feat: add GroupColumn support for Interval in multi-column GROUP BY

datafusion/physical-plan/benches/multi_group_by.rs

@@ -27,9 +27,11 @@
 //! covers a `(FixedSizeBinary, Int32)` key to exercise the
 //! `FixedSizeBinaryGroupValueBuilder`.
 
-use arrow::array::{ArrayRef, Int32Array, UInt32Array};
+use arrow::array::{ArrayRef, Int32Array, IntervalMonthDayNanoArray, UInt32Array};
 use arrow::compute::take;
-use arrow::datatypes::{DataType, Field, Schema, SchemaRef};
+use arrow::datatypes::{
+    DataType, Field, IntervalMonthDayNano, IntervalUnit, Schema, SchemaRef,
+};
 use arrow::util::bench_util::create_fsb_array;
 use criterion::{BenchmarkId, Criterion, criterion_group, criterion_main};
 use datafusion_physical_plan::aggregates::group_values::GroupValues;
@@ -444,6 +446,91 @@ fn bench_fixed_size_binary(c: &mut Criterion) {
     group.finish();
 }
 
+fn make_interval_schema() -> SchemaRef {
+    Arc::new(Schema::new(vec![
+        Field::new("iv", DataType::Interval(IntervalUnit::MonthDayNano), false),
+        Field::new("id", DataType::Int32, false),
+    ]))
+}
+
+/// Generate `(Interval(MonthDayNano), Int32)` batches with `num_distinct_groups`
+/// distinct keys. Each distinct interval is `MonthDayNano(g, 0, 0)`; the `Int32`
+/// column is keyed identically so the combined cardinality equals
+/// `num_distinct_groups`.
+fn generate_interval_batches(
+    num_distinct_groups: usize,
+    num_rows: usize,
+    batch_size: usize,
+) -> Vec<Vec<ArrayRef>> {
+    let num_full_batches = num_rows / batch_size;
+    let remainder = num_rows % batch_size;
+    let num_batches = num_full_batches + if remainder > 0 { 1 } else { 0 };
+
+    (0..num_batches)
+        .map(|batch_idx| {
+            let batch_start = batch_idx * batch_size;
+            let current_batch_size = if batch_idx == num_batches - 1 && remainder > 0 {
+                remainder
+            } else {
+                batch_size
+            };
+
+            let group_ids = (0..current_batch_size)
+                .map(|row| (batch_start + row) % num_distinct_groups);
+
+            let keys = IntervalMonthDayNanoArray::from_iter_values(
+                group_ids
+                    .clone()
+                    .map(|g| IntervalMonthDayNano::new(g as i32, 0, 0)),
+            );
+            let id: Int32Array = group_ids.map(|g| g as i32).collect();
+
+            vec![Arc::new(keys) as ArrayRef, Arc::new(id) as ArrayRef]
+        })
+        .collect()
+}
+
+/// Experiment 8: Group count sweep for an `(Interval, Int32)` key.
+///
+/// Exercises the primitive `GroupColumn` builder for `Interval` on the
+/// multi-column path (previously such a schema fell back to `GroupValuesRows`).
+fn bench_interval(c: &mut Criterion) {
+    let mut group = c.benchmark_group("interval");
+    group.sample_size(15);
+
+    let schema = make_interval_schema();
+
+    for num_groups in [1_000, 1_000_000] {
+        let batches =
+            generate_interval_batches(num_groups, 1_000_000, DEFAULT_BATCH_SIZE);
+
+        for vectorized in [true, false] {
+            let label = if vectorized {
+                "vectorized"
+            } else {
+                "row_based"
+            };
+            group.bench_with_input(
+                BenchmarkId::new(label, format!("grp_{num_groups}")),
+                &batches,
+                |b, batches| {
+                    b.iter_batched_ref(
+                        || {
+                            (
+                                create_group_values(&schema, vectorized),
+                                Vec::<usize>::with_capacity(DEFAULT_BATCH_SIZE),
+                            )
+                        },
+                        |(gv, groups)| bench_intern(gv, batches, groups),
+                        criterion::BatchSize::LargeInput,
+                    );
+                },
+            );
+        }
+    }
+    group.finish();
+}
+
 criterion_group!(
     benches,
     bench_issue_17850_regression,
@@ -453,5 +540,6 @@ criterion_group!(
     bench_high_cardinality_scaling,
     bench_group_count_sweep,
     bench_fixed_size_binary,
+    bench_interval,
 );
 criterion_main!(benches);

