oracle exadata product overview ow

Exadata BenefitsExtreme Performance10X to 100X speedup for data warehousingMore pipes to data Massively parallel architectureWider pipes to data 5X faster than conventional storageShip less data through the pipes Process data in storageUnlimited ScalabilityLinear Scaling of Data BandwidthTransaction/Job level Quality of ServiceMission Critical Availability and ProtectionDisaster recovery, backup, point-in-time recovery, data validation, encryption

The Performance ChallengeStorage Data Bandwidth BottleneckCurrent warehouse deployments often have bottlenecks limiting the movement of data from disks to serversStorage Array internal bottlenecks on processors and Fibre Channel LoopsLimited Fibre Channel host bus adapters in serversUnder configured and complex SANsPipes between disks and servers are 10x to 100x too slow for data size

Solutions To Data Bandwidth BottleneckAdd more pipes Massively parallel architectureMake the pipes wider 5X faster than conventional storageShip less data through the pipes Process data in storage

Exadata A New ArchitectureBreaks Data Bandwidth BottleneckExadata Ships Less Data Through PipesQuery processing is moved into storage to dramatically reduce data sent to servers while offloading server CPUs

Exadata has More PipesModular storage cell building blocks organized into Massively Parallel Grid Bandwidth scales with capacity

Exadata has Bigger PipesInfiniBand interconnect transfers data 5x faster than Fibre ChannelExadata Moves a Lot Less Data a Lot Faster

Oracle Exadata Storage ServerOptimized Storage Product for the Oracle DatabaseExtreme I/O and SQL Processing performance for data warehousingCombination of hardware and softwareHardware bySoftware by

HP Exadata Storage Server HardwareBuilding block of massively parallel Exadata Storage GridUp to 1GB/sec data bandwidth per cellHP DL180 G52 Intel quad-core processors8GB RAMDual-port 4X DDR InfiniBand card12 SAS or SATA disksSoftware pre-installedOracle Exadata Storage Server SoftwareOracle Enterprise LinuxHP Management SoftwareHardware Warranty3 YR Parts/3 YR Labor/3 YR On-site 24X7, 4 Hour responseExadata Storage ServerRacked Exadata Storage Servers

HP Exadata Storage Server Hardware Details

8 GB DRAMRedundant 110/220V Power Supplies2 Intel Xeon Quad-core Processors 12 x 3.5 Disk Drives Included Software: Oracle Exadata Storage Server Software Oracle Enterprise Linux HP Management Software

Scalable

Massively Parallel Storage GridStorage cells are organized into a massively parallel storage grid

ScalableScales to hundreds of storage cellsData automatically distributed across cells by ASMTransparently redistributed when cells are added or removedData bandwidth scales linearly with capacity

AvailableData is mirrored across cellsFailure of disk or cell transparently tolerated

SimpleWorks transparently - no application changesExadata bandwidth scales linearly with capacity

Exadata Performance ScalesExadata delivers brawny hardware for use by Oracles brainy software

Performance scales with size

ResultMore business insightBetter decisionsImproved competitivenessTable Scan TimeTable Size1TB10 TB100TB1 Hour10 Hour5 HourTypical WarehouseExadata

HP Oracle Database MachinePre-Configured High Performance Data Warehouse8 DL360 Oracle Database servers2 quad-core Intel Xeon, 32GB RAMOracle Enterprise LinuxOracle RAC14 Exadata Storage Cells (SAS or SATA) Up to 14 TB uncompressed user data on SASUp to 46 TB uncompressed user data on SATA4 InfiniBand switches1 Gigabit Ethernet switchKeyboard, Video, Mouse (KVM) hardwareHardware Warranty3 YR Parts/3 YR Labor/3 YR On-site 24X7, 4 Hour response timeAdd more racks for unlimited scalability

