Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.

Sun Oracle Exadata V2 For OLTP And DWH

13.864 Aufrufe

Veröffentlicht am

Sun Oracle Exadata Version 2 For Online Transaction Processing And Data Warehousing

  • DOWNLOAD THAT BOOKS INTO AVAILABLE FORMAT (2019 Update) ......................................................................................................................... ......................................................................................................................... Download Full PDF EBOOK here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download Full EPUB Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download Full doc Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download PDF EBOOK here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download EPUB Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download doc Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... ......................................................................................................................... ................................................................................................................................... eBook is an electronic version of a traditional print book that can be read by using a personal computer or by using an eBook reader. (An eBook reader can be a software application for use on a computer such as Microsoft's free Reader application, or a book-sized computer that is used solely as a reading device such as Nuvomedia's Rocket eBook.) Users can purchase an eBook on diskette or CD, but the most popular method of getting an eBook is to purchase a downloadable file of the eBook (or other reading material) from a Web site (such as Barnes and Noble) to be read from the user's computer or reading device. Generally, an eBook can be downloaded in five minutes or less ......................................................................................................................... .............. Browse by Genre Available eBooks .............................................................................................................................. Art, Biography, Business, Chick Lit, Children's, Christian, Classics, Comics, Contemporary, Cookbooks, Manga, Memoir, Music, Mystery, Non Fiction, Paranormal, Philosophy, Poetry, Psychology, Religion, Romance, Science, Science Fiction, Self Help, Suspense, Spirituality, Sports, Thriller, Travel, Young Adult, Crime, Ebooks, Fantasy, Fiction, Graphic Novels, Historical Fiction, History, Horror, Humor And Comedy, ......................................................................................................................... ......................................................................................................................... .....BEST SELLER FOR EBOOK RECOMMEND............................................................. ......................................................................................................................... Blowout: Corrupted Democracy, Rogue State Russia, and the Richest, Most Destructive Industry on Earth,-- The Ride of a Lifetime: Lessons Learned from 15 Years as CEO of the Walt Disney Company,-- Call Sign Chaos: Learning to Lead,-- StrengthsFinder 2.0,-- Stillness Is the Key,-- She Said: Breaking the Sexual Harassment Story That Helped Ignite a Movement,-- Atomic Habits: An Easy & Proven Way to Build Good Habits & Break Bad Ones,-- Everything Is Figureoutable,-- What It Takes: Lessons in the Pursuit of Excellence,-- Rich Dad Poor Dad: What the Rich Teach Their Kids About Money That the Poor and Middle Class Do Not!,-- The Total Money Makeover: Classic Edition: A Proven Plan for Financial Fitness,-- Shut Up and Listen!: Hard Business Truths that Will Help You Succeed, ......................................................................................................................... .........................................................................................................................
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier
  • DOWNLOAD FULL BOOKS INTO AVAILABLE FORMAT ......................................................................................................................... ......................................................................................................................... 1.DOWNLOAD FULL PDF EBOOK here { https://tinyurl.com/y8nn3gmc } ......................................................................................................................... 1.DOWNLOAD FULL EPUB Ebook here { https://tinyurl.com/y8nn3gmc } ......................................................................................................................... 1.DOWNLOAD FULL doc Ebook here { https://tinyurl.com/y8nn3gmc } ......................................................................................................................... 1.DOWNLOAD FULL PDF EBOOK here { https://tinyurl.com/y8nn3gmc } ......................................................................................................................... 1.DOWNLOAD FULL EPUB Ebook here { https://tinyurl.com/y8nn3gmc } ......................................................................................................................... 1.DOWNLOAD FULL doc Ebook here { https://tinyurl.com/y8nn3gmc } ......................................................................................................................... ......................................................................................................................... ......................................................................................................................... .............. Browse by Genre Available eBooks ......................................................................................................................... Art, Biography, Business, Chick Lit, Children's, Christian, Classics, Comics, Contemporary, Cookbooks, Crime, Ebooks, Fantasy, Fiction, Graphic Novels, Historical Fiction, History, Horror, Humor And Comedy, Manga, Memoir, Music, Mystery, Non Fiction, Paranormal, Philosophy, Poetry, Psychology, Religion, Romance, Science, Science Fiction, Self Help, Suspense, Spirituality, Sports, Thriller, Travel, Young Adult,
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier

Sun Oracle Exadata V2 For OLTP And DWH

  1. 2. Oracle Exadata for OLTP and DWH
  2. 3. The following is intended to outline our general product direction. It is intended for information purposes only, and may not be incorporated into any contract. It is not a commitment to deliver any material, code, or functionality, and should not be relied upon in making purchasing decisions. The development, release, and timing of any features or functionality described for Oracle’s products remain at the sole discretion of Oracle.
