diff --git a/datafusion-cli/src/main.rs b/datafusion-cli/src/main.rs index 6d127a7e1cc71..726bd6e71634e 100644 --- a/datafusion-cli/src/main.rs +++ b/datafusion-cli/src/main.rs @@ -856,7 +856,11 @@ mod tests { .build_arc() .unwrap(); - let ctx = SessionContext::new_with_config_rt(SessionConfig::default(), rt); + // Pin `created_by` so the size of the written parquet files (checked + // below) does not depend on the DataFusion version string + let config = SessionConfig::default() + .set_str("datafusion.execution.parquet.created_by", "datafusion"); + let ctx = SessionContext::new_with_config_rt(config, rt); ctx.register_object_store( &Url::parse("mem://test_table").unwrap(), @@ -929,8 +933,8 @@ mod tests { +---------------------+-----------+-----------------+------+------+ | metadata_size_bytes | filename | file_size_bytes | etag | hits | +---------------------+-----------+-----------------+------+------+ - | 216 | 0.parquet | 3620 | "0" | 2 | - | 216 | 1.parquet | 3620 | "1" | 2 | + | 216 | 0.parquet | 3605 | "0" | 2 | + | 216 | 1.parquet | 3605 | "1" | 2 | +---------------------+-----------+-----------------+------+------+ "#); diff --git a/datafusion/sqllogictest/src/test_context.rs b/datafusion/sqllogictest/src/test_context.rs index c85642bb0a67d..f6e2c256230f1 100644 --- a/datafusion/sqllogictest/src/test_context.rs +++ b/datafusion/sqllogictest/src/test_context.rs @@ -105,7 +105,13 @@ impl TestContext { let file_name = relative_path.file_name().unwrap().to_str().unwrap(); let config = SessionConfig::new() // hardcode target partitions so plans are deterministic - .with_target_partitions(4); + .with_target_partitions(4) + // The default `created_by` embeds the DataFusion version, which + // changes the size of written parquet files (and thus metrics such + // as `scan_efficiency_ratio` in EXPLAIN ANALYZE output) whenever + // the version string length changes. Pin it so test output is + // independent of the version. + .set_str("datafusion.execution.parquet.created_by", "datafusion"); let pool = crate::memory_drift::wrap_pool( Arc::new(UnboundedMemoryPool::default()), &relative_path.display().to_string(), diff --git a/datafusion/sqllogictest/test_files/cte.slt b/datafusion/sqllogictest/test_files/cte.slt index 7dc707fb71477..4da264bcd0736 100644 --- a/datafusion/sqllogictest/test_files/cte.slt +++ b/datafusion/sqllogictest/test_files/cte.slt @@ -1980,7 +1980,7 @@ Plan with Metrics 07)--------ProjectionExec: expr=[n@0 as n, n@0 + 1 as w.n + Int64(1)], metrics=[] 08)----------FilterExec: n@0 < 5, metrics=[] 09)------------WorkTableExec: name=w, metrics=[] -10)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/cte/hash_join_dynamic_filter.parquet]]}, projection=[k], output_ordering=[k@0 ASC NULLS LAST], file_type=parquet, predicate=DynamicFilter [ true ], dynamic_rg_pruning=eligible, metrics=[output_rows=4, output_batches=4, files_ranges_pruned_statistics=4 total → 4 matched, row_groups_pruned_statistics=4 total → 4 matched, page_index_pages_pruned=4 total → 4 matched, page_index_rows_pruned=400 total → 400 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=4, files_processed=4, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=4, pushdown_rows_pruned=396, predicate_cache_inner_records=400, predicate_cache_records=4, scan_efficiency_ratio=157.36% (1.14 K/727)] +10)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/cte/hash_join_dynamic_filter.parquet]]}, projection=[k], output_ordering=[k@0 ASC NULLS LAST], file_type=parquet, predicate=DynamicFilter [ true ], dynamic_rg_pruning=eligible, metrics=[output_rows=4, output_batches=4, files_ranges_pruned_statistics=4 total → 4 matched, row_groups_pruned_statistics=4 total → 4 matched, page_index_pages_pruned=4 total → 4 matched, page_index_rows_pruned=400 total → 400 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=4, files_processed=4, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=4, pushdown_rows_pruned=396, predicate_cache_inner_records=400, predicate_cache_records=4, scan_efficiency_ratio=160.67% (1.14 K/712)] statement ok DROP TABLE hash_join_dynamic_filter; @@ -2060,7 +2060,7 @@ Plan with Metrics 07)--------FilterExec: n@0 < 4, metrics=[] 08)----------WorkTableExec: name=w, metrics=[] 09)--------SortExec: TopK(fetch=1), expr=[k@0 ASC NULLS LAST], preserve_partitioning=[false], metrics=[] -10)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/cte/topk_dynamic_filter.parquet]]}, projection=[k], file_type=parquet, predicate=DynamicFilter [ true ], sort_order_for_reorder=[k@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, metrics=[output_rows=30, output_batches=3, files_ranges_pruned_statistics=3 total → 3 matched, row_groups_pruned_statistics=30 total → 30 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=3, files_processed=3, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=30, pushdown_rows_pruned=0, predicate_cache_inner_records=30, predicate_cache_records=30, scan_efficiency_ratio=9.9% (279/2.82 K)] +10)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/cte/topk_dynamic_filter.parquet]]}, projection=[k], file_type=parquet, predicate=DynamicFilter [ true ], sort_order_for_reorder=[k@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, metrics=[output_rows=30, output_batches=3, files_ranges_pruned_statistics=3 total → 3 matched, row_groups_pruned_statistics=30 total → 30 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=3, files_processed=3, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=30, pushdown_rows_pruned=0, predicate_cache_inner_records=30, predicate_cache_records=30, scan_efficiency_ratio=9.96% (279/2.80 K)] statement ok DROP TABLE topk_dynamic_filter; diff --git a/datafusion/sqllogictest/test_files/dynamic_filter_pushdown_config.slt b/datafusion/sqllogictest/test_files/dynamic_filter_pushdown_config.slt index 524e922765a62..40d311f32fa8d 100644 --- a/datafusion/sqllogictest/test_files/dynamic_filter_pushdown_config.slt +++ b/datafusion/sqllogictest/test_files/dynamic_filter_pushdown_config.slt @@ -91,7 +91,7 @@ Plan with Metrics 03)----ProjectionExec: expr=[id@0 as id, value@1 as v, value@1 + id@0 as name], metrics=[output_rows=10, ] 04)------FilterExec: value@1 > 3, metrics=[output_rows=10, , selectivity=100% (10/10)] 05)--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1, metrics=[output_rows=10, ] -06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/dynamic_filter_pushdown_config/test_data.parquet]]}, projection=[id, value], file_type=parquet, predicate=value@1 > 3 AND DynamicFilter [ value@1 IS NULL OR value@1 > 800 ], dynamic_rg_pruning=eligible, pruning_predicate=value_null_count@1 != row_count@2 AND value_max@0 > 3 AND (value_null_count@1 > 0 OR value_null_count@1 != row_count@2 AND value_max@0 > 800), required_guarantees=[], metrics=[output_rows=10, elapsed_compute=, output_bytes=80.0 B, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched -> 1 fully matched, page_index_pages_pruned=0 total → 0 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, bytes_processed=1147.0 B, bytes_scanned=210.0 B, page_index_load_skipped=1, row_groups_pruned_dynamic_filter=0, metadata_load_time=, scan_efficiency_ratio=18.31% (210/1.15 K)] +06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/dynamic_filter_pushdown_config/test_data.parquet]]}, projection=[id, value], file_type=parquet, predicate=value@1 > 3 AND DynamicFilter [ value@1 IS NULL OR value@1 > 800 ], dynamic_rg_pruning=eligible, pruning_predicate=value_null_count@1 != row_count@2 AND value_max@0 > 3 AND (value_null_count@1 > 0 OR value_null_count@1 != row_count@2 AND value_max@0 > 800), required_guarantees=[], metrics=[output_rows=10, elapsed_compute=, output_bytes=80.0 B, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched -> 1 fully matched, page_index_pages_pruned=0 total → 0 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, bytes_processed=1132.0 B, bytes_scanned=210.0 B, page_index_load_skipped=1, row_groups_pruned_dynamic_filter=0, metadata_load_time=, scan_efficiency_ratio=18.55% (210/1.13 K)] statement ok set datafusion.explain.analyze_level = dev; diff --git a/datafusion/sqllogictest/test_files/explain_analyze.slt b/datafusion/sqllogictest/test_files/explain_analyze.slt index 7a883f6b5d783..42ca513f29efd 100644 --- a/datafusion/sqllogictest/test_files/explain_analyze.slt +++ b/datafusion/sqllogictest/test_files/explain_analyze.slt @@ -234,7 +234,7 @@ explain analyze select * from cat_tracking where species > 'M' AND s >= 50 order ---- Plan with Metrics 01)SortExec: TopK(fetch=3), expr=[species@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[species@0 < Nlpine Sheep], metrics=[output_rows=3] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.75% (485/2.23 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.9% (485/2.21 K)] statement ok reset datafusion.explain.analyze_categories; @@ -546,7 +546,7 @@ EXPLAIN (ANALYZE, METRICS 'rows', LEVEL summary) select * from cat_tracking wher ---- Plan with Metrics 01)SortExec: TopK(fetch=3), expr=[species@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[species@0 < Nlpine Sheep], metrics=[output_rows=3] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.75% (485/2.23 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.9% (485/2.21 K)] # ---- Quoted-string METRICS with multiple categories ---- @@ -584,7 +584,7 @@ EXPLAIN (ANALYZE, METRICS 'rows', TIMING on, LEVEL summary) select * from cat_tr ---- Plan with Metrics 01)SortExec: TopK(fetch=3), expr=[species@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[species@0 < Nlpine Sheep], metrics=[output_rows=3, elapsed_compute=] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, elapsed_compute=, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, metadata_load_time=, scan_efficiency_ratio=21.75% (485/2.23 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, elapsed_compute=, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, metadata_load_time=, scan_efficiency_ratio=21.9% (485/2.21 K)] # ---- SUMMARY sugar: `SUMMARY on` ↔ `LEVEL summary` ---- # Equivalent to METRICS 'rows', LEVEL summary above. @@ -594,7 +594,7 @@ EXPLAIN (ANALYZE, METRICS 'rows', SUMMARY on) select * from cat_tracking where s ---- Plan with Metrics 01)SortExec: TopK(fetch=3), expr=[species@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[species@0 < Nlpine Sheep], metrics=[output_rows=3] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.75% (485/2.23 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.9% (485/2.21 K)] # ---- Statement option overrides session config ---- # Session says 'timing' but statement-level `METRICS 'rows'` wins. @@ -607,7 +607,7 @@ EXPLAIN (ANALYZE, METRICS 'rows', LEVEL summary) select * from cat_tracking wher ---- Plan with Metrics 01)SortExec: TopK(fetch=3), expr=[species@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[species@0 < Nlpine Sheep], metrics=[output_rows=3] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.75% (485/2.23 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.9% (485/2.21 K)] # ---- pgjson format: structural golden with no metrics ---- @@ -669,7 +669,7 @@ EXPLAIN (ANALYZE, METRICS rows, LEVEL summary) select * from cat_tracking where ---- Plan with Metrics 01)SortExec: TopK(fetch=3), expr=[species@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[species@0 < Nlpine Sheep], metrics=[output_rows=3] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.75% (485/2.23 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/explain_analyze/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, scan_efficiency_ratio=21.9% (485/2.21 K)] statement ok reset datafusion.sql_parser.dialect; diff --git a/datafusion/sqllogictest/test_files/information_schema.slt b/datafusion/sqllogictest/test_files/information_schema.slt index bd0a8faedf12b..2ec9dece06963 100644 --- a/datafusion/sqllogictest/test_files/information_schema.slt +++ b/datafusion/sqllogictest/test_files/information_schema.slt @@ -1014,5 +1014,7 @@ set datafusion.execution.target_partitions = 4; statement ok reset datafusion.execution.planning_concurrency; +# The SLT runner pins `created_by` to `datafusion` instead of using the default +# (which includes the DataFusion version), so set it back explicitly. statement ok -reset datafusion.execution.parquet.created_by; +set datafusion.execution.parquet.created_by = datafusion; diff --git a/datafusion/sqllogictest/test_files/limit_pruning.slt b/datafusion/sqllogictest/test_files/limit_pruning.slt index 5676cfe86db22..5285dd02391d8 100644 --- a/datafusion/sqllogictest/test_files/limit_pruning.slt +++ b/datafusion/sqllogictest/test_files/limit_pruning.slt @@ -50,7 +50,7 @@ set datafusion.explain.analyze_level = summary; query TT explain analyze select * from tracking_data where species > 'M' AND s >= 50 limit 3; ---- -Plan with Metrics DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/limit_pruning/data.parquet]]}, projection=[species, s], limit=3, file_type=parquet, predicate=species@0 > M AND s@1 >= 50, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50, required_guarantees=[], metrics=[output_rows=3, elapsed_compute=, output_bytes=, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=0 total → 0 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=2 total → 0 matched, bytes_processed=, bytes_scanned=, metadata_load_time=, scan_efficiency_ratio= (159/2.23 K)] +Plan with Metrics DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/limit_pruning/data.parquet]]}, projection=[species, s], limit=3, file_type=parquet, predicate=species@0 > M AND s@1 >= 50, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50, required_guarantees=[], metrics=[output_rows=3, elapsed_compute=, output_bytes=, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, page_index_pages_pruned=0 total → 0 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=2 total → 0 matched, bytes_processed=, bytes_scanned=, metadata_load_time=, scan_efficiency_ratio= (159/2.21 K)] statement ok CREATE TABLE fully_matched_limit_source AS VALUES diff --git a/datafusion/sqllogictest/test_files/push_down_filter_parquet.slt b/datafusion/sqllogictest/test_files/push_down_filter_parquet.slt index bd1213ac9945d..bc9fa4f5b9d63 100644 --- a/datafusion/sqllogictest/test_files/push_down_filter_parquet.slt +++ b/datafusion/sqllogictest/test_files/push_down_filter_parquet.slt @@ -193,7 +193,7 @@ EXPLAIN ANALYZE SELECT t FROM topk_pushdown ORDER BY t * t LIMIT 10; ---- Plan with Metrics 01)SortExec: TopK(fetch=10), expr=[t@0 * t@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[t@0 * t@0 < 1884329474306198481], metrics=[output_rows=10, output_batches=1, row_replacements=10] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_pushdown.parquet]]}, projection=[t], output_ordering=[t@0 ASC NULLS LAST], file_type=parquet, predicate=DynamicFilter [ t@0 * t@0 < 1884329474306198481 ], dynamic_rg_pruning=eligible, metrics=[output_rows=128, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=782 total → 782 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=128, pushdown_rows_pruned=99.87 K, predicate_cache_inner_records=128, predicate_cache_records=128, scan_efficiency_ratio=64.87% (258.7 K/398.8 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_pushdown.parquet]]}, projection=[t], output_ordering=[t@0 ASC NULLS LAST], file_type=parquet, predicate=DynamicFilter [ t@0 * t@0 < 1884329474306198481 ], dynamic_rg_pruning=eligible, metrics=[output_rows=128, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=782 total → 782 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=128, pushdown_rows_pruned=99.87 K, predicate_cache_inner_records=128, predicate_cache_records=128, scan_efficiency_ratio=64.87% (258.7 K/398.7 K)] statement ok reset datafusion.explain.analyze_categories; @@ -255,7 +255,7 @@ EXPLAIN ANALYZE SELECT * FROM topk_single_col ORDER BY b DESC LIMIT 1; ---- Plan with Metrics 01)SortExec: TopK(fetch=1), expr=[b@1 DESC], preserve_partitioning=[false], filter=[b@1 IS NULL OR b@1 > bd], metrics=[output_rows=1, output_batches=1, row_replacements=1] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_single_col.parquet]]}, projection=[a, b, c], file_type=parquet, predicate=DynamicFilter [ b@1 IS NULL OR b@1 > bd ], sort_order_for_reorder=[b@1 DESC], reverse_row_groups=true, dynamic_rg_pruning=eligible, pruning_predicate=b_null_count@0 > 0 OR b_null_count@0 != row_count@2 AND b_max@1 > bd, required_guarantees=[], metrics=[output_rows=4, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=4, pushdown_rows_pruned=0, predicate_cache_inner_records=4, predicate_cache_records=4, scan_efficiency_ratio=21.94% (222/1.01 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_single_col.parquet]]}, projection=[a, b, c], file_type=parquet, predicate=DynamicFilter [ b@1 IS NULL OR b@1 > bd ], sort_order_for_reorder=[b@1 DESC], reverse_row_groups=true, dynamic_rg_pruning=eligible, pruning_predicate=b_null_count@0 > 0 OR b_null_count@0 != row_count@2 AND b_max@1 > bd, required_guarantees=[], metrics=[output_rows=4, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=4, pushdown_rows_pruned=0, predicate_cache_inner_records=4, predicate_cache_records=4, scan_efficiency_ratio=22.27% (222/997)] statement ok reset datafusion.explain.analyze_categories; @@ -306,7 +306,7 @@ EXPLAIN ANALYZE SELECT * FROM topk_multi_col ORDER BY b ASC NULLS LAST, a DESC L ---- Plan with Metrics 01)SortExec: TopK(fetch=2), expr=[b@1 ASC NULLS LAST, a@0 DESC], preserve_partitioning=[false], filter=[b@1 < bb OR b@1 = bb AND (a@0 IS NULL OR a@0 > ac)], metrics=[output_rows=2, output_batches=1, row_replacements=2] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_multi_col.parquet]]}, projection=[a, b, c], file_type=parquet, predicate=DynamicFilter [ b@1 < bb OR b@1 = bb AND (a@0 IS NULL OR a@0 > ac) ], sort_order_for_reorder=[b@1 ASC NULLS LAST, a@0 DESC], dynamic_rg_pruning=eligible, pruning_predicate=b_null_count@1 != row_count@2 AND b_min@0 < bb OR b_null_count@1 != row_count@2 AND b_min@0 <= bb AND bb <= b_max@3 AND (a_null_count@4 > 0 OR a_null_count@4 != row_count@2 AND a_max@5 > ac), required_guarantees=[], metrics=[output_rows=4, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=4, pushdown_rows_pruned=0, predicate_cache_inner_records=8, predicate_cache_records=8, scan_efficiency_ratio=21.94% (222/1.01 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_multi_col.parquet]]}, projection=[a, b, c], file_type=parquet, predicate=DynamicFilter [ b@1 < bb OR b@1 = bb AND (a@0 IS NULL OR a@0 > ac) ], sort_order_for_reorder=[b@1 ASC NULLS LAST, a@0 DESC], dynamic_rg_pruning=eligible, pruning_predicate=b_null_count@1 != row_count@2 AND b_min@0 < bb OR b_null_count@1 != row_count@2 AND b_min@0 <= bb AND bb <= b_max@3 AND (a_null_count@4 > 0 OR a_null_count@4 != row_count@2 AND a_max@5 > ac), required_guarantees=[], metrics=[output_rows=4, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=4, pushdown_rows_pruned=0, predicate_cache_inner_records=8, predicate_cache_records=8, scan_efficiency_ratio=22.27% (222/997)] statement ok reset datafusion.explain.analyze_categories; @@ -384,8 +384,8 @@ FROM join_probe p INNER JOIN join_build AS build ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(a@0, a@0), (b@1, b@1)], projection=[a@3, b@4, c@2, e@5], metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=2, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/join_build.parquet]]}, projection=[a, b, c], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=19.88% (196/986)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/join_probe.parquet]]}, projection=[a, b, e], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= ba AND b@1 <= bb AND struct(a@0, b@1) IN (SET) ([{c0:aa,c1:ba}, {c0:ab,c1:bb}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= ba AND b_null_count@5 != row_count@2 AND b_min@6 <= bb, required_guarantees=[a in (aa, ab), b in (ba, bb)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=3 total → 3 matched, row_groups_pruned_bloom_filter=3 total → 2 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=4, predicate_cache_records=4, scan_efficiency_ratio=23.61% (606/2.57 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/join_build.parquet]]}, projection=[a, b, c], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=20.19% (196/971)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/join_probe.parquet]]}, projection=[a, b, e], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= ba AND b@1 <= bb AND struct(a@0, b@1) IN (SET) ([{c0:aa,c1:ba}, {c0:ab,c1:bb}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= ba AND b_null_count@5 != row_count@2 AND b_min@6 <= bb, required_guarantees=[a in (aa, ab), b in (ba, bb)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=3 total → 3 matched, row_groups_pruned_bloom_filter=3 total → 2 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=4, predicate_cache_records=4, scan_efficiency_ratio=23.75% (606/2.55 K)] statement ok reset datafusion.explain.analyze_categories; @@ -470,9 +470,9 @@ INNER JOIN nested_t3 ON nested_t2.c = nested_t3.d; Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(c@3, d@0)], metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=2, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] 02)--HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(a@0, b@0)], metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=2, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] -03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nested_t1.parquet]]}, projection=[a, x], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=17.72% (132/745)] -04)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nested_t2.parquet]]}, projection=[b, c, y], file_type=parquet, predicate=DynamicFilter [ b@0 >= aa AND b@0 <= ab AND b@0 IN (SET) ([aa, ab]) ], dynamic_rg_pruning=eligible, pruning_predicate=b_null_count@1 != row_count@2 AND b_max@0 >= aa AND b_null_count@1 != row_count@2 AND b_min@3 <= ab AND (b_null_count@1 != row_count@2 AND b_min@3 <= aa AND aa <= b_max@0 OR b_null_count@1 != row_count@2 AND b_min@3 <= ab AND ab <= b_max@0), required_guarantees=[b in (aa, ab)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=5 total → 5 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=3, predicate_cache_inner_records=5, predicate_cache_records=2, scan_efficiency_ratio=22.78% (234/1.03 K)] -05)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nested_t3.parquet]]}, projection=[d, z], file_type=parquet, predicate=DynamicFilter [ d@0 >= ca AND d@0 <= cb AND hash_lookup ], dynamic_rg_pruning=eligible, pruning_predicate=d_null_count@1 != row_count@2 AND d_max@0 >= ca AND d_null_count@1 != row_count@2 AND d_min@3 <= cb, required_guarantees=[], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=8 total → 8 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=6, predicate_cache_inner_records=8, predicate_cache_records=2, scan_efficiency_ratio=21.86% (172/787)] +03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nested_t1.parquet]]}, projection=[a, x], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=18.08% (132/730)] +04)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nested_t2.parquet]]}, projection=[b, c, y], file_type=parquet, predicate=DynamicFilter [ b@0 >= aa AND b@0 <= ab AND b@0 IN (SET) ([aa, ab]) ], dynamic_rg_pruning=eligible, pruning_predicate=b_null_count@1 != row_count@2 AND b_max@0 >= aa AND b_null_count@1 != row_count@2 AND b_min@3 <= ab AND (b_null_count@1 != row_count@2 AND b_min@3 <= aa AND aa <= b_max@0 OR b_null_count@1 != row_count@2 AND b_min@3 <= ab AND ab <= b_max@0), required_guarantees=[b in (aa, ab)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=5 total → 5 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=3, predicate_cache_inner_records=5, predicate_cache_records=2, scan_efficiency_ratio=23.12% (234/1.01 K)] +05)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nested_t3.parquet]]}, projection=[d, z], file_type=parquet, predicate=DynamicFilter [ d@0 >= ca AND d@0 <= cb AND hash_lookup ], dynamic_rg_pruning=eligible, pruning_predicate=d_null_count@1 != row_count@2 AND d_max@0 >= ca AND d_null_count@1 != row_count@2 AND d_min@3 <= cb, required_guarantees=[], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=8 total → 8 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=6, predicate_cache_inner_records=8, predicate_cache_records=2, scan_efficiency_ratio=22.28% (172/772)] statement ok reset datafusion.explain.analyze_categories; @@ -601,8 +601,8 @@ LIMIT 2; Plan with Metrics 01)SortExec: TopK(fetch=2), expr=[e@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[e@0 < bb], metrics=[output_rows=2, output_batches=1, row_replacements=2] 02)--HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(a@0, d@0)], projection=[e@2], metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=2, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] -03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_join_build.parquet]]}, projection=[a], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=6.49% (64/986)] -04)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_join_probe.parquet]]}, projection=[d, e], file_type=parquet, predicate=DynamicFilter [ d@0 >= aa AND d@0 <= ab AND d@0 IN (SET) ([aa, ab]) ] AND DynamicFilter [ e@1 < bb ], dynamic_rg_pruning=eligible, pruning_predicate=d_null_count@1 != row_count@2 AND d_max@0 >= aa AND d_null_count@1 != row_count@2 AND d_min@3 <= ab AND (d_null_count@1 != row_count@2 AND d_min@3 <= aa AND aa <= d_max@0 OR d_null_count@1 != row_count@2 AND d_min@3 <= ab AND ab <= d_max@0) AND e_null_count@5 != row_count@2 AND e_min@4 < bb, required_guarantees=[d in (aa, ab)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=4 total → 4 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=15.11% (154/1.02 K)] +03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_join_build.parquet]]}, projection=[a], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=6.59% (64/971)] +04)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_join_probe.parquet]]}, projection=[d, e], file_type=parquet, predicate=DynamicFilter [ d@0 >= aa AND d@0 <= ab AND d@0 IN (SET) ([aa, ab]) ] AND DynamicFilter [ e@1 < bb ], dynamic_rg_pruning=eligible, pruning_predicate=d_null_count@1 != row_count@2 AND d_max@0 >= aa AND d_null_count@1 != row_count@2 AND d_min@3 <= ab AND (d_null_count@1 != row_count@2 AND d_min@3 <= aa AND aa <= d_max@0 OR d_null_count@1 != row_count@2 AND d_min@3 <= ab AND ab <= d_max@0) AND e_null_count@5 != row_count@2 AND e_min@4 < bb, required_guarantees=[d in (aa, ab)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=4 total → 4 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=15.34% (154/1.00 K)] statement ok reset datafusion.explain.analyze_categories; @@ -652,7 +652,7 @@ EXPLAIN ANALYZE SELECT b, a FROM topk_proj ORDER BY a LIMIT 2; Plan with Metrics 01)ProjectionExec: expr=[b@1 as b, a@0 as a], metrics=[output_rows=2, output_batches=1] 02)--SortExec: TopK(fetch=2), expr=[a@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[a@0 < 2], metrics=[output_rows=2, output_batches=1, row_replacements=2] -03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_proj.parquet]]}, projection=[a, b], file_type=parquet, predicate=DynamicFilter [ a@0 < 2 ], sort_order_for_reorder=[a@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_min@0 < 2, required_guarantees=[], metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=13.4% (141/1.05 K)] +03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_proj.parquet]]}, projection=[a, b], file_type=parquet, predicate=DynamicFilter [ a@0 < 2 ], sort_order_for_reorder=[a@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_min@0 < 2, required_guarantees=[], metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=13.6% (141/1.04 K)] # Case 2: prune — `SELECT a` — filter stays as `a < 2` on the scan. query TT @@ -660,7 +660,7 @@ EXPLAIN ANALYZE SELECT a FROM topk_proj ORDER BY a LIMIT 2; ---- Plan with Metrics 01)SortExec: TopK(fetch=2), expr=[a@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[a@0 < 2], metrics=[output_rows=2, output_batches=1, row_replacements=2] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_proj.parquet]]}, projection=[a], file_type=parquet, predicate=DynamicFilter [ a@0 < 2 ], sort_order_for_reorder=[a@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_min@0 < 2, required_guarantees=[], metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=6.94% (73/1.05 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_proj.parquet]]}, projection=[a], file_type=parquet, predicate=DynamicFilter [ a@0 < 2 ], sort_order_for_reorder=[a@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_min@0 < 2, required_guarantees=[], metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=7.04% (73/1.04 K)] # Case 3: expression — `SELECT a+1 AS a_plus_1` — the TopK filter is on # `a_plus_1`, the scan predicate must read `a@0 + 1`. @@ -669,7 +669,7 @@ EXPLAIN ANALYZE SELECT a + 1 AS a_plus_1, b FROM topk_proj ORDER BY a_plus_1 LIM ---- Plan with Metrics 01)SortExec: TopK(fetch=2), expr=[a_plus_1@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[a_plus_1@0 < 3], metrics=[output_rows=2, output_batches=1, row_replacements=2] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_proj.parquet]]}, projection=[CAST(a@0 AS Int64) + 1 as a_plus_1, b], file_type=parquet, predicate=DynamicFilter [ CAST(a@0 AS Int64) + 1 < 3 ], dynamic_rg_pruning=eligible, metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=13.4% (141/1.05 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_proj.parquet]]}, projection=[CAST(a@0 AS Int64) + 1 as a_plus_1, b], file_type=parquet, predicate=DynamicFilter [ CAST(a@0 AS Int64) + 1 < 3 ], dynamic_rg_pruning=eligible, metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=13.6% (141/1.04 K)] # Case 4: alias shadowing — `SELECT a+1 AS a` — the projection renames # `a+1` to `a`, so the TopK's `a < 3` must still be rewritten to @@ -679,7 +679,7 @@ EXPLAIN ANALYZE SELECT a + 1 AS a, b FROM topk_proj ORDER BY a LIMIT 2; ---- Plan with Metrics 01)SortExec: TopK(fetch=2), expr=[a@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[a@0 < 3], metrics=[output_rows=2, output_batches=1, row_replacements=2] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_proj.parquet]]}, projection=[CAST(a@0 AS Int64) + 1 as a, b], file_type=parquet, predicate=DynamicFilter [ CAST(a@0 AS Int64) + 1 < 3 ], sort_order_for_reorder=[a@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=13.4% (141/1.05 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/topk_proj.parquet]]}, projection=[CAST(a@0 AS Int64) + 1 as a, b], file_type=parquet, predicate=DynamicFilter [ CAST(a@0 AS Int64) + 1 < 3 ], sort_order_for_reorder=[a@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=13.6% (141/1.04 K)] statement ok reset datafusion.explain.analyze_categories; @@ -736,12 +736,12 @@ INNER JOIN ( ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(a@0, a@0)], projection=[a@0, min_value@2], metrics=[output_rows=2, output_batches=2, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=2, input_rows=2, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/join_agg_build.parquet]]}, projection=[a], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=14.45% (64/443)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/join_agg_build.parquet]]}, projection=[a], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=14.95% (64/428)] 03)--ProjectionExec: expr=[a@0 as a, min(join_agg_probe.value)@1 as min_value], metrics=[output_rows=2, output_batches=2] 04)----AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[min(join_agg_probe.value)], metrics=[output_rows=2, output_batches=2, spill_count=0, spilled_rows=0] 