free Low LatencySpike Free Low Latency
Spike Free Low Latency
 
Violin Memory DOAG (German Oracle User Group) Nov 2012
Violin Memory DOAG (German Oracle User Group) Nov 2012Violin Memory DOAG (German Oracle User Group) Nov 2012
Violin Memory DOAG (German Oracle User Group) Nov 2012
 
MariaDB 10 and what's new with the project
MariaDB 10 and what's new with the projectMariaDB 10 and what's new with the project
MariaDB 10 and what's new with the project
 
Nvmfs benchmark
Nvmfs benchmarkNvmfs benchmark
Nvmfs benchmark
 
MySQL on Ceph
MySQL on CephMySQL on Ceph
MySQL on Ceph
 
My SQL and Ceph: Head-to-Head Performance Lab
My SQL and Ceph: Head-to-Head Performance LabMy SQL and Ceph: Head-to-Head Performance Lab
My SQL and Ceph: Head-to-Head Performance Lab
 
PostgreSQL - Ups, DevOps..., Алексей Лесовский (PostgreSQL-Consulting)
PostgreSQL - Ups, DevOps..., Алексей Лесовский (PostgreSQL-Consulting)PostgreSQL - Ups, DevOps..., Алексей Лесовский (PostgreSQL-Consulting)
PostgreSQL - Ups, DevOps..., Алексей Лесовский (PostgreSQL-Consulting)
 
ICDE2014 Session 14 Data Warehousing
ICDE2014 Session 14 Data WarehousingICDE2014 Session 14 Data Warehousing
ICDE2014 Session 14 Data Warehousing
 
VLDB2013 Session 1 Emerging Hardware
VLDB2013 Session 1 Emerging HardwareVLDB2013 Session 1 Emerging Hardware
VLDB2013 Session 1 Emerging Hardware
 
Webinar: Capacity Planning
Webinar: Capacity PlanningWebinar: Capacity Planning
Webinar: Capacity Planning
 
SSD для вашей базы данных, Петр Зайцев (Percona)
SSD для вашей базы данных, Петр Зайцев (Percona)SSD для вашей базы данных, Петр Зайцев (Percona)
SSD для вашей базы данных, Петр Зайцев (Percona)
 
Infiniflash benchmark
Infiniflash benchmarkInfiniflash benchmark
Infiniflash benchmark
 
(BDT323) Amazon EBS & Cassandra: 1 Million Writes Per Second
(BDT323) Amazon EBS & Cassandra: 1 Million Writes Per Second(BDT323) Amazon EBS & Cassandra: 1 Million Writes Per Second
(BDT323) Amazon EBS & Cassandra: 1 Million Writes Per Second
 
MongoDB on EC2 and EBS
MongoDB on EC2 and EBSMongoDB on EC2 and EBS
MongoDB on EC2 and EBS
 
VMware Performance for Gurus - A Tutorial
VMware Performance for Gurus - A TutorialVMware Performance for Gurus - A Tutorial
VMware Performance for Gurus - A Tutorial
 

Similar to Next-gen Flash-based MySQL and NoSQL Solutions (Real World Case Studies of Extreme Performance, Scalability and Availability)

SQL Server 2008 para Implementar Biztalk
SQL Server 2008 para Implementar BiztalkSQL Server 2008 para Implementar Biztalk
SQL Server 2008 para Implementar BiztalkEduardo Castro
 
Future Proofing MySQL by Robert Hodges, Continuent
Future Proofing MySQL by Robert Hodges, ContinuentFuture Proofing MySQL by Robert Hodges, Continuent
Future Proofing MySQL by Robert Hodges, ContinuentEero Teerikorpi
 
NoSQL and MySQL webinar - best of both worlds
NoSQL and MySQL webinar - best of both worldsNoSQL and MySQL webinar - best of both worlds
NoSQL and MySQL webinar - best of both worldsMat Keep
 
MySQL HA Solutions
MySQL HA SolutionsMySQL HA Solutions
MySQL HA SolutionsMat Keep
 
Virtualizing Business Critical Apps
Virtualizing Business Critical AppsVirtualizing Business Critical Apps
Virtualizing Business Critical Appsheraldschelke
 
Architecting Cloud Solutions
Architecting Cloud SolutionsArchitecting Cloud Solutions
Architecting Cloud SolutionsAMD
 
