SlideShare a Scribd company logo
GET MORE FROM YOUR WEB SERVICE

Scaling MySQL By
Leveraging Sun Systems


  Steve Staso
  Chief Architect, Web Infrastructure Solutions
  Global Systems Practice




                                                  1
Agenda

Scaling Concepts and
Approaches
Recommendations When/How to Scale
Scaling Test Results
Sun Systems for MySQL
Learn more

                                    2
Dramatically Change Economics
of Web Service Delivery
          Drive better performance, value
          ●
            Get greater performance
          ●
            Improve price performance, reduce costs
          ●
            Operating System, processor choice

          Simplify Deployments
          ●
              Leverage best practices, Blue Prints, reference
              architectures, subscriptions, systems, software,
              management expertise

          Scale for explosive Growth
          ●
            Scale to +1M concurrent users
          ●
            Choose best deployment technologies
          ●
            Predict performance under stress                     3
Agenda

Scaling Concepts and
Approaches
Recommendations When/How to Scale
Scaling Test Results
Sun Systems for MySQL
Learn more

                                    4
How to Scale?
Network         • Distribute the connections over
                  multiple servers
Load            • Increase the number of NICs and
                  networks
                • More CPUs help up to optimal thread
                  count, more than that is useless
CPU             • Scale-out can impact app server
Load              activity, scalability can be difficult
                • Reduce the logic in the DB server
                • More memory is always good
RAM/            • A scale-out can increase the
                  complexity of the environment
Caching         • External distributed caching
                • Faster disks and controllers always
I/O               help
Load            • Scale-out is the best option after an
                  initial optimization at server level


Storage         • SAN and NAS for large data centers
Requirement     • Scale-out is often cost effective
                                                      5
Choose the Right Server
      Architecture
      Server Scale-up vs. Scale-out for Database Deployments
Scaling Up




                               Scaling Out                     6
Choose the Right Server
      Architecture
      Server Scale-up vs. Scale-out for Database Deployments
Scaling Up




                               Scaling Out                     7
Choose the Right Server
      Architecture
      Server Scale-up vs. Scale-out for Database Deployments
Scaling Up




                                                                 g
                                                            alin
                                                        l Sc
                                                     ona
                                                Diag




                               Scaling Out                           8
Virtualize
Methods, benefits,
recommendations
                                         Memory latency   Compute


   Build Next Generation Virtual Datacenter


  Increase utilization, less heat
  and energy usage


   Up to 10 x better price/performance
                                                                    9
Implementations of Virtualization
                       Type I                 Type I             Type II

   App     App   App     App            App      App       App        App         App        App



  App      App   App     App            App      App       App        App         App        App



   App     App   App     App            App      App       App        App         App        App



                  OS      OS             OS       OS       OS         OS
                                                                                             Zone
   OS       OS    LD       LD                                                     Zone
                                         VM       VM       VM         VM


                                         Hypervisor         Hypervisor            Zone Support

                                                                                        OS
Software

                 Hypervisor                                                                  Hardware


  Hardware
                                                                  Virtualization Enablement Layer
                 Hardware                                        OS


                                         Hardware          Hardware               Hardware

   Hardware      Hardware based           Software based      Desktop             OS Virtualization   10
  Partitioning             System Virtualization           Virtualization
Leading Virtualization Choices
Different approaches, benefits in virtualizing web stack




                                  (future plans)




                               Hyper-V




              BSD                opensolaris™          opensolaris™




                         Sun xVM                   LDOMS
                                                                  11
Server/OS Virtualization
Sun Server Virtualization = Decreased Costs, Reduced Complexity




     CoolThreads Servers                          x64/x86 Servers
• Integrated, open source, no cost, and   • Most powerful, scalable, virtualized
  flexible virtualization technology –      designs, operating on today’s range of
  Logical Domains (LDoms)                   OS options
• Record-breaking performance             • Choice of hypervisor and OS allows for
• Breakthrough energy and space             investment protection
  efficiency                              • Available in racks or blades
• Available in racks or blades


  LDOMS
                                                                                12
Agenda

Scaling Concepts and
Approaches
Recommendations When/How to Scale
Scaling Test Results
Sun Systems for MySQL
Learn more

                                    13
The Benchmark
                                                     ●
                                                             Red Hat Ent Linux 5.1 64 bit
MySQL testbed                                        ●
                                                             Solaris 10 x86_64 and SPARC 64
                                                             mysql 5.1.26 rc 64 bit
environment
                                                     ●

                                                     ●
                                                             mysql coolstack 1.3.1 (based on 5.1.26) 64 bit


                                                     ●
                                                             100 warehouses created with the datagen utility
DBT2                                                 ●
                                                             15 GB of data generated for each DB
                                                             Extra table used to set random conditions
datagen
                                                     ●

                                                     ●
                                                             Extra tables added for transaction count


                                                     SP calls to:
DBT2                                                 ●
                                                       Delivery                 ●
                                                                                    Order Status
                                                                                    Stock Level
                                                       New Order
Stored Procedures
                                                     ●                          ●


                                                     ●
                                                       Payment


                                                         ●
                                                             100 calls:
DBT2 call set with                                       ●
                                                             4 Delivery         ●
                                                                                    4 Order Status
                                                                                    4 Stock Level
random IDs                                                   45 New Order
                                                         ●                      ●


                                                         ●
                                                             43 Payment         ●
                                                                                    + internal SP calls


