This is an automated email from the ASF dual-hosted git repository.
yumwang pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark-docker.git
The following commit(s) were added to refs/heads/master by this push:
new 5ba4b67 [SPARK-40929] Add Apache Spark 3.3.1 Dockerfiles
5ba4b67 is described below
commit 5ba4b67d88f101a8491f39030b38ca8f2c6d6351
Author: Yikun Jiang <yikunk...@gmail.com>
AuthorDate: Thu Oct 27 13:56:21 2022 +0800
[SPARK-40929] Add Apache Spark 3.3.1 Dockerfiles
### What changes were proposed in this pull request?
Add Apache Spark 3.3.1 Dockerfiles.
- Add 3.3.1 GPG key
- Add .github/workflows/build_3.3.1.yaml
- ./add-dockerfiles.sh 3.3.1
### Why are the changes needed?
Apache Spark 3.3.1 released.
https://lists.apache.org/thread/7x5s8fpg16jvlm4cng5kvfk3njhwd0zh
### Does this PR introduce _any_ user-facing change?
Yes in future, new image will publised in future
### How was this patch tested?
Add workflow and CI passed
Closes #20 from Yikun/SPARK-40929.
Authored-by: Yikun Jiang <yikunk...@gmail.com>
Signed-off-by: Yuming Wang <yumw...@ebay.com>
---
.github/workflows/build_3.3.1.yaml | 39 +++++++
3.3.1/scala2.12-java11-python3-r-ubuntu/Dockerfile | 86 ++++++++++++++++
.../entrypoint.sh | 114 +++++++++++++++++++++
3.3.1/scala2.12-java11-python3-ubuntu/Dockerfile | 83 +++++++++++++++
.../scala2.12-java11-python3-ubuntu/entrypoint.sh | 114 +++++++++++++++++++++
3.3.1/scala2.12-java11-r-ubuntu/Dockerfile | 82 +++++++++++++++
3.3.1/scala2.12-java11-r-ubuntu/entrypoint.sh | 114 +++++++++++++++++++++
3.3.1/scala2.12-java11-ubuntu/Dockerfile | 79 ++++++++++++++
3.3.1/scala2.12-java11-ubuntu/entrypoint.sh | 114 +++++++++++++++++++++
tools/template.py | 2 +
10 files changed, 827 insertions(+)
diff --git a/.github/workflows/build_3.3.1.yaml
b/.github/workflows/build_3.3.1.yaml
new file mode 100644
index 0000000..f6a4b7d
--- /dev/null
+++ b/.github/workflows/build_3.3.1.yaml
@@ -0,0 +1,39 @@
+#
+# 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: "Build and Test (3.3.1)"
+
+on:
+ pull_request:
+ branches:
+ - 'master'
+ paths:
+ - '3.3.1/**'
+ - '.github/workflows/build_3.3.1.yaml'
+ - '.github/workflows/main.yml'
+
+jobs:
+ run-build:
+ name: Run
+ secrets: inherit
+ uses: ./.github/workflows/main.yml
+ with:
+ spark: 3.3.1
+ scala: 2.12
+ java: 11
diff --git a/3.3.1/scala2.12-java11-python3-r-ubuntu/Dockerfile
b/3.3.1/scala2.12-java11-python3-r-ubuntu/Dockerfile
new file mode 100644
index 0000000..b126f1f
--- /dev/null
+++ b/3.3.1/scala2.12-java11-python3-r-ubuntu/Dockerfile
@@ -0,0 +1,86 @@
+#
+# 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 eclipse-temurin:11-jre-focal
+
+ARG spark_uid=185
+
+RUN groupadd --system --gid=${spark_uid} spark && \
+ useradd --system --uid=${spark_uid} --gid=spark spark
+
+RUN set -ex && \
+ apt-get update && \
+ ln -s /lib /lib64 && \
+ apt install -y gnupg2 wget bash tini libc6 libpam-modules krb5-user
libnss3 procps net-tools gosu && \
+ apt install -y python3 python3-pip && \
+ apt install -y r-base r-base-dev && \
+ mkdir -p /opt/spark && \
+ mkdir /opt/spark/python && \
+ mkdir -p /opt/spark/examples && \
+ mkdir -p /opt/spark/work-dir && \
+ touch /opt/spark/RELEASE && \
+ chown -R spark:spark /opt/spark && \
+ rm /bin/sh && \
+ ln -sv /bin/bash /bin/sh && \
+ echo "auth required pam_wheel.so use_uid" >> /etc/pam.d/su && \