Exadata ConfigurationEach Exadata Cell is a self-contained server which houses disk storage and runs the Exadata softwareDatabases are deployed across multiple Exadata CellsDatabase enhanced to work in cooperation with Exadata intelligent storageNo practical limit to number of Cells that can be in the grid

Exadata Architecture

Smart Scan Offload ProcessingExadata storage cells implement smart scans to greatly reduce the data that needs to be processed by database hostsOffload predicate evaluationOnly return relevant rows and columns to hostJoin filteringIncremental backup filteringFile creation

Data reduction is usually very large10x data reduction is common

Completely transparentEven if cell or disk fails during a query

Smart Scan Example:Telco wants to identify customers that spend more than $200 on a single phone callThe information about these premium customers occupies 2MB in a 1 terabyte table

Traditional Scan ProcessingWith traditional storage, all database intelligence resides in the database hostsVery large percentage of data returned from storage is discarded by database servers Discarded data consumes valuable resources, and impacts the performance of other workloadsI/Os Executed:1 terabyte of data returned to hostsDB Host reduces terabyte of data to 1000 customer names that are returned to clientRows ReturnedSELECT customer_name FROM calls WHERE amount > 200;Table Extents IdentifiedI/Os Issued

Exadata Smart Scan ProcessingOnly the relevant columns customer_nameand required rows where amount>200are are returned to hosts

CPU consumed by predicate evaluation is offloaded

Moving scan processing off the database host frees host CPU cycles and eliminates massive amounts of unproductive messagingReturns the needle, not the entire hay stack2MB of data returned to serverRows ReturnedSmart Scan Constructed And Sent To CellsSmart Scan identifies rows and columns within terabyte table that match requestConsolidated Result Set Built From All CellsSELECT customer_name FROM calls WHERE amount > 200;

Additional Smart Scan FunctionalityJoin filteringStar join filtering is performed within Exadata storage cellsDimension table predicates are transformed into filters that are applied to scan of fact tableExample - Select total sales of all Italian winesItems are scanned to identify Item numbers of Italian wineThe Item numbers are used to create a Bloom filter This filter is applied by the cells during the scan of Sales table to identify sales of Italian winesBackupsI/O for incremental backups is much more efficient since only changed blocks are returnedCreate Tablespace (file creation)Formatting of tablespace extents eliminates the I/O associated with the creation and writing of tablespace blocks

Exadata Storage GridI/O Resource ManagementWith traditional storage,creating a managing shared storage is hampered by the inability to balance the work between users on the same database or on multiple databases sharing the storage subsystemHardware isolation is the approach to ensure separation

Exadata I/O resource management ensures user defined SLAs are metCoordination and prioritization between different groups/classes of work within a database and between databases

Exadata I/O Resource ManagementDW and Mixed Workload EnvironmentsEnsure different users and tasks within a database are allocated the correct relative amount of I/O bandwidthFor example: Interactive: 50% of I/O resourcesReporting: 30% of I/O resourcesETL: 20% of I/O resources

Exadata I/O Resource ManagementMulti-Database OLTP EnvironmentEnsure different databases are allocated the correct relative amount of I/O bandwidthDatabase A: 33% I/O of resourcesDatabase B: 67% I/O of resourcesEnsure different users and tasks within a database are allocated the correct relative amount of I/O bandwidthDatabase A: Reporting: 60% of I/O resourcesETL: 40% of I/O resourcesDatabase B: Interactive: 30% of I/O resourcesBatch: 70% of I/O resources

Exadata Scale-Out Storage GridDynamic virtualized storage resources using Automatic Storage Management (ASM)Simple and non-intrusive resource allocation, and reallocation, enabling true enterprise grid storage Database work spread across storage resources for optimal performance Powerful storage allocation options and managementFlexible configuration for performance and availability

Exadata Storage Layout ExampleCell DisksCell Disk is the entity that represents a physical disk residing within a Exadata Storage CellAutomatically discovered and activatedExadata CellExadata Cell

