Add smaller optimization

Author: zhuqi-lucas

datafusion/common/src/config.rs

@@ -343,11 +343,7 @@ config_namespace! {
         /// When sorting, below what size should data be concatenated
         /// and sorted in a single RecordBatch rather than sorted in
         /// batches and merged.
-        /// Note:
-        /// In theory we should always be able to sort in place, but some corner cases for merging testing
-        /// failed, so we set a large threshold to avoid that.
-        /// Future work: potential remove this option and always sort in place.
-        pub sort_in_place_threshold_bytes: usize, default = 1000 * 1024 * 1024
+        pub sort_in_place_threshold_bytes: usize, default = 1024 * 1024
 
         /// Number of files to read in parallel when inferring schema and statistics
         pub meta_fetch_concurrency: usize, default = 32

datafusion/core/tests/memory_limit/mod.rs

@@ -459,8 +459,7 @@ async fn test_stringview_external_sort() {
     let runtime = builder.build_arc().unwrap();
 
     let config = SessionConfig::new()
-        .with_sort_spill_reservation_bytes(40 * 1024 * 1024)
-        .with_sort_in_place_threshold_bytes(1024 * 1024);
+        .with_sort_spill_reservation_bytes(40 * 1024 * 1024);
 
     let ctx = SessionContext::new_with_config_rt(config, runtime);
     ctx.register_table("t", Arc::new(table)).unwrap();
@@ -483,7 +482,6 @@ async fn test_stringview_external_sort() {
 async fn test_in_mem_buffer_almost_full() {
     let config = SessionConfig::new()
         .with_sort_spill_reservation_bytes(3000000)
-        .with_sort_in_place_threshold_bytes(1024 * 1024)
         .with_target_partitions(1);
     let runtime = RuntimeEnvBuilder::new()
         .with_memory_pool(Arc::new(FairSpillPool::new(10 * 1024 * 1024)))

datafusion/sqllogictest/test_files/information_schema.slt

@@ -260,7 +260,7 @@ datafusion.execution.skip_partial_aggregation_probe_ratio_threshold 0.8
 datafusion.execution.skip_partial_aggregation_probe_rows_threshold 100000
 datafusion.execution.skip_physical_aggregate_schema_check false
 datafusion.execution.soft_max_rows_per_output_file 50000000
-datafusion.execution.sort_in_place_threshold_bytes 1048576000
+datafusion.execution.sort_in_place_threshold_bytes 1048576
 datafusion.execution.sort_spill_reservation_bytes 10485760
 datafusion.execution.split_file_groups_by_statistics false
 datafusion.execution.target_partitions 7
@@ -360,7 +360,7 @@ datafusion.execution.skip_partial_aggregation_probe_ratio_threshold 0.8 Aggregat
 datafusion.execution.skip_partial_aggregation_probe_rows_threshold 100000 Number of input rows partial aggregation partition should process, before aggregation ratio check and trying to switch to skipping aggregation mode
 datafusion.execution.skip_physical_aggregate_schema_check false When set to true, skips verifying that the schema produced by planning the input of `LogicalPlan::Aggregate` exactly matches the schema of the input plan. When set to false, if the schema does not match exactly (including nullability and metadata), a planning error will be raised. This is used to workaround bugs in the planner that are now caught by the new schema verification step.
 datafusion.execution.soft_max_rows_per_output_file 50000000 Target number of rows in output files when writing multiple. This is a soft max, so it can be exceeded slightly. There also will be one file smaller than the limit if the total number of rows written is not roughly divisible by the soft max
-datafusion.execution.sort_in_place_threshold_bytes 1048576000 When sorting, below what size should data be concatenated and sorted in a single RecordBatch rather than sorted in batches and merged. Note: In theory we should always be able to sort in place, but some corner cases for merging testing failed, so we set a large threshold to avoid that. Future work: potential remove this option and always sort in place.
+datafusion.execution.sort_in_place_threshold_bytes 1048576 When sorting, below what size should data be concatenated and sorted in a single RecordBatch rather than sorted in batches and merged.
 datafusion.execution.sort_spill_reservation_bytes 10485760 Specifies the reserved memory for each spillable sort operation to facilitate an in-memory merge. When a sort operation spills to disk, the in-memory data must be sorted and merged before being written to a file. This setting reserves a specific amount of memory for that in-memory sort/merge process. Note: This setting is irrelevant if the sort operation cannot spill (i.e., if there's no `DiskManager` configured).
 datafusion.execution.split_file_groups_by_statistics false Attempt to eliminate sorts by packing & sorting files with non-overlapping statistics into the same file groups. Currently experimental
 datafusion.execution.target_partitions 7 Number of partitions for query execution. Increasing partitions can increase concurrency. Defaults to the number of CPU cores on the system

docs/source/user-guide/configs.md

@@ -84,7 +84,7 @@ Environment variables are read during `SessionConfig` initialisation so they mus
 | datafusion.execution.planning_concurrency                               | 0                         | Fan-out during initial physical planning. This is mostly use to plan `UNION` children in parallel. Defaults to the number of CPU cores on the system                                                                                                                                                                                                                                                                                                                                                                                                                     |
 | datafusion.execution.skip_physical_aggregate_schema_check               | false                     | When set to true, skips verifying that the schema produced by planning the input of `LogicalPlan::Aggregate` exactly matches the schema of the input plan. When set to false, if the schema does not match exactly (including nullability and metadata), a planning error will be raised. This is used to workaround bugs in the planner that are now caught by the new schema verification step.                                                                                                                                                                        |
 | datafusion.execution.sort_spill_reservation_bytes                       | 10485760                  | Specifies the reserved memory for each spillable sort operation to facilitate an in-memory merge. When a sort operation spills to disk, the in-memory data must be sorted and merged before being written to a file. This setting reserves a specific amount of memory for that in-memory sort/merge process. Note: This setting is irrelevant if the sort operation cannot spill (i.e., if there's no `DiskManager` configured).                                                                                                                                        |
-| datafusion.execution.sort_in_place_threshold_bytes                      | 1048576000                | When sorting, below what size should data be concatenated and sorted in a single RecordBatch rather than sorted in batches and merged. Note: In theory we should always be able to sort in place, but some corner cases for merging testing failed, so we set a large threshold to avoid that. Future work: potential remove this option and always sort in place.                                                                                                                                                                                                       |
+| datafusion.execution.sort_in_place_threshold_bytes                      | 1048576                   | When sorting, below what size should data be concatenated and sorted in a single RecordBatch rather than sorted in batches and merged.                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 | datafusion.execution.meta_fetch_concurrency                             | 32                        | Number of files to read in parallel when inferring schema and statistics                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
 | datafusion.execution.minimum_parallel_output_files                      | 4                         | Guarantees a minimum level of output files running in parallel. RecordBatches will be distributed in round robin fashion to each parallel writer. Each writer is closed and a new file opened once soft_max_rows_per_output_file is reached.                                                                                                                                                                                                                                                                                                                             |
 | datafusion.execution.soft_max_rows_per_output_file                      | 50000000                  | Target number of rows in output files when writing multiple. This is a soft max, so it can be exceeded slightly. There also will be one file smaller than the limit if the total number of rows written is not roughly divisible by the soft max                                                                                                                                                                                                                                                                                                                         |