+ chgrp root /etc/passwd && chmod ug+rw /etc/passwd && \
+ rm -rf /var/cache/apt/* && \
+ rm -rf /var/lib/apt/lists/*
+
+# Install Apache Spark
+# https://downloads.apache.org/spark/KEYS
+ENV
SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz
\
+
SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc
\
+ GPG_KEY=86727D43E73A415F67A0B1A14E68B3E6CD473653
+
+RUN set -ex; \
+ export SPARK_TMP="$(mktemp -d)"; \
+ cd $SPARK_TMP; \
+ wget -nv -O spark.tgz "$SPARK_TGZ_URL"; \
+ wget -nv -O spark.tgz.asc "$SPARK_TGZ_ASC_URL"; \
+ export GNUPGHOME="$(mktemp -d)"; \
+ gpg --keyserver hkps://keys.openpgp.org --recv-key "$GPG_KEY" || \
+ gpg --keyserver hkps://keyserver.ubuntu.com --recv-keys "$GPG_KEY"; \
+ gpg --batch --verify spark.tgz.asc spark.tgz; \
+ gpgconf --kill all; \
+ rm -rf "$GNUPGHOME" spark.tgz.asc; \
+ \
+ tar -xf spark.tgz --strip-components=1; \
+ chown -R spark:spark .; \
+ mv jars /opt/spark/; \
+ mv bin /opt/spark/; \
+ mv sbin /opt/spark/; \
+ mv kubernetes/dockerfiles/spark/decom.sh /opt/; \
+ mv examples /opt/spark/; \
+ mv kubernetes/tests /opt/spark/; \
+ mv data /opt/spark/; \
+ mv python/pyspark /opt/spark/python/pyspark/; \
+ mv python/lib /opt/spark/python/lib/; \
+ mv R /opt/spark/; \
+ cd ..; \
+ rm -rf "$SPARK_TMP";
+
+COPY entrypoint.sh /opt/
+
+ENV SPARK_HOME /opt/spark
+ENV R_HOME /usr/lib/R
+
+WORKDIR /opt/spark/work-dir
+RUN chmod g+w /opt/spark/work-dir
+RUN chmod a+x /opt/decom.sh
+RUN chmod a+x /opt/entrypoint.sh
+
+ENTRYPOINT [ "/opt/entrypoint.sh" ]
diff --git a/3.3.1/scala2.12-java11-python3-r-ubuntu/entrypoint.sh
b/3.3.1/scala2.12-java11-python3-r-ubuntu/entrypoint.sh
new file mode 100644
index 0000000..4bb1557
--- /dev/null
+++ b/3.3.1/scala2.12-java11-python3-r-ubuntu/entrypoint.sh
@@ -0,0 +1,114 @@
+#!/bin/bash
+#
+# 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.
+#
+
+# Check whether there is a passwd entry for the container UID
+myuid=$(id -u)
+mygid=$(id -g)
+# turn off -e for getent because it will return error code in anonymous uid
case
+set +e
+uidentry=$(getent passwd $myuid)
+set -e
+
+# If there is no passwd entry for the container UID, attempt to create one
+if [ -z "$uidentry" ] ; then
+ if [ -w /etc/passwd ] ; then
+ echo "$myuid:x:$myuid:$mygid:${SPARK_USER_NAME:-anonymous
uid}:$SPARK_HOME:/bin/false" >> /etc/passwd
+ else
+ echo "Container ENTRYPOINT failed to add passwd entry for anonymous
UID"
+ fi
+fi
+
+if [ -z "$JAVA_HOME" ]; then
+ JAVA_HOME=$(java -XshowSettings:properties -version 2>&1 > /dev/null | grep
'java.home' | awk '{print $3}')
+fi
+
+SPARK_CLASSPATH="$SPARK_CLASSPATH:${SPARK_HOME}/jars/*"
+env | grep SPARK_JAVA_OPT_ | sort -t_ -k4 -n | sed 's/[^=]*=\(.*\)/\1/g' >
/tmp/java_opts.txt
+readarray -t SPARK_EXECUTOR_JAVA_OPTS < /tmp/java_opts.txt
+
+if [ -n "$SPARK_EXTRA_CLASSPATH" ]; then
+ SPARK_CLASSPATH="$SPARK_CLASSPATH:$SPARK_EXTRA_CLASSPATH"
+fi
+
+if ! [ -z ${PYSPARK_PYTHON+x} ]; then
+ export PYSPARK_PYTHON
+fi
+if ! [ -z ${PYSPARK_DRIVER_PYTHON+x} ]; then
+ export PYSPARK_DRIVER_PYTHON
+fi
+
+# If HADOOP_HOME is set and SPARK_DIST_CLASSPATH is not set, set it here so
Hadoop jars are available to the executor.
+# It does not set SPARK_DIST_CLASSPATH if already set, to avoid overriding
customizations of this value from elsewhere e.g. Docker/K8s.