  3. 4. The Architecture of the Future Exadata Massively Parallel Grids <ul><li>Best for Data Warehousing </li></ul><ul><li>Best for OLTP </li></ul><ul><li>Best for Consolidation </li></ul>
  4. 5. Database Machine Success
  5. 6. “ Every query was faster on Exadata compared to our current systems. The smallest performance improvement was 10x and the biggest one was an incredible 72x .” Simeon Dimitrov, Enterprise Resources Manager “ Call Data Record queries that used to run for over 30 minutes now complete in under 1 minute . That's extreme performance.” Grant Salmon , CEO, LGR Telecommunications “ A query that used to take 24 hours now runs in less than 30 minutes . The Oracle Database Machine beats competing solutions on bandwidth, load rate, disk capacity, and transparency . ” Christian Maar, CIO Database Machine Success
  6. 7. “ The Oracle Database Machine is an ideal cost-effective platform to meet our speed and scalability needs . ” Ketan Parekh, Manager Database Systems “ After carefully testing several data warehouse platforms, we chose the Oracle Database Machine. Oracle Exadata was able to speed up one of our critical processes from days to minutes ..” Brian Camp, Sr. VP of Infrastructure Services Database Machine Success
  7. 8. Extreme Performance Gains Customer Benchmark Results Average Gain Customer Industry 20x 16x 15x Telecom 28x Retail Finance Telecom
  8. 9. “ When it comes to speed, Oracle Exadata technology has changed the game completely…..” Grant Salmon CEO LGR Telecommunications from Profit Magazine, February 2009
  9. 10. <Insert Picture Here> Introducing Oracle Exadata Version 2
  10. 11. Oracle Exadata Database Machine <ul><li>Version 1 </li></ul><ul><ul><li>World’s Fastest Machine for Data Warehousing </li></ul></ul><ul><ul><li>Extreme Performance for Sequential I/O </li></ul></ul><ul><ul><li>10x Faster than other Oracle D/W Systems </li></ul></ul><ul><li>Version 2 </li></ul><ul><ul><li>World’s Fastest Machine for OLTP </li></ul></ul><ul><ul><li>Extreme Performance for Random I/O </li></ul></ul><ul><ul><li>2x Version 1 Data Warehousing Performance </li></ul></ul><ul><ul><li>Dramatic new Exadata Software Capabilities </li></ul></ul>
  11. 12. Oracle Exadata V2 - Best OLTP Machine <ul><li>Only Oracle runs real-world business applications “on the Grid” </li></ul><ul><li>Unique fault-tolerant scale-out OLTP database </li></ul><ul><ul><li>RAC, Data Guard, Online Operations </li></ul></ul><ul><li>Unique fault-tolerant scale-out storage suitable for OLTP </li></ul><ul><ul><li>ASM, Exadata </li></ul></ul>
  12. 13. Best Data Warehouse Machine <ul><li>Massively parallel high volume hardware to quickly process vast amounts of data </li></ul><ul><ul><li>Exadata runs data intensive processing directly in storage </li></ul></ul><ul><li>Most complete analytic capabilities </li></ul><ul><ul><li>OLAP, Analytic SQL, Spatial, Data Mining, Real-time transactional ETL, Efficient queries </li></ul></ul><ul><li>Powerful warehouse specific optimizations </li></ul><ul><ul><li>Flexible Partitioning, Bitmap Indexing, Join indexing, Materialized Views, Result Cache </li></ul></ul>Data Mining OLAP ETL
  13. 14. Drastically Simplified Deployments <ul><li>Database Machine eliminates the complexity of deploying database systems </li></ul><ul><ul><li>Months of configuration, troubleshooting, tuning </li></ul></ul><ul><li>Database Machine is ready on day one </li></ul><ul><ul><li>Pre-built, tested, standard, supportable configuration </li></ul></ul><ul><ul><li>Runs existing applications unchanged </li></ul></ul><ul><li>Extreme performance out of the box </li></ul>From Months to Days
  14. 15. Sun Oracle Database Machine Hardware <ul><li>Complete, Pre-configured, Tested for Extreme Performance </li></ul><ul><ul><li>Database Servers </li></ul></ul><ul><ul><li>Exadata Storage Servers </li></ul></ul><ul><ul><li>InfiniBand Switches </li></ul></ul><ul><ul><li>Ethernet Switch </li></ul></ul><ul><ul><li>Pre-cabled </li></ul></ul><ul><ul><li>Keyboard, Video, Mouse (KVM) hardware </li></ul></ul><ul><ul><li>Power Distribution Units (PDUs) </li></ul></ul><ul><li>Ready to Deploy </li></ul><ul><ul><li>Plug in power </li></ul></ul><ul><ul><li>Connect to Network </li></ul></ul><ul><ul><li>Ready to Run Database </li></ul></ul>
  15. 16. <Insert Picture Here> Familiar Technology with Powerful Performance