                     ●
                         Shoot-out with:                                            ●
                                                                                        512k complex transactions
                     ●
                         1,2,4,8,16,32,64,128,256 concurrent connections            ●
                                                                                        51,200 per iteration
mysqlslap            ●
                         10 iterations                                              ●
                                                                                        250M single queries
                     ●
                         Warm-up (cold) and hot phases                              ●
                                                                                        high peak of 40k qps with “s” 14
The Systems
For MySQL Scaling
                        ●
                          2xAMD 2220 Dual Core 2.8Ghz, 1MB Cache/core
                        ●
                          12 GB RAM, 73 GB SAS Drives 15krpm
                        ●
                          2U Rack Unit, 550PS
                        ●
                          MySQL x 1 instance 8GB buffer pool
Sun Fire x4200 Server   ●
                          Estimated List Price: US$5,888
                        ●
                          8xAMD 8220 Dual Core 2.8Ghz, 1MB Cache/core
                        ●
                          64 GB RAM, 73 GB 15k SAS Drives+External Storage
                        ●
                          4U Rack Unit, 850PS
                        ●
                          MySQL x 4 instances 6GB buffer pool
Sun Fire x4600 Server   ●
                          Estimated List Price: US$29,995
                        ●
                          1T2 8 Cores 64 Threads 1.4Ghz, 4MB Cache
                        ●
                          64 GB RAM, 73 GB 15k SAS Drives+External Storage
                        ●
                          2U Rack Unit, 750PS
                        ●
                          MySQL x 6 instances 6GB buffer pool
Sun Fire T5220 Server   ●
                          Estimated List Price: US$32,115               15
The Database
MySQL Enterprise Solution
Enterprise software and services delivered in an annual subscription
                     ●
                         The most up-to-date MySQL Enterprise
                         software
 Database            ●
                         Monthly rapid updates
                     ●
                         Quarterly service packs
                     ●
                         Hot-fix program • Subscription:
                     ●
                         Indemnification     • MySQL Enterprise
                                         • License (OEM):
                                              • Embedded Server
                     ●
                         Virtual database assistant
                                              • Support
                     ●
                         Global monitoring of all servers
                                          • MySQL Cluster Carrier-Grade
  Monitoring         ●
                         Web-based central console
                     ●
                                          • Training
                         Built-in advisors, expert advice
                     ●                    • Consulting
                         Problem query detection/analysis
                                         • NRE
                     ●
                         Online self-help MySQL Knowledge Base
                     ●
                         24/7 problem resolution with priority
 Support                 escalation
                     ●
                         Consultative help
                     ●
                         High-Availability and Scale-Out
                                                                          16
Test Results: Single Instance


                                Sun Fire x4200




                                             17
Test Results: Single Instance



                                 Sun Fire x4600




                                Sun Fire T5220




                                           18
Test Results: Four Instances



                          Sun Fire x4600




                                           19
Test Results: Six Instances

                              Sun Fire T5220




                                          20
Agenda

Scaling Concepts and
Approaches
Recommendations When/How to Scale
Scaling Test Results
Sun Systems for MySQL
Learn more

                                    21
The application life-cycle
The takeaway for how and when to scale

                  Start-up
                  ●
                    Single instance
                  ●
                    Small box or full virtualization   Sun Fire x4200



                  Digital Entrepreneur
                                                        Sun Fire x4200
                  ●
                    Multiple instances
                  ●
                    Virtualized, consolidated
                    environment
                                                       Sun Fire x4600


                  Enterprise
                  ●
                    Multiple instances
                  ●
                    Virtualized, consolidated          Sun FireT5220
                    environment                                     22
What Can Sun Systems for MySQL
Do for Your Web Deployments
          ●
            Linux, OpenSolaris, Solaris and Windows; Intel,
            AMD and SPARC
          ●
            Up to 3x more transactions, 3x less power &
            space,10x price/performance
          ● Open Storage delivers 2x better storage density,

            2x better price/performance,10x the capacity
          ● Deliver competitive advantage with fast I/O, large

            memory, optimized Web Stack, system design
            innovations, SSDs, open source virtualization
          ● Reduce power, space, cooling costs


          ● Get to market faster with new Web services

          ● Scalability to support millions of users


          ● Free 60 day Try & Buy of systems plus MySQL

            Enterprise, get up to 40% off to keep
                                                          23
World Record Performance
                                             Best19% Faster than the Dell PE R900
                                                  x86 single Java Virtual Machine
                                                          SPEC® JBB2005
                                          performance on SPEC®jbb2005 benchmark




                                                              Sun Fire X4450 Server
         • Solaris 10 10/08 Operating system
         • Java HotSpot™software version 1.6.0_06 Performance Release

                    Targeted at enterprise customers looking for exceptional business
                     process performance in a dense 2RU, 24-processor core platform


 Source: SPEC and SPECjbb are registered trademarks of the Standard Performance Evaluation Corporation. Competitive benchmark results reflect data published as of 9/12/08. For the latest results, visit http://www.spec.org.Sun Fire X4450
                                                                                                                                                                                                                                        24
 (Intel Xeon X7460, 24 cores, 4 chips, 6 cores/chip, Solaris 10): 448,262 SPECjbb2005 bops, 448,262 SPECjbb2005 bops/JVM.
Half the Space!



    X4450             DL580 G5          PE R900              X3850 M2




            Reduced Operating Costs for the Eco Enterprise
                                                                        25
Sun™ Blade Servers: Superior
 Flexibility and Efficiency
 Modular architecture delivers flexibility and efficiencies
• Aggregation of
  multiple servers
                                                          Power
• Common power,
  cooling, and I/O
  improves efficiency                                     Compute
  and reliability
• Modular hot-swappable                                   Storage
                                  Modular
  form factor improves
  serviceability                  computing               Cooling

                                                          I/O

                                                          Management
                                                                       26
●
                    DTrace: safe, comprehensive
                    observability
                  ●
                    Predictive Self Healing for
                    reliability
                  ●
                    ZFS: innovative approach to data
                    Mgmt, scalability, integrity and
                    performance
                  ●
                    Record setting performance
                  ●
                    Built-in virtualization
                  ●
                    Over 1000 x86 and SPARC
                    systems supported
                  ●
                    180+ open source applications


Fast and Open; Optimized for the Web
                                               27
Professional Network Site Increases
Performance by 54% on MySQL
Business Issues
• Fast growth was causing reduced
  MySQL database response times
• Needed scale and manageability for
  exponential growth
Sun Solution                             “By using Sun products and Sun
• Sun & MySQL Enterprise Platinum,
                                           Professional Services for our
  Professional Services                 solution, we can scale horizontally,
• Sun Servers & Solaris                 and we can scale vertically. And we
                                         don't have to change one line of
Business Results                        our software code to run dual-core,
• 54% improvement in query                  quad-core, or sixteen-core
  performance                           machines – or any other hardware
• 39% reduction in database footprint          that Sun provides. ”
• Scalable, manageable infrastructure             ― Jean-Luc Vaillant, CTO, LinkedIn
  for further growth                                              sun.com/customers
                                                                                28
Sun Systems for MySQL Virtualization
Reduce Environmental Costs, Virtualize & Scale for Maximum Eco-Efficiency

