yihua commented on code in PR #9136:
URL: https://github.com/apache/hudi/pull/9136#discussion_r1273945242
##########
.github/workflows/bot.yml:
##########
@@ -112,6 +112,61 @@ jobs:
run:
mvn test -Pfunctional-tests -D"$SCALA_PROFILE" -D"$SPARK_PROFILE"
-pl "$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
+ test-spark-java17:
+ runs-on: ubuntu-latest
+ strategy:
+ matrix:
+ include:
+ - scalaProfile: "scala-2.12"
+ sparkProfile: "spark3.3"
+ sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
+ - scalaProfile: "scala-2.12"
+ sparkProfile: "spark3.4"
+ sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
+
+ steps:
+ - uses: actions/checkout@v3
+ - name: Set up JDK 8
+ uses: actions/setup-java@v3
+ with:
+ java-version: '8'
+ distribution: 'adopt'
+ architecture: x64
+ - name: Build Project
+ env:
+ SCALA_PROFILE: ${{ matrix.scalaProfile }}
+ SPARK_PROFILE: ${{ matrix.sparkProfile }}
+ run:
+ mvn clean install -D"$SCALA_PROFILE" -D"$SPARK_PROFILE"
-DskipTests=true $MVN_ARGS
+ - name: Set up JDK 17
+ uses: actions/setup-java@v3
+ with:
+ java-version: '17'
+ distribution: 'adopt'
+ architecture: x64
+ - name: Quickstart Test
+ env:
+ SCALA_PROFILE: ${{ matrix.scalaProfile }}
+ SPARK_PROFILE: ${{ matrix.sparkProfile }}
+ run:
+ mvn test -Punit-tests -Pjava17 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE"
-pl hudi-examples/hudi-examples-spark $MVN_ARGS
+ - name: UT - Common & Spark
+ env:
+ SCALA_PROFILE: ${{ matrix.scalaProfile }}
+ SPARK_PROFILE: ${{ matrix.sparkProfile }}
+ SPARK_MODULES: ${{ matrix.sparkModules }}
+ if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2
as it's covered by Azure CI
Review Comment:
nit: not required.
##########
.github/workflows/bot.yml:
##########
@@ -151,6 +206,34 @@ jobs:
mvn clean install -Pintegration-tests -D"$SCALA_PROFILE"
-D"$FLINK_PROFILE" -pl hudi-flink-datasource/hudi-flink -am
-Davro.version=1.10.0 -DskipTests=true $MVN_ARGS
mvn verify -Pintegration-tests -D"$SCALA_PROFILE" -D"$FLINK_PROFILE"
-pl hudi-flink-datasource/hudi-flink $MVN_ARGS
+ docker-java17-test:
+ runs-on: ubuntu-latest
+ strategy:
+ matrix:
+ include:
+ - flinkProfile: 'flink1.17'
+ sparkProfile: 'spark3.4'
+ sparkRuntime: 'spark3.4.0'
+
+ steps:
+ - uses: actions/checkout@v3
+ - name: Set up JDK 8
+ uses: actions/setup-java@v3
+ with:
+ java-version: '8'
+ distribution: 'adopt'
+ architecture: x64
+ - name: UT/FT - Docker Test - OpenJDK 17
+ env:
+ FLINK_PROFILE: ${{ matrix.flinkProfile }}
+ SPARK_PROFILE: ${{ matrix.sparkProfile }}
+ SPARK_RUNTIME: ${{ matrix.sparkRuntime }}
+ SCALA_PROFILE: 'scala-2.12'
+ if: ${{ env.SPARK_PROFILE >= 'spark3.4' }} # Only support Spark 3.4
for now
Review Comment:
nit: not required.
##########
packaging/bundle-validation/run_docker_java17.sh:
##########
@@ -0,0 +1,116 @@
+#!/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.