14h00 aws deck-summit2012_sap_on_aws_s_jones_final
14h00   aws deck-summit2012_sap_on_aws_s_jones_final14h00   aws deck-summit2012_sap_on_aws_s_jones_final
14h00 aws deck-summit2012_sap_on_aws_s_jones_finalLuiz Gustavo Santos
 
SQL Server Clustering and High Availability
SQL Server Clustering and High AvailabilitySQL Server Clustering and High Availability
SQL Server Clustering and High Availability► Supreme Mandal ◄
 
MySQL Cluster 7.2 e 7.3 - por Andrew Morgan
MySQL Cluster 7.2 e 7.3 - por Andrew MorganMySQL Cluster 7.2 e 7.3 - por Andrew Morgan
MySQL Cluster 7.2 e 7.3 - por Andrew MorganMySQL Brasil
 
SQL Server Workshop Paul Bertucci
SQL Server Workshop Paul BertucciSQL Server Workshop Paul Bertucci
SQL Server Workshop Paul BertucciMark Ginnebaugh
 
SQL Server 2008 Migration Workshop 04/29/2009
SQL Server 2008 Migration Workshop 04/29/2009SQL Server 2008 Migration Workshop 04/29/2009
SQL Server 2008 Migration Workshop 04/29/2009Database Architechs
 
The Hybrid Windows Azure Application
The Hybrid Windows Azure ApplicationThe Hybrid Windows Azure Application
The Hybrid Windows Azure ApplicationMichael Collier
 
NLJUG: Content Management, Standards, Opensource & JCP
NLJUG: Content Management, Standards, Opensource & JCPNLJUG: Content Management, Standards, Opensource & JCP
NLJUG: Content Management, Standards, Opensource & JCPDavid Nuescheler
 
Tivoli Development Cloud Pennock Final Web
Tivoli Development Cloud Pennock Final WebTivoli Development Cloud Pennock Final Web
Tivoli Development Cloud Pennock Final WebKennisportal
 
How AOL Advertising Uses NoSQL to Make Millions of Smart Targeting Decisions ...
How AOL Advertising Uses NoSQL to Make Millions of Smart Targeting Decisions ...How AOL Advertising Uses NoSQL to Make Millions of Smart Targeting Decisions ...
How AOL Advertising Uses NoSQL to Make Millions of Smart Targeting Decisions ...DATAVERSITY
 
Mark Kurzava, SQL Server Developer
Mark Kurzava, SQL Server DeveloperMark Kurzava, SQL Server Developer
Mark Kurzava, SQL Server DeveloperMark Kurzava
 
Mule ESB - Integration Simplified
Mule ESB - Integration SimplifiedMule ESB - Integration Simplified
Mule ESB - Integration SimplifiedRich Software
 

Similar to Next-gen Flash-based MySQL and NoSQL Solutions (Real World Case Studies of Extreme Performance, Scalability and Availability) (20)

SQL Server 2008 para Implementar Biztalk
SQL Server 2008 para Implementar BiztalkSQL Server 2008 para Implementar Biztalk
SQL Server 2008 para Implementar Biztalk
 
Future Proofing MySQL by Robert Hodges, Continuent
Future Proofing MySQL by Robert Hodges, ContinuentFuture Proofing MySQL by Robert Hodges, Continuent
Future Proofing MySQL by Robert Hodges, Continuent
 
NoSQL and MySQL webinar - best of both worlds
NoSQL and MySQL webinar - best of both worldsNoSQL and MySQL webinar - best of both worlds
NoSQL and MySQL webinar - best of both worlds
 
MySQL HA Solutions
MySQL HA SolutionsMySQL HA Solutions
MySQL HA Solutions
 
SAP on AWS
SAP on AWSSAP on AWS
SAP on AWS
 
MySQL Cluster
MySQL ClusterMySQL Cluster
MySQL Cluster
 
Virtualizing Business Critical Apps
Virtualizing Business Critical AppsVirtualizing Business Critical Apps
Virtualizing Business Critical Apps
 
Architecting Cloud Solutions
Architecting Cloud SolutionsArchitecting Cloud Solutions
Architecting Cloud Solutions
 
14h00 aws deck-summit2012_sap_on_aws_s_jones_final
14h00   aws deck-summit2012_sap_on_aws_s_jones_final14h00   aws deck-summit2012_sap_on_aws_s_jones_final
14h00 aws deck-summit2012_sap_on_aws_s_jones_final
 