+if [ -n "${HADOOP_HOME}" ] && [ -z "${SPARK_DIST_CLASSPATH}" ]; then
+ export SPARK_DIST_CLASSPATH="$($HADOOP_HOME/bin/hadoop classpath)"
+fi
+
+if ! [ -z ${HADOOP_CONF_DIR+x} ]; then
+ SPARK_CLASSPATH="$HADOOP_CONF_DIR:$SPARK_CLASSPATH";
+fi
+
+if ! [ -z ${SPARK_CONF_DIR+x} ]; then
+ SPARK_CLASSPATH="$SPARK_CONF_DIR:$SPARK_CLASSPATH";
+elif ! [ -z ${SPARK_HOME+x} ]; then
+ SPARK_CLASSPATH="$SPARK_HOME/conf:$SPARK_CLASSPATH";
+fi
+
+case "$1" in
+ driver)
+ shift 1
+ CMD=(
+ "$SPARK_HOME/bin/spark-submit"
+ --conf "spark.driver.bindAddress=$SPARK_DRIVER_BIND_ADDRESS"
+ --deploy-mode client
+ "$@"
+ )
+ ;;
+ executor)
+ shift 1
+ CMD=(
+ ${JAVA_HOME}/bin/java
+ "${SPARK_EXECUTOR_JAVA_OPTS[@]}"
+ -Xms$SPARK_EXECUTOR_MEMORY
+ -Xmx$SPARK_EXECUTOR_MEMORY
+ -cp "$SPARK_CLASSPATH:$SPARK_DIST_CLASSPATH"
+ org.apache.spark.scheduler.cluster.k8s.KubernetesExecutorBackend
+ --driver-url $SPARK_DRIVER_URL
+ --executor-id $SPARK_EXECUTOR_ID
+ --cores $SPARK_EXECUTOR_CORES
+ --app-id $SPARK_APPLICATION_ID
+ --hostname $SPARK_EXECUTOR_POD_IP
+ --resourceProfileId $SPARK_RESOURCE_PROFILE_ID
+ --podName $SPARK_EXECUTOR_POD_NAME
+ )
+ ;;
+
+ *)
+ # Non-spark-on-k8s command provided, proceeding in pass-through mode...
+ CMD=("$@")
+ ;;
+esac
+
+# Switch to spark if no USER specified (root by default) otherwise use USER
directly
+switch_spark_if_root() {
+ if [ $(id -u) -eq 0 ]; then
+ echo gosu spark
+ fi
+}
+
+# Execute the container CMD under tini for better hygiene
+exec $(switch_spark_if_root) /usr/bin/tini -s -- "${CMD[@]}"
diff --git a/3.3.1/scala2.12-java11-python3-ubuntu/Dockerfile
b/3.3.1/scala2.12-java11-python3-ubuntu/Dockerfile
new file mode 100644
index 0000000..af02e65
--- /dev/null
+++ b/3.3.1/scala2.12-java11-python3-ubuntu/Dockerfile
@@ -0,0 +1,83 @@
+#
+# 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 eclipse-temurin:11-jre-focal
+
+ARG spark_uid=185
+
+RUN groupadd --system --gid=${spark_uid} spark && \
+ useradd --system --uid=${spark_uid} --gid=spark spark
+
+RUN set -ex && \
+ apt-get update && \
+ ln -s /lib /lib64 && \
+ apt install -y gnupg2 wget bash tini libc6 libpam-modules krb5-user
libnss3 procps net-tools gosu && \
+ apt install -y python3 python3-pip && \
+ mkdir -p /opt/spark && \
+ mkdir /opt/spark/python && \
+ mkdir -p /opt/spark/examples && \
+ mkdir -p /opt/spark/work-dir && \
+ touch /opt/spark/RELEASE && \
+ chown -R spark:spark /opt/spark && \
+ rm /bin/sh && \
+ ln -sv /bin/bash /bin/sh && \
+ echo "auth required pam_wheel.so use_uid" >> /etc/pam.d/su && \
+ chgrp root /etc/passwd && chmod ug+rw /etc/passwd && \
+ rm -rf /var/cache/apt/* && \
+ rm -rf /var/lib/apt/lists/*
+
+# Install Apache Spark
+# https://downloads.apache.org/spark/KEYS
+ENV
SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz
\
+
SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc
\
+ GPG_KEY=86727D43E73A415F67A0B1A14E68B3E6CD473653
+
+RUN set -ex; \
+ export SPARK_TMP="$(mktemp -d)"; \
+ cd $SPARK_TMP; \
+ wget -nv -O spark.tgz "$SPARK_TGZ_URL"; \
+ wget -nv -O spark.tgz.asc "$SPARK_TGZ_ASC_URL"; \
+ export GNUPGHOME="$(mktemp -d)"; \
+ gpg --keyserver hkps://keys.openpgp.org --recv-key "$GPG_KEY" || \
+ gpg --keyserver hkps://keyserver.ubuntu.com --recv-keys "$GPG_KEY"; \
+ gpg --batch --verify spark.tgz.asc spark.tgz; \
+ gpgconf --kill all; \
+ rm -rf "$GNUPGHOME" spark.tgz.asc; \
+ \
+ tar -xf spark.tgz --strip-components=1; \
+ chown -R spark:spark .; \
+ mv jars /opt/spark/; \
+ mv bin /opt/spark/; \
+ mv sbin /opt/spark/; \
