Skip to content

Run benchmarks

Run benchmarks #1

Workflow file for this run

#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
#
name: Run benchmarks
on:
workflow_dispatch:
inputs:
class:
description: 'Benchmark class'
required: true
default: '*'
jdk:
description: 'JDK version: 17 or 21'
required: true
default: '17'
scala:
description: 'Scala version: 2.13'
required: true
default: '2.13'
failfast:
description: 'Failfast: true or false'
required: true
default: 'true'
num-splits:
description: 'Number of job splits'
required: true
default: '1'
jobs:
matrix-gen:
name: Generate matrix for job splits
runs-on: ubuntu-20.04
outputs:
matrix: ${{ steps.set-matrix.outputs.matrix }}
env:
SPARK_BENCHMARK_NUM_SPLITS: ${{ github.event.inputs.num-splits }}
steps:
- name: Generate matrix
id: set-matrix
run: echo "matrix=["`seq -s, 1 $SPARK_BENCHMARK_NUM_SPLITS`"]" >> $GITHUB_OUTPUT
# Any TPC-DS related updates on this job need to be applied to tpcds-1g job of build_and_test.yml as well
tpcds-1g-gen:
name: "Generate an input dataset for TPCDSQueryBenchmark with SF=1"
if: contains(github.event.inputs.class, 'TPCDSQueryBenchmark') || contains(github.event.inputs.class, '*')
runs-on: ubuntu-20.04
env:
SPARK_LOCAL_IP: localhost
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
# In order to get diff files
with:
fetch-depth: 0
- name: Cache Scala, SBT and Maven
uses: actions/cache@v3
with:
path: |
build/apache-maven-*
build/scala-*
build/*.jar
~/.sbt
key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
restore-keys: |
build-
- name: Cache Coursier local repository
uses: actions/cache@v3
with:
path: ~/.cache/coursier
key: benchmark-coursier-${{ github.event.inputs.jdk }}-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
restore-keys: |
benchmark-coursier-${{ github.event.inputs.jdk }}
- name: Cache TPC-DS generated data
id: cache-tpcds-sf-1
uses: actions/cache@v3
with:
path: ./tpcds-sf-1
key: tpcds-${{ hashFiles('.github/workflows/benchmark.yml', 'sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala') }}
- name: Checkout tpcds-kit repository
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
uses: actions/checkout@v3
with:
repository: databricks/tpcds-kit
ref: 2a5078a782192ddb6efbcead8de9973d6ab4f069
path: ./tpcds-kit
- name: Build tpcds-kit
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
run: cd tpcds-kit/tools && make OS=LINUX
- name: Install Java ${{ github.event.inputs.jdk }}
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
uses: actions/setup-java@v3
with:
distribution: zulu
java-version: ${{ github.event.inputs.jdk }}
- name: Generate TPC-DS (SF=1) table data
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
run: build/sbt "sql/Test/runMain org.apache.spark.sql.GenTPCDSData --dsdgenDir `pwd`/tpcds-kit/tools --location `pwd`/tpcds-sf-1 --scaleFactor 1 --numPartitions 1 --overwrite"
benchmark:
name: "Run benchmarks: ${{ github.event.inputs.class }} (JDK ${{ github.event.inputs.jdk }}, Scala ${{ github.event.inputs.scala }}, ${{ matrix.split }} out of ${{ github.event.inputs.num-splits }} splits)"
if: always()
needs: [matrix-gen, tpcds-1g-gen]
# Ubuntu 20.04 is the latest LTS. The next LTS is 22.04.
runs-on: ubuntu-20.04
strategy:
fail-fast: false
matrix:
split: ${{fromJSON(needs.matrix-gen.outputs.matrix)}}
env:
SPARK_BENCHMARK_FAILFAST: ${{ github.event.inputs.failfast }}
SPARK_BENCHMARK_NUM_SPLITS: ${{ github.event.inputs.num-splits }}
SPARK_BENCHMARK_CUR_SPLIT: ${{ matrix.split }}
SPARK_GENERATE_BENCHMARK_FILES: 1
SPARK_LOCAL_IP: localhost
# To prevent spark.test.home not being set. See more detail in SPARK-36007.
SPARK_HOME: ${{ github.workspace }}
SPARK_TPCDS_DATA: ${{ github.workspace }}/tpcds-sf-1
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
# In order to get diff files
with:
fetch-depth: 0
- name: Cache Scala, SBT and Maven
uses: actions/cache@v3
with:
path: |
build/apache-maven-*
build/scala-*
build/*.jar
~/.sbt
key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
restore-keys: |
build-
- name: Cache Coursier local repository
uses: actions/cache@v3
with:
path: ~/.cache/coursier
key: benchmark-coursier-${{ github.event.inputs.jdk }}-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
restore-keys: |
benchmark-coursier-${{ github.event.inputs.jdk }}
- name: Install Java ${{ github.event.inputs.jdk }}
uses: actions/setup-java@v3
with:
distribution: zulu
java-version: ${{ github.event.inputs.jdk }}
- name: Cache TPC-DS generated data
if: contains(github.event.inputs.class, 'TPCDSQueryBenchmark') || contains(github.event.inputs.class, '*')
id: cache-tpcds-sf-1
uses: actions/cache@v3
with:
path: ./tpcds-sf-1
key: tpcds-${{ hashFiles('.github/workflows/benchmark.yml', 'sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala') }}
- name: Run benchmarks
run: |
./build/sbt -Pscala-${{ github.event.inputs.scala }} -Pyarn -Pkubernetes -Phive -Phive-thriftserver -Phadoop-cloud -Pkinesis-asl -Pspark-ganglia-lgpl Test/package
# Make less noisy
cp conf/log4j2.properties.template conf/log4j2.properties
sed -i 's/rootLogger.level = info/rootLogger.level = warn/g' conf/log4j2.properties
# In benchmark, we use local as master so set driver memory only. Note that GitHub Actions has 7 GB memory limit.
bin/spark-submit \
--driver-memory 6g --class org.apache.spark.benchmark.Benchmarks \
--jars "`find . -name '*-SNAPSHOT-tests.jar' -o -name '*avro*-SNAPSHOT.jar' | paste -sd ',' -`" \
"`find . -name 'spark-core*-SNAPSHOT-tests.jar'`" \
"${{ github.event.inputs.class }}"
# To keep the directory structure and file permissions, tar them
# See also https://github.com/actions/upload-artifact#maintaining-file-permissions-and-case-sensitive-files
echo "Preparing the benchmark results:"
tar -cvf benchmark-results-${{ github.event.inputs.jdk }}-${{ github.event.inputs.scala }}.tar `git diff --name-only` `git ls-files --others --exclude=tpcds-sf-1 --exclude-standard`
- name: Upload benchmark results
uses: actions/upload-artifact@v3
with:
name: benchmark-results-${{ github.event.inputs.jdk }}-${{ github.event.inputs.scala }}-${{ matrix.split }}
path: benchmark-results-${{ github.event.inputs.jdk }}-${{ github.event.inputs.scala }}.tar