SQL Server User Group 02/2009
SQL Server User Group 02/2009SQL Server User Group 02/2009
SQL Server User Group 02/2009
 
SQL Server Clustering and High Availability
SQL Server Clustering and High AvailabilitySQL Server Clustering and High Availability
SQL Server Clustering and High Availability
 
MySQL Cluster 7.2 e 7.3 - por Andrew Morgan
MySQL Cluster 7.2 e 7.3 - por Andrew MorganMySQL Cluster 7.2 e 7.3 - por Andrew Morgan
MySQL Cluster 7.2 e 7.3 - por Andrew Morgan
 
SQL Server Workshop Paul Bertucci
SQL Server Workshop Paul BertucciSQL Server Workshop Paul Bertucci
SQL Server Workshop Paul Bertucci
 
SQL Server 2008 Migration Workshop 04/29/2009
SQL Server 2008 Migration Workshop 04/29/2009SQL Server 2008 Migration Workshop 04/29/2009
SQL Server 2008 Migration Workshop 04/29/2009
 
The Hybrid Windows Azure Application
The Hybrid Windows Azure ApplicationThe Hybrid Windows Azure Application
The Hybrid Windows Azure Application
 
NLJUG: Content Management, Standards, Opensource & JCP
NLJUG: Content Management, Standards, Opensource & JCPNLJUG: Content Management, Standards, Opensource & JCP
NLJUG: Content Management, Standards, Opensource & JCP
 
Tivoli Development Cloud Pennock Final Web
Tivoli Development Cloud Pennock Final WebTivoli Development Cloud Pennock Final Web
Tivoli Development Cloud Pennock Final Web
 
How AOL Advertising Uses NoSQL to Make Millions of Smart Targeting Decisions ...
How AOL Advertising Uses NoSQL to Make Millions of Smart Targeting Decisions ...How AOL Advertising Uses NoSQL to Make Millions of Smart Targeting Decisions ...
How AOL Advertising Uses NoSQL to Make Millions of Smart Targeting Decisions ...
 
Mark Kurzava, SQL Server Developer
Mark Kurzava, SQL Server DeveloperMark Kurzava, SQL Server Developer
Mark Kurzava, SQL Server Developer
 
Mule ESB - Integration Simplified
Mule ESB - Integration SimplifiedMule ESB - Integration Simplified
Mule ESB - Integration Simplified
 

Recently uploaded

Novo Nordisk's journey in developing an open-source application on Neo4j
Novo Nordisk's journey in developing an open-source application on Neo4jNovo Nordisk's journey in developing an open-source application on Neo4j
Novo Nordisk's journey in developing an open-source application on Neo4jNeo4j
 
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENTSIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENTxtailishbaloch
 
Design and Modeling for MySQL SCALE 21X Pasadena, CA Mar 2024
Design and Modeling for MySQL SCALE 21X Pasadena, CA Mar 2024Design and Modeling for MySQL SCALE 21X Pasadena, CA Mar 2024
Design and Modeling for MySQL SCALE 21X Pasadena, CA Mar 2024Alkin Tezuysal
 
UiPath Studio Web workshop Series - Day 3
UiPath Studio Web workshop Series - Day 3UiPath Studio Web workshop Series - Day 3
UiPath Studio Web workshop Series - Day 3DianaGray10
 
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptxGraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptxNeo4j
 
Technical SEO for Improved Accessibility WTS FEST
Technical SEO for Improved Accessibility  WTS FESTTechnical SEO for Improved Accessibility  WTS FEST
Technical SEO for Improved Accessibility WTS FESTBillieHyde
 
Keep Your Finger on the Pulse of Your Building's Performance with IES Live
Keep Your Finger on the Pulse of Your Building's Performance with IES LiveKeep Your Finger on the Pulse of Your Building's Performance with IES Live
Keep Your Finger on the Pulse of Your Building's Performance with IES LiveIES VE
 
Patch notes explaining DISARM Version 1.4 update
Patch notes explaining DISARM Version 1.4 updatePatch notes explaining DISARM Version 1.4 update
Patch notes explaining DISARM Version 1.4 updateadam112203
 
CyberSecurity - Computers In Libraries 2024
CyberSecurity - Computers In Libraries 2024CyberSecurity - Computers In Libraries 2024
CyberSecurity - Computers In Libraries 2024Brian Pichman
 
