Spark35

.github/workflows/build_and_test.yml

@@ -79,25 +79,34 @@ jobs:
       id: set-outputs
       run: |
         if [ -z "${{ inputs.jobs }}" ]; then
-          pyspark=true; sparkr=true; tpcds=true; docker=true;
           pyspark_modules=`cd dev && python -c "import sparktestsupport.modules as m; print(','.join(m.name for m in m.all_modules if m.name.startswith('pyspark')))"`
           pyspark=`./dev/is-changed.py -m $pyspark_modules`
-          sparkr=`./dev/is-changed.py -m sparkr`
-          tpcds=`./dev/is-changed.py -m sql`
-          docker=`./dev/is-changed.py -m docker-integration-tests`
-          # 'build', 'scala-213', and 'java-11-17' are always true for now.
-          # It does not save significant time and most of PRs trigger the build.
+          if [[ "${{ github.repository }}" != 'apache/spark' ]]; then
+            pandas=$pyspark
+            kubernetes=`./dev/is-changed.py -m kubernetes`
+            sparkr=`./dev/is-changed.py -m sparkr`
+            tpcds=`./dev/is-changed.py -m sql`
+            docker=`./dev/is-changed.py -m docker-integration-tests`
+          else
+            pandas=false
+            kubernetes=false
+            sparkr=false
+            tpcds=false
+            docker=false
+          fi
+          build=`./dev/is-changed.py -m "core,unsafe,kvstore,avro,utils,network-common,network-shuffle,repl,launcher,examples,sketch,graphx,catalyst,hive-thriftserver,streaming,sql-kafka-0-10,streaming-kafka-0-10,mllib-local,mllib,yarn,mesos,kubernetes,hadoop-cloud,spark-ganglia-lgpl,sql,hive"`
           precondition="
             {
-              \"build\": \"true\",
+              \"build\": \"$build\",
               \"pyspark\": \"$pyspark\",
+              \"pyspark-pandas\": \"$pandas\",
               \"sparkr\": \"$sparkr\",
               \"tpcds-1g\": \"$tpcds\",
               \"docker-integration-tests\": \"$docker\",
-              \"scala-213\": \"true\",
-              \"java-11-17\": \"true\",
+              \"scala-213\": \"$build\",
+              \"java-11-17\": \"$build\",
               \"lint\" : \"true\",
-              \"k8s-integration-tests\" : \"true\",
+              \"k8s-integration-tests\" : \"$kubernetes\",
               \"breaking-changes-buf\" : \"true\",
             }"
           echo $precondition # For debugging
@@ -204,6 +213,8 @@ jobs:
       HIVE_PROFILE: ${{ matrix.hive }}
       GITHUB_PREV_SHA: ${{ github.event.before }}
       SPARK_LOCAL_IP: localhost
+      SKIP_UNIDOC: true
+      SKIP_MIMA: true
       SKIP_PACKAGING: true
     steps:
     - name: Checkout Spark repository
@@ -256,7 +267,7 @@ jobs:
     - name: Install Python packages (Python 3.8)
       if: (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-'))
       run: |
-        python3.8 -m pip install 'numpy>=1.20.0' pyarrow pandas scipy unittest-xml-reporting 'grpcio==1.56.0' 'protobuf==3.20.3'
+        python3.8 -m pip install 'numpy>=1.20.0' 'pyarrow==12.0.1' pandas scipy unittest-xml-reporting 'grpcio==1.56.0' 'protobuf==3.20.3'
         python3.8 -m pip list
     # Run the tests.
     - name: Run tests
@@ -360,6 +371,14 @@ jobs:
             pyspark-pandas-connect
           - >-
             pyspark-pandas-slow-connect
+        exclude:
+          # Always run if pyspark-pandas == 'true', even infra-image is skip (such as non-master job)
+          # In practice, the build will run in individual PR, but not against the individual commit
+          # in Apache Spark repository.
+          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas' }}
+          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-slow' }}
+          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-connect' }}
+          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-slow-connect' }}
     env:
       MODULES_TO_TEST: ${{ matrix.modules }}
       HADOOP_PROFILE: ${{ inputs.hadoop }}
@@ -407,6 +426,8 @@ jobs:
         key: pyspark-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
           pyspark-coursier-
+    - name: Free up disk space
+      run: ./dev/free_disk_space_container
     - name: Install Java ${{ matrix.java }}
       uses: actions/setup-java@v3
       with:
@@ -504,6 +525,8 @@ jobs:
