Remove parquet_filter and parquet sort benchmarks (#16730)

* Remove parquet_filter and parquet_sort benchmarks

* Remove more

Author: alamb

benchmarks/bench.sh

@@ -114,8 +114,6 @@ imdb:                   Join Order Benchmark (JOB) using the IMDB dataset conver
 
 # Micro-Benchmarks (specific operators and features)
 cancellation:           How long cancelling a query takes
-parquet:                Benchmark of parquet reader's filtering speed
-sort:                   Benchmark of sorting speed
 
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 Supported Configuration (Environment Variables)
@@ -303,8 +301,6 @@ main() {
                     run_tpch "10" "csv"
                     run_tpch_mem "10"
                     run_cancellation
-                    run_parquet
-                    run_sort
                     run_clickbench_1
                     run_clickbench_partitioned
                     run_clickbench_extended
@@ -338,12 +334,6 @@ main() {
                 cancellation)
                     run_cancellation
                     ;;
-                parquet)
-                    run_parquet
-                    ;;
-                sort)
-                    run_sort
-                    ;;
                 clickbench_1)
                     run_clickbench_1
                     ;;
@@ -528,22 +518,6 @@ run_cancellation() {
     debug_run $CARGO_COMMAND --bin dfbench -- cancellation --iterations 5 --path "${DATA_DIR}/cancellation" -o "${RESULTS_FILE}"
 }
 
-# Runs the parquet filter benchmark
-run_parquet() {
-    RESULTS_FILE="${RESULTS_DIR}/parquet.json"
-    echo "RESULTS_FILE: ${RESULTS_FILE}"
-    echo "Running parquet filter benchmark..."
-    debug_run $CARGO_COMMAND --bin parquet -- filter --path "${DATA_DIR}" --scale-factor 1.0 --iterations 5 -o "${RESULTS_FILE}"
-}
-
-# Runs the sort benchmark
-run_sort() {
-    RESULTS_FILE="${RESULTS_DIR}/sort.json"
-    echo "RESULTS_FILE: ${RESULTS_FILE}"
-    echo "Running sort benchmark..."
-    debug_run $CARGO_COMMAND --bin parquet -- sort --path "${DATA_DIR}" --scale-factor 1.0 --iterations 5 -o "${RESULTS_FILE}"
-}
-
 
 # Downloads the single file hits.parquet ClickBench datasets from
 # https://github.com/ClickHouse/ClickBench/tree/main#data-loading

benchmarks/src/bin/dfbench.rs

@@ -33,9 +33,7 @@ static ALLOC: snmalloc_rs::SnMalloc = snmalloc_rs::SnMalloc;
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 
-use datafusion_benchmarks::{
-    cancellation, clickbench, h2o, imdb, parquet_filter, sort, sort_tpch, tpch,
-};
+use datafusion_benchmarks::{cancellation, clickbench, h2o, imdb, sort_tpch, tpch};
 
 #[derive(Debug, StructOpt)]
 #[structopt(about = "benchmark command")]
@@ -44,8 +42,6 @@ enum Options {
     Clickbench(clickbench::RunOpt),
     H2o(h2o::RunOpt),
     Imdb(imdb::RunOpt),
-    ParquetFilter(parquet_filter::RunOpt),
-    Sort(sort::RunOpt),
     SortTpch(sort_tpch::RunOpt),
     Tpch(tpch::RunOpt),
     TpchConvert(tpch::ConvertOpt),
@@ -61,8 +57,6 @@ pub async fn main() -> Result<()> {
         Options::Clickbench(opt) => opt.run().await,
         Options::H2o(opt) => opt.run().await,
         Options::Imdb(opt) => Box::pin(opt.run()).await,
-        Options::ParquetFilter(opt) => opt.run().await,
-        Options::Sort(opt) => opt.run().await,
         Options::SortTpch(opt) => opt.run().await,
         Options::Tpch(opt) => Box::pin(opt.run()).await,
         Options::TpchConvert(opt) => opt.run().await,

benchmarks/src/bin/parquet.rs

@@ -20,8 +20,6 @@ pub mod cancellation;
 pub mod clickbench;
 pub mod h2o;
 pub mod imdb;
-pub mod parquet_filter;
-pub mod sort;
 pub mod sort_tpch;
 pub mod tpch;
 pub mod util;