  16. 17. © 2009 Oracle Corporation What’s Inside Exadata? Exadata Storage Server, Database Server, and Infiniband Switches <ul><li>Infiniband Switches </li></ul><ul><li>Database Servers </li></ul><ul><li>Storage Servers </li></ul>
  17. 18. Sun Oracle Database Machine <ul><li>Exadata Storage Server Grid </li></ul><ul><li>21 GB/sec disk bandwidth </li></ul><ul><li>50 GB/sec flash bandwidth </li></ul><ul><li>1 million I/Os per second </li></ul><ul><li>Oracle Database Server Grid </li></ul><ul><li>Millions of transactions per minute </li></ul><ul><li>Tens of millions of queries per minute </li></ul><ul><li>Billions of rows per minute </li></ul><ul><li>InfiniBand Network </li></ul><ul><li>880 Gb/sec aggregate throughput </li></ul>Extreme Performance
  18. 19. Sun Oracle Database Machine <ul><li>Highest performance, lowest cost per unit of performance </li></ul><ul><li>Fault tolerant, Scalable on demand </li></ul><ul><li>Exadata Storage Server Grid </li></ul><ul><li>14 storage servers </li></ul><ul><li>100 TB raw SAS disk storage </li></ul><ul><li>or </li></ul><ul><li>336 TB raw SATA disk storage </li></ul><ul><li>5TB of flash storage! </li></ul><ul><li>Oracle Database Server Grid </li></ul><ul><li>8 compute servers </li></ul><ul><li>64 Intel Cores </li></ul><ul><li>576 GB DRAM </li></ul><ul><li>InfiniBand Network </li></ul><ul><li>40 Gb/sec unified server and storage network </li></ul><ul><li>Fault Tolerant </li></ul>
  19. 20. Sun Oracle Database Machine Hardware Improvements <ul><li>Same architecture as Exadata V1 Database Machine </li></ul><ul><ul><li>Same number and type of Servers, CPUs, Disks </li></ul></ul>Plus Flash Storage! Latest Technologies 80% Faster CPUs 33% More SAS Disk Capacity 100% More SATA Disk Capacity 50% Faster Disk Throughput 100% Faster Networking 125% More Memory 200% Faster Memory 100% More Ethernet Connectivity Xeon 5500 Nehalem 600 GB SAS Disks 2 TB SATA Disks 6 Gb SAS Links 40 Gb InfiniBand 72 GB per DB Node DDR3 DRAM 4 Ethernet links per DB Node New Faster Bigger
  20. 21. <Insert Picture Here> Exadata Database Servers
  21. 22. Sun Oracle Database Server <ul><li>8 Sun Fire X4170 DB per rack </li></ul><ul><li>• 8 CPU cores – 2x performance </li></ul><ul><li>• 72 GB memory – 2.5x increase </li></ul><ul><li>• Redundant HCA path to 2 switches </li></ul><ul><li>• Fully redundant power and cooling </li></ul>
  22. 23. <Insert Picture Here> Exadata Storage Servers
  23. 24. Sun Oracle Exadata Storage Server • 14 Sun Fire X4275 per rack • 5x faster than conventional storage • 2x more storage capacity • Simplifies storage to eliminate complex SAN architectures • Sun FlashFire Technology turbocharges applications
  24. 25. <Insert Picture Here> Exadata FlashFire Card
  25. 26. Sun FlashFire Technology Extreme Performance Accelerator • 10x better IO response time • 5.25 Terabytes Flash per rack • 1,000,000 IOPS per rack • 20x IOPS speedup for Oracle • Integrated super caps for data retention New
  26. 27. <Insert Picture Here> Exadata InfiniBand Switch
  27. 28. InfiniBand Network High Bandwidth, Low Latency • Sun Datacenter InfiniBand Switch 36 • Fully redundant non-blocking IO paths from servers to storage • 2.88 Tb/sec bi-sectional bandwidth per switch • 40 Gb/sec QDR, Dual port QSFP per server
  28. 29. <Insert Picture Here> Exadata Configurations
  29. 30. Start Small and Grow Full Rack Half Rack Quarter Rack Basic System
  30. 31. Sun Oracle Database Machine Full Rack Pre-Configured for Extreme Performance <ul><li>8 Sun Fire ™ X4170 Oracle Database servers </li></ul><ul><li>14 Exadata Storage Servers (All SAS or all SATA) </li></ul><ul><li>3 Sun Datacenter InfiniBand Switch 36 </li></ul><ul><ul><li>36-port Managed QDR (40Gb/s) switch </li></ul></ul><ul><li>1 “Admin” Cisco Ethernet switch </li></ul><ul><li>Keyboard, Video, Mouse (KVM) hardware </li></ul><ul><li>Redundant Power Distributions Units (PDUs) </li></ul><ul><li>Single Point of Support from Oracle </li></ul><ul><ul><li>3 year, 24 x 7, 4 Hr On-site response </li></ul></ul>Add more racks for additional scalability