         key: sparkr-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
           sparkr-coursier-
+    - name: Free up disk space
+      run: ./dev/free_disk_space_container
     - name: Install Java ${{ inputs.java }}
       uses: actions/setup-java@v3
       with:
@@ -612,6 +635,8 @@ jobs:
         key: docs-maven-${{ hashFiles('**/pom.xml') }}
         restore-keys: |
           docs-maven-
+    - name: Free up disk space
+      run: ./dev/free_disk_space_container
     - name: Install Java 8
       uses: actions/setup-java@v3
       with:
@@ -621,6 +646,8 @@ jobs:
       run: ./dev/check-license
     - name: Dependencies test
       run: ./dev/test-dependencies.sh
+    - name: MIMA test
+      run: ./dev/mima
     - name: Scala linter
       run: ./dev/lint-scala
     - name: Java linter
@@ -672,16 +699,16 @@ jobs:
         #   See also https://issues.apache.org/jira/browse/SPARK-35375.
         # Pin the MarkupSafe to 2.0.1 to resolve the CI error.
         #   See also https://issues.apache.org/jira/browse/SPARK-38279.
-        python3.9 -m pip install 'sphinx<3.1.0' mkdocs pydata_sphinx_theme nbsphinx numpydoc 'jinja2<3.0.0' 'markupsafe==2.0.1' 'pyzmq<24.0.0'
+        python3.9 -m pip install 'sphinx<3.1.0' mkdocs pydata_sphinx_theme 'sphinx-copybutton==0.5.2' 'nbsphinx==0.9.3' numpydoc 'jinja2<3.0.0' 'markupsafe==2.0.1' 'pyzmq<24.0.0' 'sphinxcontrib-applehelp==1.0.4' 'sphinxcontrib-devhelp==1.0.2' 'sphinxcontrib-htmlhelp==2.0.1' 'sphinxcontrib-qthelp==1.0.3' 'sphinxcontrib-serializinghtml==1.1.5' 'nest-asyncio==1.5.8' 'rpds-py==0.16.2' 'alabaster==0.7.13'
         python3.9 -m pip install ipython_genutils # See SPARK-38517
-        python3.9 -m pip install sphinx_plotly_directive 'numpy>=1.20.0' pyarrow pandas 'plotly>=4.8'
+        python3.9 -m pip install sphinx_plotly_directive 'numpy>=1.20.0' 'pyarrow==12.0.1' pandas 'plotly>=4.8'
         python3.9 -m pip install 'docutils<0.18.0' # See SPARK-39421
         apt-get update -y
         apt-get install -y ruby ruby-dev
         Rscript -e "install.packages(c('devtools', 'testthat', 'knitr', 'rmarkdown', 'markdown', 'e1071', 'roxygen2', 'ggplot2', 'mvtnorm', 'statmod'), repos='https://cloud.r-project.org/')"
         Rscript -e "devtools::install_version('pkgdown', version='2.0.1', repos='https://cloud.r-project.org')"
         Rscript -e "devtools::install_version('preferably', version='0.4', repos='https://cloud.r-project.org')"
-        gem install bundler
+        gem install bundler -v 2.4.22
         cd docs
         bundle install
     - name: R linter
@@ -1010,9 +1037,7 @@ jobs:
       - name: start minikube
         run: |
           # See more in "Installation" https://minikube.sigs.k8s.io/docs/start/
-          # curl -LO https://storage.googleapis.com/minikube/releases/latest/minikube-linux-amd64
-          # TODO(SPARK-44495): Resume to use the latest minikube for k8s-integration-tests.
-          curl -LO https://storage.googleapis.com/minikube/releases/v1.30.1/minikube-linux-amd64
+          curl -LO https://storage.googleapis.com/minikube/releases/latest/minikube-linux-amd64
           sudo install minikube-linux-amd64 /usr/local/bin/minikube
           # Github Action limit cpu:2, memory: 6947MB, limit to 2U6G for better resource statistic
           minikube start --cpus 2 --memory 6144
@@ -1030,7 +1055,7 @@ jobs:
           kubectl create clusterrolebinding serviceaccounts-cluster-admin --clusterrole=cluster-admin --group=system:serviceaccounts || true
           kubectl apply -f https://raw.githubusercontent.com/volcano-sh/volcano/v1.7.0/installer/volcano-development.yaml || true
           eval $(minikube docker-env)
-          build/sbt -Psparkr -Pkubernetes -Pvolcano -Pkubernetes-integration-tests -Dspark.kubernetes.test.driverRequestCores=0.5 -Dspark.kubernetes.test.executorRequestCores=0.2 -Dspark.kubernetes.test.volcanoMaxConcurrencyJobNum=1 -Dtest.exclude.tags=local "kubernetes-integration-tests/test"
+          build/sbt -Psparkr -Pkubernetes -Pvolcano -Pkubernetes-integration-tests -Dspark.kubernetes.test.volcanoMaxConcurrencyJobNum=1 -Dtest.exclude.tags=local "kubernetes-integration-tests/test"
       - name: Upload Spark on K8S integration tests log files
         if: failure()
         uses: actions/upload-artifact@v3

