aokolnychyi commented on code in PR #7558: URL: https://github.com/apache/iceberg/pull/7558#discussion_r1187836896
########## spark/v3.4/spark-extensions/src/jmh/java/org/apache/iceberg/spark/MergeCardinalityCheckBenchmark.java: ########## @@ -0,0 +1,227 @@ +/* + * 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.iceberg.spark; + +import static org.apache.spark.sql.functions.current_date; +import static org.apache.spark.sql.functions.date_add; +import static org.apache.spark.sql.functions.expr; + +import java.util.UUID; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.DistributionMode; +import org.apache.iceberg.RowLevelOperationMode; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.catalyst.analysis.NoSuchTableException; +import org.apache.spark.sql.catalyst.parser.ParseException; +import org.apache.spark.sql.internal.SQLConf; +import org.apache.spark.sql.types.StructType; +import org.openjdk.jmh.annotations.Benchmark; +import org.openjdk.jmh.annotations.BenchmarkMode; +import org.openjdk.jmh.annotations.Fork; +import org.openjdk.jmh.annotations.Measurement; +import org.openjdk.jmh.annotations.Mode; +import org.openjdk.jmh.annotations.Scope; +import org.openjdk.jmh.annotations.Setup; +import org.openjdk.jmh.annotations.State; +import org.openjdk.jmh.annotations.TearDown; +import org.openjdk.jmh.annotations.Threads; +import org.openjdk.jmh.annotations.Warmup; + +/** + * A benchmark that evaluates the performance of the cardinality check in MERGE operations. + * + * <p>To run this benchmark for spark-3.3: <code> + * ./gradlew -DsparkVersions=3.4 :iceberg-spark:iceberg-spark-extensions-3.4_2.12:jmh + * -PjmhIncludeRegex=MergeCardinalityCheckBenchmark + * -PjmhOutputPath=benchmark/iceberg-merge-cardinality-check-benchmark.txt + * </code> + */ +@Fork(1) +@State(Scope.Benchmark) +@Warmup(iterations = 3) +@Measurement(iterations = 5) +@BenchmarkMode(Mode.SingleShotTime) +public class MergeCardinalityCheckBenchmark { Review Comment: ``` Benchmark Mode Cnt Score Error Units [NEW] copyOnWriteMergeCardinalityCheck10PercentUpdates ss 5 14.008 ± 1.114 s/op [OLD] copyOnWriteMergeCardinalityCheck10PercentUpdates ss 5 16.711 ± 0.288 s/op [NEW] copyOnWriteMergeCardinalityCheck30PercentUpdates ss 5 14.293 ± 2.359 s/op [OLD] copyOnWriteMergeCardinalityCheck30PercentUpdates ss 5 17.242 ± 2.855 s/op [NEW] copyOnWriteMergeCardinalityCheck90PercentUpdates ss 5 14.536 ± 1.344 s/op [OLD] copyOnWriteMergeCardinalityCheck90PercentUpdates ss 5 18.966 ± 6.966 s/op [NEW] mergeOnReadMergeCardinalityCheck10PercentUpdates ss 5 9.585 ± 0.467 s/op [OLD] mergeOnReadMergeCardinalityCheck10PercentUpdates ss 5 10.493 ± 5.130 s/op [NEW] mergeOnReadMergeCardinalityCheck30PercentUpdates ss 5 14.910 ± 0.264 s/op [OLD] mergeOnReadMergeCardinalityCheck30PercentUpdates ss 5 15.171 ± 0.275 s/op [NEW] mergeOnReadMergeCardinalityCheck90PercentUpdates ss 5 30.746 ± 0.237 s/op [OLD] mergeOnReadMergeCardinalityCheck90PercentUpdates ss 5 32.714 ± 0.544 s/op ``` Here is a shorter representation. There is a small reduction in terms memory too. Like said above, this run still does a local sort and trigger a spill, we just reduce the amount of spilled data. If we skip the final sort, we can actually avoid the local sort altogether. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