The Zero-ETL Approach: Enhancing Data Agility and Insight
The Zero-ETL Approach: Enhancing Data Agility and InsightThe Zero-ETL Approach: Enhancing Data Agility and Insight
The Zero-ETL Approach: Enhancing Data Agility and InsightSafe Software
 
My key hands-on projects in Quantum, and QAI
My key hands-on projects in Quantum, and QAIMy key hands-on projects in Quantum, and QAI
My key hands-on projects in Quantum, and QAIVijayananda Mohire
 
Where developers are challenged, what developers want and where DevEx is going
Where developers are challenged, what developers want and where DevEx is goingWhere developers are challenged, what developers want and where DevEx is going
Where developers are challenged, what developers want and where DevEx is goingFrancesco Corti
 
Introduction to RAG (Retrieval Augmented Generation) and its application
Introduction to RAG (Retrieval Augmented Generation) and its applicationIntroduction to RAG (Retrieval Augmented Generation) and its application
Introduction to RAG (Retrieval Augmented Generation) and its applicationKnoldus Inc.
 
Introduction - IPLOOK NETWORKS CO., LTD.
Introduction - IPLOOK NETWORKS CO., LTD.Introduction - IPLOOK NETWORKS CO., LTD.
Introduction - IPLOOK NETWORKS CO., LTD.IPLOOK Networks
 
Q4 2023 Quarterly Investor Presentation - FINAL - v1.pdf
Q4 2023 Quarterly Investor Presentation - FINAL - v1.pdfQ4 2023 Quarterly Investor Presentation - FINAL - v1.pdf
Q4 2023 Quarterly Investor Presentation - FINAL - v1.pdfTejal81
 
EMEA What is ThousandEyes? Webinar
EMEA What is ThousandEyes? WebinarEMEA What is ThousandEyes? Webinar
EMEA What is ThousandEyes? WebinarThousandEyes
 
Extra-120324-Visite-Entreprise-icare.pdf
Extra-120324-Visite-Entreprise-icare.pdfExtra-120324-Visite-Entreprise-icare.pdf
Extra-120324-Visite-Entreprise-icare.pdfInfopole1
 
3 Pitfalls Everyone Should Avoid with Cloud Data
3 Pitfalls Everyone Should Avoid with Cloud Data3 Pitfalls Everyone Should Avoid with Cloud Data
3 Pitfalls Everyone Should Avoid with Cloud DataEric D. Schabell
 
LF Energy Webinar - Unveiling OpenEEMeter 4.0
LF Energy Webinar - Unveiling OpenEEMeter 4.0LF Energy Webinar - Unveiling OpenEEMeter 4.0
LF Energy Webinar - Unveiling OpenEEMeter 4.0DanBrown980551
 
2024.03.12 Cost drivers of cultivated meat production.pdf
2024.03.12 Cost drivers of cultivated meat production.pdf2024.03.12 Cost drivers of cultivated meat production.pdf
2024.03.12 Cost drivers of cultivated meat production.pdfThe Good Food Institute
 

Recently uploaded (20)

Novo Nordisk's journey in developing an open-source application on Neo4j
Novo Nordisk's journey in developing an open-source application on Neo4jNovo Nordisk's journey in developing an open-source application on Neo4j
Novo Nordisk's journey in developing an open-source application on Neo4j
 
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENTSIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
 
Design and Modeling for MySQL SCALE 21X Pasadena, CA Mar 2024
Design and Modeling for MySQL SCALE 21X Pasadena, CA Mar 2024Design and Modeling for MySQL SCALE 21X Pasadena, CA Mar 2024
Design and Modeling for MySQL SCALE 21X Pasadena, CA Mar 2024
 
UiPath Studio Web workshop Series - Day 3
UiPath Studio Web workshop Series - Day 3UiPath Studio Web workshop Series - Day 3
UiPath Studio Web workshop Series - Day 3
 
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptxGraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
 
Technical SEO for Improved Accessibility WTS FEST
Technical SEO for Improved Accessibility  WTS FESTTechnical SEO for Improved Accessibility  WTS FEST
Technical SEO for Improved Accessibility WTS FEST
 
Keep Your Finger on the Pulse of Your Building's Performance with IES Live
Keep Your Finger on the Pulse of Your Building's Performance with IES LiveKeep Your Finger on the Pulse of Your Building's Performance with IES Live
Keep Your Finger on the Pulse of Your Building's Performance with IES Live
 
