Apache Spark TPC-H 1.0.0

pts/spark-tpch-1.0.0 - 04 December 2023 - Add Apache Spark TPC-H benchmark.

downloads.xml

<?xml version="1.0"?>
<!--Phoronix Test Suite v10.8.4-->
<PhoronixTestSuite>
  <Downloads>
    <Package>
      <URL>https://archive.apache.org/dist/spark/spark-3.5.0/spark-3.5.0-bin-hadoop3.tgz</URL>
      <MD5>4a3b0cfc251827d78ff468db7016f2ee</MD5>
      <SHA256>ac064ec620129b4b9630e180e25ac2b71a8ccd4c6912bf5b5631943b742f0379</SHA256>
      <FileName>spark-3.5.0-bin-hadoop3.tgz</FileName>
      <FileSize>400395283</FileSize>
    </Package>
    <Package>
      <URL>https://github.com/ssavvides/tpch-spark/archive/7d64aa57368f092969a855fdd10781c00813c9c4.zip</URL>
      <MD5>1f981d33ba100fc31c51204156037bab</MD5>
      <SHA256>55a82833b0e76e77c1d0bc95ff3a04f5c9bee9b8bc02a5c64193ad4cbc9e4a0b</SHA256>
      <FileName>tpch-spark-7d64aa57368f092969a855fdd10781c00813c9c4.zip</FileName>
      <FileSize>1705811</FileSize>
    </Package>
    <Package>
      <URL>https://github.com/sbt/sbt/releases/download/v1.9.7/sbt-1.9.7.zip</URL>
      <MD5>9e4cdee25e6076a78810f02f0bda77ef</MD5>
      <SHA256>74f36c2b044b63f3a24300b8e32eea20afc462b16974bf13f6e393a64530116d</SHA256>
      <FileName>sbt-1.9.7.zip</FileName>
      <FileSize>47154988</FileSize>
    </Package>
  </Downloads>
</PhoronixTestSuite>

install.sh

#!/bin/sh
tar -xf spark-3.5.0-bin-hadoop3.tgz
unzip -o tpch-spark-7d64aa57368f092969a855fdd10781c00813c9c4.zip
unzip -o sbt-1.9.7.zip
export PATH=$HOME/spark-3.5.0-bin-hadoop3/bin:$HOME/sbt/bin:$PATH
# Avoid out of memory errors
echo "spark.driver.memory              16g
spark.executor.memory              16g" > ~/spark-3.5.0-bin-hadoop3/conf/spark-defaults.conf
cd tpch-spark-7d64aa57368f092969a855fdd10781c00813c9c4/dbgen/
make
cd ~/tpch-spark-7d64aa57368f092969a855fdd10781c00813c9c4/
sbt package
echo $? > ~/install-exit-status
cd ~
echo "#!/bin/bash
export PATH=\$HOME/spark-3.5.0-bin-hadoop3/bin:\$PATH
cd tpch-spark-7d64aa57368f092969a855fdd10781c00813c9c4/
rm -f tpch_execution_times.txt
spark-submit --class \"main.scala.TpchQuery\" target/scala-2.12/spark-tpc-h-queries_2.12-1.0.jar > \$LOG_FILE 2>&1
echo \$? > ~/test-exit-status
cat tpch_execution_times.txt >> \$LOG_FILE
" > spark-tpch
chmod +x spark-tpch

post.sh

#!/bin/sh
export PATH=$HOME/spark-3.5.0-bin-hadoop3/bin:$PATH
cd tpch-spark-7d64aa57368f092969a855fdd10781c00813c9c4/
rm -f dbgen/*.tbl

pre.sh

#!/bin/sh
export PATH=$HOME/spark-3.5.0-bin-hadoop3/bin:$PATH
cd tpch-spark-7d64aa57368f092969a855fdd10781c00813c9c4/
rm -f tpch_execution_times.txt
rm -f dbgen/*.tbl
cd dbgen
./dbgen $@

