Reduccion TCO sistemas Integrados
Upcoming SlideShare
Loading in...5
×
 

Like this? Share it with your network

Share

Reduccion TCO sistemas Integrados

on

  • 1,065 views

 

Statistics

Views

Total Views
1,065
Views on SlideShare
1,064
Embed Views
1

Actions

Likes
0
Downloads
12
Comments
0

1 Embed 1

https://www.linkedin.com 1

Accessibility

Categories

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment
  • It’s not just about rising costs, but where the money goes. All of us are probably familiar with this statistic: 70-80 percent of corporate money budgeted for IT is spent for ongoing operations and maintenance, which doesn’t leave much to invest in innovation.Let’s say that a company spends 5% of revenue on IT, and 80% of that goes toward keeping the lights on, then 4% of revenue is being spent on a commodity that does not improve competitiveness. (Source: InformationWeek)
  • 5X or more is typicalperformance gain for many applications:WebLogic Server applicationsOLTP with Exadata, Oracle DB and/or RACEnterprise Data Grids (Coherence)Mainframe applications (Tuxedo)SOAWebCenterOracle Business ApplicationsAny I/O-intensive application
  • This is clearly a big vision. How are we going to execute? Java PerformanceJava is an essential technology to Oracle and almost all of our customers. There was a real focus on what we could do for Java and there was a lot of opportunity: Java is well known for being sophisticated to tune, and performance was something we could optimizeMission Critical CloudReal end to end standardization, consolidation and ultimately CLOUD – IT as a serviceThis isn’t something that just works for small enterprise applications. The real business value is when it can be deployed across the enterprise, which means you need an infrastructure that can support the most mission critical applicationsEngineered SystemWe focused on the benefits of what can be delivered out of the box while carefully balancing the requirement to not take too much control from customersWe have a long standing commitment to best of breed components, and our business is likely not going to move away from selling those componentsWe focused on the best standalone components that our customers would use to build their own systems and used those same components to build this new engineered system that we can deliver out of the box, pre-integrated and ready to run.These were our goals, and we achieved them! We are very pleased with what we have done accomplished with this product.
  • SimpleComplete, plug-and-go hardware and softwareScaleStart with as few as two cores, and scale all the way to 24 total cores without the usual expense and downtime of a typical hardware upgradeReliableConfigure highly available database cluster in minutesAdvanced management features and single vendor supportAffordablePay for capacity as you need itConsolidate small databases for even more savings
  • The Oracle Database Appliance hardware is a single 4U rackmountable chassis containing two Oracle Linux server nodes, each with two 6-core Intel Xeon processors X5675 and 96 GB of memory. The two server nodes are connected via an internal redundant gigabit Ethernet (GbE) interconnect for cluster communication, and each provides both GbE and 10 GbE external networking connectivity. The appliance contains 12 TB of raw storage that’s triple-mirrored, offering 4 TB of resilient usable database storage. There are also four 73 GB solid-state disks for database redo logs to boost performance. The appliance is designed with mission-critical requirements in mind, with hot-swappable and redundant components.
  • The Oracle Database Appliance runs Oracle Database 11g Enterprise Edition, that stripes and mirrors all the data with Auto Storage ManagementFor high availability and to take advantage of the “cluster in a box” of the Oracle Database Appliance, customers have the choice of running Oracle Real Application Clusters (Oracle RAC) or Oracle RAC One Node for “active-active” or “active-passive” database server failover. Oracle RAC can be part of the initial deployment, or added in the future to extend high availability easily within the same server hardware. This takes advantage or Oracle Clusterware (http://www.oracle.com/technetwork/database/clusterware/overview/index.html) and runs on top of Oracle Linux.The Oracle Database Appliance comes with the extremely easy-to-use Application Manager software, which can automatically notify you and your Oracle Support Team of issues, and even automatically open Service Requests. Application Manager provide significantly more benefits beyond extending reliability and resilience, and I’ll talk more about it in just a moment.
  • Running the appliance does not require specialized clustering or high availability skills. Just plug in the power, plug it into the network, push the one-button install on Application manager software, and you’re ready to go.
