[HUDI-1851] Adding test suite long running automate scripts for docker (#2880)

docker/demo/config/test-suite/templates/clustering.yaml.template

@@ -0,0 +1,76 @@
+# 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.
+dag_name: NAME-clustering.yaml
+dag_rounds: clustering_num_iterations
+dag_intermittent_delay_mins: clustering_delay_in_mins
+dag_content:
+  first_insert:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: InsertNode
+    deps: none
+  second_insert:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 10000
+    deps: first_insert
+    type: InsertNode
+  third_insert:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 300
+    deps: second_insert
+    type: InsertNode
+  first_delete:
+    config:
+      num_partitions_delete: 1
+      num_records_delete: 9000
+    type: DeleteNode
+    deps: third_insert
+  first_hive_sync:
+    config:
+      queue_name: "adhoc"
+      engine: "mr"
+    type: HiveSyncNode
+    deps: first_delete
+  first_validate:
+    config:
+      validate_hive: true
+    type: ValidateDatasetNode
+    deps: first_hive_sync
+  first_cluster:
+    config:
+      execute_itr_count: clustering_itr_count
+    type: ClusteringNode
+    deps: first_validate
+  second_hive_sync:
+    config:
+      queue_name: "adhoc"
+      engine: "mr"
+    type: HiveSyncNode
+    deps: first_cluster
+  second_validate:
+    config:
+      validate_hive: true
+    type: ValidateDatasetNode
+    deps: second_hive_sync

docker/demo/config/test-suite/templates/long-running.yaml.template

@@ -0,0 +1,89 @@
+# 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.
+dag_name: NAME-long-running-multi-partitions.yaml
+dag_rounds: num_iterations
+dag_intermittent_delay_mins: delay_in_mins
+dag_content:
+  first_insert:
+    config:
+      record_size: 1000
+      num_partitions_insert: 5
+      repeat_count: 1
+      num_records_insert: 1000
+    type: InsertNode
+    deps: none
+  second_insert:
+    config:
+      record_size: 1000
+      num_partitions_insert: 50
+      repeat_count: 1
+      num_records_insert: 10000
+    deps: first_insert
+    type: InsertNode
+  third_insert:
+    config:
+      record_size: 1000
+      num_partitions_insert: 2
+      repeat_count: 1
+      num_records_insert: 300
+    deps: second_insert
+    type: InsertNode
+  first_hive_sync:
+    config:
+      queue_name: "adhoc"
+      engine: "mr"
+    type: HiveSyncNode
+    deps: third_insert
+  first_validate:
+    config:
+      validate_hive: true
+    type: ValidateDatasetNode
+    deps: first_hive_sync
+  first_upsert:
+    config:
+      record_size: 1000
+      num_partitions_insert: 2
+      num_records_insert: 300
+      repeat_count: 1
+      num_records_upsert: 100
+      num_partitions_upsert: 1
+    type: UpsertNode
+    deps: first_validate
+  first_delete:
+    config:
+      num_partitions_delete: 50
+      num_records_delete: 8000
+    type: DeleteNode
+    deps: first_upsert
+  second_hive_sync:
+    config:
+      queue_name: "adhoc"
+      engine: "mr"
+    type: HiveSyncNode
+    deps: first_delete
+  second_validate:
+    config:
+      validate_hive: true
+      delete_input_data: true
+    type: ValidateDatasetNode
+    deps: second_hive_sync
+  last_validate:
+    config:
+      execute_itr_count: 50
+      validate_clean: true
+      validate_archival: true
+    type: ValidateAsyncOperations
+    deps: second_validate