Patch notes explaining DISARM Version 1.4 update
Patch notes explaining DISARM Version 1.4 updatePatch notes explaining DISARM Version 1.4 update
Patch notes explaining DISARM Version 1.4 update
 
CyberSecurity - Computers In Libraries 2024
CyberSecurity - Computers In Libraries 2024CyberSecurity - Computers In Libraries 2024
CyberSecurity - Computers In Libraries 2024
 
The Zero-ETL Approach: Enhancing Data Agility and Insight
The Zero-ETL Approach: Enhancing Data Agility and InsightThe Zero-ETL Approach: Enhancing Data Agility and Insight
The Zero-ETL Approach: Enhancing Data Agility and Insight
 
My key hands-on projects in Quantum, and QAI
My key hands-on projects in Quantum, and QAIMy key hands-on projects in Quantum, and QAI
My key hands-on projects in Quantum, and QAI
 
Where developers are challenged, what developers want and where DevEx is going
Where developers are challenged, what developers want and where DevEx is goingWhere developers are challenged, what developers want and where DevEx is going
Where developers are challenged, what developers want and where DevEx is going
 
Introduction to RAG (Retrieval Augmented Generation) and its application
Introduction to RAG (Retrieval Augmented Generation) and its applicationIntroduction to RAG (Retrieval Augmented Generation) and its application
Introduction to RAG (Retrieval Augmented Generation) and its application
 
Introduction - IPLOOK NETWORKS CO., LTD.
Introduction - IPLOOK NETWORKS CO., LTD.Introduction - IPLOOK NETWORKS CO., LTD.
Introduction - IPLOOK NETWORKS CO., LTD.
 
Q4 2023 Quarterly Investor Presentation - FINAL - v1.pdf
Q4 2023 Quarterly Investor Presentation - FINAL - v1.pdfQ4 2023 Quarterly Investor Presentation - FINAL - v1.pdf
Q4 2023 Quarterly Investor Presentation - FINAL - v1.pdf
 
EMEA What is ThousandEyes? Webinar
EMEA What is ThousandEyes? WebinarEMEA What is ThousandEyes? Webinar
EMEA What is ThousandEyes? Webinar
 
Extra-120324-Visite-Entreprise-icare.pdf
Extra-120324-Visite-Entreprise-icare.pdfExtra-120324-Visite-Entreprise-icare.pdf
Extra-120324-Visite-Entreprise-icare.pdf
 
3 Pitfalls Everyone Should Avoid with Cloud Data
3 Pitfalls Everyone Should Avoid with Cloud Data3 Pitfalls Everyone Should Avoid with Cloud Data
3 Pitfalls Everyone Should Avoid with Cloud Data
 
LF Energy Webinar - Unveiling OpenEEMeter 4.0
LF Energy Webinar - Unveiling OpenEEMeter 4.0LF Energy Webinar - Unveiling OpenEEMeter 4.0
LF Energy Webinar - Unveiling OpenEEMeter 4.0
 
2024.03.12 Cost drivers of cultivated meat production.pdf
2024.03.12 Cost drivers of cultivated meat production.pdf2024.03.12 Cost drivers of cultivated meat production.pdf
2024.03.12 Cost drivers of cultivated meat production.pdf
 

Next-gen Flash-based MySQL and NoSQL Solutions (Real World Case Studies of Extreme Performance, Scalability and Availability)