  31. 32. <ul><li>4 Sun Fire ™ X4170 Oracle Database servers </li></ul><ul><li>7 Exadata Storage Servers (All SAS or all SATA) </li></ul><ul><li>2 Sun Datacenter InfiniBand Switch 36 </li></ul><ul><ul><li>36-port Managed QDR (40Gb/s) switch </li></ul></ul><ul><li>1 “Admin” Cisco Ethernet switch </li></ul><ul><li>Keyboard, Video, Mouse (KVM) hardware </li></ul><ul><li>Redundant PDUs </li></ul><ul><li>Single Point of Support from Oracle </li></ul><ul><ul><li>3 year, 24 x 7, 4 Hr On-site response </li></ul></ul>Sun Oracle Database Machine Half Rack Pre-Configured for Extreme Performance Can Upgrade to a Full Rack
  32. 33. <ul><li>2 Sun Fire ™ X4170 Oracle Database servers </li></ul><ul><li>3 Exadata Storage Servers (All SAS or all SATA) </li></ul><ul><li>2 Sun Datacenter InfiniBand Switch 36 </li></ul><ul><ul><li>36-port Managed QDR (40Gb/s) InfiniBand switch </li></ul></ul><ul><li>1 “Admin” Cisco Ethernet switch </li></ul><ul><li>Keyboard, Video, Mouse (KVM) hardware </li></ul><ul><li>Redundant PDUs </li></ul><ul><li>Single Point of Support from Oracle </li></ul><ul><ul><li>3 year, 24 x 7, 4 Hr On-site response </li></ul></ul>Sun Oracle Database Machine Quarter Rack Pre-Configured for Extreme Performance Can Upgrade to an Half Rack
  33. 34. Sun Oracle Database Machine Basic System Entry Level non-HA Configuration <ul><li>1 Sun Fire ™ X4170 Oracle Database servers </li></ul><ul><li>1 Exadata Storage Servers (All SAS or all SATA) </li></ul><ul><li>1 Sun Datacenter InfiniBand Switch 36 </li></ul><ul><ul><li>36-port Managed QDR (40Gb/s) InfiniBand switch </li></ul></ul><ul><li>InfiniBand Cables </li></ul><ul><li>Installed in Customer supplied Rack </li></ul><ul><li>Customer supplied Ethernet and KVM Infrastructure </li></ul><ul><li>Single Point of Support from Oracle </li></ul><ul><ul><li>3 year, 24 x 7, 4 Hr On-site response </li></ul></ul>
  34. 35. Exadata Product Capacity 1 – Raw capacity calculated using 1 GB = 1000 x 1000 x 1000 bytes and 1 TB = 1000 x 1000 x 1000 x 1000 bytes. 2 - User Data: Actual space for end-user data, computed after single mirroring (ASM normal redundancy) and after allowing space for database structures such as temp, logs, undo, and indexes. Actual user data capacity varies by application. User Data capacity calculated using 1 TB = 1024 * 1024 * 10 24 * 1024 bytes. Single Server Quarter Rack Half Rack Full Rack Raw Disk 1 SAS 7.2 TB 21 TB 50 TB 100 TB SATA 24 TB 72 TB 168 TB 336 TB Raw Flash 1 384 GB 1.1 TB 2.6 TB 5.3 TB User Data 2 (assuming no compression) SAS 2 TB 6 TB 14 TB 28 TB SATA 7 TB 21 TB 50 TB 100 TB
  35. 36. Exadata Product Performance 1 – Bandwidth is peak physical disk scan bandwidth, assuming no compression. 2 - Max User Data Bandwidth assumes scanned data is compressed by factor of 10 and is on Flash. 3 – IOPs – Based on IO requests of size 8K 4 - Actual performance will vary by application. Single Server Quarter Rack Half Rack Full Rack Raw Disk Data Bandwidth 1,4 SAS 1.5 GB/s 4.5 GB/s 10.5 GB/s 21 GB/s SATA 0.85 GB/s 2.5 GB/s 6 GB/s 12 GB/s Raw Flash Data Bandwidth 1,4 3.6 GB/s 11 GB/s 25 GB/s 50 GB/s Max User Data Bandwidth 2,4 (10x compression & Flash) 36 GB/s 110 GB/s 250 GB/s 500 GB/s Disk IOPS 3,4 SAS 3,600 10,800 25,000 50,000 SATA 1,440 4,300 10,000 20,000 Flash IOPS 3,4 75,000 225,000 500,000 1,000,000 Data Load Rate 4 0.65 TB/hr 1 TB/hr 2.5 TB/hr 5 TB/hr
  36. 37. <Insert Picture Here> Exadata Storage Server Software
  37. 38. Exadata Storage Features <ul><li>Exadata Smart Scans </li></ul><ul><ul><li>10X or greater reduction in data sent to database servers </li></ul></ul><ul><li>Exadata Storage Indexes </li></ul><ul><ul><li>Eliminate unnecessary I/Os to disk </li></ul></ul><ul><li>Hybrid Columnar Compression </li></ul><ul><ul><li>Efficient compression increases user data scan rates </li></ul></ul><ul><li>Flash increases scan rates </li></ul><ul><ul><li>Flash cache removed spinning magnetic media bottleneck </li></ul></ul>
  38. 39. Exadata Smart Storage Breaks Data Bandwidth and Random I/O Bottleneck <ul><li>Oracle addresses data bandwidth bottleneck in three ways </li></ul><ul><ul><li>Massively parallel storage grid of high performance Exadata storage servers (cells). </li></ul></ul><ul><ul><ul><li>Data bandwidth scales with data volume </li></ul></ul></ul><ul><ul><li>Data intensive processing runs in Exadata storage. </li></ul></ul><ul><ul><ul><li>Queries run in storage as data streams from disk, offloading database server CPUs </li></ul></ul></ul><ul><ul><li>Columnar compression reduces data volume up to 10x </li></ul></ul><ul><ul><ul><li>Exadata Hybrid Columnar Compression provides 10x lower cost, 10x higher performance </li></ul></ul></ul><ul><li>Oracle solves random I/O bottlenecks using Exadata Smart Flash Cache </li></ul><ul><ul><li>Increase random I/Os by factor of 20X </li></ul></ul>Exadata Storage Cells
