vinothchandar commented on a change in pull request #991: Hudi Test Suite (Refactor) URL: https://github.com/apache/incubator-hudi/pull/991#discussion_r344981980
########## File path: hudi-bench/src/main/java/org/apache/hudi/bench/generator/DeltaGenerator.java ########## @@ -0,0 +1,236 @@ +/* + * 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. + */ + +package org.apache.hudi.bench.generator; + +import com.google.common.annotations.VisibleForTesting; +import java.io.IOException; +import java.io.Serializable; +import java.io.UncheckedIOException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashMap; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.stream.StreamSupport; +import org.apache.avro.generic.GenericRecord; +import org.apache.hudi.KeyGenerator; +import org.apache.hudi.bench.DeltaOutputType; +import org.apache.hudi.bench.DeltaWriterAdapter; +import org.apache.hudi.bench.DeltaWriterFactory; +import org.apache.hudi.bench.configuration.DFSDeltaConfig; +import org.apache.hudi.bench.configuration.DeltaConfig; +import org.apache.hudi.bench.configuration.DeltaConfig.Config; +import org.apache.hudi.bench.converter.UpdateConverter; +import org.apache.hudi.bench.reader.DFSAvroDeltaInputReader; +import org.apache.hudi.bench.reader.DFSHoodieDatasetInputReader; +import org.apache.hudi.bench.reader.DeltaInputReader; +import org.apache.hudi.bench.writer.WriteStats; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.utilities.converter.Converter; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.storage.StorageLevel; +import scala.Tuple2; + +/** + * The delta generator generates all types of workloads (insert, update) for the given configs + */ +public class DeltaGenerator implements Serializable { + + private static Logger log = LogManager.getLogger(DFSHoodieDatasetInputReader.class); + + private DeltaConfig sinkConfig; + private transient JavaSparkContext jsc; + private transient SparkSession sparkSession; + private String schemaStr; + private List<String> recordRowKeyFieldNames; + private List<String> partitionPathFieldNames; + private int batchId; + + public DeltaGenerator(DeltaConfig sinkConfig, JavaSparkContext jsc, SparkSession sparkSession, String schemaStr, + KeyGenerator keyGenerator) { + this.sinkConfig = sinkConfig; + this.jsc = jsc; + this.sparkSession = sparkSession; + this.schemaStr = schemaStr; + this.recordRowKeyFieldNames = keyGenerator.getRecordKeyFields(); + this.partitionPathFieldNames = keyGenerator.getPartitionPathFields(); + } + + public JavaRDD<WriteStats> writeRecords(JavaRDD<GenericRecord> records) { + // The following creates a new anonymous function for iterator and hence results in serialization issues + JavaRDD<WriteStats> ws = records.mapPartitions(itr -> { + try { + // TODO : change this factory and adapter stuff + DeltaWriterAdapter<GenericRecord> deltaWriterAdapter = DeltaWriterFactory + .getDeltaWriterAdapter(sinkConfig, batchId); + return Collections.singletonList(deltaWriterAdapter.write(itr)).iterator(); + } catch (IOException io) { + throw new UncheckedIOException(io); + } + }).flatMap(List::iterator); + batchId++; + return ws; + } + + public JavaRDD<GenericRecord> generateInserts(Config operation) { + long recordsPerPartition = operation.getNumRecordsInsert(); + int minPayloadSize = operation.getRecordSize(); + JavaRDD<GenericRecord> inputBatch = jsc.parallelize(Collections.EMPTY_LIST) + .repartition(operation.getNumInsertPartitions()).mapPartitions(p -> { + return new LazyRecordGeneratorIterator(new FlexibleSchemaRecordGenerationIterator(recordsPerPartition, + minPayloadSize, schemaStr, partitionPathFieldNames)); + }); + return inputBatch; + } + + public JavaRDD<GenericRecord> generateUpdates(Config config) throws IOException { + if (sinkConfig.getDeltaOutputType() == DeltaOutputType.DFS) { + JavaRDD<GenericRecord> inserts = null; + if (config.getNumRecordsInsert() > 0) { + inserts = generateInserts(config); + } + DeltaInputReader sinkReader = null; + JavaRDD<GenericRecord> adjustedRDD = null; + if (config.getNumUpsertPartitions() < 1) { + // randomly generate updates for a given number of records without regard to partitions and files + sinkReader = new DFSAvroDeltaInputReader(sparkSession, schemaStr, Review comment: so updates are generated by randomly reading previous input? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