datafusion/physical-plan/src/aggregates/group_values/multi_group_by/mod.rs

@@ -33,7 +33,8 @@ use arrow::array::{Array, ArrayRef, BooleanBufferBuilder};
 use arrow::compute::cast;
 use arrow::datatypes::{
     BinaryViewType, DataType, Date32Type, Date64Type, Decimal128Type, Field, Float32Type,
-    Float64Type, Int8Type, Int16Type, Int32Type, Int64Type, Schema, SchemaRef,
+    Float64Type, Int8Type, Int16Type, Int32Type, Int64Type, IntervalDayTimeType,
+    IntervalMonthDayNanoType, IntervalUnit, IntervalYearMonthType, Schema, SchemaRef,
     StringViewType, Time32MillisecondType, Time32SecondType, Time64MicrosecondType,
     Time64NanosecondType, TimeUnit, TimestampMicrosecondType, TimestampMillisecondType,
     TimestampNanosecondType, TimestampSecondType, UInt8Type, UInt16Type, UInt32Type,
@@ -952,6 +953,7 @@ fn group_column_supported_type(data_type: &DataType) -> bool {
             | DataType::Time64(TimeUnit::Microsecond)
             | DataType::Time64(TimeUnit::Nanosecond)
             | DataType::Timestamp(_, _)
+            | DataType::Interval(_)
             | DataType::Utf8View
             | DataType::BinaryView
             | DataType::Boolean
@@ -1031,6 +1033,19 @@ fn make_group_column(field: &Field) -> Result<Box<dyn GroupColumn>> {
                 instantiate_primitive!(v, nullable, TimestampNanosecondType, data_type)
             }
         },
+        // `IntervalUnit` has exactly three variants, so this match is exhaustive
+        // with no fallback arm (unlike Time32 / Time64).
+        DataType::Interval(u) => match u {
+            IntervalUnit::YearMonth => {
+                instantiate_primitive!(v, nullable, IntervalYearMonthType, data_type)
+            }
+            IntervalUnit::DayTime => {
+                instantiate_primitive!(v, nullable, IntervalDayTimeType, data_type)
+            }
+            IntervalUnit::MonthDayNano => {
+                instantiate_primitive!(v, nullable, IntervalMonthDayNanoType, data_type)
+            }
+        },
         DataType::Decimal128(_, _) => {
             instantiate_primitive!(v, nullable, Decimal128Type, data_type)
         }
@@ -1259,7 +1274,10 @@ enum Nulls {
 mod tests {
     use std::{collections::HashMap, sync::Arc};
 
-    use arrow::array::{ArrayRef, Int64Array, RecordBatch, StringArray, StringViewArray};
+    use arrow::array::{
+        Array, ArrayRef, Int64Array, IntervalMonthDayNanoArray, RecordBatch, StringArray,
+        StringViewArray,
+    };
     use arrow::datatypes::{DataType, Field, Schema, SchemaRef};
     use arrow::{compute::concat_batches, util::pretty::pretty_format_batches};
     use datafusion_common::utils::proxy::HashTableAllocExt;
@@ -1309,6 +1327,9 @@ mod tests {
             DataType::Time64(arrow::datatypes::TimeUnit::Microsecond),
             DataType::Time64(arrow::datatypes::TimeUnit::Nanosecond),
             DataType::Timestamp(arrow::datatypes::TimeUnit::Nanosecond, None),
+            DataType::Interval(arrow::datatypes::IntervalUnit::YearMonth),
+            DataType::Interval(arrow::datatypes::IntervalUnit::DayTime),
+            DataType::Interval(arrow::datatypes::IntervalUnit::MonthDayNano),
         ];
 
         for dt in &supported_cases {
@@ -1352,6 +1373,56 @@ mod tests {
         }
     }
 