  39. 40. Exadata Smart Scans <ul><li>Exadata storage servers implement data intensive processing in storage </li></ul><ul><ul><li>Row filtering based on “where” predicate </li></ul></ul><ul><ul><li>Column filtering </li></ul></ul><ul><ul><li>Join filtering </li></ul></ul><ul><ul><li>Incremental backup filtering </li></ul></ul><ul><ul><li>Storage Indexing </li></ul></ul><ul><ul><li>Scans on encrypted data </li></ul></ul><ul><ul><li>Data Mining model scoring </li></ul></ul><ul><li>10x reduction in data sent to DB servers is common </li></ul><ul><li>No application changes needed </li></ul><ul><ul><li>Processing is automatic and transparent </li></ul></ul><ul><ul><li>Even if cell or disk fails during a query </li></ul></ul>New
  40. 41. Exadata Smart Scan Query Example Exadata Storage Grid Oracle Database Grid SUM Optimizer Chooses Partitions and Indexes to Access 10 TB scanned 1 MB returned to servers What were my sales yesterday? Select sum(sales) where Date=’24-Sept’ Scan compressed blocks in partitions/indexes Retrieve sales amounts for Sept 24
  41. 42. Exadata Storage Index Transparent I/O Elimination with No Overhead <ul><li>Exadata Storage Indexes maintain summary information about table data in memory </li></ul><ul><ul><li>Store MIN and MAX values of columns </li></ul></ul><ul><ul><li>Typically one index entry for every MB of disk </li></ul></ul><ul><li>Eliminates disk I/Os if MIN and MAX can never match “where” clause of a query </li></ul><ul><li>Completely automatic and transparent </li></ul>Min B = 1 Max B =5 Table Index Min B = 3 Max B =8 Select * from Table where B<2 - Only first set of rows can match A B C D 1 3 5 5 8 3
  42. 43. Exadata Hybrid Columnar Compression <ul><li>Data is grouped by column and then compressed </li></ul><ul><li>Query Mode for data warehousing </li></ul><ul><ul><li>Optimized for speed </li></ul></ul><ul><ul><li>10X compression typical </li></ul></ul><ul><ul><li>Scans improve proportionally </li></ul></ul><ul><li>Archival Mode for infrequently accessed data </li></ul><ul><ul><li>Optimized to reduce space </li></ul></ul><ul><ul><li>15X compression is typical </li></ul></ul><ul><ul><li>Up to 50X for some data </li></ul></ul>50X Up To New
  43. 44. Exadata Hybrid Columnar Compression Warehousing and Archiving <ul><li>Warehouse Compression </li></ul><ul><li>10x average storage savings </li></ul><ul><li>10x Scan I/O reduction </li></ul><ul><li>Archive Compression </li></ul><ul><li>15x average storage savings </li></ul><ul><ul><li>Up to 50x on some data </li></ul></ul><ul><li>Some access overhead </li></ul><ul><li>For cold or historical data </li></ul>Optimized for Speed Optimized for Space Smaller Warehouse Faster Performance Reclaim 93% of Disks Keep Data Online Can mix compression types by partition for ILM
  44. 45. Exadata Real-World Compression Ratios Oracle Production E-Business Suite Tables <ul><li>Columnar compression ratios </li></ul><ul><ul><li>Query = 14.6X </li></ul></ul><ul><ul><li>Archive = 22.6X </li></ul></ul><ul><ul><li>Vary by application and table </li></ul></ul>52
  45. 46. <Insert Picture Here> Exadata Flash Cache
  46. 47. The Disk Random I/O Bottleneck <ul><li>Disk drives hold vast amounts of data </li></ul><ul><ul><li>But are limited to about 300 I/Os per second </li></ul></ul><ul><li>Flash technology holds much less data </li></ul><ul><ul><li>But can run tens of thousands of I/Os per second </li></ul></ul><ul><li>Ideal Solution </li></ul><ul><ul><li>Keep most data on disk for low cost </li></ul></ul><ul><ul><li>Transparently move hot data to flash </li></ul></ul><ul><ul><li>Use flash cards instead of flash disks to avoid disk controller limitations </li></ul></ul><ul><ul><li>Flash cards in Exadata storage </li></ul></ul><ul><ul><ul><li>High bandwidth, low latency interconnect </li></ul></ul></ul>300 I/O per Sec Tens of Thousands of I/O’s per Second
