1. TPC - E TPC-E Benchmark Overview TPC-PR Subcommittee Feb 2007 © 2007 TPC

2. TPC - E TPC-E Goals OLTP Database-centric workload Comparability of results (*) Familiar business model – easy to understand Reduce cost/complexity of running benchmark Enhance schema complexity Encourage DB uses which are more representative of what customers do Address aspects of PDG (*) TPC-E results are intended for OLTP database testing and are not an indicator for past or future market performance, nor should they be used as such.

3. TPC - E Stock Exchange Brokerage House Customers Synchronous Txns C2B Environment Customer Initiated Request a Trade Check Status of Trade Portfolio Summary Asynchronous Txns B2B Environment Send Trade to Market Receive Trade Result Ticker Feed Customer Request Brokerage Response Customer Request Brokerage Response Brokerage Request Brokerage Request Market Response Market Response Ticker Feed Business Model – Financial Market

4. TPC - E DRIVER SUT Stock Exchange Brokerage House Customers Ticker Feed Customer Request Brokerage Response Customer Request Brokerage Response Brokerage Request Brokerage Request Market Response Market Response Ticker Feed Business Model – Financial Market

5. TPC - E Business Model – Comparison TPC-C Wholesale supplier Organized by Warehouses Districts Customers TPC-E Brokerage house Organized by Customers Accounts Securities

6. TPC - E Database Tables

7. TPC - E Database Scaling

8. TPC - E CharacteristicTPC-ETPC-C Tables339 Columns18892 Min Cols / Table23 Max Cols / Table2421 Data Type CountMany4 Data TypesUID, CHAR, NUM, DATE, BOOL, LOB UID, CHAR, NUM, DATE Primary Keys338 Foreign Keys509 Tables w/ Foreign Keys 277 Check Constraints220 Referential Integrity YesNo Database Schema Summary

9. TPC - E Database – Mile High View Broker Customer Market Dimension

10. TPC - E Database – Content Populated with pseudo-real data Distributions based on: –2000 U.S. and Canada census data (*) Used for generating name, address, gender, etc. Introduces natural data skew –Actual listings on the NYSE and NASDAQ Benefits –Realistic looking data –Compressible for backup testing, etc. –Closer match to actual customer databases –Anticipate usage well beyond benchmark (*) only names of 2000 census have been used – all other data are fictional and any similarities are purely coincidental

11. TPC - E Database – Content C_FIRSTC_MIDDLEC_LASTC_STREET_1C_CITY RONpTGcv5ZBZO8QOEBARBARABLEbR7QLfDBhZPHlyDXsOmWlmelzIJ0GeP kYM e8u6FMxFLtt6p QOEBARBARPRIeEbgKxoIzx99ZTD S4V1t1VmdVcXyoTOMwpPz bTUkSuVQGdXLjGeOEBARBARPRESQCGLjWnsqSQPN D SjVHBwIGFh2k oTOMwpPz 18AEf3ObueKvubUXOEBARBARESEJnBSg4RtZbALYu S5g8XMnlegn oTOMwpPz mFFsJYeYE6AR bUXOEBARBARANTIMLEwwdy3dXfqngFcEyVVR4iEtj0ADEwe wpPz C_TAX_IDC_L_NAMEC_F_NAMEC_M_NAMEC_GNDRC_DOBC_EMAIL_1 757FI2006HD923MexicanoCourtneyTF1997-11-30CMexicano@hotmail.com 922SN3775RQ823UdleyJudithFF1954-09-27JUdley@earthlink.com 006GT3444BE624BuchananJohnRM1971-06-13JBuchanan@msn.com 181UZ4114LR434SolomanClintonDM1938-02-27CSoloman@rr.com 355IE4773VF335OrnerHarryPM1974-11-15Horner@attbi.com Sample data from TPC-E CUSTOMER table Sample data from TPC-C CUSTOMER table

12. TPC - E Database – Content Database creation is vendor specific, but… Database population can be vendor neutral TPC-E includes a data generator for database loading C++ code to generate data MSSQL ODBC interface provided Flat file generation provided Sponsor is free to customize interface

13. TPC - E Transactions - Overview NameSymbolAccessDescription Broker-VolumeBVRODSS-type medium query Customer-PositionCPRO “ What am I worth? ” Market-FeedMFRWProcessing of Stock Ticker Market-WatchMWRO “ What ’ s the market doing? ” Security-DetailSDRODetails about a security Trade-LookupTLROLook up historical trade info Trade-OrderTORWEnter a stock trade Trade-ResultTRRWCompletion of a stock trade Trade-StatusTSROCheck status of trade order Trade-UpdateTURWCorrect historical trade info

14. TPC - E Transactions – Runtime Flow

15. TPC - E “Real-world” basis for TPC-E

16. TPC - E Abstraction of “Real-world” Points to remember –Data generator code provide by TPC –PDG requested User Interface not be present –Goal: Database-centric workload

17. TPC - E Functional Components of TPC-E

18. TPC - E Driver & System Under Test (SUT)

19. TPC - E Implementation Details Transaction Harness –Transaction pseudo code provided –C++ class for each transaction –The Harness defines Inputs Outputs Transaction logic “Frames”

20. TPC - E Sample Implementation

21. TPC - E Summary - Highlights Financial business model Rich transaction set Major components provided Diverse, realistic schema Extensive use of non-primary key access Foreign key relationships Complex DML Referential integrity Availability requirements Storage media must be fault tolerant Practical implication: RAID-1 or RAID-5

22. TPC - E Server-centric workload with strong DB focus Broader coverage: database functions, schema, features Realistic application transaction model Ease of benchmarking: quicker startup, lower cost Reduced I/O requirements Comparability of results Realistic database schema, population, and transactions Learns from TPC history Specification provides code where sponsor creativity not being tested Summary - Benefits

23. TPC - E TPC, TPC Benchmark and TPC-C are trademarks of the Transaction Processing Performance Council. All other materials are © 2007 TPC. All rights reserved. Trademarks and Copyright