+
+echo "SPARK_RUNTIME: $SPARK_RUNTIME SPARK_PROFILE (optional): $SPARK_PROFILE"
+echo "SCALA_PROFILE: $SCALA_PROFILE"
+CONTAINER_NAME=hudi_docker
+DOCKER_TEST_DIR=/opt/bundle-validation/docker-test
+
+# choose versions based on build profiles
+if [[ ${SPARK_RUNTIME} == 'spark2.4.8' ]]; then
+ HADOOP_VERSION=2.7.7
+ HIVE_VERSION=2.3.9
+ DERBY_VERSION=10.10.2.0
+ FLINK_VERSION=1.13.6
+ SPARK_VERSION=2.4.8
+ SPARK_HADOOP_VERSION=2.7
+ CONFLUENT_VERSION=5.5.12
+ KAFKA_CONNECT_HDFS_VERSION=10.1.13
+ IMAGE_TAG=flink1136hive239spark248
+elif [[ ${SPARK_RUNTIME} == 'spark3.0.2' ]]; then
+ HADOOP_VERSION=2.7.7
+ HIVE_VERSION=3.1.3
+ DERBY_VERSION=10.14.1.0
+ FLINK_VERSION=1.14.6
+ SPARK_VERSION=3.0.2
+ SPARK_HADOOP_VERSION=2.7
+ CONFLUENT_VERSION=5.5.12
+ KAFKA_CONNECT_HDFS_VERSION=10.1.13
+ IMAGE_TAG=flink1146hive313spark302
+elif [[ ${SPARK_RUNTIME} == 'spark3.1.3' ]]; then
+ HADOOP_VERSION=2.7.7
+ HIVE_VERSION=3.1.3
+ DERBY_VERSION=10.14.1.0
+ FLINK_VERSION=1.13.6
+ SPARK_VERSION=3.1.3
+ SPARK_HADOOP_VERSION=2.7
+ CONFLUENT_VERSION=5.5.12
+ KAFKA_CONNECT_HDFS_VERSION=10.1.13
+ IMAGE_TAG=flink1136hive313spark313
+elif [[ ${SPARK_RUNTIME} == 'spark3.2.3' ]]; then
+ HADOOP_VERSION=2.7.7
+ HIVE_VERSION=3.1.3
+ DERBY_VERSION=10.14.1.0
+ FLINK_VERSION=1.14.6
+ SPARK_VERSION=3.2.3
+ SPARK_HADOOP_VERSION=2.7
+ CONFLUENT_VERSION=5.5.12
+ KAFKA_CONNECT_HDFS_VERSION=10.1.13
+ IMAGE_TAG=flink1146hive313spark323
Review Comment:
nit: older Spark versions can be removed.
##########
pom.xml:
##########
@@ -156,7 +156,7 @@
<flink.clients.artifactId>flink-clients</flink.clients.artifactId>
<flink.connector.kafka.artifactId>flink-connector-kafka</flink.connector.kafka.artifactId>
<flink.hadoop.compatibility.artifactId>flink-hadoop-compatibility_2.12</flink.hadoop.compatibility.artifactId>
- <rocksdbjni.version>5.17.2</rocksdbjni.version>
+ <rocksdbjni.version>7.5.3</rocksdbjni.version>
Review Comment:
After reading the code, `RocksDbBasedFileSystemView` is the only place using
RocksDb. So this should be ok.
##########
.github/workflows/bot.yml:
##########
@@ -112,6 +112,61 @@ jobs:
run:
mvn test -Pfunctional-tests -D"$SCALA_PROFILE" -D"$SPARK_PROFILE"
-pl "$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
+ test-spark-java17:
+ runs-on: ubuntu-latest
+ strategy:
+ matrix:
+ include:
+ - scalaProfile: "scala-2.12"
+ sparkProfile: "spark3.3"
+ sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
+ - scalaProfile: "scala-2.12"
+ sparkProfile: "spark3.4"
+ sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
+
+ steps:
+ - uses: actions/checkout@v3
+ - name: Set up JDK 8
+ uses: actions/setup-java@v3
+ with:
+ java-version: '8'
+ distribution: 'adopt'
+ architecture: x64
+ - name: Build Project
+ env:
+ SCALA_PROFILE: ${{ matrix.scalaProfile }}
+ SPARK_PROFILE: ${{ matrix.sparkProfile }}
+ run:
+ mvn clean install -D"$SCALA_PROFILE" -D"$SPARK_PROFILE"
-DskipTests=true $MVN_ARGS
+ - name: Set up JDK 17
+ uses: actions/setup-java@v3
+ with:
+ java-version: '17'
+ distribution: 'adopt'
+ architecture: x64
+ - name: Quickstart Test
+ env:
+ SCALA_PROFILE: ${{ matrix.scalaProfile }}
+ SPARK_PROFILE: ${{ matrix.sparkProfile }}
+ run:
+ mvn test -Punit-tests -Pjava17 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE"
-pl hudi-examples/hudi-examples-spark $MVN_ARGS
+ - name: UT - Common & Spark
+ env:
+ SCALA_PROFILE: ${{ matrix.scalaProfile }}
+ SPARK_PROFILE: ${{ matrix.sparkProfile }}
+ SPARK_MODULES: ${{ matrix.sparkModules }}
+ if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2
as it's covered by Azure CI
+ run:
+ mvn test -Punit-tests -Pjava17 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE"
-pl "hudi-common,$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
+ - name: FT - Spark
+ env:
+ SCALA_PROFILE: ${{ matrix.scalaProfile }}
+ SPARK_PROFILE: ${{ matrix.sparkProfile }}
+ SPARK_MODULES: ${{ matrix.sparkModules }}
+ if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2
as it's covered by Azure CI
Review Comment:
nit: not required.
##########
hudi-common/pom.xml:
##########
@@ -248,6 +248,13 @@
</exclusions>
</dependency>
+ <dependency>
+ <groupId>org.apache.spark</groupId>
+
<artifactId>spark-streaming-kafka-0-10_${scala.binary.version}</artifactId>
+ <scope>test</scope>
+ <version>${spark.version}</version>
+ </dependency>
Review Comment:
Which test caused the failure? Could we move this to the client module in a
follow-up, if the test is the client module?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@hudi.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