+ mv kubernetes/dockerfiles/spark/decom.sh /opt/; \
+ mv examples /opt/spark/; \
+ mv kubernetes/tests /opt/spark/; \
+ mv data /opt/spark/; \
+ mv python/pyspark /opt/spark/python/pyspark/; \
+ mv python/lib /opt/spark/python/lib/; \
+ cd ..; \
+ rm -rf "$SPARK_TMP";
+
+COPY entrypoint.sh /opt/
+
+ENV SPARK_HOME /opt/spark
+
+WORKDIR /opt/spark/work-dir
+RUN chmod g+w /opt/spark/work-dir
+RUN chmod a+x /opt/decom.sh
+RUN chmod a+x /opt/entrypoint.sh
+
+ENTRYPOINT [ "/opt/entrypoint.sh" ]
diff --git a/3.3.1/scala2.12-java11-python3-ubuntu/entrypoint.sh
b/3.3.1/scala2.12-java11-python3-ubuntu/entrypoint.sh
new file mode 100644
index 0000000..4bb1557
--- /dev/null
+++ b/3.3.1/scala2.12-java11-python3-ubuntu/entrypoint.sh
@@ -0,0 +1,114 @@
+#!/bin/bash
+#
+# 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.
+#
+
+# Check whether there is a passwd entry for the container UID
+myuid=$(id -u)
+mygid=$(id -g)
+# turn off -e for getent because it will return error code in anonymous uid
case
+set +e
+uidentry=$(getent passwd $myuid)
+set -e
+
+# If there is no passwd entry for the container UID, attempt to create one
+if [ -z "$uidentry" ] ; then
+ if [ -w /etc/passwd ] ; then
+ echo "$myuid:x:$myuid:$mygid:${SPARK_USER_NAME:-anonymous
uid}:$SPARK_HOME:/bin/false" >> /etc/passwd
+ else
+ echo "Container ENTRYPOINT failed to add passwd entry for anonymous
UID"
+ fi
+fi
+
+if [ -z "$JAVA_HOME" ]; then
+ JAVA_HOME=$(java -XshowSettings:properties -version 2>&1 > /dev/null | grep
'java.home' | awk '{print $3}')
+fi
+
+SPARK_CLASSPATH="$SPARK_CLASSPATH:${SPARK_HOME}/jars/*"
+env | grep SPARK_JAVA_OPT_ | sort -t_ -k4 -n | sed 's/[^=]*=\(.*\)/\1/g' >
/tmp/java_opts.txt
+readarray -t SPARK_EXECUTOR_JAVA_OPTS < /tmp/java_opts.txt
+
+if [ -n "$SPARK_EXTRA_CLASSPATH" ]; then
+ SPARK_CLASSPATH="$SPARK_CLASSPATH:$SPARK_EXTRA_CLASSPATH"
+fi
+
+if ! [ -z ${PYSPARK_PYTHON+x} ]; then
+ export PYSPARK_PYTHON
+fi
+if ! [ -z ${PYSPARK_DRIVER_PYTHON+x} ]; then
+ export PYSPARK_DRIVER_PYTHON
+fi
+
+# If HADOOP_HOME is set and SPARK_DIST_CLASSPATH is not set, set it here so
Hadoop jars are available to the executor.
+# It does not set SPARK_DIST_CLASSPATH if already set, to avoid overriding
customizations of this value from elsewhere e.g. Docker/K8s.
+if [ -n "${HADOOP_HOME}" ] && [ -z "${SPARK_DIST_CLASSPATH}" ]; then
+ export SPARK_DIST_CLASSPATH="$($HADOOP_HOME/bin/hadoop classpath)"
+fi
+
+if ! [ -z ${HADOOP_CONF_DIR+x} ]; then
+ SPARK_CLASSPATH="$HADOOP_CONF_DIR:$SPARK_CLASSPATH";
+fi
+
+if ! [ -z ${SPARK_CONF_DIR+x} ]; then
+ SPARK_CLASSPATH="$SPARK_CONF_DIR:$SPARK_CLASSPATH";
+elif ! [ -z ${SPARK_HOME+x} ]; then
+ SPARK_CLASSPATH="$SPARK_HOME/conf:$SPARK_CLASSPATH";
+fi
+
+case "$1" in
+ driver)
+ shift 1
+ CMD=(
+ "$SPARK_HOME/bin/spark-submit"
+ --conf "spark.driver.bindAddress=$SPARK_DRIVER_BIND_ADDRESS"
+ --deploy-mode client
+ "$@"
+ )
+ ;;
+ executor)
+ shift 1
+ CMD=(
+ ${JAVA_HOME}/bin/java
+ "${SPARK_EXECUTOR_JAVA_OPTS[@]}"
+ -Xms$SPARK_EXECUTOR_MEMORY
+ -Xmx$SPARK_EXECUTOR_MEMORY
+ -cp "$SPARK_CLASSPATH:$SPARK_DIST_CLASSPATH"
+ org.apache.spark.scheduler.cluster.k8s.KubernetesExecutorBackend
+ --driver-url $SPARK_DRIVER_URL
+ --executor-id $SPARK_EXECUTOR_ID
+ --cores $SPARK_EXECUTOR_CORES
+ --app-id $SPARK_APPLICATION_ID
+ --hostname $SPARK_EXECUTOR_POD_IP
+ --resourceProfileId $SPARK_RESOURCE_PROFILE_ID
+ --podName $SPARK_EXECUTOR_POD_NAME
+ )
+ ;;
+
+ *)
+ # Non-spark-on-k8s command provided, proceeding in pass-through mode...
+ CMD=("$@")
+ ;;
+esac
+
+# Switch to spark if no USER specified (root by default) otherwise use USER
directly
+switch_spark_if_root() {
+ if [ $(id -u) -eq 0 ]; then
+ echo gosu spark
+ fi
+}
+
+# Execute the container CMD under tini for better hygiene
+exec $(switch_spark_if_root) /usr/bin/tini -s -- "${CMD[@]}"
diff --git a/3.3.1/scala2.12-java11-r-ubuntu/Dockerfile
b/3.3.1/scala2.12-java11-r-ubuntu/Dockerfile
new file mode 100644
index 0000000..bc2dcf7
--- /dev/null
+++ b/3.3.1/scala2.12-java11-r-ubuntu/Dockerfile
@@ -0,0 +1,82 @@
+#
+# 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 eclipse-temurin:11-jre-focal
+
+ARG spark_uid=185
+
+RUN groupadd --system --gid=${spark_uid} spark && \
+ useradd --system --uid=${spark_uid} --gid=spark spark
+
+RUN set -ex && \
+ apt-get update && \
+ ln -s /lib /lib64 && \
+ apt install -y gnupg2 wget bash tini libc6 libpam-modules krb5-user
libnss3 procps net-tools gosu && \
+ apt install -y r-base r-base-dev && \
+ mkdir -p /opt/spark && \
+ mkdir -p /opt/spark/examples && \
+ mkdir -p /opt/spark/work-dir && \
+ touch /opt/spark/RELEASE && \
+ chown -R spark:spark /opt/spark && \
+ rm /bin/sh && \
+ ln -sv /bin/bash /bin/sh && \
+ echo "auth required pam_wheel.so use_uid" >> /etc/pam.d/su && \
+ chgrp root /etc/passwd && chmod ug+rw /etc/passwd && \
+ rm -rf /var/cache/apt/* && \
+ rm -rf /var/lib/apt/lists/*
+
+# Install Apache Spark
+# https://downloads.apache.org/spark/KEYS
+ENV
SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz
\
+
SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc
\
+ GPG_KEY=86727D43E73A415F67A0B1A14E68B3E6CD473653
+
+RUN set -ex; \
+ export SPARK_TMP="$(mktemp -d)"; \
+ cd $SPARK_TMP; \
+ wget -nv -O spark.tgz "$SPARK_TGZ_URL"; \
+ wget -nv -O spark.tgz.asc "$SPARK_TGZ_ASC_URL"; \
+ export GNUPGHOME="$(mktemp -d)"; \
+ gpg --keyserver hkps://keys.openpgp.org --recv-key "$GPG_KEY" || \
+ gpg --keyserver hkps://keyserver.ubuntu.com --recv-keys "$GPG_KEY"; \
+ gpg --batch --verify spark.tgz.asc spark.tgz; \
+ gpgconf --kill all; \
+ rm -rf "$GNUPGHOME" spark.tgz.asc; \
+ \
+ tar -xf spark.tgz --strip-components=1; \
+ chown -R spark:spark .; \
+ mv jars /opt/spark/; \
+ mv bin /opt/spark/; \
+ mv sbin /opt/spark/; \
+ mv kubernetes/dockerfiles/spark/decom.sh /opt/; \
+ mv examples /opt/spark/; \
+ mv kubernetes/tests /opt/spark/; \
+ mv data /opt/spark/; \
+ mv R /opt/spark/; \
+ cd ..; \
+ rm -rf "$SPARK_TMP";
+
+COPY entrypoint.sh /opt/
+
+ENV SPARK_HOME /opt/spark
+ENV R_HOME /usr/lib/R
+
+WORKDIR /opt/spark/work-dir
+RUN chmod g+w /opt/spark/work-dir
+RUN chmod a+x /opt/decom.sh
+RUN chmod a+x /opt/entrypoint.sh
+
+ENTRYPOINT [ "/opt/entrypoint.sh" ]
diff --git a/3.3.1/scala2.12-java11-r-ubuntu/entrypoint.sh
b/3.3.1/scala2.12-java11-r-ubuntu/entrypoint.sh
new file mode 100644
index 0000000..4bb1557
--- /dev/null
+++ b/3.3.1/scala2.12-java11-r-ubuntu/entrypoint.sh
@@ -0,0 +1,114 @@
+#!/bin/bash
+#
+# 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.
