diff --git a/datafusion/common/src/config.rs b/datafusion/common/src/config.rs index dedce74ff40d..5b1325ec06ee 100644 --- a/datafusion/common/src/config.rs +++ b/datafusion/common/src/config.rs @@ -273,11 +273,11 @@ config_namespace! { /// memory consumption pub max_buffered_batches_per_output_file: usize, default = 2 - /// When scanning file paths, whether to ignore subdirectory files, - /// ignored by default (true), when reading a partitioned table, - /// `listing_table_ignore_subdirectory` is always equal to false, even if set to true + /// Should sub directories be ignored when scanning directories for data + /// files. Defaults to true (ignores subdirectories), consistent with + /// Hive. Note that this setting does not affect reading partitioned + /// tables (e.g. `/table/year=2021/month=01/data.parquet`). pub listing_table_ignore_subdirectory: bool, default = true - } } diff --git a/datafusion/sqllogictest/test_files/information_schema.slt b/datafusion/sqllogictest/test_files/information_schema.slt index 36876beb1447..1b5ad86546a3 100644 --- a/datafusion/sqllogictest/test_files/information_schema.slt +++ b/datafusion/sqllogictest/test_files/information_schema.slt @@ -225,7 +225,7 @@ datafusion.execution.aggregate.scalar_update_factor 10 Specifies the threshold f datafusion.execution.batch_size 8192 Default batch size while creating new batches, it's especially useful for buffer-in-memory batches since creating tiny batches would result in too much metadata memory consumption datafusion.execution.coalesce_batches true When set to true, record batches will be examined between each operator and small batches will be coalesced into larger batches. This is helpful when there are highly selective filters or joins that could produce tiny output batches. The target batch size is determined by the configuration setting datafusion.execution.collect_statistics false Should DataFusion collect statistics after listing files -datafusion.execution.listing_table_ignore_subdirectory true When scanning file paths, whether to ignore subdirectory files, ignored by default (true), when reading a partitioned table, `listing_table_ignore_subdirectory` is always equal to false, even if set to true +datafusion.execution.listing_table_ignore_subdirectory true Should sub directories be ignored when scanning directories for data files. Defaults to true (ignores subdirectories), consistent with Hive. Note that this setting does not affect reading partitioned tables (e.g. `/table/year=2021/month=01/data.parquet`). datafusion.execution.max_buffered_batches_per_output_file 2 This is the maximum number of RecordBatches buffered for each output file being worked. Higher values can potentially give faster write performance at the cost of higher peak memory consumption 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. diff --git a/docs/source/user-guide/configs.md b/docs/source/user-guide/configs.md index 1f7fa7760b94..0a5c221c5034 100644 --- a/docs/source/user-guide/configs.md +++ b/docs/source/user-guide/configs.md @@ -82,7 +82,7 @@ Environment variables are read during `SessionConfig` initialisation so they mus | 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 | | datafusion.execution.max_buffered_batches_per_output_file | 2 | This is the maximum number of RecordBatches buffered for each output file being worked. Higher values can potentially give faster write performance at the cost of higher peak memory consumption | -| datafusion.execution.listing_table_ignore_subdirectory | true | When scanning file paths, whether to ignore subdirectory files, ignored by default (true), when reading a partitioned table, `listing_table_ignore_subdirectory` is always equal to false, even if set to true | +| datafusion.execution.listing_table_ignore_subdirectory | true | Should sub directories be ignored when scanning directories for data files. Defaults to true (ignores subdirectories), consistent with Hive. Note that this setting does not affect reading partitioned tables (e.g. `/table/year=2021/month=01/data.parquet`). | | datafusion.optimizer.enable_distinct_aggregation_soft_limit | true | When set to true, the optimizer will push a limit operation into grouped aggregations which have no aggregate expressions, as a soft limit, emitting groups once the limit is reached, before all rows in the group are read. | | datafusion.optimizer.enable_round_robin_repartition | true | When set to true, the physical plan optimizer will try to add round robin repartitioning to increase parallelism to leverage more CPU cores | | datafusion.optimizer.enable_topk_aggregation | true | When set to true, the optimizer will attempt to perform limit operations during aggregations, if possible |