.gitignore

@@ -26,6 +26,7 @@
 .scala_dependencies
 .settings
 .vscode
+artifacts/
 /lib/
 R-unit-tests.log
 R/unit-tests.out
@@ -50,6 +51,7 @@ dev/create-release/*final
 dev/create-release/*txt
 dev/pr-deps/
 dist/
+docs/_generated/
 docs/_site/
 docs/api
 docs/.local_ruby_bundle

LICENSE

@@ -218,11 +218,6 @@ docs/js/vendor/bootstrap.js
 connector/spark-ganglia-lgpl/src/main/java/com/codahale/metrics/ganglia/GangliaReporter.java
 
 
-Python Software Foundation License
-----------------------------------
-
-python/docs/source/_static/copybutton.js
-
 BSD 3-Clause
 ------------
 

R/pkg/DESCRIPTION

@@ -1,6 +1,6 @@
 Package: SparkR
 Type: Package
-Version: 3.5.0
+Version: 3.5.4
 Title: R Front End for 'Apache Spark'
 Description: Provides an R Front end for 'Apache Spark' <https://spark.apache.org>.
 Authors@R:

assembly/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.12</artifactId>
-    <version>3.5.0</version>
+    <version>3.5.4-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
@@ -159,6 +159,12 @@
           <groupId>org.apache.spark</groupId>
           <artifactId>spark-connect_${scala.binary.version}</artifactId>
           <version>${project.version}</version>
+          <exclusions>
+            <exclusion>
+              <groupId>org.apache.spark</groupId>
+              <artifactId>spark-connect-common_${scala.binary.version}</artifactId>
+            </exclusion>
+          </exclusions>
         </dependency>
         <dependency>
           <groupId>org.apache.spark</groupId>

binder/Dockerfile

@@ -0,0 +1,43 @@
+#
+# 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.
+#
+
+FROM python:3.10-slim
+# install the notebook package
+RUN  pip install --no-cache notebook jupyterlab
+
+# create user with a home directory
+ARG NB_USER
+ARG NB_UID
+ENV USER ${NB_USER}
+ENV HOME /home/${NB_USER}
+
+RUN adduser --disabled-password \
+    --gecos "Default user" \
+    --uid ${NB_UID} \
+    ${NB_USER}
+WORKDIR ${HOME}
+USER ${USER}
+
+# Make sure the contents of our repo are in ${HOME}
+COPY . ${HOME}
+USER root
+RUN chown -R ${NB_UID} ${HOME}
+RUN apt-get update && apt-get install -y openjdk-17-jre git coreutils
+USER ${NB_USER}
+
+RUN binder/postBuild
+

binder/postBuild

@@ -20,8 +20,13 @@
 # This file is used for Binder integration to install PySpark available in
 # Jupyter notebook.
 
+# SPARK-45706: Should fail fast. Otherwise, the Binder image is successfully
+# built, and it cannot be rebuilt.
+set -o pipefail
+set -e
+
 VERSION=$(python -c "exec(open('python/pyspark/version.py').read()); print(__version__)")
-TAG=$(git describe --tags --exact-match 2>/dev/null)
+TAG=$(git describe --tags --exact-match 2> /dev/null || true)
 
 # If a commit is tagged, exactly specified version of pyspark should be installed to avoid
 # a kind of accident that an old version of pyspark is installed in the live notebook environment.
@@ -33,9 +38,9 @@ else
 fi
 
 if [[ ! $VERSION < "3.4.0" ]]; then
-  pip install plotly "pandas<2.0.0" "pyspark[sql,ml,mllib,pandas_on_spark,connect]$SPECIFIER$VERSION"
+  pip install plotly "pandas<2.0.0" "numpy>=1.15,<2" "pyspark[sql,ml,mllib,pandas_on_spark,connect]$SPECIFIER$VERSION"
 else
-  pip install plotly "pandas<2.0.0" "pyspark[sql,ml,mllib,pandas_on_spark]$SPECIFIER$VERSION"
+  pip install plotly "pandas<2.0.0" "numpy>=1.15,<2" "pyspark[sql,ml,mllib,pandas_on_spark]$SPECIFIER$VERSION"
 fi
 
 # Set 'PYARROW_IGNORE_TIMEZONE' to surpress warnings from PyArrow.

common/kvstore/pom.xml

@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.12</artifactId>
-    <version>3.5.0</version>
+    <version>3.5.4-SNAPSHOT</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 
@@ -66,6 +66,11 @@
       <artifactId>commons-io</artifactId>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>org.apache.commons</groupId>
+      <artifactId>commons-lang3</artifactId>
+      <scope>test</scope>
+    </dependency>
 
     <dependency>
       <groupId>org.apache.logging.log4j</groupId>

common/network-common/pom.xml

@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.12</artifactId>
-    <version>3.5.0</version>
+    <version>3.5.4-SNAPSHOT</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

common/network-common/src/main/java/org/apache/spark/network/client/TransportClient.java

@@ -325,7 +325,10 @@ public TransportResponseHandler getHandler() {
 
   @Override
   public void close() {
-    // close is a local operation and should finish with milliseconds; timeout just to be safe
+    // Mark the connection as timed out, so we do not return a connection that's being closed
+    // from the TransportClientFactory if closing takes some time (e.g. with SSL)
+    this.timedOut = true;
+    // close should not take this long; use a timeout just to be safe
     channel.close().awaitUninterruptibly(10, TimeUnit.SECONDS);
   }