TPC BENCHMARK (TM) H (779138), страница 23

Просмтор этого файла доступен только зарегистрированным пользователям. Но у нас супер быстрая регистрация: достаточно только электронной почты!

Текст из файла (страница 23)

Any usage pricing for this number of users must bebased on the pricing policy of the company supplying the priced component.7.2Allowable Substitutions7.2.1Substitution is defined as a deliberate act to replace components of the Priced Configuration by the test sponsor as aresult of failing the availability requirements of the TPC Pricing Specification or when the part number for a component changes.Comment 1: Corrections or "fixes" to components of the Priced Configuration are often required during the life ofproducts.

These changes are not considered Substitutions so long as the part number of the priced component doesnot change. Suppliers of hardware and software may update the components of the Priced Configuration, but theseupdates must not impact the reported performance metric or numerical quantities.

The following are not consideredsubstitutions:software patches to resolve a security vulnerabilitysilicon revision to correct errorsnew supplier of functionally equivalent components (i.e. memory chips, disk drives, ...)Durable Medium is defined as a data storage medium that is inherently non-volatile such as a magnetic disk or tape.7.2.2Some hardware components of the Priced Configuration may be substituted after the test sponsor has demonstratedto the auditor's satisfaction that the substituting components do not negatively impact the reported performancemetric or numerical quantities.

All substitutions must be reported in the FDR and noted in the auditor's attestationletter. The following hardware components may be substituted:Durable Medium, Disk Enclosure, external storage controllersNetwork interface cardsRouters, Bridges, Repeaters, SwitchesCablesTPC BenchmarkTM H Standard Specification Revision 2.17.1Page 1068: FULL DISCLOSURERules for reporting Pricing information are included in the TPC Pricing Specification located at www.tpc.org.8.1Reporting Requirements8.1.1A Full Disclosure Report (FDR) in pdf format, Executive Summary and a Supporting Files Archive (zip format)consisting of various source files, scripts, and listing files are required.8.1.2The intent of this disclosure is to simplify comparison between results and for a customer to be able to replicate theresults of this benchmark given appropriate documentation and products.8.2Format Guidelines8.2.1While established practice or practical limitations may cause a particular benchmark disclosure to differ from theexamples provided in various small ways, every effort should be made to conform to the format guidelines.

Theintent is to make it as easy as possible for a reviewer to read, compare and evaluate material in different benchmarkdisclosures.8.2.2All sections of the report, including appendices, must be printed using font sizes of a minimum of 8 points.8.2.3The Executive Summary must be included near the beginning of the full disclosure report.8.3Full Disclosure Report Contents and Supporting Files ArchiveThe FDR should be sufficient to allow an interested reader to evaluate and, if necessary, recreate an implementationof TPC-H. If any sections in the FDR refer to another section of the report (e.g., an appendix), the names of the referenced scripts/programs must be clearly labeled in each section.

Unless explicitly stated otherwise “disclosed”refers to disclosed in the FDR.The “Supporting Files Archive” are compressed files containing a directory tree of all the files required to bedisclosed electronically as part of the FDR. All files must be compressed using the Zip 2.0 standard file formatwithout password protection or encryption. These archives will contain a mix of human readable and machineexecutable code or scripts (i.e., able to be performed by the appropriate program without modification) that arerequired to recreate the benchmark result.

Any machine executable code or scripts requiring compilation must beincluded as source code including any build or compilation flags (e.g., a make file). If there is a choice of using aGUI (Graphical User Interface) or a script, then the machine executable script must be provided in the SupportingFiles Archive. If no corresponding script is available for a GUI, then the Supporting Files Archive must contain adetailed step-by-step description of how to manipulate the GUI (e.g. a PDF document containing screen shots ofeach completed dialog just prior to clicking “ok” with clear instructions on how to bring up each dialog or window).These archives will also contain all the output required to validate the result’s compliance with the specification.The Supporting Files Archive should be split into three separate compressed files.

For the query output data of Q11,Q16, and Q20, the sponsor must report the first and last 1000 rows, 1000 random non-consecutive rows between thefirst and last 1000 rows, and the row number from the respective query output. All output from other queries mustbe provided in their entirety. The sponsor must provide the full query output for the duration of the review periodupon request. All query output data from the 1st run of both the power and throughput tests must be contained in the firstfile named “run1result.zip” All query output data from the 2nd successful run of both the power and throughput tests must be containedin the second file named “run2result.zip”. All other data that is required to be disclosed in the Supporting Files Archive must be contained in the thirdfile named “benchmark_scripts.zip”.If any one compressed file will be greater than 2GB, it must be broken into multiple files, each of which is nogreater than 2GB.

In this case, a sequence number must be appended to the appropriate filename above (e.g.run1result_1.zip, run1result_2.zip).TPC BenchmarkTM H Standard Specification Revision 2.17.1Page 107Comment: Since the building of a database may consist of a set of scripts and corresponding input files, it is important to disclose and clearly identify, by name, scripts and input files in the FDR.The order and titles of sections in the test sponsor's full disclosure report must correspond with the order and titles ofsections from the TPC-H standard specification (i.e., this document).Comment: The purpose of disclosing Supporting Files is to show how the hardware and software is changed fromtheir defaults to reproduce the benchmark result.8.3.1General Items8.3.1.1 A statement identifying the benchmark sponsor(s) and other participating companies must be provided.8.3.1.2 Settings must be provided for all customer-tunable parameters and options that have been changed from the defaultsfound in actual products, including but not limited to:Database tuning options;Optimizer/Query execution options;Query processing tool/language configuration parameters;Recovery/commit options;Consistency/locking options;Operating system and configuration parameters;Configuration parameters and options for any other software component incorporated into the pricing structure;Compiler optimization options.Comment 1: In the event that some parameters and options are set multiple times, it must be easily discernible by aninterested reader when the parameter or option was modified and what new value it received each time.Comment 2: This requirement can be satisfied by providing a full list of all parameters and options, as long as allthose that have been modified from their default values have been clearly identified and these parameters andoptions are only set once.8.3.1.3 Explicit response to individual disclosure requirements specified in the body of earlier sections of this documentmust be provided.8.3.1.4 Diagrams of both measured and priced configurations must be provided, accompanied by a description of the differences.

