vamsikarnika commented on code in PR #17693: URL: https://github.com/apache/hudi/pull/17693#discussion_r2677113810
########## hudi-utilities/src/main/java/org/apache/hudi/utilities/benchmarking/MetadataBenchmarkingTool.java: ########## @@ -0,0 +1,700 @@ +/* + * 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.utilities.benchmarking; + +import org.apache.hudi.BaseHoodieTableFileIndex; +import org.apache.hudi.HoodieFileIndex; +import org.apache.hudi.client.common.HoodieSparkEngineContext; +import org.apache.hudi.common.config.HoodieMetadataConfig; +import org.apache.hudi.common.config.HoodieStorageConfig; +import org.apache.hudi.common.config.TypedProperties; +import org.apache.hudi.common.data.HoodieData; +import org.apache.hudi.common.engine.EngineType; +import org.apache.hudi.common.engine.HoodieEngineContext; +import org.apache.hudi.common.fs.ConsistencyGuardConfig; +import org.apache.hudi.common.model.FileSlice; +import org.apache.hudi.common.model.HoodieCommitMetadata; +import org.apache.hudi.common.model.HoodieFailedWritesCleaningPolicy; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.model.HoodieTableType; +import org.apache.hudi.common.model.HoodieWriteStat; +import org.apache.hudi.common.model.WriteOperationType; +import org.apache.hudi.common.table.HoodieTableMetaClient; +import org.apache.hudi.common.table.HoodieTableVersion; +import org.apache.hudi.common.table.timeline.HoodieInstantTimeGenerator; +import org.apache.hudi.common.table.timeline.versioning.TimelineLayoutVersion; +import org.apache.hudi.common.table.view.FileSystemViewStorageConfig; +import org.apache.hudi.common.testutils.HoodieTestTable; +import org.apache.hudi.common.testutils.InProcessTimeGenerator; +import org.apache.hudi.common.util.HoodieTimer; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.StringUtils; +import org.apache.hudi.common.util.collection.Pair; +import org.apache.hudi.config.HoodieCleanConfig; +import org.apache.hudi.config.HoodieCompactionConfig; +import org.apache.hudi.config.HoodieIndexConfig; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.data.HoodieJavaRDD; +import org.apache.hudi.index.HoodieIndex; +import org.apache.hudi.metadata.HoodieMetadataPayload; +import org.apache.hudi.metadata.HoodieTableMetadataUtil; +import org.apache.hudi.stats.HoodieColumnRangeMetadata; +import org.apache.hudi.stats.ValueMetadata; +import org.apache.hudi.storage.StoragePath; +import org.apache.hudi.testutils.MetadataMergeWriteStatus; +import org.apache.hudi.utilities.IdentitySplitter; +import org.apache.hudi.utilities.UtilHelpers; + +import com.beust.jcommander.JCommander; +import com.beust.jcommander.Parameter; +import org.apache.hadoop.fs.Path; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.HoodieCatalystExpressionUtils$; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.catalyst.expressions.Expression; +import org.apache.spark.sql.execution.datasources.NoopCache$; +import org.apache.spark.sql.types.StructType; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.Closeable; +import java.io.IOException; +import java.io.Serializable; +import java.time.LocalDate; +import java.time.LocalDateTime; +import java.time.format.DateTimeFormatter; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Random; +import java.util.stream.Collectors; + +import scala.Tuple2; +import scala.collection.JavaConverters; +import scala.collection.Seq; + +import static org.apache.hudi.metadata.HoodieTableMetadata.SOLO_COMMIT_TIMESTAMP; +import static org.apache.hudi.metadata.MetadataPartitionType.COLUMN_STATS; +import static org.apache.hudi.metadata.MetadataPartitionType.FILES; + +public class MetadataBenchmarkingTool implements Closeable { + + private static final Logger LOG = LoggerFactory.getLogger(MetadataBenchmarkingTool.class); + + // Table and column constants + private static final String TABLE_NAME = "test_mdt_stats_tbl"; + private static final String COL_TENANT_ID = "tenantID"; + private static final String COL_AGE = "age"; + + // Partition generation constants + private static final LocalDate PARTITION_START_DATE = LocalDate.of(2020, 1, 1); + private static final DateTimeFormatter DATE_FORMATTER = DateTimeFormatter.ofPattern("yyyy-MM-dd"); + + // TenantID column stats range: 30000-60000 + private static final long TENANT_ID_MIN_BASE = 30000L; + private static final int TENANT_ID_RANGE = 30000; + private static final