  • To help customers easily deploy and manage their databases, the Oracle Database Appliance features Appliance Manager software for one-button automation to provision, patch, and diagnose database servers. The Appliance Manager feature greatly simplifies the deployment process and ensures that database configuration adheres to Oracle’s best practices. It also drastically simplifies maintenance by patching the entire appliance, including all firmware and software, in one operation, using an Oracle-tested patch engineered specifically for the appliance. Its built-in diagnostics also monitor the system and detect component failures, configuration issues, and deviations from best practices. Should it be necessary to contact Oracle Support, Appliance Manager collects all relevant log files and environmental data into a single compressed file. In addition, the Oracle Database Appliance Automatic Service Request feature can automatically log service requests with Oracle Support to help speed resolution of issues.Self-managing database features pre-configured Automatic Storage Management, Automatic Memory Management, …Automatic detection and correction of many failure conditionsFast problem diagnosisAutomated Service Request filing (phone home)Relevant logs gathered and packaged for Oracle supportOne-button patching for entire stackSingle point of contact for all support issues
  • To help customers easily deploy and manage their databases, the Oracle Database Appliance features Appliance Manager software for one-button automation to provision, patch, and diagnose database servers. The Appliance Manager feature greatly simplifies the deployment process and ensures that database configuration adheres to Oracle’s best practices. It also drastically simplifies maintenance by patching the entire appliance, including all firmware and software, in one operation, using an Oracle-tested patch engineered specifically for the appliance. Its built-in diagnostics also monitor the system and detect component failures, configuration issues, and deviations from best practices. Should it be necessary to contact Oracle Support, Appliance Manager collects all relevant log files and environmental data into a single compressed file. In addition, the Oracle Database Appliance Automatic Service Request feature can automatically log service requests with Oracle Support to help speed resolution of issues.Self-managing database features pre-configured Automatic Storage Management, Automatic Memory Management, …Automatic detection and correction of many failure conditionsFast problem diagnosisAutomated Service Request filing (phone home)Relevant logs gathered and packaged for Oracle supportOne-button patching for entire stackSingle point of contact for all support issues
  • The Oracle Database Appliance runs Oracle Database 11g Enterprise Edition, that stripes and mirrors all the data with Auto Storage ManagementFor high availability and to take advantage of the “cluster in a box” of the Oracle Database Appliance, customers have the choice of running Oracle Real Application Clusters (Oracle RAC) or Oracle RAC One Node for “active-active” or “active-passive” database server failover. Oracle RAC can be part of the initial deployment, or added in the future to extend high availability easily within the same server hardware. This takes advantage or Oracle Clusterware (http://www.oracle.com/technetwork/database/clusterware/overview/index.html) and runs on top of Oracle Linux.The Oracle Database Appliance comes with the extremely easy-to-use Application Manager software, which can automatically notify you and your Oracle Support Team of issues, and even automatically open Service Requests. Application Manager provide significantly more benefits beyond extending reliability and resilience, and I’ll talk more about it in just a moment.
  • The Oracle Database Appliance offers customers a unique pay-as-you-grow software licensing model to quickly scale from 2 to 24 processor cores without any hardware upgrades. Customers can deploy the Oracle Database Appliance with as few as 2 processors cores to run their database servers, and incrementally scale up to the maximum of 24 processor cores within the same hardware envelope. This avoids the usual costs and scheduled downtime of a typical hardware upgrade, and enables customers to deliver the performance and high availability that business users demand as they align software spending with business growth.
  • The Oracle Database Appliance is the ideal database platform for SMB and departmental solutions running databases up to 4TB. Whether you are looking to deploy new databases or replace aging systems with faster and more efficient new servers, the Oracle Database Appliance can deliver the high availability many of your applications require today or in the future. And as you look at all of your servers running databases, the Oracle Database Appliance provides you a very affordable platform to migrate and consolidate various databases while improving quality of service.
  • Fastest Data Warehouse & OLTPBest Cost/Performance Data Warehouse & OLTPOptimized Hardware (per rack)Processor: up to128 Intel Cores and 2 TB DRAMNetwork: 880 Gb/Sec ThroughputStorage: 5 TB Flash and up to 336 TB DiskSoftware BreakthroughsExadata Smart Storage GridSmart Flash CacheHybrid Columnar CompressionParallel Scale-Out Database and StorageScales from ¼ Rack to 8 Full Racks