This includes, but is not limited to:Total number of nodes used, total number and type of processors used/total number of cores used/totalnumber of threads used (including sizes of L2 and L3 caches);Size of allocated memory, and any specific mapping/partitioning of memory unique to the test;Number and type of disk units (and controllers, if applicable);Number of channels or bus connections to disk units, including their protocol type;Number of LAN (e.g., Ethernet) connections, including routers, workstations, terminals, etc., that werephysically used in the test or are incorporated into the pricing structure;Type and the run-time execution location of software components (e.g., DBMS, query processing tools/languages, middleware components, software drivers, etc.).The following sample diagram illustrates a measured benchmark configuration using Ethernet, an external driver,and four processors each with two cores and four threads per node in the SUT.

Note that this diagram does notdepict or imply any optimal configuration for the TPC-H benchmark measurement.Figure 1: Sample Configuration Diagram (the front system box describes one node)TPC BenchmarkTM H Standard Specification Revision 2.17.1Page 108LAN: Ethernet using NETplus routersTotal number of nodes used/total number of processors used/total number of cores used/total number of threadsused:4/16/32/64 x a243DX 3GHz with 4 MByte Second Level Cache4 gigabyte of main memory16 x SCSI-2 Fast ControllersDisk: 96 x 2.1 gigabyte SCSI-2 drivesComment: Detailed diagrams for system configurations and architectures can vary widely, and it is impossible toprovide exact guidelines suitable for all implementations.

The intent here is to describe the system components andconnections in sufficient detail to allow independent reconstruction of the measurement environment. This examplediagram shows homogeneous nodes. This does not preclude tests sponsors from using heterogeneous nodes as longas the system diagram reflects the correct system configuration.8.3.2Supporting Files Index Table8.3.2.1 An index for all files and/or directories included in the Supporting Files Archive as required by Clauses 8.3.2through 8.3.8 must be provided in the report. The “Supporting Files Index Table” is presented in a tabular formatwhere the columns specify the following:The first column denotes the clause in the TPC-H SpecificationThe second column provides a short description of the file(s) and/or directory(s) contents.The third column contains the zip filename(s) containing this file(s) or directory(s).The fourth column contains the pathname for the file(s) or directory(s) starting at the root of the archive.Patterns and/or wildcards may be used to specify multiple files or directories.If there are no supporting files or directories provided then the description column must indicate that there is nosupporting file and the pathname column must be left blank8.3.2.2 The following table is an example of the Supporting Files Index Table that must be reported in the Report.ClauseClause 1Clause 2DescriptionArchive FilePathnamePartitioning scriptsbenchmark_scripts.zipSupportingFiles/Clause1/Partitioning/OS Tunable Parametersbenchmark_scripts.zipSupportingFiles/Clause1/OStune.txtQGEN Modificationsbenchmark_scripts.zipSupportingFiles/Clause2/QGEN.txtMinor querymodificationsbenchmark_scripts.zipSupportingFiles/Clause2/MinorQuery.txtTPC BenchmarkTM H Standard Specification Revision 2.17.1Page 109Clause 3Clause 4Code Style Usagebenchmark_scripts.zipSupportingFiles/Clause2/CodeStyle.txtACID Test scriptsbenchmark_scripts.zipSupportingFiles/Clause3/ACIDScripts/ACID Test Resultsbenchmark_scripts.zipSupportingFiles/Clause3/ACIDResults/Qualification dbdifferencesbenchmark_scripts.zipDBGEN Modificationsbenchmark_scripts.zipSupportingFiles/Clause4/DBGEN.txtDatabase Load Scriptsbenchmark_scripts.zipSupportingFiles/Clause4/Load.txtData Transfer Programsbenchmark_scripts.zipSupportingFiles/Clause4/DataTransfer/run1results.zipSupportingFiles/Clause5/QueryOutput/Run1/SupportingFiles/Clause5/QueryOutput/Run2/Query Output Resultsrun2results.zipSession ImplementationConfigurationbenchmark_scripts.zipPDO Proceduresbenchmark_scripts.zipSteps performedbetween end of Loadand start of PerformanceRun.benchmark_scripts.zipClause 6Implementation Specificlayer source codebenchmark_scripts.zipClause 7There are no filesrequired to be includedfor Clause 7.Clause 5Clause 88.3.3SupportingFiles/Clause4/QualResults/SupportingFiles/Clause5/Session.txtSupportingFiles/Clause5/PDO.txtSupportingFiles/Clause5/EOLStart.txtn/aHorizontal Partitioningscriptsbenchmark_scripts.zipExecutable query testbenchmark_scripts.zipQuery substitutionparameters and seedsbenchmark_scripts.zipRF function source codebenchmark_scripts.zipSupportingFiles/Clause6/ImplementationSource/n/aSupportingFiles/Clause8/HorizontalPart.txtSupportingFiles/Clause8/QueryText.txtSupportingFiles/Clause8/QueryParmsSeeds.txtSupportingFiles/Clause8/RFfunctionsource/Clause 1 - Logical Database Design Related Items8.3.3.1 Listings must be provided for all table definition statements and all other statements used to set-up the test and qualification databases.

Характеристики

Список файлов книги