                                       ●
                                         10x prove price/performance, 3x
                                         more throughput, 83% less power
                                       ●
                                         Fast, free, open hypervisor, low
                                         cost storage arrays
                                       ●
                                         Breakthrough throughput, eco-
                                         efficiency and reliability
                                       ●
                                         Consolidate up to 128 virtual
                                         MySQL servers in 1U/blade format
                                       ●
                                         Scale MySQL with TomCat, Apache,
                                         Lighttpd, SugarCRM, Drupal, others
                                       ●
                                         Try risk, cost, hassle free, get up to
                                         40% off to convert Try & Buy
        T5220               T6320


    Scaling Sky-high for MySQL Virtualization
                                                                          29
Virtualization with LDoms
                                              Tomcat running JPetStore, MySQL Backend
                                            9000



            Transactions per Second (TPS)   8000


                                            7000


                                            6000


                                            5000


                                            4000


                                            3000


                                            2000


                                            1000


                                              0
                                                   1   2      4       6       8        10   12

                                                           Number of Logical Domains



• LDoms & CoolThreads improve scalability and utilization
• Blueprint demonstrating how LDoms enabled a TomCat / MySQL
  service to scale 10x when compared to a single application instance.

• http://wikis.sun.com/download/attachments/24543563/820-4995.pdf                                30
Messaging Services Innovator Gets
10X Better MySQL Price/Performance
 Business Issues
 •Deliver highly scalable advanced
 messaging services
 •Process messages faster and at reduced
 cost, operate more efficiently
 Sun Solution                               “We are a company that believes
 •Sun & MySQL Enterprise Platinum,           in empowering our customers,
 Professional Services                     and that power for us comes from
 •Sun Servers & Solaris                      Sun. With Sun technology, the
                                             only limitation on what we can
 Business Results                            deliver is our ability to dream. If
 •4.5x higher performance, 2x headroom      we can dream it, we can do it ”
 •4x less, 83% less power use                         ― Jason Williams, CTO at DigiTar
 •Storage admin from weeks to hours                          www.sun.com/customers
 •10x better $/performance for MySQL
 infrastructure
                                                                                   31
Sun Systems MySQL Rich Media Storage
Gain Control of Exploding Storage Costs for Rich Media
                                         ●
                                           2x cost/performance over closest
                                           competitive offering
                                         ●
                                           Industry's highest data throughput
                                         ●
                                           15% less than HP with 2x density,
                                           10% less Dell at nearly 3x density
                                         ●
                                           Up to 70% less power, cooling
       J7000                             ●
                                           Reduces common admin tasks by
                                           as much as 82%
       J4200             x4540           ●
                                           Ideal for rapid Rich Media growth:
                                           photo, video, audio
                                         ●
                                           Try risk, cost and hassle free, get
                                           20% off to convert Try & Buy

    Store Rich Media Without Paying the Price
                                                                          32
Tune and Scale MySQL: Providing
 Unprecedented Storage Analytics
• Automatic real-time visualization of
  application and storage related workloads
• Solve performance issues through
  understanding data usage
• Simple, sophisticated instrumentation
  with real-time comprehensive analysis
• Supports multiple simultaneous
  application
  and workload analysis in real- time
• Analysis can be saved, exported and
  replayed for further analysis.
• Built on DTrace instrumentation
                                              33
ZFS Hybrid Storage Pool
Sun X4250 Storage Server Example


      Configuration A                        Configuration B
                    ●
                        4 Xeon 7350 Processors
                    ●
                        32GB FB DDR2 ECC DRAM
                    ●
                        OpenSolaris with ZFS                (1) 80G SSD Cache
                                                               Device


                                                      (1) 32G SSD ZIL
                                                          Device




          (7) 146GB 10,000 RPM SAS Drives        (5) 400GB 4200 RPM SATA Drives
                                                                                  34
ZFS Hybrid Pool Example
Based on Actual Benchmark Results
                                                            4.9x
   3.2x                            4%



                                                                        2x

                  11%




   Read IOPs       Write IOPs        Cost           Storage Power      Raw Capacity
                                                        (Watts)           (TB)



           Hybrid Storage Pool (DRAM + Read SSD + Write SSD + 5x 4200 RPM SATA)
           Traditional Storage Pool (DRAM + 7x 10K RPM 2.5”)




                                                                                      35
MySQL Unlimited
• Fixed annual subscription            MySQL
 > Unlimited servers                  Enterprise
 > Unlimited CPUs                     Unlimited
 > Unlimited cores

• Simplify
 > No counting
 > No compliance issues

• Pricing
 > No proprietary DBMS license fees
 > Price starts at $40K/year

                                                   36
Agenda

Scaling Concepts and
Approaches
Recommendations When/How to Scale
Scaling Test Results
Sun Systems for MySQL
Learn more

                                    37
Start Scaling Your MySQL With
Sun Systems for MySQL



        Learn More                       Try it Yourself
                              • Try a Sun system free for 60 days with
 • Download MySQL TCO White     MySQL Enterprise
   paper                      • Kick the tires. Check under the hood.
 • Download “Scaling Beyond     Test it. Stress it.
   x86: Using LDOMS”          • Get up to 40% to convert Try & Buy to
                                purchase
                              • Buy it or return it and pay nothing – not
                                even shipping



   sun.com/mysqlsystems               sun.com/tryandbuy                     38
Performance Tuning - Benchmarks - Cloud Computing
Data Warehousing - Business Intelligence - Replication
        Scale-Out - Java, PHP, .NET, Ruby & AJAX
 High Availability - MySQL Cluster - And much more…



    Early Registration Now Open!
https://en.oreilly.com/mysql2009/public/register/        39
GET MORE FROM YOUR WEB SERVICE

Scaling MySQL By
Leveraging Sun Systems
Learn More:
http://www.sun.com/mysqlsystems
Steve Staso
Sun Microsystems




                                  40

More Related Content

What's hot

Solaris 8 containers and solaris 9 containers customer presentation
Solaris 8 containers and solaris 9 containers customer presentationSolaris 8 containers and solaris 9 containers customer presentation
Solaris 8 containers and solaris 9 containers customer presentation
xKinAnx
 
TechNet Live spor 1 sesjon 6 - more vdi
TechNet Live spor 1   sesjon 6 - more vdiTechNet Live spor 1   sesjon 6 - more vdi
TechNet Live spor 1 sesjon 6 - more vdi
Anders Borchsenius
 
virtualization tutorial at ACM bangalore Compute 2009
virtualization tutorial at ACM bangalore Compute 2009virtualization tutorial at ACM bangalore Compute 2009
virtualization tutorial at ACM bangalore Compute 2009
ACMBangalore
 
Windows Server 2012 - Dynamische opslag met Storage Pools
Windows Server 2012 - Dynamische opslag met Storage PoolsWindows Server 2012 - Dynamische opslag met Storage Pools
Windows Server 2012 - Dynamische opslag met Storage Pools
CompuTrain. De IT opleider.
 