+#
+
+# Check whether there is a passwd entry for the container UID
+myuid=$(id -u)
+mygid=$(id -g)
+# turn off -e for getent because it will return error code in anonymous uid
case
+set +e
+uidentry=$(getent passwd $myuid)
+set -e
+
+# If there is no passwd entry for the container UID, attempt to create one
+if [ -z "$uidentry" ] ; then
+ if [ -w /etc/passwd ] ; then
+ echo "$myuid:x:$myuid:$mygid:${SPARK_USER_NAME:-anonymous
uid}:$SPARK_HOME:/bin/false" >> /etc/passwd
+ else
+ echo "Container ENTRYPOINT failed to add passwd entry for anonymous
UID"
+ fi
+fi
+
+if [ -z "$JAVA_HOME" ]; then
+ JAVA_HOME=$(java -XshowSettings:properties -version 2>&1 > /dev/null | grep
'java.home' | awk '{print $3}')
+fi
+
+SPARK_CLASSPATH="$SPARK_CLASSPATH:${SPARK_HOME}/jars/*"
+env | grep SPARK_JAVA_OPT_ | sort -t_ -k4 -n | sed 's/[^=]*=\(.*\)/\1/g' >
/tmp/java_opts.txt
+readarray -t SPARK_EXECUTOR_JAVA_OPTS < /tmp/java_opts.txt
+
+if [ -n "$SPARK_EXTRA_CLASSPATH" ]; then
+ SPARK_CLASSPATH="$SPARK_CLASSPATH:$SPARK_EXTRA_CLASSPATH"
+fi
+
+if ! [ -z ${PYSPARK_PYTHON+x} ]; then
+ export PYSPARK_PYTHON
+fi
+if ! [ -z ${PYSPARK_DRIVER_PYTHON+x} ]; then
+ export PYSPARK_DRIVER_PYTHON
+fi
+
+# If HADOOP_HOME is set and SPARK_DIST_CLASSPATH is not set, set it here so
Hadoop jars are available to the executor.
+# It does not set SPARK_DIST_CLASSPATH if already set, to avoid overriding
customizations of this value from elsewhere e.g. Docker/K8s.
+if [ -n "${HADOOP_HOME}" ] && [ -z "${SPARK_DIST_CLASSPATH}" ]; then
+ export SPARK_DIST_CLASSPATH="$($HADOOP_HOME/bin/hadoop classpath)"
+fi
+
+if ! [ -z ${HADOOP_CONF_DIR+x} ]; then
+ SPARK_CLASSPATH="$HADOOP_CONF_DIR:$SPARK_CLASSPATH";
+fi
+
+if ! [ -z ${SPARK_CONF_DIR+x} ]; then
+ SPARK_CLASSPATH="$SPARK_CONF_DIR:$SPARK_CLASSPATH";
+elif ! [ -z ${SPARK_HOME+x} ]; then
+ SPARK_CLASSPATH="$SPARK_HOME/conf:$SPARK_CLASSPATH";
+fi
+
+case "$1" in
+ driver)
+ shift 1
+ CMD=(
+ "$SPARK_HOME/bin/spark-submit"
+ --conf "spark.driver.bindAddress=$SPARK_DRIVER_BIND_ADDRESS"
+ --deploy-mode client
+ "$@"
+ )
+ ;;
+ executor)
+ shift 1
+ CMD=(
+ ${JAVA_HOME}/bin/java
+ "${SPARK_EXECUTOR_JAVA_OPTS[@]}"
+ -Xms$SPARK_EXECUTOR_MEMORY
+ -Xmx$SPARK_EXECUTOR_MEMORY
+ -cp "$SPARK_CLASSPATH:$SPARK_DIST_CLASSPATH"
+ org.apache.spark.scheduler.cluster.k8s.KubernetesExecutorBackend
+ --driver-url $SPARK_DRIVER_URL
+ --executor-id $SPARK_EXECUTOR_ID
+ --cores $SPARK_EXECUTOR_CORES
+ --app-id $SPARK_APPLICATION_ID
+ --hostname $SPARK_EXECUTOR_POD_IP
+ --resourceProfileId $SPARK_RESOURCE_PROFILE_ID
+ --podName $SPARK_EXECUTOR_POD_NAME
+ )
+ ;;
+
+ *)
+ # Non-spark-on-k8s command provided, proceeding in pass-through mode...