  • 10- 50x performance improvements- The architecture of the Exadata storage cells is that instead of a server asking for a block of data and the block of data coming back to the server, we’re actually constructing queries that are executed in parallel across the different storage devices. Flash memory in the storage device caches the intermediate results, as well as do advanced compression and allow you to run queries and do data warehousing against compressed and encrypted data. This further demonstrates the value of integrated hardware and software. It’s not possible for a conventional storage system to equal this. And so there is no possible way from any other vendor that you can run Oracle Database 11g faster than it runs on Exadata or on SuperCluster by virtue of the fact that we have an architecturally different coupling between the database and the storage. This result of engineering the hardware and software together between the database and storage is very fundamental because that’s what gives us the IO capability and performance of SuperCluster, as well as Exadata.
  • The resulting impact of Oracle Engineered Systems is truly enormous. Performance gains of over 10x are very common for applications running unmodified on engineered systems, and the overall increase in price performance and total cost of ownership are often 10x previous generations of best of breed solutions or versus the competition.In many cases, overall application performance far exceeds 10x.
  • For illustrative purposes, this diagram shows InfiniBand connectivity on the vertical axis and Ethernet connectivity on the horizontal axis.The compute nodes and the storage device within Exalogic are provisioned with redundant InfiniBand connections. These devices have access to the datacenter “external” network via the Ethernet ports on the InfiniBand Gateways.Ethernet connectivity to the compute servers and cloud storage is provided through the InfiniBand fabric. Virtual Ethernet NICs are instantiated within the host stack and Ethernet frames are encapsulated within InfiniBand packets which are forwarded to the gateway, which has physical Ethernet ports.Note that there is an independent 1 GbE network for device management that connects to all components in Exalogic
  • Nodes1481630240RAM963847681536288023040SSD20080016003200600048000ZFSSA6060606060480
  • EL 1.0 multiple for Web: 3.4EL 1.0 multiple for JMS: 1.6EL 1.0 multiple for Enterprise Java: 2.2
  • EL 1.0 multiple for Web: 3.4EL 1.0 multiple for JMS: 1.6EL 1.0 multiple for Enterprise Java: 2.2
  • Starting with the SPARC SuperCluster, the most important point to think about is it’s best for Oracle. Exadata purpose built for the database runs that extraordinarily well, and Exalogic runs middleware, Java middleware, WebLogic and those applications extraordinarily well. But what we wanted to do here is to bring those pieces of technology together with any other stuff you have running in your enterprise.  So, we have many customers that have hundreds or thousands of applications, whether they’re packaged applications or written in traditional languages, running many parts of their enterprise. And we bring together these core technologies into a platform that lets you run those applications, but also have the best of the best from Oracle so you can run side-by-side with database 11, you can run side-by-side with WebLogic, and so on.Performance substantiation:1M IOPS: Based on internal measurement of Exadata Storage cells10x Java performance: Based on internal measurement of Exalogic ZFS 2x faster, ½ the price of NetApp: Demonstrates the performance of ZFS Storage via the Oracle Sun ZFS Storage 7420 appliance which delivered outstanding performance and price/performance on the SPC Benchmark 1, beating results published on the NetApp FAS3270A.The Sun ZFS Storage 7420 appliance delivered 137,066.20 SPC-1 IOPS at $2.99 $/SPC-1 IOPS on the SPC-1 benchmark. The Sun ZFS Storage 7420 appliance outperformed the NetApp FAS3270A by 2x on the SPC-1 benchmark. The Sun ZFS Storage 7420 appliance outperformed the NetApp FAS3270A by 2.5x on price/performance on the SPC-1 benchmark.SPC-1, SPC-1 IOPS, $/SPC-1 IOPS reg tm of Storage Performance Council (SPC). More info www.storageperformance.org. Oracle Sun ZFS Storage 7420 Appliance http://www.storageperformance.org/results/benchmark_results_spc1#a00108 As of October 3, 2011.Cloud provisioning, unmatched scalability: Scalability of Solaris 11, leader in scaling to 512 threadsNear zero virtualization overhead: Solaris Zones, based on internal testsInfiniBand: 5-8x speed of current networksEnterprise Manager reduction of downtime: Oracle is helping to streamline operations, increase productivity, reduce downtime, and remove management barriers with Oracle Enterprise Manager Ops Center. With the ability to manage today’s increasingly heterogeneous, diverse, and complex datacenters, Oracle Enterprise Manager Ops Center helps IT staff create dynamic, scalable, datacenter infrastructure that adapts to ever-changing business priorities and demands. White paper including description of reduced downtime: http://www.oracle.com/oms/enterprisemanager11g/application-to-disk-067846.html