long TENANT_ID_MAX = 60000L; + + // Age column stats range: 20-99 + private static final int AGE_MIN_BASE = 20; + private static final int AGE_MIN_RANGE = 30; + private static final int AGE_MAX_RANGE = 50; + + // Column stats metadata defaults + private static final int COL_STATS_NULL_COUNT = 0; + private static final int COL_STATS_VALUE_COUNT = 1000; + private static final long COL_STATS_TOTAL_SIZE = 123456L; + private static final long COL_STATS_TOTAL_UNCOMPRESSED_SIZE = 123456L; + + private final Config cfg; + // Properties with source, hoodie client, key generator etc. + private TypedProperties props; + + private final SparkSession spark; + + private final JavaSparkContext jsc; + + private final HoodieEngineContext engineContext; + + /** + * Returns the AVRO schema string for the table. + * Schema includes: id, name, city, age, tenantID, dt + */ + private static String getAvroSchema() { + return "{\n" + + " \"type\": \"record\",\n" + + " \"name\": \"Employee\",\n" + + " \"namespace\": \"com.example.avro\",\n" + + " \"fields\": [\n" + + " { \"name\": \"id\", \"type\": \"string\" },\n" + + " { \"name\": \"name\", \"type\": \"string\" },\n" + + " { \"name\": \"city\", \"type\": \"string\" },\n" + + " { \"name\": \"age\", \"type\": \"int\" },\n" + + " { \"name\": \"tenantID\", \"type\": \"long\" },\n" + + " { \"name\": \"dt\", \"type\": \"string\" }\n" + + " ]\n" + + "}\n"; + } + + private static final String RECORD_ID = "id"; + + private static final String PARTITION_FIELDS = "dt"; + /** + * Returns the Spark StructType schema for data skipping queries. + * Reused across multiple places to avoid duplication. + */ + private static StructType getDataSchema() { + return new StructType() + .add("id", "string") + .add("name", "string") + .add("city", "string") + .add("age", "int") + .add("tenantID", "long") + .add("dt", "string"); + } + + /** + * Returns the list of columns to index based on numColumnsToIndex config. + * @param numColumnsToIndex 1 for tenantID only, 2 for tenantID & age + * @return List of column names to index + */ + private List<String> getColumnsToIndex(int numColumnsToIndex) { + return numColumnsToIndex == 2 ? Arrays.asList(COL_TENANT_ID, COL_AGE) + : Collections.singletonList(COL_TENANT_ID); + } + + private String getColumnsToIndexString(int numColumnsToIndex) { + return String.join(",", getColumnsToIndex(numColumnsToIndex)); + } + + public MetadataBenchmarkingTool(SparkSession spark, Config cfg) { + this.spark = spark; + this.jsc = new JavaSparkContext(spark.sparkContext()); + this.engineContext = new HoodieSparkEngineContext(jsc); + this.cfg = cfg; + this.props = StringUtils.isNullOrEmpty(cfg.propsFilePath) + ? UtilHelpers.buildProperties(cfg.configs) + : readConfigFromFileSystem(jsc, cfg); + } + + private TypedProperties readConfigFromFileSystem(JavaSparkContext jsc, Config cfg) { + return UtilHelpers.readConfig(jsc.hadoopConfiguration(), new Path(cfg.propsFilePath), cfg.configs) + .getProps(true); + } + + public static class Config implements Serializable { + @Parameter(names = {"--table-base-path", "-tbp"}, description = "Base path for the Hudi table", required = true) + public String tableBasePath = null; + + @Parameter(names = {"--num-cols-to-index", "-num-cols"}, description = "Number of columns to index (1 for tenantID, 2 for tenantID & age)", required = true) + public Integer numColumnsToIndex = 1; + + @Parameter(names = {"--col-stats-file-group-count", "-col-fg-count"}, description = "Number of file groups for column stats partition in metadata table", required = true) + public Integer colStatsFileGroupCount = 10; + + @Parameter(names = {"--num-files", "-nf"}, description = "Number of files to create in the table", required = true) + public Integer numFiles = 1000; + + @Parameter(names = {"--num-partitions", "-np"}, description = "Number of partitions to create in the table", required = true) + public Integer numPartitions = 1; + + @Parameter(names = {"--partition-filter-percentage", "-pfp"}, description = "Percentage of partitions to exclude during querying (0 = include all, 100 = exclude all)", required = false) + public Integer partitionFilterPercentage = 0; + + @Parameter(names = {"--hoodie-conf"}, description = "Any configuration that can be set in the properties file " Review Comment: Added config for data filters -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