Private cloud virtual reality to reality a partner story daniel mar_technicom
Private cloud virtual reality to reality a partner story daniel mar_technicomPrivate cloud virtual reality to reality a partner story daniel mar_technicom
Private cloud virtual reality to reality a partner story daniel mar_technicom
Microsoft Singapore
 
Advanced performance troubleshooting using esxtop
Advanced performance troubleshooting using esxtopAdvanced performance troubleshooting using esxtop
Advanced performance troubleshooting using esxtop
Alan Renouf
 
Architecting a Private Cloud - Cloud Expo
Architecting a Private Cloud - Cloud ExpoArchitecting a Private Cloud - Cloud Expo
Architecting a Private Cloud - Cloud Expo
smw355
 
Building Business Continuity Solutions With Hyper V
Building Business Continuity Solutions With Hyper VBuilding Business Continuity Solutions With Hyper V
Building Business Continuity Solutions With Hyper V
rsnarayanan
 
ttec infortrend ds
ttec infortrend dsttec infortrend ds
ttec infortrend ds
TTEC
 
Solaris 10 virtualization presentation
Solaris 10 virtualization presentationSolaris 10 virtualization presentation
Solaris 10 virtualization presentation
xKinAnx
 
SANsymphony V
SANsymphony VSANsymphony V
SANsymphony V
TTEC
 
HDFS - What's New and Future
HDFS - What's New and FutureHDFS - What's New and Future
HDFS - What's New and Future
DataWorks Summit
 
Cvc2009 Moscow Xd3 Fabian Kienle Final
Cvc2009 Moscow Xd3  Fabian Kienle FinalCvc2009 Moscow Xd3  Fabian Kienle Final
Cvc2009 Moscow Xd3 Fabian Kienle Final
Liudmila Li
 
Tivoli Storage Productivity Center... What’s new in v4.2.2?
Tivoli Storage Productivity Center... What’s new in v4.2.2?Tivoli Storage Productivity Center... What’s new in v4.2.2?
Tivoli Storage Productivity Center... What’s new in v4.2.2?
IBM India Smarter Computing
 
15 stephan pfister citrix day hdx-multimedia
15 stephan pfister citrix day   hdx-multimedia15 stephan pfister citrix day   hdx-multimedia
15 stephan pfister citrix day hdx-multimedia
Digicomp Academy AG
 
Branch repeater technical training presentation 26 oct-12
Branch repeater technical training presentation 26 oct-12Branch repeater technical training presentation 26 oct-12
Branch repeater technical training presentation 26 oct-12
Nuno Alves
 
Scvmm 2012 (maarten wijsman)
Scvmm 2012 (maarten wijsman)Scvmm 2012 (maarten wijsman)
Scvmm 2012 (maarten wijsman)
hypervnu
 
Sql server 2012 ha and dr sql saturday dc
Sql server 2012 ha and dr sql saturday dcSql server 2012 ha and dr sql saturday dc
Sql server 2012 ha and dr sql saturday dc
Joseph D'Antoni
 
IBM SmartCloud Enterprise - A Secure Infrastructure for Test and Development
IBM SmartCloud Enterprise - A Secure Infrastructure for Test and DevelopmentIBM SmartCloud Enterprise - A Secure Infrastructure for Test and Development
IBM SmartCloud Enterprise - A Secure Infrastructure for Test and Development
Piotr Pietrzak
 
9sept2009 concept electronics
9sept2009 concept electronics9sept2009 concept electronics
9sept2009 concept electronics
Agora Group
 

What's hot (20)

Solaris 8 containers and solaris 9 containers customer presentation
Solaris 8 containers and solaris 9 containers customer presentationSolaris 8 containers and solaris 9 containers customer presentation
Solaris 8 containers and solaris 9 containers customer presentation
 
TechNet Live spor 1 sesjon 6 - more vdi
TechNet Live spor 1   sesjon 6 - more vdiTechNet Live spor 1   sesjon 6 - more vdi
TechNet Live spor 1 sesjon 6 - more vdi
 
virtualization tutorial at ACM bangalore Compute 2009
virtualization tutorial at ACM bangalore Compute 2009virtualization tutorial at ACM bangalore Compute 2009
virtualization tutorial at ACM bangalore Compute 2009
 
Windows Server 2012 - Dynamische opslag met Storage Pools
Windows Server 2012 - Dynamische opslag met Storage PoolsWindows Server 2012 - Dynamische opslag met Storage Pools
Windows Server 2012 - Dynamische opslag met Storage Pools
 
Private cloud virtual reality to reality a partner story daniel mar_technicom
Private cloud virtual reality to reality a partner story daniel mar_technicomPrivate cloud virtual reality to reality a partner story daniel mar_technicom
Private cloud virtual reality to reality a partner story daniel mar_technicom
 
Advanced performance troubleshooting using esxtop
Advanced performance troubleshooting using esxtopAdvanced performance troubleshooting using esxtop
Advanced performance troubleshooting using esxtop
 
Architecting a Private Cloud - Cloud Expo
Architecting a Private Cloud - Cloud ExpoArchitecting a Private Cloud - Cloud Expo
Architecting a Private Cloud - Cloud Expo
 
Building Business Continuity Solutions With Hyper V
Building Business Continuity Solutions With Hyper VBuilding Business Continuity Solutions With Hyper V
Building Business Continuity Solutions With Hyper V
 
ttec infortrend ds
ttec infortrend dsttec infortrend ds
ttec infortrend ds
 
Solaris 10 virtualization presentation
Solaris 10 virtualization presentationSolaris 10 virtualization presentation
Solaris 10 virtualization presentation
 
SANsymphony V
SANsymphony VSANsymphony V
SANsymphony V
 
HDFS - What's New and Future
HDFS - What's New and FutureHDFS - What's New and Future
HDFS - What's New and Future
 
Cvc2009 Moscow Xd3 Fabian Kienle Final
Cvc2009 Moscow Xd3  Fabian Kienle FinalCvc2009 Moscow Xd3  Fabian Kienle Final
Cvc2009 Moscow Xd3 Fabian Kienle Final
 
Tivoli Storage Productivity Center... What’s new in v4.2.2?
Tivoli Storage Productivity Center... What’s new in v4.2.2?Tivoli Storage Productivity Center... What’s new in v4.2.2?
Tivoli Storage Productivity Center... What’s new in v4.2.2?
 
