squash

datafusion/common/src/config.rs

@@ -380,6 +380,10 @@ config_namespace! {
         /// repartitioning to increase parallelism to leverage more CPU cores
         pub enable_round_robin_repartition: bool, default = true
 
+        /// When set to true, the optimizer will attempt to perform limit operations
+        /// during aggregations, if possible
+        pub enable_topk_aggregation: bool, default = true
+
         /// When set to true, the optimizer will insert filters before a join between
         /// a nullable and non-nullable column to filter out nulls on the nullable side. This
         /// filter can add additional overhead when the file format does not fully support

datafusion/core/Cargo.toml

@@ -83,7 +83,7 @@ parking_lot = "0.12"
 parquet = { workspace = true }
 percent-encoding = "2.2.0"
 pin-project-lite = "^0.2.7"
-rand = "0.8"
+rand = { version = "0.8", features = ["small_rng"] }
 sqlparser = { workspace = true }
 tempfile = "3"
 tokio = { version = "1.28", features = ["macros", "rt", "rt-multi-thread", "sync", "fs", "parking_lot"] }
@@ -105,6 +105,8 @@ env_logger = "0.10"
 half = "2.2.1"
 postgres-protocol = "0.6.4"
 postgres-types = { version = "0.2.4", features = ["derive", "with-chrono-0_4"] }
+ptree = "0.4.0"
+rand_distr = "0.4.3"
 regex = "1.5.4"
 rstest = "0.18.0"
 rust_decimal = { version = "1.27.0", features = ["tokio-pg"] }
@@ -157,3 +159,7 @@ name = "sql_query_with_io"
 [[bench]]
 harness = false
 name = "sort"
+
+[[bench]]
+harness = false
+name = "topk_aggregate"