Reduccion TCO sistemas Integrados Presentation Transcript

  • 1. 1 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 2. Como Reducir el TCO con sistemas integrados Fran Navarro Presales Specialist2 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 3. Como Reducir el TCO con sistemas integrados Fran Navarro Presales Specialist3 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 4. Agenda Cómo reducir TCO con Sistemas Integrados • Introducción sistemas Integrados • Oracle Database Apliance • Exadata • Exalogic • SuperCluster4 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 5. Market Analysis Enterprise Computing is too Complex 35-65% is integration Bottom line: 4% of revenue is spent on a commodity that does not improve competitiveness.5 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 6. Fundamental Value of Engineered Systems Easy, predictable 100’s of Components  1 Machine 1000’s of Hours  1 Day 6 | © 2011 Oracle Corporation – Proprietary and ConfidentialCopyright © 2011 Oracle Corporation - Proprietary and Confidential
  • 7. Exa ROI I Performance Comparative ROI• 25% processor • Up to 5X processor utilization utilization advantage advantage for for many other standard application types: Hardware and • Java EE and Fusion applications Middleware • Oracle Applications 25% 50% 2X 3X 5X • OLTP with Oracle Exadata Exalogic ROI Standard Hardware ROI Exalogic Processor Utilization Efficiency Advantage Less hardware, Less software: Easier to Deploy, Manage, Maintain 12 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 8. Whole Application Lifecycle Enterprise IT Budget • Sizing & Deployment Planning • Installation & Configuration • Deploying and Scaling • Patching & Maintenance • Platform Administration13 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 9. Whole Application LifecycleKey Savings Area #1 – Software Licensing Because Exa offers superior overall performance and Enterprise IT Budgetresource efficiency and therefore uses software fewerprocessor cores for any given workload, software licensescosts are reduced.Key Savings Area #2 – Support CostsSupport and Maintenance costs are lower becausehardware + OS is included no added charge andfewer hardware and software licenses are requiredfor the Exa systemKey Savings Area #3 – Setup & AdminA single system (vs. 100’s of components) simply takes lesstime to install, setup, deploy and maintain 14 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 10. Eng System Vision I Cloud-in-a-box • Full-featured, ready-to-deploy private cloud • Extreme performance for Oracle Applications • Engineered System with best ROI 18 | © 2011 Oracle Corporation – Proprietary and ConfidentialCopyright © 2011 Oracle Corporation
  • 11. Oracle + Sun: Hardware and Software Complete, Open, Engineered to Work Together Integrated Systems • Optimized and integrated for better performance, reliability, security, management • Reduced change management risk • Lower cost of ownership19 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 12. Engineered Systems & Appliances Cloud Built In Purpose Built General Purpose Exadata Exalogic Big Data SPARC SuperCluster Database Appliance Exalytics20 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 13. Engineered Systems & Appliances Scale and RAS SPARC SuperCluster Exadata ExalogicPrice/Perf Big Data Appliance Purpose Built Universal Purpose21 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 14. Oracle Database Appliance Ideal for SMBs and Departmental Systems • Simple to implement • Designed and priced to scale • Performance improves as you scale • Highest levels of serviceability • Highest availability for this class of machine 22 | ©© 2011 Oracle2011 Oracle Corporation – Proprietary and Confidential Corporation
  • 15. Fully Redundant Hardware • 2 x dual-socket Oracle Linux servers – 24 Intel Xeon processor X5675 cores – 192 GB main memory • 12 TB raw disk storage • 292 GB solid state storage • Built-in redundancy – Server, storage, network, power and cooling 23 | ©© 2011 Oracle2011 Oracle Corporation – Proprietary and Confidential Corporation
  • 16. Highly Reliable Software • Oracle Database 11g Enterprise Edition – Automatic Storage Management • Oracle Real Application Clusters – Oracle Clusterware • Oracle Linux • Oracle Appliance Manager software – Phones home automatically to file Service Requests 24 | ©© 2011 Oracle2011 Oracle Corporation – Proprietary and Confidential Corporation
  • 17. Easy to Install Rapidly Deploy a Database Cluster • Plug in the power • Plug in the network • Wizard-driven install 25 | ©© 2011 Oracle2011 Oracle Corporation – Proprietary and Confidential Corporation
