diff --git a/.github/workflows/pr_tests_spark.yml b/.github/workflows/pr_tests_spark.yml index f6a74ced..3085d4ea 100644 --- a/.github/workflows/pr_tests_spark.yml +++ b/.github/workflows/pr_tests_spark.yml @@ -109,7 +109,8 @@ jobs: # Install AWS Glue libraries and Iceberg RUN curl -L -o /spark/jars/aws-java-sdk-bundle-1.11.1026.jar https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-bundle/1.11.1026/aws-java-sdk-bundle-1.11.1026.jar && \ curl -L -o /spark/jars/hadoop-aws-3.3.4.jar https://repo1.maven.org/maven2/org/apache/hadoop/hadoop-aws/3.3.4/hadoop-aws-3.3.4.jar && \ - curl -L -o /spark/jars/iceberg-spark-runtime-3.5_2.12-\${ICEBERG_VERSION}.jar https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-spark-runtime-3.5_2.12/\${ICEBERG_VERSION}/iceberg-spark-runtime-3.5_2.12-\${ICEBERG_VERSION}.jar + curl -L -o /spark/jars/iceberg-spark-runtime-3.5_2.12-\${ICEBERG_VERSION}.jar https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-spark-runtime-3.5_2.12/\${ICEBERG_VERSION}/iceberg-spark-runtime-3.5_2.12-\${ICEBERG_VERSION}.jar && \ + curl -L -o /spark/jars/iceberg-aws-bundle-\${ICEBERG_VERSION}.jar https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-aws-bundle/\${ICEBERG_VERSION}/iceberg-aws-bundle-\${ICEBERG_VERSION}.jar WORKDIR \${SPARK_HOME} @@ -122,6 +123,8 @@ jobs: spark.master spark://spark-master:7077 spark.sql.warehouse.dir s3a://dbt-spark-iceberg/github-integration-testing spark.sql.extensions org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions + spark.sql.catalog.spark_catalog org.apache.iceberg.spark.SparkSessionCatalog + spark.sql.catalog.spark_catalog.type hive spark.sql.catalog.glue org.apache.iceberg.spark.SparkCatalog spark.sql.catalog.glue.catalog-impl org.apache.iceberg.aws.glue.GlueCatalog spark.sql.catalog.glue.warehouse s3a://dbt-spark-iceberg/github-integration-testing @@ -189,7 +192,7 @@ jobs: - spark-network thrift-server: build: . - command: ["/bin/bash", "-c", "sleep 30 && /spark/sbin/start-thriftserver.sh --master spark://spark-master:7077 --driver-memory 2g --executor-memory 3g --hiveconf hive.server2.thrift.port=10000 --hiveconf hive.server2.thrift.bind.host=0.0.0.0 --conf spark.sql.hive.thriftServer.async=true --conf spark.sql.hive.thriftServer.workerQueue.size=2000 --conf spark.sql.hive.thriftServer.maxWorkerThreads=100 --conf spark.sql.hive.thriftServer.minWorkerThreads=50 && tail -f /spark/logs/spark--org.apache.spark.sql.hive.thriftserver.HiveThriftServer2-*.out"] + command: ["/bin/bash", "-c", "sleep 30 && /spark/sbin/start-thriftserver.sh --master spark://spark-master:7077 --driver-memory 2g --executor-memory 3g --hiveconf hive.server2.thrift.port=10000 --hiveconf hive.server2.thrift.bind.host=0.0.0.0 --conf spark.sql.hive.thriftServer.async=true --conf spark.sql.hive.thriftServer.workerQueue.size=2000 --conf spark.sql.hive.thriftServer.maxWorkerThreads=100 --conf spark.sql.hive.thriftServer.minWorkerThreads=50 --jars /spark/jars/iceberg-spark-runtime-3.5_2.12-1.3.1.jar,/spark/jars/iceberg-aws-bundle-1.3.1.jar && tail -f /spark/logs/spark--org.apache.spark.sql.hive.thriftserver.HiveThriftServer2-*.out"] ports: - '10000:10000' depends_on: @@ -300,9 +303,4 @@ jobs: - name: 'Post-test: Drop ci schemas' run: | - dbt run-operation post_ci_cleanup --target spark - - - name: Cleanup Spark cluster - if: always() - run: | - docker-compose down \ No newline at end of file + dbt run-operation post_ \ No newline at end of file