Exadata Storage Layout Example Grid DisksCell Disks are logically partitioned into Grid DisksGrid Disk is the entity allocated to ASM as an ASM diskMinimum of one Grid Disk per Cell DiskCan be used to allocate hot, warm and cold regions of a Cell Disk or to separate databases sharing Exadata CellsExadata CellExadata Cell

Exadata Storage Layout Example ASM Disk Groups and MirroringTwo ASM disk groups definedOne for the active, or hot portion, of the database and a second for the cold or inactive portionASM striping evenly distributes I/O across the disk groupASM mirroring is used protect against disk failuresOptional for one or both disk groupsExadata CellExadata Cell

Exadata Storage Layout Example ASM Mirroring and Failure GroupsASM mirroring is used protect against disk failuresASM failure groups are used to protect against cell failuresExadata CellExadata CellASMDisk Group

Exadata Storage Management & AdministrationEnterprise Manager Manage & administer Database and ASM Exadata Storage Plug-inEnterprise Manager Grid Control Plug-in to monitor & manage Exadata Storage CellsComprehensive CLILocal Exadata Storage cell management Distributed shell utility to execute CLI across multiple cellsLights-out 100Remote management and administration of hardware

Data Protection SolutionsAll single points of failure eliminated by the Exadata Storage architectureHardware Assisted Resilient Data (HARD) built in to Exadata StoragePrevent data corruption before it happensData Guard provides disaster protection and data corruption protection Automatically maintained second copy of databaseFlashback provides human error protectionSnapshot-like capabilities to rewind database to before errorRecovery Manager (RMAN) provide backup to diskArchiving and corruption protectionCan be used with Oracle Secure Backup (OSB) or third party tape backup software These work just as they do for traditional non-Exadata storageUsers and database administrator use familiar tools

Exadata Co-Existence and MigrationDatabases can be concurrently deployed on Exadata and traditional storageTablespaces can exist on Exadata storage, traditional storage, or a combination of the two, and is transparent to database applicationsSQL offload processing requires all pieces of a tablespace reside on Exadata Online migration if currently using ASM and ASM redundancyMigration can be done using RMAN or Data Guard

Telco Exadata Speedup 10X to 72X28xAverageSpeedup

Retailer Exadata Speedup 3x to 50x16xAverageSpeedup

summary

Qry #Queryprod in secssage in secs% improvement

10Materialized Views Rebuild148.003.004933.33%

13.3OBI-EE: Supply Chain Vendor - Year - Item Movement (YAGO - Extended Pricing)733.0016.004581.25%

13.2OBI-EE: Supply Chain Vendor - Year - Item Movement (YAGO - Extended Pricing & RSC Info)732.0018.004066.67%

13.4OBI-EE: Supply Chain Vendor - Year - Item Movement (current/Extended Pricing)733.0024.003054.17%

11.1.5OBI-EE: Merchandising Level 1 Detail: Current - 52 weeks - parallel 8166.736.642510.99%

13.1OBI-EE: Supply Chain Vendor - Year - Item Movement (current/Extended Pricing & RSC Info)732.0036.002033.33%

11.1.1OBI-EE: Merchandising Level 1 Detail: Current - 4 weeks47.892.431970.78%

1Recall Query562.0033.001703.03%

11.2.1OBI-EE: Merchandising Level 1 Detail: Period Ago - 4 weeks53.093.151685.40%

7Query for Ben Moravitz214.0013.001646.15%



11.2.5OBI-EE: Merchandising Level 1 Detail: Period Ago - parallel 8120.0410.201176.86%



11.1.6OBI-EE: Merchandising Level 1 Detail: Current - parallel 1673.046.641100.00%

11.2.6OBI-EE: Merchandising Level 1 Detail: Period Ago - parallel 1692.358.681063.94%

5Prompt04 Clone for ACL audit402.0039.001030.77%



4Sales and Customer Counts513.0075.00684.00%

12.1OBI-EE: Merchandising Level 1 Detail by Week: Current - 4 weeks19.003.00633.33%