  • 18. Appliance Manager Software 26 | ©© 2011 Oracle2011 Oracle Corporation – Proprietary and Confidential Corporation
  • 19. Easy to Deploy, Manage, and Maintain Reduced Installation and Administration Effort Installation Expertise Optimization Expertise Network Administration Savings Time Cost Storage Administration System Administration Database Oracle Appliance Administration Manager Oracle Database Build Your Own Appliance 28 | ©© 2011 Oracle2011 Oracle Corporation – Proprietary and Confidential Corporation
  • 20. Three Tiers of Availability Single Instance Active – Passive Active – Active • Good Availability • Better Availability • Best Availability • Oracle Database 11g • Oracle Database 11g • Oracle Database 11g Enterprise Edition Enterprise Edition Enterprise Edition • Oracle Real • Oracle Real Application Clusters Application Clusters One Node • Mutual failover and • Can have mutual loadbalancing failover 29 | ©© 2011 Oracle2011 Oracle Corporation – Proprietary and Confidential Corporation
  • 21. ‘Pay-as-you-Grow’ Database Licensing • Purchase single hardware configuration • Start with minimum of 2 processor core licenses • Scale to maximum of 24 processor core licenses • No hardware upgrades required • License database software just for the cores you use 30 | ©© 2011 Oracle2011 Oracle Corporation – Proprietary and Confidential Corporation
  • 22. ORACLE EXADATA32 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 23. ORACLE EXADATA DATABASE MACHINETransaction Processing, Data Warehousing, Consolidation • Fastest Data Warehouse & OLTP • Best Cost/Performance Data Warehouse & OLTP • Optimized Hardware (per rack) • Software Breakthroughs • Scales from ¼ Rack to 8 Full Racks33 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 24. Exadata Architecture A complete system: compute, storage, networking • Database Cluster – Intel-based database servers – Oracle Linux or Solaris 11 – Oracle Database 11g – 10 Gig Ethernet (to data center) • Storage Grid – Intel-based storage servers – Up to 504 terabytes raw disk – 5.3 terabytes Flash storage – Exadata Storage Server Software • InfiniBand Network – Internal connectivity ( 40 Gb/sec )34 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 25. Up to 10X 50X + + + Hybrid Columnar Compression Smart Flash Smart Scan Queries Cache35 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 26. The Exadata Difference Exadata DB Machine Custom Configuration Storage scans & filters data Storage just ships blocks Storage offloads DB* DB-unaware storage 168 CPU Flash caches relevant data No DB-aware flash managementcores in 40 Gb/sec network 8 – 10 Gb/sec networkstorage Pre-built for DB workload Assembled by customer Redundancy built-in Build-your-own HA Compression built-in Compression optional Workload mgmt built-in Workload mgmt optional * Backups, compression, decryption, data mining Exadata is not a general-purpose system, It’s a Database Machine36 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 27. COMPLETE FAMILY OF DATABASE MACHINES Oracle Exadata X2-2 Oracle Exadata X2-8 2 to 8 (12 core) database nodes 2 (64 core) database nodesQuarter Half Full, Multi-Rack38 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 28. Best Machine for Database Consolidation • Exadata serves as farm/cloud for databases • Extreme performance for complex workloads that mix OLTP, DW, batch, reporting • I/O and CPU resource management isolates workloads Lower Costs Increase Utilization Reduce Management41 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 29. ORACLE EXADATA Extreme Performance. Extreme Value.Lower data center costsStore 10x more dataSearch data 10 X fasterReal time decision makingSpeed time-to-market for new products and servicesMitigate deployment risks 42 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 30. ORACLE EXALOGIC43 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 31. Exalogic X2-2 I Complete, Integrated Compute Power • 2.93 GHz Xeon processors • 1333MHz DRAM, RAID SSD Disks • Redundant QDR InfiniBand, Power, Management Internal I/O Fabric and Data Center Connectivity • 40 Gb/sec internal I/O backplane • 10 Gigabit Ethernet connectivity to datacenter Integrated Storage • Shared storage for applications • Clustered for HA • 60 TB SAS disk • 4 TB read cache,72 GB write cache EL X2-244 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 32. Exalogic X2-2 Hardware Architecture System Design Exalogic X2-2 Ethernet Gateways Spine Switch 10GbE QDR InfiniBand I/O Backplane Data Center Service Compute Nodes Exabus Network Direct IB Integration: Standard • Exadata Oracle • Additional Exalogic … Database configurations • ZFS Storage ApplianceExadata Management • Backup Media Servers Storage Switch Data Center Mgmt