  47. 48. Semiconductor Cache Hierarchy <ul><li>Massive throughput and IOs through innovative Cache Hierarchy </li></ul><ul><li>Database DRAM Cache </li></ul><ul><ul><li>400GB raw capacity </li></ul></ul><ul><ul><li>Up to 4TB compressed user data </li></ul></ul><ul><ul><li>100 GB per sec </li></ul></ul><ul><li>Exadata Smart Flash Cache </li></ul><ul><ul><li>5TB raw capacity </li></ul></ul><ul><ul><li>Up to 50TB compressed user data </li></ul></ul><ul><ul><li>50 GB/sec raw scan </li></ul></ul><ul><ul><li>1 million I/O per sec </li></ul></ul><ul><li>Exadata disks </li></ul><ul><ul><li>100TB or 336TB raw </li></ul></ul><ul><ul><li>Up to 500TB compressed user data </li></ul></ul><ul><ul><li>21 GB/sec scan </li></ul></ul><ul><ul><li>50,000 I/O per sec </li></ul></ul>
  48. 49. Exadata Smart Flash Cache Extreme Performance <ul><li>Database Machine achieves: </li></ul><ul><li>20x more random I/Os </li></ul><ul><ul><li>Over 1 million per second </li></ul></ul><ul><li>2x faster sequential query I/O </li></ul><ul><ul><li>50 GB/sec </li></ul></ul><ul><li>10x better I/O response time </li></ul><ul><ul><li>Sub-millisecond </li></ul></ul><ul><li>Greatly Reduced Cost </li></ul><ul><ul><li>10x fewer disks needed for I/O </li></ul></ul><ul><ul><li>Lower Power </li></ul></ul>5X More I/Os than 1000 Disk Enterprise Storage Array
  49. 50. Exadata Flash Cache Extreme Performance for Random I/O <ul><li>Sun Oracle Database Machine has 5 TB of flash storage </li></ul><ul><ul><li>4 high-performance flash cards in every Exadata Storage Server </li></ul></ul><ul><li>Smart Flash Cache caches hot data </li></ul><ul><ul><li>Not just simple LRU </li></ul></ul><ul><ul><ul><li>Knows when to avoid caching to avoid flushing cache </li></ul></ul></ul><ul><ul><li>Allows optimization by application table </li></ul></ul>Oracle is the First Flash Optimized Database New
  50. 51. Flash Cache <ul><li>Flash storage more than doubles scan throughput </li></ul><ul><ul><li>50 GB/sec </li></ul></ul><ul><li>Combined with Hybrid Columnar Compression </li></ul><ul><ul><li>Up to 50 TB of data fits in flash </li></ul></ul><ul><ul><li>Queries on compressed data run up to </li></ul></ul><ul><ul><li>500 GB/sec </li></ul></ul>HITACHI USP V TERADATA 2550 NETEZZA TwinFin 12 SUN ORACLE Database Machine Query Throughput GB/sec Uncompressed Data Flash Disk 50
  51. 52. Comparison to Specialty Solutions <ul><li>A single database machine has over 400GB of memory usable for caching </li></ul><ul><li>Database release 11.2 introduces parallel query processing on memory cached data </li></ul><ul><ul><li>Harnesses memory capacity of entire database cluster for queries </li></ul></ul><ul><ul><li>Foundation for world record 1TB TPC-H </li></ul></ul><ul><li>Exadata Hybrid Columnar Compression enables multi-terabyte tables or partitions to be cached in memory </li></ul>Faster than in-memory specialized startups Source: Transaction Processing Council, as of 9/14/2009: Oracle on HP Bladesystem c-Class 128P RAC, 1,166,976 QphH@1000GB, $5.42/QphH@1000GB, available 12/1/09. Exasol on PRIMERGY RX300 S4 , 1,018,321 QphH@1000GB, $1.18/QphH@1000GB, available 08/01/08. ParAccel on SunFire X4100 315,842 QphH@1000GB, $ 4.57 /QphH@1000GB, available 10/29/07. QphH: 1 TB TPC-H Memory has 100x more bandwidth than Disk
  52. 53. Benefits Multiply with Compression 1 TB with compression 10 TB of user data Requires 10 TB of IO 100 GB with partition pruning 20 GB with Storage Indexes 5 GB Smart Scan on Memory or Flash Subsecond On Database Machine Data is 10x Smaller, Scans are 2000x faster
  53. 54. <Insert Picture Here> Disk Management With Automatic Storage Management
  54. 55. Automatic Storage Management (ASM) Simplifies Provisioning, Improves Performance <ul><li>Automatic I/O load balancing </li></ul><ul><ul><li>Stripes data across disks to balance load </li></ul></ul><ul><ul><li>Best I/O throughput </li></ul></ul><ul><li>Automatic mirroring </li></ul><ul><li>Efficient, online add/remove of disk </li></ul><ul><li>Consolidate data from multiple databases into same shared storage environment </li></ul><ul><li>Automatic data rebalancing – NO HOT SPOTS! </li></ul>Automatic Storage Management Database C Database B Database A
  55. 56. Exadata Storage Layout Cell Disk Sys Area Sys Area Grid Disk n Grid Disk 1 … ASM disk ASM disk <ul><li>Physical disks map to Cell Disks </li></ul><ul><li>Cell Disks are partitioned into one or more Grid Disks </li></ul><ul><li>Grid Disks are created in order of “hottest” (first) to “coldest” portion of the disk (last) </li></ul><ul><li>ASM diskgroups are created from Grid Disks </li></ul><ul><li>Transparent above the ASM layer </li></ul>Physical Disk
