chore: Add Iceberg TPC-H benchmarking scripts #3294
There are no files selected for viewing
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,114 @@ | ||
| #!/bin/bash | ||
| # | ||
| # 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. | ||
| # | ||
|
|
||
| # TPC-H benchmark using Iceberg tables with Comet's native iceberg-rust integration. | ||
| # | ||
| # Required environment variables: | ||
| # SPARK_HOME - Path to Spark installation | ||
| # SPARK_MASTER - Spark master URL (e.g., spark://localhost:7077) | ||
| # COMET_JAR - Path to Comet JAR | ||
| # ICEBERG_JAR - Path to Iceberg Spark runtime JAR | ||
| # ICEBERG_WAREHOUSE - Path to Iceberg warehouse directory | ||
| # TPCH_QUERIES - Path to TPC-H query files | ||
| # | ||
| # Optional: | ||
| # ICEBERG_CATALOG - Catalog name (default: local) | ||
| # ICEBERG_DATABASE - Database name (default: tpch) | ||
| # | ||
| # Setup (run once to create Iceberg tables from Parquet): | ||
| # $SPARK_HOME/bin/spark-submit \ | ||
| # --packages org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.8.1 \ | ||
| # --conf spark.sql.catalog.local=org.apache.iceberg.spark.SparkCatalog \ | ||
| # --conf spark.sql.catalog.local.type=hadoop \ | ||
| # --conf spark.sql.catalog.local.warehouse=$ICEBERG_WAREHOUSE \ | ||
| # create-iceberg-tpch.py \ | ||
| # --parquet-path $TPCH_DATA \ | ||
| # --catalog local \ | ||
| # --database tpch | ||
|
|
||
| set -e | ||
|
|
||
| # Defaults | ||
| ICEBERG_CATALOG=${ICEBERG_CATALOG:-local} | ||
| ICEBERG_DATABASE=${ICEBERG_DATABASE:-tpch} | ||
|
|
||
| # Validate required variables | ||
| if [ -z "$SPARK_HOME" ]; then | ||
| echo "Error: SPARK_HOME is not set" | ||
| exit 1 | ||
| fi | ||
| if [ -z "$COMET_JAR" ]; then | ||
| echo "Error: COMET_JAR is not set" | ||
| exit 1 | ||
| fi | ||
| if [ -z "$ICEBERG_JAR" ]; then | ||
| echo "Error: ICEBERG_JAR is not set" | ||
| echo "Download from: https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-spark-runtime-3.5_2.12/1.8.1/" | ||
| exit 1 | ||
| fi | ||
| if [ -z "$ICEBERG_WAREHOUSE" ]; then | ||
| echo "Error: ICEBERG_WAREHOUSE is not set" | ||
| exit 1 | ||
| fi | ||
| if [ -z "$TPCH_QUERIES" ]; then | ||
| echo "Error: TPCH_QUERIES is not set" | ||
| exit 1 | ||
| fi | ||
|
|
||
| $SPARK_HOME/sbin/stop-master.sh 2>/dev/null || true | ||
| $SPARK_HOME/sbin/stop-worker.sh 2>/dev/null || true | ||
|
|
||
| $SPARK_HOME/sbin/start-master.sh | ||
| $SPARK_HOME/sbin/start-worker.sh $SPARK_MASTER | ||
|
|
||
| $SPARK_HOME/bin/spark-submit \ | ||
| --master $SPARK_MASTER \ | ||
| --jars $COMET_JAR,$ICEBERG_JAR \ | ||
| --driver-class-path $COMET_JAR:$ICEBERG_JAR \ | ||
| --conf spark.driver.memory=8G \ | ||
| --conf spark.executor.instances=1 \ | ||
| --conf spark.executor.cores=8 \ | ||
| --conf spark.cores.max=8 \ | ||
| --conf spark.executor.memory=16g \ | ||
| --conf spark.memory.offHeap.enabled=true \ | ||
| --conf spark.memory.offHeap.size=16g \ | ||
| --conf spark.eventLog.enabled=true \ | ||
| --conf spark.driver.extraClassPath=$COMET_JAR:$ICEBERG_JAR \ | ||
| --conf spark.executor.extraClassPath=$COMET_JAR:$ICEBERG_JAR \ | ||
| --conf spark.plugins=org.apache.spark.CometPlugin \ | ||
| --conf spark.shuffle.manager=org.apache.spark.sql.comet.execution.shuffle.CometShuffleManager \ | ||
| --conf spark.comet.exec.replaceSortMergeJoin=true \ | ||
| --conf spark.comet.expression.Cast.allowIncompatible=true \ | ||
| --conf spark.comet.enabled=true \ | ||
