Created
December 30, 2020 19:42
-
-
Save nsivabalan/086f77cb25b8927fcf955111e35ae217 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 \ | |
/home/sivabala/test_suite/hudi-integ-test-bundle-0.6.1-SNAPSHOT.jar \ | |
--source-ordering-field test_suite_source_ordering_field \ | |
--use-deltastreamer \ | |
--target-base-path /tmp/test_suite_trial1/output \ | |
--input-base-path /tmp/test_suite_trial1/input \ | |
--target-table table1 \ | |
--props file:/home/sivabala/test_suite/prod_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:/home/sivabala/test_suite/complex-dag-cow.yaml \ | |
--workload-generator-classname org.apache.hudi.integ.testsuite.dag.WorkflowDagGenerator \ | |
--table-type COPY_ON_WRITE \ | |
--compact-scheduling-minshare 1 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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.insert.shuffle.parallelism=100 | |
hoodie.upsert.shuffle.parallelism=100 | |
hoodie.bulkinsert.shuffle.parallelism=100 | |
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.deltastreamer.source.dfs.root=/user/hive/warehouse/hudi-integ-test-suite/input | |
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 | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment