zhuqi-lucas commented on code in PR #19042: URL: https://github.com/apache/datafusion/pull/19042#discussion_r2591923940
########## benchmarks/sort_clickbench.py: ########## @@ -0,0 +1,244 @@ +#!/usr/bin/env python3 + +# 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. + +""" +Sort ClickBench data by EventTime for reverse scan benchmark. +Enhanced version with configurable row group size and optimization options. +""" + +import sys +import argparse +from pathlib import Path + +try: + import pyarrow.parquet as pq + import pyarrow.compute as pc +except ImportError: + print("Error: pyarrow is not installed.") + print("Please install it with: pip install pyarrow") + sys.exit(1) + + +def sort_clickbench_data( + input_path: str, + output_path: str, + row_group_size: int = 64 * 1024, # 64k rows default + compression: str = 'zstd', + verify: bool = True +): + """Sort parquet file by EventTime column with optimized settings.""" + + input_file = Path(input_path) + output_file = Path(output_path) + + if not input_file.exists(): + print(f"Error: Input file not found: {input_file}") + sys.exit(1) + + if output_file.exists(): + print(f"Sorted file already exists: {output_file}") + if verify: + verify_sorted_file(output_file) + return + + try: + print(f"Reading {input_file.name}...") + table = pq.read_table(str(input_file)) + + print(f"Original table has {len(table):,} rows") + print("Sorting by EventTime...") + + # Sort the table by EventTime + sorted_indices = pc.sort_indices(table, sort_keys=[("EventTime", "ascending")]) + sorted_table = pc.take(table, sorted_indices) + + print(f"Sorted table has {len(sorted_table):,} rows") + + # Verify sort + event_times = sorted_table.column('EventTime').to_pylist() + if event_times and verify: + print(f"First EventTime: {event_times[0]}") + print(f"Last EventTime: {event_times[-1]}") + # Verify ascending order + is_sorted = all(event_times[i] <= event_times[i+1] for i in range(min(1000, len(event_times)-1))) + print(f"Sort verification (first 1000 rows): {'✓ PASS' if is_sorted else '✗ FAIL'}") + + print(f"Writing sorted file to {output_file}...") + print(f" Row group size: {row_group_size:,} rows") + print(f" Compression: {compression}") + + # Write sorted table with optimized settings + pq.write_table( Review Comment: Great idea @alamb , addressed in latest PR, thanks! -- 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]