  56. 57. Interleaved Grid Disks <ul><li>Grid disks are optionally split and interleaved to place frequently accessed data in all grid disks on higher performing outer tracks </li></ul><ul><li>All applications benefit from higher performance outer tracks of disks </li></ul>Grid Disk 2 Hot Data, Cold Data Grid Disk 1 Hot Data, Cold Data 11gR2
  57. 58. Exadata Storage Layout Example ASM Mirroring and Failure Groups <ul><li>Example shows Cell Disks divided into two Grid Disks </li></ul><ul><ul><li>Hot and Cold </li></ul></ul><ul><li>Two ASM disk groups created across the two sets of grid disks </li></ul><ul><li>ASM striping evenly distributes I/O across the disk groups </li></ul><ul><li>ASM mirroring is used to protect against disk failures </li></ul><ul><li>ASM failure groups are used to protect against cell failures </li></ul>Exadata Cell Exadata Cell Hot Hot Hot Cold Cold Cold ASM Disk Group … Hot Hot Hot Cold Cold Cold … ASM Failure Group ASM Failure Group
  58. 59. <Insert Picture Here> Resource Management for Workload Balancing
  59. 60. Exadata I/O Resource Management Multi-Database Environment <ul><li>Ensure different databases are allocated the correct relative amount of I/O bandwidth </li></ul><ul><ul><li>Database A: 33% I/O resources </li></ul></ul><ul><ul><li>Database B: 67% I/O resources </li></ul></ul><ul><li>Ensure different users and tasks within a database are allocated the correct relative amount of I/O bandwidth </li></ul><ul><ul><li>Database A: </li></ul></ul><ul><ul><ul><li>Reporting: 60% of I/O resources </li></ul></ul></ul><ul><ul><ul><li>ETL: 40% of I/O resources </li></ul></ul></ul><ul><ul><li>Database B: </li></ul></ul><ul><ul><ul><li>Interactive: 30% of I/O resources </li></ul></ul></ul><ul><ul><ul><li>Batch: 70% of I/O resources </li></ul></ul></ul>Exadata Cell InfiniBand Switch/Network Database A Database B Exadata Cell Exadata Cell
  60. 61. Oracle Database 11g Release 2 Resource Manager Instance Caging – Ideal for Exadata <ul><li>More flexible alternative to server partitioning </li></ul><ul><li>Wider platform support than operating system resource managers </li></ul><ul><li>Lower administration overhead than virtualization </li></ul><ul><li>Set CPU_COUNT per instance and enable resource manager </li></ul>Instance A Instance B Instance C Instance D Sum of cpu_counts 8 12 16 Total Number of CPUs = 16 4
  61. 62. <Insert Picture Here> Consolidation of Mixed Workload Environments
  62. 63. Consolidating Databases <ul><li>Consolidate onto Database Machine </li></ul><ul><ul><li>High performance for all applications </li></ul></ul><ul><ul><li>Low cost platform for all applications </li></ul></ul><ul><ul><li>Predictable response times in a shared environment </li></ul></ul><ul><ul><li>Handles all data management needs </li></ul></ul><ul><ul><li>Complete, Open, Integrated </li></ul></ul>CRM ERP Warehouse Data Mart HR ERP CRM Warehouse Data Mart HR
  63. 64. Best Machine for Consolidating Databases <ul><li>Consolidation mixes many different workloads in one system </li></ul><ul><ul><li>Warehouse oriented bulk data processing </li></ul></ul><ul><ul><li>OLTP oriented random updates </li></ul></ul><ul><ul><li>Multimedia oriented streaming files </li></ul></ul><ul><li>The Sun Oracle Database Machine handles any combination of workloads with extreme performance </li></ul><ul><ul><li>And predictable response times </li></ul></ul>ERP CRM Warehouse Data Mart HR
  64. 65. Consolidate Database Servers <ul><li>Shared Configuration </li></ul><ul><ul><li>Applications connect to a database service that runs on one or more database servers </li></ul></ul><ul><ul><ul><li>Services can grow, shrink, & move dynamically </li></ul></ul></ul><ul><ul><li>Large databases can span nodes using RAC </li></ul></ul><ul><ul><li>Multiple small databases can run on a single node </li></ul></ul><ul><li>Predictable performance </li></ul><ul><ul><li>Instance caging provides predictable CPU resources when multiple databases run on the same node </li></ul></ul><ul><ul><ul><li>Restricts a database to subset of processors </li></ul></ul></ul>ERP CRM Warehouse Data Mart HR
  65. 66. <Insert Picture Here> Exadata High Availability and Disaster Recovery