Network GbE GbE GbE Management Network (GbE) 45 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 33. Exalogic X2-2 I Seamless ScalabilityEighth Rack Eighth Rack QuarterRack Quarter Rack Half Rack Half Rack Full Rack Rack Multi-rack Multi-Rack 4 Nodes 8 Nodes 16 Nodes 30 Nodes 240+ Nodes384 GB RAM 768 GB RAM 1.5 TB RAM 2.8 TB RAM 23+ TB RAM800 GB SSD 1.6 TB SSD 3.2 TB SSD 6 TB SSD 48+ TB SSD 60 TB NAS 60 TB NAS 60 TB NAS 60 TB NAS 480+ TB NAS46 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 34. Exabus I Optimized Network Virtualization Standard Hardware I/O Exabus Application Application Application Application Application Buffer Application Buffer Copy TCP IP Transport Kernel 20% Buffer Copies Zero Buffer Copy 40% Transport Processing Direct Memory Access 40 % Kernel Context Switches Kernel Bypass 4X Throughput, 6X Lower Latency47 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 35. EECS I Performance Benchmark 5-10x improvements from baseline Web JMS Enterprise Java Requests/Sec. Messages/sec. Operations/Sec. 22,481 246,035 1,237,462 3.1X 3.1X 2.3X 9,560 78,840 401,070 Standard HW EL 1.0 Standard HW EL 1.0 Standard HW EL 1.048 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 36. ORACLE SUPERCLUSTER51 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 37. SPARC SuperCluster Best for Oracle. Runs All Existing Workloads. SPARC T4 Compute Pool Solaris 11 More than a dozen World Records Cloud provisioning in seconds over IBM and HP across every tier Unmatched Scalability Exadata Storage Cells Virtualization 1M IOPS, 32 GB/s query throughput Near zero virtualization overhead Exalogic Elastic Cloud InfiniBand 10x Java performance 5-8x the speed of current networks Integrated ZFS Storage Enterprise Manager Increase productivity, reduce 2x faster and ½ the price of NetApp downtime As fast as Exadata for Database / as fast as Exalogic for JavaSee performance substantiation slides 52 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 38. SPARC SuperCluster Architecture Best infrastructure solution for enterprise applications Exadata Storage Servers • 1,200 CPU threads • 4 TB DRAMSPARC T4-4 Compute Nodes • 97 to 270 TB Hard Disk ZFS Storage Appliance • 8.66 TB Flash InfiniBand Switches • 1M IOPS • 42 Gb/sec Storage Bandwidth • 896 Gb/sec InfiniBand Interconnect 53 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 39. SPARC SuperCluster T4-4 Engineered to Work Together Extreme Performance Virtualization Breakthrough Innovation Low Overhead Exadata Storage Cells, Intelligent Storage Grid, SPARC T4- Oracle VM, Solaris Zones, low latency 4 compute nodes, and the Solaris 11 Operating System. virtualized environments Ease of Deployment High Availability Built in Integrated Hardware and Software All fully redundant hardware, shorter Fully failover times, Solaris tested, configured, optimized, sized, and Cluster, physically partitioned compute certified nodes, ASM Secure by Design Streamlined Management SPARC/Solaris Built-in Encryption & Fast & foolproof upgrades. Compression Integrated crypto hardware automatically Resource Management Telemetry across the stack, Integration across secures Performance Workload Management the stack, Solaris Ease of Patching, NewDatabase, Middleware, Applications, and Solaris Dynamic Threads image packaging system provides fastFile System, new admin controls, and secure OS application installs. startup. 60 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 40. Pre-built and Optimized Out-of-the-Box 100% Performance Achievement Custom Configuration Performance Achievement Test & debug failure modes Measure, di agnose, tun Multi- Assemble e and dozens of vendor reconfigure finger components pointing Time Time (Days) (Months)64 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 41. Oracle Enterprise Manager for Exa Management Integrated View of Hardware and Software• Hardware view • Schematic of cells, compute nodes and switches • Hardware components alerts• Software/system view • Performance, availability, usage by databases, services, clusters • Software alerts db, cluster, ASM • Topology view of DB systems/clusters• Configuration view • Version summary of all components along with patch recommendations 65 | © 2011 Oracle Corporation – Proprietary and ConfidentialCopyright © 2012, Oracle Corporation and/or its affiliates – 65 –
  • 42. Data Center Evolution I Paradigm Shift 1950 201266 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 43. Engineered Systems I Dawn of a New Era Before Now67 | © 2011 Oracle Corporation – Proprietary and Confidential
  • 44. Sistemas de Ingenieria Conjunta Simplificación It y Reducción de Costes68 | © 2011 Oracle Corporation – Proprietary and Confidential