[GitHub] [arrow-datafusion] thinkharderdev commented on a diff in pull request #3769: Add benchmarks for testing row filtering

[GitBox <gi...@apache.org>]

thinkharderdev commented on code in PR #3769:
URL: https://github.com/apache/arrow-datafusion/pull/3769#discussion_r992723442


##########
benchmarks/src/bin/parquet_filter_pushdown.rs:
##########
@@ -0,0 +1,462 @@
+// 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.
+
+use arrow::array::{
+    Int32Builder, StringBuilder, StringDictionaryBuilder, TimestampNanosecondBuilder,
+    UInt16Builder,
+};
+use arrow::datatypes::{DataType, Field, Int32Type, Schema, SchemaRef, TimeUnit};
+use arrow::record_batch::RecordBatch;
+use arrow::util::pretty;
+use datafusion::common::Result;
+use datafusion::datasource::listing::{ListingTableUrl, PartitionedFile};
+use datafusion::datasource::object_store::ObjectStoreUrl;
+use datafusion::execution::context::ExecutionProps;
+use datafusion::logical_expr::{lit, or, Expr};
+use datafusion::logical_plan::ToDFSchema;
+use datafusion::physical_expr::create_physical_expr;
+use datafusion::physical_plan::collect;
+use datafusion::physical_plan::file_format::{
+    FileScanConfig, ParquetExec, ParquetScanOptions,
+};
+use datafusion::physical_plan::filter::FilterExec;
+use datafusion::prelude::{col, combine_filters, SessionConfig, SessionContext};
+use object_store::path::Path;
+use object_store::ObjectMeta;
+use parquet::arrow::ArrowWriter;
+use rand::rngs::StdRng;
+use rand::{Rng, SeedableRng};
+use std::fs::File;
+use std::ops::Range;
+use std::path::PathBuf;
+use std::sync::Arc;
+use std::time::Instant;
+use structopt::StructOpt;
+
+#[cfg(feature = "snmalloc")]
+#[global_allocator]
+static ALLOC: snmalloc_rs::SnMalloc = snmalloc_rs::SnMalloc;
+
+#[derive(Debug, StructOpt)]
+#[structopt(name = "Benchmarks", about = "Apache Arrow Rust Benchmarks.")]
+struct Opt {
+    /// Activate debug mode to see query results
+    #[structopt(short, long)]
+    debug: bool,
+
+    /// Number of iterations of each test run
+    #[structopt(short = "i", long = "iterations", default_value = "3")]
+    iterations: usize,
+
+    /// Number of partitions to process in parallel
+    #[structopt(long = "partitions", default_value = "2")]
+    partitions: usize,
+
+    /// Path to folder where access log file will be generated
+    #[structopt(parse(from_os_str), required = true, short = "p", long = "path")]
+    path: PathBuf,
+
+    /// Batch size when reading Parquet files
+    #[structopt(short = "s", long = "batch-size", default_value = "8192")]

Review Comment:
   Yeah, just removed one of them. I don't think batch size needs to be a cli option in this benchmark. 



-- 
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: github-unsubscribe@arrow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org