15 stephan pfister citrix day hdx-multimedia
15 stephan pfister citrix day   hdx-multimedia15 stephan pfister citrix day   hdx-multimedia
15 stephan pfister citrix day hdx-multimedia
 
Branch repeater technical training presentation 26 oct-12
Branch repeater technical training presentation 26 oct-12Branch repeater technical training presentation 26 oct-12
Branch repeater technical training presentation 26 oct-12
 
Scvmm 2012 (maarten wijsman)
Scvmm 2012 (maarten wijsman)Scvmm 2012 (maarten wijsman)
Scvmm 2012 (maarten wijsman)
 
Sql server 2012 ha and dr sql saturday dc
Sql server 2012 ha and dr sql saturday dcSql server 2012 ha and dr sql saturday dc
Sql server 2012 ha and dr sql saturday dc
 
IBM SmartCloud Enterprise - A Secure Infrastructure for Test and Development
IBM SmartCloud Enterprise - A Secure Infrastructure for Test and DevelopmentIBM SmartCloud Enterprise - A Secure Infrastructure for Test and Development
IBM SmartCloud Enterprise - A Secure Infrastructure for Test and Development
 
9sept2009 concept electronics
9sept2009 concept electronics9sept2009 concept electronics
9sept2009 concept electronics
 

Similar to Scaling With Sun Systems For MySQL Jan09

Top 6 Reasons to Use a Distributed Data Grid
Top 6 Reasons to Use a Distributed Data GridTop 6 Reasons to Use a Distributed Data Grid
Top 6 Reasons to Use a Distributed Data Grid
ScaleOut Software
 
Varrow Q4 Lunch & Learn Presentation - Virtualizing Business Critical Applica...
Varrow Q4 Lunch & Learn Presentation - Virtualizing Business Critical Applica...Varrow Q4 Lunch & Learn Presentation - Virtualizing Business Critical Applica...
Varrow Q4 Lunch & Learn Presentation - Virtualizing Business Critical Applica...
Andrew Miller
 
Hadoop World 2011: Hadoop as a Service in Cloud
Hadoop World 2011: Hadoop as a Service in CloudHadoop World 2011: Hadoop as a Service in Cloud
Hadoop World 2011: Hadoop as a Service in Cloud
Cloudera, Inc.
 
What's New in RHEL 6 for Linux on System z?
What's New in RHEL 6 for Linux on System z?What's New in RHEL 6 for Linux on System z?
What's New in RHEL 6 for Linux on System z?
IBM India Smarter Computing
 
Private cloud server virtualization
Private cloud server virtualization Private cloud server virtualization
Private cloud server virtualization
Pierre-Juan Labeyrie
 
Virtualizing Tier One Applications - Varrow
Virtualizing Tier One Applications - VarrowVirtualizing Tier One Applications - Varrow
Virtualizing Tier One Applications - Varrow
Andrew Miller
 
VMware End-User-Computing Best Practices Poster
VMware End-User-Computing Best Practices PosterVMware End-User-Computing Best Practices Poster
VMware End-User-Computing Best Practices Poster
VMware Academy
 
Couchbase Performance Benchmarking
Couchbase Performance BenchmarkingCouchbase Performance Benchmarking
Couchbase Performance Benchmarking
Renat Khasanshyn
 
Couchbase Performance Benchmarking 2012
Couchbase Performance Benchmarking 2012Couchbase Performance Benchmarking 2012
Couchbase Performance Benchmarking 2012
Altoros
 
Virtualization
VirtualizationVirtualization
Virtualization
Birju Tank
 
Hadoop on VMware
Hadoop on VMwareHadoop on VMware
Hadoop on VMware
Richard McDougall
 
Is your cloud ready for Big Data? Strata NY 2013
Is your cloud ready for Big Data? Strata NY 2013Is your cloud ready for Big Data? Strata NY 2013
Is your cloud ready for Big Data? Strata NY 2013
Richard McDougall
 
Presentation architecting a cloud infrastructure
Presentation   architecting a cloud infrastructurePresentation   architecting a cloud infrastructure
Presentation architecting a cloud infrastructure
solarisyourep
 
Presentation architecting a cloud infrastructure
Presentation   architecting a cloud infrastructurePresentation   architecting a cloud infrastructure
Presentation architecting a cloud infrastructure
xKinAnx
 
VMWARE VS MS-HYPER-V
VMWARE VS MS-HYPER-VVMWARE VS MS-HYPER-V
VMWARE VS MS-HYPER-V
David Ramirez
 
Understanding Database Options
Understanding Database OptionsUnderstanding Database Options
Understanding Database Options
Amazon Web Services
 
Tokyo azure meetup #12 service fabric internals
Tokyo azure meetup #12   service fabric internalsTokyo azure meetup #12   service fabric internals
Tokyo azure meetup #12 service fabric internals
Tokyo Azure Meetup
 
Enterprise Journey to the Cloud
Enterprise Journey to the CloudEnterprise Journey to the Cloud
Enterprise Journey to the Cloud
Amazon Web Services
 
End of RAID as we know it with Ceph Replication
End of RAID as we know it with Ceph ReplicationEnd of RAID as we know it with Ceph Replication
End of RAID as we know it with Ceph Replication
Ceph Community
 
Updates to Apache CloudStack and LINBIT SDS
Updates to Apache CloudStack and LINBIT SDSUpdates to Apache CloudStack and LINBIT SDS
Updates to Apache CloudStack and LINBIT SDS
ShapeBlue
 

Similar to Scaling With Sun Systems For MySQL Jan09 (20)

Top 6 Reasons to Use a Distributed Data Grid
Top 6 Reasons to Use a Distributed Data GridTop 6 Reasons to Use a Distributed Data Grid
Top 6 Reasons to Use a Distributed Data Grid
 
Varrow Q4 Lunch & Learn Presentation - Virtualizing Business Critical Applica...
Varrow Q4 Lunch & Learn Presentation - Virtualizing Business Critical Applica...Varrow Q4 Lunch & Learn Presentation - Virtualizing Business Critical Applica...
Varrow Q4 Lunch & Learn Presentation - Virtualizing Business Critical Applica...
 