docker/demo/config/test-suite/templates/spark_command.txt.template

@@ -0,0 +1,34 @@
+spark-submit \
+--packages org.apache.spark:spark-avro_2.11:2.4.0 \
+--conf spark.task.cpus=1 \
+--conf spark.executor.cores=1 \
+--conf spark.task.maxFailures=100 \
+--conf spark.memory.fraction=0.4  \
+--conf spark.rdd.compress=true  \
+--conf spark.kryoserializer.buffer.max=2000m \
+--conf spark.serializer=org.apache.spark.serializer.KryoSerializer \
+--conf spark.memory.storageFraction=0.1 \
+--conf spark.shuffle.service.enabled=true  \
+--conf spark.sql.hive.convertMetastoreParquet=false  \
+--conf spark.driver.maxResultSize=12g \
+--conf spark.executor.heartbeatInterval=120s \
+--conf spark.network.timeout=600s \
+--conf spark.yarn.max.executor.failures=10 \
+--conf spark.sql.catalogImplementation=hive \
+--class org.apache.hudi.integ.testsuite.HoodieTestSuiteJob \
+/opt/JAR_NAME \
+--source-ordering-field test_suite_source_ordering_field \
+--use-deltastreamer \
+--target-base-path OUTPUT_PATH \
+--input-base-path INPUT_PATH \
+--target-table table1 \
+--props file:/opt/staging/test.properties \
+--schemaprovider-class org.apache.hudi.integ.testsuite.schema.TestSuiteFileBasedSchemaProvider \
+--source-class org.apache.hudi.utilities.sources.AvroDFSSource \
+--input-file-size 125829120 \
+--workload-yaml-path file:/opt/staging/input_yaml \
+--workload-generator-classname org.apache.hudi.integ.testsuite.dag.WorkflowDagGenerator \
+--table-type TABLE_TYPE \
+--compact-scheduling-minshare 1 \
+--clean-input \
+--clean-output

docker/demo/config/test-suite/templates/test.properties.template

@@ -0,0 +1,50 @@
+
+#  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.
+
+hoodie.insert.shuffle.parallelism=100
+hoodie.upsert.shuffle.parallelism=100
+hoodie.bulkinsert.shuffle.parallelism=100
+
+hoodie.deltastreamer.source.test.num_partitions=100
+hoodie.deltastreamer.source.test.datagen.use_rocksdb_for_storing_existing_keys=false
+hoodie.deltastreamer.source.test.max_unique_records=100000000
+hoodie.embed.timeline.server=false
+hoodie.deltastreamer.source.input.selector=org.apache.hudi.integ.testsuite.helpers.DFSTestSuitePathSelector
+
+hoodie.datasource.hive_sync.skip_ro_suffix=true
+
+hoodie.datasource.write.recordkey.field=_row_key
+hoodie.datasource.write.keygenerator.class=org.apache.hudi.keygen.TimestampBasedKeyGenerator
+hoodie.datasource.write.partitionpath.field=timestamp
+
+hoodie.clustering.plan.strategy.sort.columns=_row_key
+hoodie.clustering.plan.strategy.daybased.lookback.partitions=0
+hoodie.clustering.inline.max.commits=1
+
+hoodie.deltastreamer.source.dfs.root=INPUT_PATH
+hoodie.deltastreamer.schemaprovider.target.schema.file=file:/var/hoodie/ws/docker/demo/config/test-suite/source.avsc
+hoodie.deltastreamer.schemaprovider.source.schema.file=file:/var/hoodie/ws/docker/demo/config/test-suite/source.avsc
+hoodie.deltastreamer.keygen.timebased.timestamp.type=UNIX_TIMESTAMP
+hoodie.deltastreamer.keygen.timebased.output.dateformat=yyyy/MM/dd
+
+hoodie.datasource.hive_sync.jdbcurl=jdbc:hive2://hiveserver:10000/
+hoodie.datasource.hive_sync.database=testdb
+hoodie.datasource.hive_sync.table=table1
+hoodie.datasource.hive_sync.assume_date_partitioning=false
+hoodie.datasource.hive_sync.partition_fields=_hoodie_partition_path
+hoodie.datasource.hive_sync.partition_extractor_class=org.apache.hudi.hive.SlashEncodedDayPartitionValueExtractor
+