| --conf spark.comet.exec.enabled=true \ | ||
| --conf spark.comet.scan.icebergNative.enabled=true \ | ||
| --conf spark.comet.explainFallback.enabled=true \ | ||
| --conf spark.sql.catalog.${ICEBERG_CATALOG}=org.apache.iceberg.spark.SparkCatalog \ | ||
| --conf spark.sql.catalog.${ICEBERG_CATALOG}.type=hadoop \ | ||
| --conf spark.sql.catalog.${ICEBERG_CATALOG}.warehouse=$ICEBERG_WAREHOUSE \ | ||
| --conf spark.sql.defaultCatalog=${ICEBERG_CATALOG} \ | ||
| tpcbench.py \ | ||
| --name comet-iceberg \ | ||
| --benchmark tpch \ | ||
| --catalog $ICEBERG_CATALOG \ | ||
| --database $ICEBERG_DATABASE \ | ||
| --queries $TPCH_QUERIES \ | ||
| --output . \ | ||
| --iterations 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,88 @@ | ||
| # 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. | ||
|
|
||
| """ | ||
| Convert TPC-H Parquet data to Iceberg tables. | ||
|
|
||
| Usage: | ||
| spark-submit \ | ||
| --packages org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.8.1 \ | ||
| --conf spark.sql.catalog.local=org.apache.iceberg.spark.SparkCatalog \ | ||
| --conf spark.sql.catalog.local.type=hadoop \ | ||
| --conf spark.sql.catalog.local.warehouse=/path/to/iceberg-warehouse \ | ||
| create-iceberg-tpch.py \ | ||
| --parquet-path /path/to/tpch/parquet \ | ||
| --catalog local \ | ||
| --database tpch | ||
| """ | ||
|
|
||
| import argparse | ||
| from pyspark.sql import SparkSession | ||
| import time | ||
|
|
||
|
|
||
| def main(parquet_path: str, catalog: str, database: str): | ||
| spark = SparkSession.builder \ | ||
| .appName("Create Iceberg TPC-H Tables") \ | ||
| .getOrCreate() | ||
|
|
||
| table_names = [ | ||
| "customer", | ||
| "lineitem", | ||
| "nation", | ||
| "orders", | ||
| "part", | ||
| "partsupp", | ||
| "region", | ||
| "supplier" | ||
| ] | ||
|
|
||
| # Create database if it doesn't exist | ||
| spark.sql(f"CREATE DATABASE IF NOT EXISTS {catalog}.{database}") | ||
|
|
||
| for table in table_names: | ||
| parquet_table_path = f"{parquet_path}/{table}.parquet" | ||
| iceberg_table = f"{catalog}.{database}.{table}" | ||
|
|
||
| print(f"Converting {parquet_table_path} -> {iceberg_table}") | ||
| start_time = time.time() | ||
|
|
||
| # Drop table if exists to allow re-running | ||
| spark.sql(f"DROP TABLE IF EXISTS {iceberg_table}") | ||
|
|
||
| # Read parquet and write as Iceberg | ||
| df = spark.read.parquet(parquet_table_path) | ||
| df.writeTo(iceberg_table).using("iceberg").create() | ||
|
|
||
| row_count = spark.table(iceberg_table).count() | ||
| elapsed = time.time() - start_time | ||
| print(f" Created {iceberg_table} with {row_count} rows in {elapsed:.2f}s") | ||
|
|
||
| print("\nAll TPC-H tables created successfully!") | ||
| print(f"Tables available at: {catalog}.{database}.*") | ||
|
|
||
| spark.stop() | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| parser = argparse.ArgumentParser(description="Convert TPC-H Parquet data to Iceberg tables") | ||
| parser.add_argument("--parquet-path", required=True, help="Path to TPC-H Parquet data directory") | ||
| parser.add_argument("--catalog", required=True, help="Iceberg catalog name (e.g., 'local')") | ||
| parser.add_argument("--database", default="tpch", help="Database name to create tables in") | ||
| args = parser.parse_args() | ||
|
|
||
| main(args.parquet_path, args.catalog, args.database) |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.