Hadoop World 2011: Hadoop as a Service in Cloud
Hadoop World 2011: Hadoop as a Service in CloudHadoop World 2011: Hadoop as a Service in Cloud
Hadoop World 2011: Hadoop as a Service in Cloud
 
What's New in RHEL 6 for Linux on System z?
What's New in RHEL 6 for Linux on System z?What's New in RHEL 6 for Linux on System z?
What's New in RHEL 6 for Linux on System z?
 
Private cloud server virtualization
Private cloud server virtualization Private cloud server virtualization
Private cloud server virtualization
 
Virtualizing Tier One Applications - Varrow
Virtualizing Tier One Applications - VarrowVirtualizing Tier One Applications - Varrow
Virtualizing Tier One Applications - Varrow
 
VMware End-User-Computing Best Practices Poster
VMware End-User-Computing Best Practices PosterVMware End-User-Computing Best Practices Poster
VMware End-User-Computing Best Practices Poster
 
Couchbase Performance Benchmarking
Couchbase Performance BenchmarkingCouchbase Performance Benchmarking
Couchbase Performance Benchmarking
 
Couchbase Performance Benchmarking 2012
Couchbase Performance Benchmarking 2012Couchbase Performance Benchmarking 2012
Couchbase Performance Benchmarking 2012
 
Virtualization
VirtualizationVirtualization
Virtualization
 
Hadoop on VMware
Hadoop on VMwareHadoop on VMware
Hadoop on VMware
 
Is your cloud ready for Big Data? Strata NY 2013
Is your cloud ready for Big Data? Strata NY 2013Is your cloud ready for Big Data? Strata NY 2013
Is your cloud ready for Big Data? Strata NY 2013
 
Presentation architecting a cloud infrastructure
Presentation   architecting a cloud infrastructurePresentation   architecting a cloud infrastructure
Presentation architecting a cloud infrastructure
 
Presentation architecting a cloud infrastructure
Presentation   architecting a cloud infrastructurePresentation   architecting a cloud infrastructure
Presentation architecting a cloud infrastructure
 
VMWARE VS MS-HYPER-V
VMWARE VS MS-HYPER-VVMWARE VS MS-HYPER-V
VMWARE VS MS-HYPER-V
 
Understanding Database Options
Understanding Database OptionsUnderstanding Database Options
Understanding Database Options
 
Tokyo azure meetup #12 service fabric internals
Tokyo azure meetup #12   service fabric internalsTokyo azure meetup #12   service fabric internals
Tokyo azure meetup #12 service fabric internals
 
Enterprise Journey to the Cloud
Enterprise Journey to the CloudEnterprise Journey to the Cloud
Enterprise Journey to the Cloud
 
End of RAID as we know it with Ceph Replication
End of RAID as we know it with Ceph ReplicationEnd of RAID as we know it with Ceph Replication
End of RAID as we know it with Ceph Replication
 
Updates to Apache CloudStack and LINBIT SDS
Updates to Apache CloudStack and LINBIT SDSUpdates to Apache CloudStack and LINBIT SDS
Updates to Apache CloudStack and LINBIT SDS
 

Recently uploaded

Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
Jason Packer
 
Choosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptxChoosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptx
Brandon Minnick, MBA
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
Chart Kalyan
 
Presentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of GermanyPresentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of Germany
innovationoecd
 
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdfMonitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Tosin Akinosho
 
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean lotus Threat actors project by John Sitima 2024 (1).pptxOcean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
SitimaJohn
 
Building Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and MilvusBuilding Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and Milvus
Zilliz
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
MichaelKnudsen27
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
名前 です男
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
panagenda
 
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing InstancesEnergy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Alpen-Adria-Universität
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
Tomaz Bratanic
 
Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)
Jakub Marek
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Malak Abu Hammad
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
DanBrown980551
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
Zilliz
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
Ivanti
 
Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
Tatiana Kojar
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
panagenda
 

Recently uploaded (20)

Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
 
Choosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptxChoosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptx
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
 
Presentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of GermanyPresentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of Germany
 
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdfMonitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdf
 
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean lotus Threat actors project by John Sitima 2024 (1).pptxOcean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
 
Building Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and MilvusBuilding Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and Milvus
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
 
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing InstancesEnergy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
 
Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
 
Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
 

Scaling With Sun Systems For MySQL Jan09

  • 1. GET MORE FROM YOUR WEB SERVICE Scaling MySQL By Leveraging Sun Systems Steve Staso Chief Architect, Web Infrastructure Solutions Global Systems Practice 1
  • 2. Agenda Scaling Concepts and Approaches Recommendations When/How to Scale Scaling Test Results Sun Systems for MySQL Learn more 2
  • 3. Dramatically Change Economics of Web Service Delivery Drive better performance, value ● Get greater performance ● Improve price performance, reduce costs ● Operating System, processor choice Simplify Deployments ● Leverage best practices, Blue Prints, reference architectures, subscriptions, systems, software, management expertise Scale for explosive Growth ● Scale to +1M concurrent users ● Choose best deployment technologies ● Predict performance under stress 3
  • 4. Agenda Scaling Concepts and Approaches Recommendations When/How to Scale Scaling Test Results Sun Systems for MySQL Learn more 4
  • 5. How to Scale? Network • Distribute the connections over multiple servers Load • Increase the number of NICs and networks • More CPUs help up to optimal thread count, more than that is useless CPU • Scale-out can impact app server Load activity, scalability can be difficult • Reduce the logic in the DB server • More memory is always good RAM/ • A scale-out can increase the complexity of the environment Caching • External distributed caching • Faster disks and controllers always I/O help Load • Scale-out is the best option after an initial optimization at server level Storage • SAN and NAS for large data centers Requirement • Scale-out is often cost effective 5
  • 6. Choose the Right Server Architecture Server Scale-up vs. Scale-out for Database Deployments Scaling Up Scaling Out 6
  • 7. Choose the Right Server Architecture Server Scale-up vs. Scale-out for Database Deployments Scaling Up Scaling Out 7
  • 8. Choose the Right Server Architecture Server Scale-up vs. Scale-out for Database Deployments Scaling Up g alin l Sc ona Diag Scaling Out 8
  • 9. Virtualize Methods, benefits, recommendations Memory latency Compute Build Next Generation Virtual Datacenter Increase utilization, less heat and energy usage Up to 10 x better price/performance 9
  • 10. Implementations of Virtualization Type I Type I Type II App App App App App App App App App App App App App App App App App App App App App App App App App App App App App App OS OS OS OS OS OS Zone OS OS LD LD Zone VM VM VM VM Hypervisor Hypervisor Zone Support OS Software Hypervisor Hardware Hardware Virtualization Enablement Layer Hardware OS Hardware Hardware Hardware Hardware Hardware based Software based Desktop OS Virtualization 10 Partitioning System Virtualization Virtualization
  • 11. Leading Virtualization Choices Different approaches, benefits in virtualizing web stack (future plans) Hyper-V BSD opensolaris™ opensolaris™ Sun xVM LDOMS 11
  • 12. Server/OS Virtualization Sun Server Virtualization = Decreased Costs, Reduced Complexity CoolThreads Servers x64/x86 Servers • Integrated, open source, no cost, and • Most powerful, scalable, virtualized flexible virtualization technology – designs, operating on today’s range of Logical Domains (LDoms) OS options • Record-breaking performance • Choice of hypervisor and OS allows for • Breakthrough energy and space investment protection efficiency • Available in racks or blades • Available in racks or blades LDOMS 12
  • 13. Agenda Scaling Concepts and Approaches Recommendations When/How to Scale Scaling Test Results Sun Systems for MySQL Learn more 13
  • 14. The Benchmark ● Red Hat Ent Linux 5.1 64 bit MySQL testbed ● Solaris 10 x86_64 and SPARC 64 mysql 5.1.26 rc 64 bit environment ● ● mysql coolstack 1.3.1 (based on 5.1.26) 64 bit ● 100 warehouses created with the datagen utility DBT2 ● 15 GB of data generated for each DB Extra table used to set random conditions datagen ● ● Extra tables added for transaction count SP calls to: DBT2 ● Delivery ● Order Status Stock Level New Order Stored Procedures ● ● ● Payment ● 100 calls: DBT2 call set with ● 4 Delivery ● 4 Order Status 4 Stock Level random IDs 45 New Order ● ● ● 43 Payment ● + internal SP calls ● Shoot-out with: ● 512k complex transactions ● 1,2,4,8,16,32,64,128,256 concurrent connections ● 51,200 per iteration mysqlslap ● 10 iterations ● 250M single queries ● Warm-up (cold) and hot phases ● high peak of 40k qps with “s” 14
  • 15. The Systems For MySQL Scaling ● 2xAMD 2220 Dual Core 2.8Ghz, 1MB Cache/core ● 12 GB RAM, 73 GB SAS Drives 15krpm ● 2U Rack Unit, 550PS ● MySQL x 1 instance 8GB buffer pool Sun Fire x4200 Server ● Estimated List Price: US$5,888 ● 8xAMD 8220 Dual Core 2.8Ghz, 1MB Cache/core ● 64 GB RAM, 73 GB 15k SAS Drives+External Storage ● 4U Rack Unit, 850PS ● MySQL x 4 instances 6GB buffer pool Sun Fire x4600 Server ● Estimated List Price: US$29,995 ● 1T2 8 Cores 64 Threads 1.4Ghz, 4MB Cache ● 64 GB RAM, 73 GB 15k SAS Drives+External Storage ● 2U Rack Unit, 750PS ● MySQL x 6 instances 6GB buffer pool Sun Fire T5220 Server ● Estimated List Price: US$32,115 15
  • 16. The Database MySQL Enterprise Solution Enterprise software and services delivered in an annual subscription ● The most up-to-date MySQL Enterprise software Database ● Monthly rapid updates ● Quarterly service packs ● Hot-fix program • Subscription: ● Indemnification • MySQL Enterprise • License (OEM): • Embedded Server ● Virtual database assistant • Support ● Global monitoring of all servers • MySQL Cluster Carrier-Grade Monitoring ● Web-based central console ● • Training Built-in advisors, expert advice ● • Consulting Problem query detection/analysis • NRE ● Online self-help MySQL Knowledge Base ● 24/7 problem resolution with priority Support escalation ● Consultative help ● High-Availability and Scale-Out 16
  • 17. Test Results: Single Instance Sun Fire x4200 17
  • 18. Test Results: Single Instance Sun Fire x4600 Sun Fire T5220 18
  • 19. Test Results: Four Instances Sun Fire x4600 19
  • 20. Test Results: Six Instances Sun Fire T5220 20
  • 21. Agenda Scaling Concepts and Approaches Recommendations When/How to Scale Scaling Test Results Sun Systems for MySQL Learn more 21
  • 22. The application life-cycle The takeaway for how and when to scale Start-up ● Single instance ● Small box or full virtualization Sun Fire x4200 Digital Entrepreneur Sun Fire x4200 ● Multiple instances ● Virtualized, consolidated environment Sun Fire x4600 Enterprise ● Multiple instances ● Virtualized, consolidated Sun FireT5220 environment 22
  • 23. What Can Sun Systems for MySQL Do for Your Web Deployments ● Linux, OpenSolaris, Solaris and Windows; Intel, AMD and SPARC ● Up to 3x more transactions, 3x less power & space,10x price/performance ● Open Storage delivers 2x better storage density, 2x better price/performance,10x the capacity ● Deliver competitive advantage with fast I/O, large memory, optimized Web Stack, system design innovations, SSDs, open source virtualization ● Reduce power, space, cooling costs ● Get to market faster with new Web services ● Scalability to support millions of users ● Free 60 day Try & Buy of systems plus MySQL Enterprise, get up to 40% off to keep 23