+    /// Interval GROUP BY on the column-wise fast path: dedups (incl. nulls),
+    /// keeps "1 month" and "30 days" distinct (field-wise compare, no cross-unit
+    /// folding), and preserves the Interval output type. One unit exercises the
+    /// shared builder; the fuzz above covers routing for all three.
+    #[test]
+    fn test_group_values_column_interval() {
+        use arrow::datatypes::{IntervalMonthDayNano, IntervalUnit};
+
+        let schema = Arc::new(Schema::new(vec![Field::new(
+            "i",
+            DataType::Interval(IntervalUnit::MonthDayNano),
+            true,
+        )]));
+        assert!(supported_schema(&schema));
+        let mut group_values =
+            GroupValuesColumn::<false>::try_new(Arc::clone(&schema)).unwrap();
+
+        // "1 month" and "30 days" are distinct Interval values, not folded
+        // together. Row 3 repeats row 0, row 4 repeats the null of row 1.
+        let one_month = IntervalMonthDayNano::new(1, 0, 0);
+        let thirty_days = IntervalMonthDayNano::new(0, 30, 0);
+        let input: ArrayRef = Arc::new(IntervalMonthDayNanoArray::from(vec![
+            Some(one_month),
+            None,
+            Some(thirty_days),
+            Some(one_month),
+            None,
+        ]));
+        let mut groups = Vec::new();
+        group_values.intern(&[input], &mut groups).unwrap();
+        assert_eq!(groups, vec![0, 1, 2, 0, 1]);
+
+        let emitted = group_values.emit(EmitTo::All).unwrap();
+        assert_eq!(emitted.len(), 1);
+        // The emitted key keeps its Interval type, not the bare native.
+        assert_eq!(
+            emitted[0].data_type(),
+            &DataType::Interval(IntervalUnit::MonthDayNano)
+        );
+        let actual = emitted[0]
+            .as_any()
+            .downcast_ref::<IntervalMonthDayNanoArray>()
+            .expect("emitted column should be an IntervalMonthDayNanoArray");
+        // Three groups in first-seen order: 1 month, null, 30 days.
+        assert_eq!(actual.len(), 3);
+        assert_eq!(actual.value(0), one_month);
+        assert!(actual.is_null(1));
+        assert_eq!(actual.value(2), thirty_days);
+    }
+
     #[test]
     fn supported_schema_rejects_mix_of_supported_and_unsupported() {
         // One Float16 column among supported columns flips the whole

datafusion/sqllogictest/test_files/aggregate.slt

@@ -2297,6 +2297,39 @@ statement ok
 DROP TABLE approx_distinct_interval_test;
 
 
+# GROUP BY over Interval group keys. Interval columns route through the
+# GroupValuesColumn column-wise fast path, so an Interval key no longer forces
+# the row-encoded fallback. Equal intervals collapse and "1 month" / "30 days"
+# stay distinct (no cross-unit folding); a primitive and an Interval key also
+# group together on the multi-column path. Queries project only the INT counts
+# / keys so the expected output does not depend on interval Display formatting.
+statement ok
+CREATE TABLE interval_group_test AS VALUES
+  (1, INTERVAL '1' MONTH),
+  (1, INTERVAL '1' MONTH),
+  (1, INTERVAL '30' DAY),
+  (2, INTERVAL '1' MONTH);
+
+# Single Interval group key: {1 month, 30 days}, with 1 month appearing 3 times.
+query I
+SELECT count(*) FROM interval_group_test GROUP BY column2 ORDER BY count(*);
+----
+1
+3
+
+# Multi-column GROUP BY: a primitive key and an Interval key on the same path.
+query II
+SELECT column1, count(*)
+FROM interval_group_test GROUP BY column1, column2 ORDER BY column1, count(*);
+----
+1 1
+1 2
+2 1
+
+statement ok
+DROP TABLE interval_group_test;
+
+
 
 ## This test executes the APPROX_PERCENTILE_CONT aggregation against the test
 ## data, asserting the estimated quantiles are ±5% their actual values.