12.2OBI-EE: Merchandising Level 1 Detail by Week: Period Ago - 4 weeks19.003.00633.33%

9.6Date to Date Movement Comparison - 53 weeks - paralllel6385.701215.40525.40%

9.7Date to Date Movement Comparison - 53 weeks - parallel6256.301257.00497.72%

9.3Date to Date Movement Comparison - 16 weeks1745.90399.20437.35%

6Kim Smith request394.0096.00410.42%




2Gift Card Activations55.0019.00289.47%


Chart3

1483

73316

73218

73324

166.736.64

73236

47.892.43

56233

53.093.15

21413

472.6531.65

108.817.89

120.0410.2

176.5615.65

116.4810.51

73.046.64

92.358.68

40239

191.9320.89

365.745.43

51375

193

193

prod in secs

sage in secs

Chart5

1483

73316

73218

73324

166.736.64

73236

47.892.43

56233

53.093.15

21413

472.6531.65

108.817.89

120.0410.2

176.5615.65

116.4810.51

73.046.64

92.358.68

40239

191.9320.89

365.745.43

51375

193

193

prod in secs

sage in secs

Queries

CodeNameQuerytablesrequestor

Q1Recall QuerySELECT DISTINCT str_no , tx_dte_tme , trml_no , tx_no , loyal_card_no , hshld_no , mem_no , mem_fst_nme , mem_lst_nme , ph_noFROM ( SELECT DISTINCT str_no , tx_dte_tme , trml_no , m.loyal_card_no , m.hshld_nodwa001.retail_transaction_detail dwa001.retail_itemdwp005.MEMBER_CARD_LAST_MVBob George

Q2Gift Card Activations/* Formatted on 2008/07/21 12:55 (Formatter Plus v4.8.8) */SELECT wk_end_dte, retailer_nme AS prtnr_name, upc, scan_dscr, day_no, SUM (sales) AS sales, SUM (card_cnt) AS card_cnt, 'A' AS typ FROM (SELECT /*+ PARALLEL(t2,12) */dwp001.giftcard_activation_aggrdwa001.giftcard_retailerdwp005.retail_item_upc_last_mvdwa001.calendardwa001.calendar_weekdwa001.calendar_week_daydwa001.giftcard_retailerdwa001.giftcard_fee_commissiondwp005.retail_item_upc_last_mvTerri Boyt

Q3Getgo TransactionsSELECT TO_CHAR (rbd.tx_dte_tme, 'Day') AS tx_dte, rbd.str_no, rbd.hr_no, t.trml_dscr, t.trml_loc_cd--, rbd.tx_no , count(distinct rbd.tx_dte_tme||rbd.str_no||rbd.tx_no||rbd.trml_no) as txs FROM retail_baskedwp001.retail_basket_detaildwg001.terminalJamie Baleno for Jim Claypoole

Q4Sales and Customer CountsSELECT str_no ,wk_end ,SUM (sales_count) AS SALES_COUNT ,SUM (CUS_COUNT) AS CUS_COUNTFROM (SELECT str_no ,CASE WHEN TYPE = 'SALES' THEN SUM (sls)dwp001.retail_basket_detail dwp005.store_last_mv dwa001.retail_transactionRon Sullivan

Q5Prompt04 Clone for ACL audit/* Formatted on 06/19/2008 09:27 AM (Formatter Plus v4.8.8) (DW Options Version 0)*/SELECT T.po_no ,T.rcpt_no ,T.rcpt_sfx ,T.rcv_dte ,T.po_ord_dte ,T.status ,T.rsc_no ,T.inv_no ,T.vend_no ,T.ap_vend_nRob Canavan

Q6Kim Smith requestSELECT str_no ,trml_no ,SUM(sunday_count) AS sun_basket_count ,SUM(monday_count) AS mon_basket_countdwa001.retail_transaction dwa001.retail_transaction_detailDoug Baughman