  • 1. Next-gen Flash-based MySQL and NoSQL Solutions Real World Case Studies of Extreme Performance, Scalability, and Availability Darpan Dinker Vice President, Database Technologies Partnership Power > © 2010 Schooner Information Technology. All rights reserved.
  • 2. MySQL Conference & Expo, 2010 Agenda • Datacenter trends and challenges • Next-gen flash-based solutions • MySQL case studies • NoSQL case studies Partnership Power > © 2010 Schooner Information Technology. All rights reserved. 2
  • 3. MySQL Conference & Too Much Rack, Power, Pipe, and Expo, 2010 Complexity For every 100 U.S. data- The number of units of energy Datacenter installed servers From 2003 to 2008 piped into a data centers use equipment is more energy in the U.S. will the data size of the center, only only utilized increase from 2.2 average web page has three are used than the entire 6% to 10%. nation of million in 2007 to more than tripled. for actual Sweden. - William Forrest 6.8 million in 2010. –websiteoptimization.com computing. Forbes - Frost & Sullivan - EE Times - U.S. Department of Energy © 2010 Schooner Information Technology. All rights reserved. 3
  • 4. MySQL Conference & Expo, 2010 Typical Datacenter Deployment Data Access Tier Web/App Tier Caching Tier Database Tier PHP, Perl, Memcached MySQL Ruby, Java Slaves POOL 1 Master POOL 2 Ensure Scale End Minimize User Quality of to Meet Costs Service NoSQL Tier Demand Key-Value Store, Document Store, etc. POOL3 4 © 2010 Schooner Information Technology. All rights reserved. 4
  • 5. MySQL Conference & Expo, 2010 Key Challenges Pain of sharding and re-sharding Scale Complexity of adding new servers to Meet Demand Headache of managing server sprawl Poor response time and availability Ensure Trade-offs in consistency models Quality of Service Complex, defensive app development Too much underutilized hardware Wasted power, pipe, and cooling Minimize Costs Integration & management burden © 2009 Schooner Information Technology. Confidential 5
  • 6. MySQL Conference & Vision: Tightly Coupled, Scalable MySQL Expo, 2010 and NoSQL Building Blocks Integrated, optimized, scalable MySQL & NoSQL solutions:  Effectively leverage flash memory, multi-core processors, high- speed networking, scalable data access software  Incorporate highly optimized, balanced hardware platform, operating environment, integrated MySQL and NoSQL  Provide efficient, higher level scalable building blocks  Eliminate complex integration projects and leverage out of the box performance, scalability and availability  Deliver enterprise class reliability © 2010 Schooner Information Technology. All rights reserved. 6
  • 7. MySQL Conference & Tightly Coupled Software Expo, 2010 Architecture Networked Clients MySQL NoSQL Operating Environment Intelligent Caching Optimized Flash Multi-Core Transparent Hierarchy Memory Access Scalability HA/DR • Optimized buffer mgmt & • Highly parallel read and • Fine grain locking • Synchronous and async scan resistant algorithms write access replication • Scalable and concurrent • Write-through and write- • Intelligent flash wear data structures • Failure detection and back caching flexibility algorithms automated VIP failover • Optimized thread to core • Adaptive , fine-grained • Durability with high- allocation • Fast, incremental data memory management performance recovery • Efficient handling of • Efficient object meta- • High-performance, network interrupts • Incremental,/full online data for persistence integrated RAID backup and restore Optimized, Balanced Hardware Platform © 2010 Schooner Information Technology. All rights reserved. 7
  • 8. MySQL Conference & Schooner MySQL and Expo, 2010 NoSQL Solutions • Integrated, turnkey appliance 1 The Schooner Appliance for MySQL EnterpriseTM with InnoDB – Integrated hardware and software – Enterprise-class support – 100% compatibility, fully certified • High performance + – 8x performance improvement – 1/8x the power and rack space – 50% lower TCO over 3 years 2 The Schooner Appliance for Memcached / NoSQL • High availability – Complete data & service availability – Transparent and fully integrated High Persistent 100% – 90% higher availability Capacity Cache + Key-Value Store + Memcapable © 2010 Schooner Information Technology. All rights reserved. 8
  • 9. MySQL Conference & Expo, 2010 Schooner Powered Datacenter Data Access Tier Web/App Tier Caching Tier Caching Tier Database Tier Database Tier PHP, Perl, Memcached Memcached MySQL MySQL Ruby, Java Slaves POOL 1 Master POOL 2 Ensure Scale Minimize End NoSQL Tier User Quality of to Meet Costs Service Key-Value Store, NoSQL Tier Demand Document Store, etc. Key-Value Store, Document Store, etc. POOL3 9 © 2010 Schooner Information Technology. All rights reserved. 9
  • 10. MySQL Conference & Schooner Appliance for Expo, 2010 MySQL Enterprise™ with InnoDB High Performance High Availability Turnkey Appliance • Highly parallel, optimized • Fully ACID-compliant with • Multi-instance consolidation flash memory access data durability on single appliance • Advanced buffer pool • Integrated replication and • Web-based GUI/CLI for caching algorithms automated failover centralized management • Multi-core scalability with fine • Integrated, high-performance • Integration with 3rd party grained locking backup and restore mgmt & monitoring tools • Delivered on proven IBM • RAID across SSDs and • 100% compatible and fully server with up to 1TB of flash HDDs certified by Sun/MySQL DBT2 Performance (TPM) Connection Scalability 75000 40000 Master Server TPS 60000 30000 45000 20000 30000 10000 15000 0 64 256 1024 4096 16384 0 Legacy MySQL Legacy MySQL with SSDs Schooner Appliance Schooner MySQL Measured DBT2 throughput at 1000 warehouses,32 connections, 8 SSDs/HDDS with RAID 5. All databases configured for durability and consistency. Legacy results were on MySQL version 5.1.44 (most commonly used today). Schooner MySQL Appliance results were on Schooner-optimized 5.1.44 © 2010 Schooner Information Technology. All rights reserved. 10
  • 11. MySQL Conference & MySQL Expo, 2010 Consolidation and Cost Savings TCO: $832,000 TCO: $282,000 TCO SAVINGS: $550,000 3 Year TCO (2 TB MySQL) OpEx OpEx THE BOTTOM LINE CapEx: 32 Servers CapEx: 4 • Immediate capex savings Appliances • 66 % TCO savings ($550,000) Without Schooner With Schooner over 3 years 32 servers, 17.9 kW 4 Schooner • Power & space reductions appliances, 1.8 kW enable green datacenter © 2010 Schooner Information Technology. All rights reserved. 11
  • 12. MySQL Conference & Expo, 2010 MySQL What Can I Do With It? Reduce sharding and Scale performance and consolidate slaves process queries faster Apps Masters Slaves Apps Schooner 70K TPM (DBT2) 20K Connections ½ TB or 1TB Flash … … Reduce planned and Eliminate integration and unplanned downtime optimization headaches • Software MySQL Replication + MMM Failover Install/Config • Hardware HA Tools • Support SSD RAID & SSD RAID & SSD RAID & Data Durability Data Durability Data Durability • Certified Tuning Services • Complete © 2009 Schooner Information Technology. Confidential 12
  • 13. MySQL Conference & Expo, 2010 Case Study: Financial Services Scale Performance and Process Queries Faster High-performance, out-of-the-box 100% compatible "Our ad-hoc MySQL queries run at least five times faster after installing the Schooner Appliances. They deliver a huge performance benefit and are a breeze to install and manage.“ – Darryl Weatherspoon, VP of Eng at Xoom. © 2010 Schooner Information Technology. All rights reserved. 13
  • 14. MySQL Conference & Expo, 2010 Case Study: Social Networking Consolidate Slaves Apps Masters Slaves Apps Masters Schooner "In our business, website performance and efficiency is key to the success of our web properties. The Schooner MySQL Appliances have significantly helped GuteFrage improve their overall website response time while at the same time allowing them to consolidate their database slaves onto a single Schooner appliance, dramatically reducing the time necessary for database administration.“ – Frank Penning, CTO of Holzbrinck Digital © 2010 Schooner Information Technology. All rights reserved. 14
  • 15. MySQL Conference & Schooner Appliance for Memcached Expo, 2010 / NoSQL High Performance High Availability Easy Appliance • Highly parallel, optimized • Persistent key-value store • Dynamic containers for flash memory access mode and cache mode consolidation & multi-tenancy • Fast, efficient DRAM-to- • Transparent replication and • Web-based GUI/CLI for Flash caching algorithms automated failover centralized management • Multi-core scalability with • Non-disruptive, rolling • Integration with 3rd party parallel thread allocation upgrades mgmt & monitoring tools • Delivered on a proven IBM • RAID & high-performance • 100% compatible and fully server with a ½ TB of flash backup and restore memcapable compliant Key-Value Store Service Memcached Caching Service • 350GB capacity, 150K TPS • 150GB capacity, 250K TPS • Replication & Failover • Replication & Failover • Persistence, RAID, and Backup • 100% Memcapable • Memcached-based key-value API © 2010 Schooner Information Technology. All rights reserved. 15
  • 16. MySQL Conference & Schooner Memcached / NoSQL: Expo, 2010 Capacity and Availability Cache Capacity per Node (GB) Reduction in Downtime (%) 600 100 500 80 400 60 300 40 200 100 20 0 0 Traditional Schooner Appliance Traditional Persistent Storage Replication Memcached Memcached Caching RAID & Failover © 2010 Schooner Information Technology. All rights reserved. 16