+ CMD=("$@")
+ ;;
+esac
+
+# Switch to spark if no USER specified (root by default) otherwise use USER
directly
+switch_spark_if_root() {
+ if [ $(id -u) -eq 0 ]; then
+ echo gosu spark
+ fi
+}
+
+# Execute the container CMD under tini for better hygiene
+exec $(switch_spark_if_root) /usr/bin/tini -s -- "${CMD[@]}"
diff --git a/3.3.1/scala2.12-java11-ubuntu/Dockerfile
b/3.3.1/scala2.12-java11-ubuntu/Dockerfile
new file mode 100644
index 0000000..c732406
--- /dev/null
+++ b/3.3.1/scala2.12-java11-ubuntu/Dockerfile
@@ -0,0 +1,79 @@
+#
+# 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 eclipse-temurin:11-jre-focal
+
+ARG spark_uid=185
+
+RUN groupadd --system --gid=${spark_uid} spark && \
+ useradd --system --uid=${spark_uid} --gid=spark spark
+
+RUN set -ex && \
+ apt-get update && \
+ ln -s /lib /lib64 && \
+ apt install -y gnupg2 wget bash tini libc6 libpam-modules krb5-user
libnss3 procps net-tools gosu && \
+ mkdir -p /opt/spark && \
+ mkdir -p /opt/spark/examples && \
+ mkdir -p /opt/spark/work-dir && \
+ touch /opt/spark/RELEASE && \
+ chown -R spark:spark /opt/spark && \
+ rm /bin/sh && \
+ ln -sv /bin/bash /bin/sh && \
+ echo "auth required pam_wheel.so use_uid" >> /etc/pam.d/su && \
+ chgrp root /etc/passwd && chmod ug+rw /etc/passwd && \
+ rm -rf /var/cache/apt/* && \
+ rm -rf /var/lib/apt/lists/*
+
+# Install Apache Spark
+# https://downloads.apache.org/spark/KEYS
+ENV
SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz
\
+
SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc
\
+ GPG_KEY=86727D43E73A415F67A0B1A14E68B3E6CD473653
+
+RUN set -ex; \
+ export SPARK_TMP="$(mktemp -d)"; \
+ cd $SPARK_TMP; \
+ wget -nv -O spark.tgz "$SPARK_TGZ_URL"; \
+ wget -nv -O spark.tgz.asc "$SPARK_TGZ_ASC_URL"; \
+ export GNUPGHOME="$(mktemp -d)"; \
+ gpg --keyserver hkps://keys.openpgp.org --recv-key "$GPG_KEY" || \
+ gpg --keyserver hkps://keyserver.ubuntu.com --recv-keys "$GPG_KEY"; \
+ gpg --batch --verify spark.tgz.asc spark.tgz; \
+ gpgconf --kill all; \
+ rm -rf "$GNUPGHOME" spark.tgz.asc; \
+ \
+ tar -xf spark.tgz --strip-components=1; \
+ chown -R spark:spark .; \
+ mv jars /opt/spark/; \
+ mv bin /opt/spark/; \
+ mv sbin /opt/spark/; \
+ mv kubernetes/dockerfiles/spark/decom.sh /opt/; \
+ mv examples /opt/spark/; \
+ mv kubernetes/tests /opt/spark/; \
+ mv data /opt/spark/; \
+ cd ..; \
+ rm -rf "$SPARK_TMP";
+
+COPY entrypoint.sh /opt/
+
+ENV SPARK_HOME /opt/spark
+
+WORKDIR /opt/spark/work-dir
+RUN chmod g+w /opt/spark/work-dir
+RUN chmod a+x /opt/decom.sh
+RUN chmod a+x /opt/entrypoint.sh
+
+ENTRYPOINT [ "/opt/entrypoint.sh" ]
diff --git a/3.3.1/scala2.12-java11-ubuntu/entrypoint.sh
b/3.3.1/scala2.12-java11-ubuntu/entrypoint.sh
new file mode 100644
index 0000000..4bb1557
--- /dev/null
+++ b/3.3.1/scala2.12-java11-ubuntu/entrypoint.sh
@@ -0,0 +1,114 @@
+#!/bin/bash
+#
+# 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.
