Merge remote-tracking branch 'apache/main' into alamb/unnest_api_try3

.asf.yaml

@@ -45,7 +45,9 @@ github:
   features:
     issues: true
   protected_branches:
-    main: { }
+    main:
+      required_pull_request_reviews:
+        required_approving_review_count: 1
 
 # publishes the content of the `asf-site` branch to
 # https://arrow.apache.org/datafusion/

.github/pull_request_template.md

@@ -1,25 +1,25 @@
-# Which issue does this PR close?
+## Which issue does this PR close?
 
 <!--
 We generally require a GitHub issue to be filed for all bug fixes and enhancements and this helps us generate change logs for our releases. You can link an issue to this PR using the GitHub syntax. For example `Closes #123` indicates that this PR will close issue #123.
 -->
 
 Closes #.
 
-# Rationale for this change
+## Rationale for this change
 
 <!--
  Why are you proposing this change? If this is already explained clearly in the issue then this section is not needed.
  Explaining clearly why changes are proposed helps reviewers understand your changes and offer better suggestions for fixes.  
 -->
 
-# What changes are included in this PR?
+## What changes are included in this PR?
 
 <!--
 There is no need to duplicate the description in the issue here but it is sometimes worth providing a summary of the individual changes in this PR.
 -->
 
-# Are these changes tested?
+## Are these changes tested?
 
 <!--
 We typically require tests for all PRs in order to:
@@ -29,7 +29,7 @@ We typically require tests for all PRs in order to:
 If tests are not included in your PR, please explain why (for example, are they covered by existing tests)?
 -->
 
-# Are there any user-facing changes?
+## Are there any user-facing changes?
 
 <!--
 If there are user-facing changes then we may require documentation to be updated before approving the PR.

Cargo.toml

@@ -17,7 +17,7 @@
 
 [workspace]
 exclude = ["datafusion-cli"]
-members = ["datafusion/common", "datafusion/core", "datafusion/expr", "datafusion/execution", "datafusion/optimizer", "datafusion/physical-expr", "datafusion/proto", "datafusion/proto/gen", "datafusion/sql", "datafusion/substrait", "datafusion-examples", "test-utils", "benchmarks",
+members = ["datafusion/common", "datafusion/core", "datafusion/expr", "datafusion/execution", "datafusion/optimizer", "datafusion/physical-expr", "datafusion/proto", "datafusion/proto/gen", "datafusion/sql", "datafusion/sqllogictest", "datafusion/substrait", "datafusion-examples", "test-utils", "benchmarks",
 ]
 resolver = "2"
 
@@ -56,4 +56,4 @@ lto = false
 opt-level = 3
 overflow-checks = false
 panic = 'unwind'
-rpath = false
+rpath = false

benchmarks/README.md

@@ -272,24 +272,6 @@ SUBCOMMANDS:
 
 ```
 
-## NYC Taxi Benchmark
-
-These benchmarks are based on the [New York Taxi and Limousine Commission][2] data set.
-
-```bash
-cargo run --release --bin nyctaxi -- --iterations 3 --path /mnt/nyctaxi/csv --format csv --batch-size 4096
-```
-
-Example output:
-
-```bash
-Running benchmarks with the following options: Opt { debug: false, iterations: 3, batch_size: 4096, path: "/mnt/nyctaxi/csv", file_format: "csv" }
-Executing 'fare_amt_by_passenger'
-Query 'fare_amt_by_passenger' iteration 0 took 7138 ms
-Query 'fare_amt_by_passenger' iteration 1 took 7599 ms
-Query 'fare_amt_by_passenger' iteration 2 took 7969 ms
-```
-
 ## h2o benchmarks
 
 ```bash

benchmarks/bench.sh

@@ -303,7 +303,7 @@ run_tpch() {
     RESULTS_FILE="${RESULTS_DIR}/tpch.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running tpch benchmark..."
-    $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 10 --path "${TPCH_DIR}" --format parquet -o ${RESULTS_FILE}
+    $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 5 --path "${TPCH_DIR}" --format parquet -o ${RESULTS_FILE}
 }
 
 # Runs the tpch in memory
@@ -319,23 +319,23 @@ run_tpch_mem() {
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running tpch_mem benchmark..."
     # -m means in memory
-    $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 10 --path "${TPCH_DIR}" -m --format parquet -o ${RESULTS_FILE}
+    $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 5 --path "${TPCH_DIR}" -m --format parquet -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..."
-    $CARGO_COMMAND --bin parquet -- filter --path "${DATA_DIR}" --scale-factor 1.0 --iterations 10 -o ${RESULTS_FILE}
+    $CARGO_COMMAND --bin parquet -- filter --path "${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..."
-    $CARGO_COMMAND --bin parquet -- sort --path "${DATA_DIR}" --scale-factor 1.0 --iterations 10 -o ${RESULTS_FILE}
+    $CARGO_COMMAND --bin parquet -- sort --path "${DATA_DIR}" --scale-factor 1.0 --iterations 5 -o ${RESULTS_FILE}
 }
 
 
@@ -389,15 +389,15 @@ run_clickbench_1() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_1.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (1 file) benchmark..."
-    $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 10 --path "${DATA_DIR}/hits.parquet" --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o ${RESULTS_FILE}
+    $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet" --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o ${RESULTS_FILE}
 }
 
  # Runs the clickbench benchmark with a single large parquet file
 run_clickbench_partitioned() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_1.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (partitioned, 100 files) benchmark..."
-    $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 10 --path "${DATA_DIR}/hits_partitioned" --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o ${RESULTS_FILE}
+    $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits_partitioned" --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o ${RESULTS_FILE}
 }
 
 compare_benchmarks() {

benchmarks/src/tpch/mod.rs

@@ -20,10 +20,10 @@
 use arrow::datatypes::SchemaBuilder;
 use datafusion::{
     arrow::datatypes::{DataType, Field, Schema},
+    common::plan_err,
     error::{DataFusionError, Result},
 };
 use std::fs;
-
 mod run;
 pub use run::RunOpt;
 
@@ -158,13 +158,9 @@ pub fn get_query_sql(query: usize) -> Result<Vec<String>> {
                 Err(e) => errors.push(format!("{filename}: {e}")),
             };
         }
-        Err(DataFusionError::Plan(format!(
-            "invalid query. Could not find query: {errors:?}"
-        )))
+        plan_err!("invalid query. Could not find query: {:?}", errors)
     } else {
-        Err(DataFusionError::Plan(
-            "invalid query. Expected value between 1 and 22".to_owned(),
-        ))
+        plan_err!("invalid query. Expected value between 1 and 22")
     }
 }