results-definition.xml

<?xml version="1.0"?>
<!--Phoronix Test Suite v10.8.4-->
<PhoronixTestSuite>
  <ResultsParser>
    <OutputTemplate>Q05 #_RESULT_#</OutputTemplate>
    <LineHint>Q</LineHint>
    <MultiMatch>GEOMETRIC_MEAN</MultiMatch>
    <AppendToArgumentsDescription>Geometric Mean Of All Queries</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q01 #_RESULT_#</OutputTemplate>
    <LineHint>Q01</LineHint>
    <AppendToArgumentsDescription>Q01</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q02 #_RESULT_#</OutputTemplate>
    <LineHint>Q02</LineHint>
    <AppendToArgumentsDescription>Q02</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q03 #_RESULT_#</OutputTemplate>
    <LineHint>Q03</LineHint>
    <AppendToArgumentsDescription>Q03</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q04 #_RESULT_#</OutputTemplate>
    <LineHint>Q04</LineHint>
    <AppendToArgumentsDescription>Q04</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q05 #_RESULT_#</OutputTemplate>
    <LineHint>Q05</LineHint>
    <AppendToArgumentsDescription>Q05</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q06 #_RESULT_#</OutputTemplate>
    <LineHint>Q06</LineHint>
    <AppendToArgumentsDescription>Q06</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q07 #_RESULT_#</OutputTemplate>
    <LineHint>Q07</LineHint>
    <AppendToArgumentsDescription>Q07</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q08 #_RESULT_#</OutputTemplate>
    <LineHint>Q08</LineHint>
    <AppendToArgumentsDescription>Q08</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q09 #_RESULT_#</OutputTemplate>
    <LineHint>Q09</LineHint>
    <AppendToArgumentsDescription>Q09</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q10 #_RESULT_#</OutputTemplate>
    <LineHint>Q10</LineHint>
    <AppendToArgumentsDescription>Q10</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q11 #_RESULT_#</OutputTemplate>
    <LineHint>Q11</LineHint>
    <AppendToArgumentsDescription>Q11</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q12 #_RESULT_#</OutputTemplate>
    <LineHint>Q12</LineHint>
    <AppendToArgumentsDescription>Q12</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q13 #_RESULT_#</OutputTemplate>
    <LineHint>Q13</LineHint>
    <AppendToArgumentsDescription>Q13</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q14 #_RESULT_#</OutputTemplate>
    <LineHint>Q14</LineHint>
    <AppendToArgumentsDescription>Q14</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q15 #_RESULT_#</OutputTemplate>
    <LineHint>Q15</LineHint>
    <AppendToArgumentsDescription>Q15</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q16 #_RESULT_#</OutputTemplate>
    <LineHint>Q16</LineHint>
    <AppendToArgumentsDescription>Q16</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q17 #_RESULT_#</OutputTemplate>
    <LineHint>Q17</LineHint>
    <AppendToArgumentsDescription>Q17</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q18 #_RESULT_#</OutputTemplate>
    <LineHint>Q18</LineHint>
    <AppendToArgumentsDescription>Q18</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q19 #_RESULT_#</OutputTemplate>
    <LineHint>Q19</LineHint>
    <AppendToArgumentsDescription>Q19</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q20 #_RESULT_#</OutputTemplate>
    <LineHint>Q20</LineHint>
    <AppendToArgumentsDescription>Q20</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q21 #_RESULT_#</OutputTemplate>
    <LineHint>Q21</LineHint>
    <AppendToArgumentsDescription>Q21</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
  <ResultsParser>
    <OutputTemplate>Q22 #_RESULT_#</OutputTemplate>
    <LineHint>Q22</LineHint>
    <AppendToArgumentsDescription>Q22</AppendToArgumentsDescription>
    <DeleteOutputBefore>Query	Time (seconds)</DeleteOutputBefore>
    <Importance>Secondary</Importance>
  </ResultsParser>
</PhoronixTestSuite>

test-definition.xml

<?xml version="1.0"?>
<!--Phoronix Test Suite v10.8.4-->
<PhoronixTestSuite>
  <TestInformation>
    <Title>Apache Spark TPC-H</Title>
    <AppVersion>3.5</AppVersion>
    <Description>This is a benchmark of Apache Spark using TPC-H data-set. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmarks the Apache Spark in a single-system configuration using spark-submit.   The test makes use of https://github.com/ssavvides/tpch-spark/ for facilitating the TPC-H benchmark.</Description>
    <ResultScale>Seconds</ResultScale>
    <Proportion>LIB</Proportion>
    <TimesToRun>3</TimesToRun>
  </TestInformation>
  <TestProfile>
    <Version>1.0.0</Version>
    <SupportedPlatforms>Linux</SupportedPlatforms>
    <SoftwareType>Application</SoftwareType>
    <TestType>System</TestType>
    <License>Free</License>
    <Status>Verified</Status>
    <ExternalDependencies>java, python</ExternalDependencies>
    <EnvironmentSize>5000</EnvironmentSize>
    <ProjectURL>https://spark.apache.org/</ProjectURL>
    <RepositoryURL>https://github.com/apache/spark</RepositoryURL>
    <Maintainer>Michael Larabel</Maintainer>
  </TestProfile>
  <TestSettings>
    <Option>
      <DisplayName>Scale Factor</DisplayName>
      <Identifier>scale</Identifier>
      <ArgumentPrefix>-s </ArgumentPrefix>
      <Menu>
        <Entry>
          <Name>1</Name>
          <Value>1</Value>
          <Message>About 1GB of data</Message>
        </Entry>
        <Entry>
          <Name>10</Name>
          <Value>10</Value>
          <Message>About 10GB of data</Message>
        </Entry>
        <Entry>
          <Name>50</Name>
          <Value>50</Value>
          <Message>About 50GB of data</Message>
        </Entry>
        <Entry>
          <Name>100</Name>
          <Value>100</Value>
          <Message>About 100GB of data</Message>
        </Entry>
        <Entry>
          <Name>3000</Name>
          <Value>3000</Value>
          <Message>About 3TB of data; many hours of testing</Message>
        </Entry>
        <Entry>
          <Name>10000</Name>
          <Value>10000</Value>
          <Message>About 10TB of data, extremely time consuming!</Message>
        </Entry>
      </Menu>
    </Option>
  </TestSettings>
</PhoronixTestSuite>