  • 24. World Record Performance Best19% Faster than the Dell PE R900 x86 single Java Virtual Machine SPEC® JBB2005 performance on SPEC®jbb2005 benchmark Sun Fire X4450 Server • Solaris 10 10/08 Operating system • Java HotSpot™software version 1.6.0_06 Performance Release Targeted at enterprise customers looking for exceptional business process performance in a dense 2RU, 24-processor core platform Source: SPEC and SPECjbb are registered trademarks of the Standard Performance Evaluation Corporation. Competitive benchmark results reflect data published as of 9/12/08. For the latest results, visit http://www.spec.org.Sun Fire X4450 24 (Intel Xeon X7460, 24 cores, 4 chips, 6 cores/chip, Solaris 10): 448,262 SPECjbb2005 bops, 448,262 SPECjbb2005 bops/JVM.
  • 25. Half the Space! X4450 DL580 G5 PE R900 X3850 M2 Reduced Operating Costs for the Eco Enterprise 25
  • 26. Sun™ Blade Servers: Superior Flexibility and Efficiency Modular architecture delivers flexibility and efficiencies • Aggregation of multiple servers Power • Common power, cooling, and I/O improves efficiency Compute and reliability • Modular hot-swappable Storage Modular form factor improves serviceability computing Cooling I/O Management 26
  • 27. DTrace: safe, comprehensive observability ● Predictive Self Healing for reliability ● ZFS: innovative approach to data Mgmt, scalability, integrity and performance ● Record setting performance ● Built-in virtualization ● Over 1000 x86 and SPARC systems supported ● 180+ open source applications Fast and Open; Optimized for the Web 27
  • 28. Professional Network Site Increases Performance by 54% on MySQL Business Issues • Fast growth was causing reduced MySQL database response times • Needed scale and manageability for exponential growth Sun Solution “By using Sun products and Sun • Sun & MySQL Enterprise Platinum, Professional Services for our Professional Services solution, we can scale horizontally, • Sun Servers & Solaris and we can scale vertically. And we don't have to change one line of Business Results our software code to run dual-core, • 54% improvement in query quad-core, or sixteen-core performance machines – or any other hardware • 39% reduction in database footprint that Sun provides. ” • Scalable, manageable infrastructure ― Jean-Luc Vaillant, CTO, LinkedIn for further growth sun.com/customers 28
  • 29. Sun Systems for MySQL Virtualization Reduce Environmental Costs, Virtualize & Scale for Maximum Eco-Efficiency ● 10x prove price/performance, 3x more throughput, 83% less power ● Fast, free, open hypervisor, low cost storage arrays ● Breakthrough throughput, eco- efficiency and reliability ● Consolidate up to 128 virtual MySQL servers in 1U/blade format ● Scale MySQL with TomCat, Apache, Lighttpd, SugarCRM, Drupal, others ● Try risk, cost, hassle free, get up to 40% off to convert Try & Buy T5220 T6320 Scaling Sky-high for MySQL Virtualization 29
  • 30. Virtualization with LDoms Tomcat running JPetStore, MySQL Backend 9000 Transactions per Second (TPS) 8000 7000 6000 5000 4000 3000 2000 1000 0 1 2 4 6 8 10 12 Number of Logical Domains • LDoms & CoolThreads improve scalability and utilization • Blueprint demonstrating how LDoms enabled a TomCat / MySQL service to scale 10x when compared to a single application instance. • http://wikis.sun.com/download/attachments/24543563/820-4995.pdf 30
  • 31. Messaging Services Innovator Gets 10X Better MySQL Price/Performance Business Issues •Deliver highly scalable advanced messaging services •Process messages faster and at reduced cost, operate more efficiently Sun Solution “We are a company that believes •Sun & MySQL Enterprise Platinum, in empowering our customers, Professional Services and that power for us comes from •Sun Servers & Solaris Sun. With Sun technology, the only limitation on what we can Business Results deliver is our ability to dream. If •4.5x higher performance, 2x headroom we can dream it, we can do it ” •4x less, 83% less power use ― Jason Williams, CTO at DigiTar •Storage admin from weeks to hours www.sun.com/customers •10x better $/performance for MySQL infrastructure 31
  • 32. Sun Systems MySQL Rich Media Storage Gain Control of Exploding Storage Costs for Rich Media ● 2x cost/performance over closest competitive offering ● Industry's highest data throughput ● 15% less than HP with 2x density, 10% less Dell at nearly 3x density ● Up to 70% less power, cooling J7000 ● Reduces common admin tasks by as much as 82% J4200 x4540 ● Ideal for rapid Rich Media growth: photo, video, audio ● Try risk, cost and hassle free, get 20% off to convert Try & Buy Store Rich Media Without Paying the Price 32
  • 33. Tune and Scale MySQL: Providing Unprecedented Storage Analytics • Automatic real-time visualization of application and storage related workloads • Solve performance issues through understanding data usage • Simple, sophisticated instrumentation with real-time comprehensive analysis • Supports multiple simultaneous application and workload analysis in real- time • Analysis can be saved, exported and replayed for further analysis. • Built on DTrace instrumentation 33
  • 34. ZFS Hybrid Storage Pool Sun X4250 Storage Server Example Configuration A Configuration B ● 4 Xeon 7350 Processors ● 32GB FB DDR2 ECC DRAM ● OpenSolaris with ZFS (1) 80G SSD Cache Device (1) 32G SSD ZIL Device (7) 146GB 10,000 RPM SAS Drives (5) 400GB 4200 RPM SATA Drives 34
  • 35. ZFS Hybrid Pool Example Based on Actual Benchmark Results 4.9x 3.2x 4% 2x 11% Read IOPs Write IOPs Cost Storage Power Raw Capacity (Watts) (TB) Hybrid Storage Pool (DRAM + Read SSD + Write SSD + 5x 4200 RPM SATA) Traditional Storage Pool (DRAM + 7x 10K RPM 2.5”) 35
  • 36. MySQL Unlimited • Fixed annual subscription MySQL > Unlimited servers Enterprise > Unlimited CPUs Unlimited > Unlimited cores • Simplify > No counting > No compliance issues • Pricing > No proprietary DBMS license fees > Price starts at $40K/year 36
  • 37. Agenda Scaling Concepts and Approaches Recommendations When/How to Scale Scaling Test Results Sun Systems for MySQL Learn more 37
  • 38. Start Scaling Your MySQL With Sun Systems for MySQL Learn More Try it Yourself • Try a Sun system free for 60 days with • Download MySQL TCO White MySQL Enterprise paper • Kick the tires. Check under the hood. • Download “Scaling Beyond Test it. Stress it. x86: Using LDOMS” • Get up to 40% to convert Try & Buy to purchase • Buy it or return it and pay nothing – not even shipping sun.com/mysqlsystems sun.com/tryandbuy 38
  • 39. Performance Tuning - Benchmarks - Cloud Computing Data Warehousing - Business Intelligence - Replication Scale-Out - Java, PHP, .NET, Ruby & AJAX High Availability - MySQL Cluster - And much more… Early Registration Now Open! https://en.oreilly.com/mysql2009/public/register/ 39
  • 40. GET MORE FROM YOUR WEB SERVICE Scaling MySQL By Leveraging Sun Systems Learn More: http://www.sun.com/mysqlsystems Steve Staso Sun Microsystems 40