Q7Query for Ben MoravitzSELECT str_no ,tndr_typ_cd ,tndr_vrty_cd ,fuel_prod_cd ,SUM(gallons) AS gallons FROM (SELECT /*+ use_hash(rtd tv trans fu) */ rtd.str_no ,NVL(rtd.tndr_typ_cd,dwg001.fuel_upc dwg001.tender_variety dwa001.retail_tender_detail dwa001.retail_transaction_detailDoug Baughman

Q8member_card_last_mv querySELECT m.MEM_ID ,m.HSHLD_ID ,m.HSHLD_NO ,m.LEGACY_MEM_ID ,mc.CARD_NO ,SUBSTR (mc.CARD_NO, 1, LENGTH (mc.CARD_NO) - 1) AS loyal_card_no ,m.MEM_NME_PFX ,m.MEM_FST_NME ,m.MEM_MI ,m.MEM_LST_NME ,m.MEdwp005.MEMBER_LAST_MV dwp005.HOUSEHOLD_LAST_MV dwa001.MEMBER_CARDBob George

Q9the Date to Date Movement ComparisonSELECT cat_cd, grp_cd, sgrp_cd, upc, whitem_no, item_sz, str_pak, item_dscr, d_cost, SUM (pkg_qty) AS ty_pkg_qty, SUM (ly_pkg_qty) AS ly_pkg_qty, SUM (pkg_qty) - SUM (ly_pkg_qty) AS pkg_qty_chg, DECODE (SUM (ly_pkg_qty),dwp005.financial_bs_store_last_mv dwp005.retail_item_upc_last_mv dwp001.retail_item_movement_week dwp005.whsl_item_last_mvJoe Roche

Q10MVsselect T30742.FULL_NME_LVL7 as c1,T30856.NEW_WK_DTE as c2,sum(T27405.TOT_EXTD_PRC) as c3,sum(case when nvl(T27405.TOT_UOM_QTY , 0) = 0 then T27405.TOT_PKG_QTY else T27405.TOT_UOM_QTY end ) as c4fromDWP005.BI_MRCH_HIERARCHY_PERSONNEL_MV T30742,DWP005

Q11.1OBI-EE: Merchandising Level 1 Detail: Currentselect T496274.FULL_NME_LVL7 as c1, T491099.NEW_WK_DTE as c2, sum(T496806.TOT_EXTD_PRC) as c3, sum(case when nvl(T496806.TOT_UOM_QTY , 0) = 0 then T496806.TOT_PKG_QTY else T496806.TOT_UOM_QTY end ) as c4from DWP005.CALENDAR_WEEK_PLUDWP005.CALENDAR_WEEK_PLUS_MVDWP005.BI_MRCH_HIERARCHY_PERSONNEL_MVDWP001.RETAIL_SUBGROUP_MOVEMENT_WEEKThomas Dodds

Q11.2OBI-EE: Merchandising Level 1 Detail: "ago"select T496274.FULL_NME_LVL7 as c1, T491099.NEW_WK_DTE as c2, sum(T496752.TOT_EXTD_PRC) as c3, sum(case when nvl(T496752.TOT_UOM_QTY , 0) = 0 then T496752.TOT_PKG_QTY else T496752.TOT_UOM_QTY end ) as c4from DWP005.BI_MRCH_HIERARCHYDWP005.BI_MRCH_HIERARCHY_PERSONNEL_MVDWP005.CALENDAR_WEEK_PLUS_MVDWP001.RETAIL_SUBGROUP_MOVEMENT_WEEKThomas Dodds

Q12.1select T496274.FULL_NME_LVL7 as c1, sum(T496806.TOT_EXTD_PRC) as c2, sum(case when nvl(T496806.TOT_UOM_QTY , 0) = 0 then T496806.TOT_PKG_QTY else T496806.TOT_UOM_QTY end ) as c3from DWP005.CALENDAR_WEEK_PLUS_MV T491099, DWP005.BI_MRDWP005.CALENDAR_WEEK_PLUS_MVDWP005.BI_MRCH_HIERARCHY_PERSONNEL_MVDWP001.RETAIL_SUBGROUP_MOVEMENT_WEEKThomas Dodds

Q12.2OBI-EE: Merchandising Level 1 Detail by Week: "ago"select T496274.FULL_NME_LVL7 as c1, sum(T496752.TOT_EXTD_PRC) as c2, sum(case when nvl(T496752.TOT_UOM_QTY , 0) = 0 then T496752.TOT_PKG_QTY else T496752.TOT_UOM_QTY end ) as c3from DWP005.BI_MRCH_HIERARCHY_PERSONNEL_MV T496274, DWPDWP005.BI_MRCH_HIERARCHY_PERSONNEL_MVDWP005.CALENDAR_WEEK_PLUS_MVDWP001.RETAIL_SUBGROUP_MOVEMENT_WEEKThomas Dodds

Q13.1OBI-EE: Supply Chain Vendor - Year - Item Movement (current/Extended Pricing & RSC Info)select T496121.RSC_NO as c3, T496806.TOT_EXTD_PRC as c5, T496121.RSC_DSCR as c6from DWP005.RSC_HIERARCHY_MV T496121, DWP005.CALENDAR_WEEK_PLUS_MV T491099, DWA001.BI_VENDOR_HIERARCHY T496219, DWP001.RETAIL_SUBGROUP_MOVEMENT_DWP005.RSC_HIERARCHY_MVDWP005.CALENDAR_WEEK_PLUS_MVDWA001.BI_VENDOR_HIERARCHYDWP001.RETAIL_SUBGROUP_MOVEMENT_WEEK

Q13.2OBI-EE: Supply Chain Vendor - Year - Item Movement (YAGO - Extended Pricing & RSC Info)select T496121.RSC_NO as c3, T496752.TOT_EXTD_PRC as c5, T496121.RSC_DSCR as c6from DWP005.RSC_HIERARCHY_MV T496121, DWA001.BI_VENDOR_HIERARCHY T496219, DWP005.CALENDAR_WEEK_PLUS_MV T491099, DWP001.RETAIL_SUBGROUP_MOVEMENT_DWP005.RSC_HIERARCHY_MVDWA001.BI_VENDOR_HIERARCHYDWP005.CALENDAR_WEEK_PLUS_MVDWP001.RETAIL_SUBGROUP_MOVEMENT_WEEK

Q13.3OBI-EE: Supply Chain Vendor - Year - Item Movement (YAGO - Extended Pricing)select sum(T496752.TOT_EXTD_PRC) as c1from DWA001.BI_VENDOR_HIERARCHY T496219, DWP005.CALENDAR_WEEK_PLUS_MV T491099, DWP001.RETAIL_SUBGROUP_MOVEMENT_WEEK T496752where ( T491099.NEW_WK_YAGO_DTE = T496752.WK_END_DTE and T496219.BASE = T49DWA001.BI_VENDOR_HIERARCHYDWP005.CALENDAR_WEEK_PLUS_MVDWP001.RETAIL_SUBGROUP_MOVEMENT_WEEK

Q13.4OBI-EE: Supply Chain Vendor - Year - Item Movement (current/Extended Pricing)select sum(T496806.TOT_EXTD_PRC) as c1from DWP005.CALENDAR_WEEK_PLUS_MV T491099, DWA001.BI_VENDOR_HIERARCHY T496219, DWP001.RETAIL_SUBGROUP_MOVEMENT_WEEK T496806where ( T491099.NEW_WK_DTE = T496806.WK_END_DTE and T496219.BASE = T496806.DWP005.CALENDAR_WEEK_PLUS_MVDWA001.BI_VENDOR_HIERARCHYDWP001.RETAIL_SUBGROUP_MOVEMENT_WEEK