+#
+
+# Check whether there is a passwd entry for the container UID
+myuid=$(id -u)
+mygid=$(id -g)
+# turn off -e for getent because it will return error code in anonymous uid
case
+set +e
+uidentry=$(getent passwd $myuid)
+set -e
+
+# If there is no passwd entry for the container UID, attempt to create one
+if [ -z "$uidentry" ] ; then
+ if [ -w /etc/passwd ] ; then
+ echo "$myuid:x:$myuid:$mygid:${SPARK_USER_NAME:-anonymous
uid}:$SPARK_HOME:/bin/false" >> /etc/passwd
+ else
+ echo "Container ENTRYPOINT failed to add passwd entry for anonymous
UID"
+ fi
+fi
+
+if [ -z "$JAVA_HOME" ]; then
+ JAVA_HOME=$(java -XshowSettings:properties -version 2>&1 > /dev/null | grep
'java.home' | awk '{print $3}')
+fi
+
+SPARK_CLASSPATH="$SPARK_CLASSPATH:${SPARK_HOME}/jars/*"
+env | grep SPARK_JAVA_OPT_ | sort -t_ -k4 -n | sed 's/[^=]*=\(.*\)/\1/g' >
/tmp/java_opts.txt
+readarray -t SPARK_EXECUTOR_JAVA_OPTS < /tmp/java_opts.txt
+
+if [ -n "$SPARK_EXTRA_CLASSPATH" ]; then
+ SPARK_CLASSPATH="$SPARK_CLASSPATH:$SPARK_EXTRA_CLASSPATH"
+fi
+
+if ! [ -z ${PYSPARK_PYTHON+x} ]; then
+ export PYSPARK_PYTHON
+fi
+if ! [ -z ${PYSPARK_DRIVER_PYTHON+x} ]; then
+ export PYSPARK_DRIVER_PYTHON
+fi
+
+# If HADOOP_HOME is set and SPARK_DIST_CLASSPATH is not set, set it here so
Hadoop jars are available to the executor.
+# It does not set SPARK_DIST_CLASSPATH if already set, to avoid overriding
customizations of this value from elsewhere e.g. Docker/K8s.
+if [ -n "${HADOOP_HOME}" ] && [ -z "${SPARK_DIST_CLASSPATH}" ]; then
+ export SPARK_DIST_CLASSPATH="$($HADOOP_HOME/bin/hadoop classpath)"
+fi
+
+if ! [ -z ${HADOOP_CONF_DIR+x} ]; then
+ SPARK_CLASSPATH="$HADOOP_CONF_DIR:$SPARK_CLASSPATH";
+fi
+
+if ! [ -z ${SPARK_CONF_DIR+x} ]; then
+ SPARK_CLASSPATH="$SPARK_CONF_DIR:$SPARK_CLASSPATH";
+elif ! [ -z ${SPARK_HOME+x} ]; then
+ SPARK_CLASSPATH="$SPARK_HOME/conf:$SPARK_CLASSPATH";
+fi
+
+case "$1" in
+ driver)
+ shift 1
+ CMD=(
+ "$SPARK_HOME/bin/spark-submit"
+ --conf "spark.driver.bindAddress=$SPARK_DRIVER_BIND_ADDRESS"
+ --deploy-mode client
+ "$@"
+ )
+ ;;
+ executor)
+ shift 1
+ CMD=(
+ ${JAVA_HOME}/bin/java
+ "${SPARK_EXECUTOR_JAVA_OPTS[@]}"
+ -Xms$SPARK_EXECUTOR_MEMORY
+ -Xmx$SPARK_EXECUTOR_MEMORY
+ -cp "$SPARK_CLASSPATH:$SPARK_DIST_CLASSPATH"
+ org.apache.spark.scheduler.cluster.k8s.KubernetesExecutorBackend
+ --driver-url $SPARK_DRIVER_URL
+ --executor-id $SPARK_EXECUTOR_ID
+ --cores $SPARK_EXECUTOR_CORES
+ --app-id $SPARK_APPLICATION_ID
+ --hostname $SPARK_EXECUTOR_POD_IP
+ --resourceProfileId $SPARK_RESOURCE_PROFILE_ID
+ --podName $SPARK_EXECUTOR_POD_NAME
+ )
+ ;;
+
+ *)
+ # Non-spark-on-k8s command provided, proceeding in pass-through mode...
+ CMD=("$@")
+ ;;
+esac
+
+# Switch to spark if no USER specified (root by default) otherwise use USER
directly
+switch_spark_if_root() {
+ if [ $(id -u) -eq 0 ]; then
+ echo gosu spark
+ fi
+}
+
+# Execute the container CMD under tini for better hygiene
+exec $(switch_spark_if_root) /usr/bin/tini -s -- "${CMD[@]}"
diff --git a/tools/template.py b/tools/template.py
index 721f968..7f80dfe 100755
--- a/tools/template.py
+++ b/tools/template.py
@@ -24,6 +24,8 @@ from jinja2 import Environment, FileSystemLoader
GPG_KEY_DICT = {
# issuer "maxg...@apache.org"
"3.3.0": "80FB8EBE8EBA68504989703491B5DC815DBF10D3",
+ # issuer "yumw...@apache.org"
+ "3.3.1": "86727D43E73A415F67A0B1A14E68B3E6CD473653",
}
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