  • 17. MySQL Conference & Memcached / NoSQL Consolidation Expo, 2010 and Cost Savings TCO: $610,000 TCO: $282,000 TCO SAVINGS: 3 Year TCO (2 TB Memcached) OpEx $328,000 OpEx THE BOTTOM LINE CapEx: 32 CapEx: 4 Servers Appliances • Immediate capex savings • 54% TCO savings ($328,000) Without Schooner With Schooner over 3 years 32 servers, 17.9 kW 4 Schooner • Power & space reductions appliances, 1.8 kW enable green datacenter © 2010 Schooner Information Technology. All rights reserved. 17
  • 18. MySQL Conference & Expo, 2010 What Can I Do With It? Consolidate and reduce Reduce planned and server sprawl unplanned downtime Traditional Memcached Schooner Application Transparent POOL 1 Synchronous Replication + Automated Failover POOL 2 SSD RAID & SSD RAID & Persistence Persistence Scale cache capacity and Reduce application process requests faster development complexity Application Tier Application Tier Failure Detection Replication Group Delete Data Durability 250K TPS M$D API ½ TB M$D API Flash Failure Detection Replication Group Delete Data Durability Traditional Memcached Schooner © 2010 Schooner Information Technology. All rights reserved. 18
  • 19. MySQL Conference & Expo, 2010 Case Study: Social Networking Consolidate and Reduce Server Sprawl Traditional Memcached POOL 1 Schooner POOL 2 Scaling with 12:1 Consolidation using Persistence, Multi-Get, Replication and Recovery Scaling the data tier is a common challenge, and Schooner is helping us do just that. Power is the big constraint right now, so anything we can do to reduce that footprint right now is helpful. From an administrative perspective, fewer machines is always better, from a monitoring and scripting standpoint, and it also means reductions in potential failures due to fewer boxes.“ – Saran Chari, CTO and Founder at Flixster © 2010 Schooner Information Technology. All rights reserved. 19
  • 20. MySQL Conference & Expo, 2010 Case Study: Media Reduce Planned and Unplanned Downtime Application Transparent Synchronous Replication + Automated Failover SSD RAID & SSD RAID & Persistence Persistence 40 Million Users Address Books in Key Value Store with 8:1 Consolidation In the wonderful Schooner world, failovers go away. Schooner replication means that you’re sure that what you have on one node will also be on the other. Our developers don’t have to worry about cache coherency. They can plan on the data being available so they don’t have to program defensively. – Ethan Erchinger, Director of Ops at Plaxo © 2010 Schooner Information Technology. All rights reserved. 20
  • 21. MySQL Conference & Expo, 2010 Market Segments Social Networking Business Analytics Gaming Cloud Media Telco Finance © 2010 Schooner Information Technology. All rights reserved. 21
  • 22. MySQL Conference & Expo, 2010 The Schooner Advantage • Vastly Higher Performance and Scalability: 8x compared to traditional servers • Significantly Lower TCO: Replacing 8 traditional servers with 1 reduces TCO by more than 50% • Quick Deployment: Easy plug-and-play installation and configuration • Seamless Operation: 100% compatible with existing client applications and management tools • Higher Reliability: Delivers enterprise-class reliability by leveraging persistence, replication, and recovery software • Easy Management: Simple but powerful centralized management and reporting with integrated CLI and GUI • More Revenue: Powers new revenue-producing applications enabled by fast access to terabyte-scale data • World-Class Support: IBM provides 24/7/365, single-point-of-contact service and support for every Schooner appliance, worldwide © 2010 Schooner Information Technology. All rights reserved. 22
  • 23. MySQL Conference & Expo, 2010 Q&A © 2010 Schooner Information Technology. All rights reserved. 23
  • 24. MySQL Conference & Expo, 2010 Abstract Scale out data centers are realizing order of magnitude improvements in performance, scalability, and availability while reducing TCO with innovative MySQL and NoSQL solutions. These architectures tightly couple MySQL and NoSQL with flash memory, multi-core processors and high performance networking into balanced, highly available, scalable solutions . In this presentation, Darpan Dinker, Vice President of Database Technologies, Schooner Information Technology, will discuss:  business and technology challenges  tightly coupled MySQL and NoSQL scale out architectures  case studies of large scale web site deployments in premier web 2.0, enterprise, and cloud companies, discussing their realized order of magnitude improvements in performance, scalability, downtime and TCO. © 2010 Schooner Information Technology. All rights reserved. 24