Q14High DOP testselect /*+ full(rdp) parallel(rdp,24) */ count(*) from retail_basket_detail rdp where net_prc_fg = 'Y'

Q

Simplified Chart

17.0303030303

2.8947368421

6.84

10.3076923077

4.97716786

49.3333333333

6.3333333333

30.5416666667

25.109939759

10.6394009217

Improvement

Simplified Data

Qry #QueryImprovementprod in secssage in secs

1Recall Query17.0562.0033.00

2Gift Card Activations2.955.0019.00

4Sales and Customer Counts6.8513.0075.00

5Prompt04 Clone for ACL audit10.3402.0039.00

9.7Date to Date Movement Comparison - 53 weeks5.06256.301257.00

10Materialized Views Rebuild49.3148.003.00

12.2Merchandising Level 1 Detail by Week6.319.003.00

13.4Supply Chain Vendor - Year - Item Movement30.5733.0024.00

11.1.5Merchandising Level 1 Detail: Current - 52 weeks25.1166.736.64

11.2.6Merchandising Level 1 Detail: Period Ago10.692.358.68

Exadata BenefitsExtreme Performance10X to 100X speedup for data warehousingMore pipes to data Massively parallel architectureWider pipes to data 5X faster than conventional storageShip less data through the pipes Process data in storageUnlimited ScalabilityLinear Scaling of Data BandwidthTransaction/Job level Quality of ServiceMission Critical Availability and ProtectionDisaster recovery, backup, point-in-time recovery, data validation, encryption

Exadata Talks At OpenWorldFour Exadata Talks on Thursday 9/25/200809:00 - 10:00 (session S298677)Moscone South Room 103Oracles New Database Accelerator: Query Processing RevolutionizedJuan Loaiza, Oracle12:00 - 13:00 (session S298679)Moscone South Room 305Oracles New Database Accelerator: Query Processing RevolutionizedJuan Loaiza, Oracle13:30 - 14:30 (session S298680)Moscone South Room 305Oracles New Database Accelerator: Query Processing RevolutionizedJuan Loaiza, Oracle15:00 - 16:00 (session S298681)Moscone South Room 305Oracles New Database Accelerator: A Technical OverviewKodi Umamageswaran, Oracle; Ron Weiss, Oracle

Exadata Demos At OpenWorldThree Demo and Q&A LocationsMoscone North LobbyLive Demonstration, Hardware, Software, and Q&AHP Booth Exhibit FloorLive Demonstration, Hardware, Software, and Q&AOracle Campground Demo Moscone West (pod L35)Q&A

AQ&

An Oracle Exadata Storage Grid is a storage product highly optimized for use with the Oracle database. Exadata Storage delivers extreme I/O and SQL processing for data warehousing applications.

The Exadata Storage Grid is a massively parallel architecture comprising on Oracle Exadata Storage Cells. The Exadata Storage Cell is a combination of hardware and software. The hardware is provided by HP and the The Infiniband cards are also capable of running 10g Ethernet. We are only certifying Infiniband initially, but the possibility exists of running 10gE in the future.Oracle's Hardware Assisted Resilient Data (HARD) Initiative is a comprehensive program designed to prevent data corruptions before they happen. Data corruptions are very rare, but when they happen, they can have a catastrophic effect on a database, and therefore a business.

Exadata has enhanced HARD functionality embedded in it to provide even higher levels of protection and end-to-end data validation for your data. Exadata performs extensive validation of the data stored in it including checksums, block locations, magic numbers, head and tail checks, alignment errors, etc.

Implementing these data validation algorithms within Exadata will prevent corrupted data from being written to permanent storage. Furthermore, these checks and protections are provided without the manual steps required when using HARD with conventional storage.

oracle exadata product overview ow

Documents

data validation

data sizesolutions

movement of data

gbsec data bandwidth

data bandwidth bottleneckadd

pipes process data

data warehousingmore

pipesmodular storage