  66. 67. Complete, Open, Integrated Availability Maximum Availability Architecture <ul><li>Protection from </li></ul><ul><ul><li>Server Failures </li></ul></ul><ul><ul><li>Storage Failures </li></ul></ul><ul><ul><li>Network Failures </li></ul></ul><ul><ul><li>Site Failures </li></ul></ul><ul><li>Real-time remote standby open for queries </li></ul><ul><li>Human error correction </li></ul><ul><ul><li>Database, table, row, transaction level </li></ul></ul><ul><li>Online indexing and table redefinition </li></ul><ul><li>Online patching and upgrades </li></ul>WAN Real Application Clusters ASM Fast Recovery Area Active Data Guard Secure Backup
  67. 68. Active Data Guard and Low Cost DR Either Physical or Logical Standbys Can Be Opened Primary database Standby database Exadata Racks with SAS disks Exadata Rack with SATA disks Redo transport Oracle Net Backups Reporting
  68. 69. <Insert Picture Here> Exadata and Oracle Enterprise Manager
  69. 70. Exadata Storage Management & Administration <ul><li>Enterprise Manager </li></ul><ul><ul><li>Manage & administer Database and ASM </li></ul></ul><ul><li>Exadata Storage Plug-in </li></ul><ul><ul><li>Enterprise Manager Grid Control Plug-in to monitor & manage Exadata Storage Cells </li></ul></ul><ul><li>Comprehensive CLI </li></ul><ul><ul><li>Local Exadata Storage cell management </li></ul></ul><ul><ul><li>Distributed shell utility to execute CLI across multiple cells </li></ul></ul><ul><li>Sun Embedded Integrated Lights Out Manager (ILOM) </li></ul><ul><ul><li>Remote management and administration of hardware </li></ul></ul>
  70. 71. Exadata Storage Plug-in <ul><li>Enterprise Manager Grid Control Plug-in to monitor & manage Exadata Storage Cells </li></ul><ul><li>Works with Enterprise Manager Grid Control 10.2.0.3 and later versions </li></ul>
  71. 72. Conclusion
  72. 73. Sun Oracle Database Machine Extreme Performance for all Data Management <ul><li>Best for Data Warehousing </li></ul><ul><ul><li>Parallel query on memory or Flash </li></ul></ul><ul><ul><ul><li>Compressed 4TB of data in DRAM, 50 TB in flash </li></ul></ul></ul><ul><ul><li>10x compressed tables with storage offload </li></ul></ul><ul><ul><li>Overall up to 5X faster than 11.1 for Warehousing </li></ul></ul><ul><li>Best for OLTP </li></ul><ul><ul><li>Only database that scales real-world applications on grid </li></ul></ul><ul><ul><li>Smart flash cache provides 1 million IOs per second </li></ul></ul><ul><ul><ul><li>Compressed 1.2 TB of data in DRAM, 15 TB in Flash </li></ul></ul></ul><ul><ul><li>Up to 50x compression for archival data </li></ul></ul><ul><ul><li>Secure, fault tolerant </li></ul></ul><ul><li>Best for Database Consolidation </li></ul><ul><ul><li>Only database machine that runs and scales all workloads </li></ul></ul><ul><ul><li>Predictable response times in multi-database, multi-application, multi-user environments </li></ul></ul>
  73. 74. Scale Both Performance and Capacity <ul><li>Scalable </li></ul><ul><ul><li>Scales to 8 rack database machine by just adding wires </li></ul></ul><ul><ul><ul><li>More with external InfiniBand switches </li></ul></ul></ul><ul><ul><li>Scales to hundreds of storage servers </li></ul></ul><ul><ul><ul><li>Multi-petabyte databases </li></ul></ul></ul><ul><li>Redundant and Fault Tolerant </li></ul><ul><ul><li>Failure of any component is tolerated </li></ul></ul><ul><ul><li>Data is mirrored across storage servers </li></ul></ul>
  74. 75. Fastest Time to Value & Lowest Risk Time to Database Available for Use Build From Scratch with Components OWI Reference Configurations Take delivery of Sun Oracle Database Machine Weeks to Months Pre-implementation System sizing Acquisition of components Installation and configuration Acquisition of components Installation and configuration Testing and Validation Testing and Validation Weeks to Months Sun Oracle Database Machine <ul><li>Faster deployment </li></ul><ul><li>Lower Risk </li></ul><ul><li>Database pre-configured </li></ul>< 1 Week after Delivery Time To ROI / Level of Risk
  75. 76. Resources <ul><li>Oracle.com: http://www.oracle.com/exadata </li></ul><ul><li>Oracle Exadata Technology Portal on OTN: http://www.oracle.com/technology/products/bi/db/exadata </li></ul><ul><li>Oracle Exadata white papers: http://www.oracle.com/technology/products/bi/db/exadata/pdf/exadata-technical-whitepaper.pdf </li></ul><ul><li>http://www.oracle.com/technology/products/bi/db/exadata/pdf/migration-to-exadata-whitepaper.pdf </li></ul>

×