05)------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1, metrics=[output_rows=2, output_batches=2, spill_count=0, spilled_rows=0] 06)--------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[min(join_agg_probe.value)], metrics=[output_rows=2, output_batches=1, spill_count=0, spilled_rows=0, skipped_aggregation_rows=0, reduction_factor=100% (2/2)] -07)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/join_agg_probe.parquet]]}, projection=[a, value], file_type=parquet, predicate=DynamicFilter [ a@0 >= h1 AND a@0 <= h2 AND a@0 IN (SET) ([h1, h2]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= h1 AND a_null_count@1 != row_count@2 AND a_min@3 <= h2 AND (a_null_count@1 != row_count@2 AND a_min@3 <= h1 AND h1 <= a_max@0 OR a_null_count@1 != row_count@2 AND a_min@3 <= h2 AND h2 <= a_max@0), required_guarantees=[a in (h1, h2)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=4 total → 4 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=4, predicate_cache_records=2, scan_efficiency_ratio=19.43% (151/777)] +07)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/join_agg_probe.parquet]]}, projection=[a, value], file_type=parquet, predicate=DynamicFilter [ a@0 >= h1 AND a@0 <= h2 AND a@0 IN (SET) ([h1, h2]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= h1 AND a_null_count@1 != row_count@2 AND a_min@3 <= h2 AND (a_null_count@1 != row_count@2 AND a_min@3 <= h1 AND h1 <= a_max@0 OR a_null_count@1 != row_count@2 AND a_min@3 <= h2 AND h2 <= a_max@0), required_guarantees=[a in (h1, h2)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=4 total → 4 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=4, predicate_cache_records=2, scan_efficiency_ratio=19.82% (151/762)] statement ok reset datafusion.explain.analyze_categories; @@ -803,8 +803,8 @@ ON nulls_build.a = nulls_probe.a AND nulls_build.b = nulls_probe.b; ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(a@0, a@0), (b@1, b@1)], metrics=[output_rows=1, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=3, input_batches=1, input_rows=1, avg_fanout=100% (1/1), probe_hit_rate=100% (1/1)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nulls_build.parquet]]}, projection=[a, b], file_type=parquet, metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=18.6% (144/774)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nulls_probe.parquet]]}, projection=[a, b, c], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= 1 AND b@1 <= 2 AND struct(a@0, b@1) IN (SET) ([{c0:aa,c1:1}, {c0:,c1:2}, {c0:ab,c1:}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= 1 AND b_null_count@5 != row_count@2 AND b_min@6 <= 2, required_guarantees=[], metrics=[output_rows=1, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=1, pushdown_rows_pruned=3, predicate_cache_inner_records=8, predicate_cache_records=2, scan_efficiency_ratio=20.45% (225/1.10 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nulls_build.parquet]]}, projection=[a, b], file_type=parquet, metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=18.97% (144/759)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nulls_probe.parquet]]}, projection=[a, b, c], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= 1 AND b@1 <= 2 AND struct(a@0, b@1) IN (SET) ([{c0:aa,c1:1}, {c0:,c1:2}, {c0:ab,c1:}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= 1 AND b_null_count@5 != row_count@2 AND b_min@6 <= 2, required_guarantees=[], metrics=[output_rows=1, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=1, pushdown_rows_pruned=3, predicate_cache_inner_records=8, predicate_cache_records=2, scan_efficiency_ratio=20.74% (225/1.08 K)] statement ok reset datafusion.explain.analyze_categories; @@ -869,8 +869,8 @@ ON lj_build.a = lj_probe.a AND lj_build.b = lj_probe.b; ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Left, on=[(a@0, a@0), (b@1, b@1)], metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=2, input_rows=2, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/lj_build.parquet]]}, projection=[a, b, c], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=19.88% (196/986)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/lj_probe.parquet]]}, projection=[a, b, e], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= ba AND b@1 <= bb AND struct(a@0, b@1) IN (SET) ([{c0:aa,c1:ba}, {c0:ab,c1:bb}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= ba AND b_null_count@5 != row_count@2 AND b_min@6 <= bb, required_guarantees=[a in (aa, ab), b in (ba, bb)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=22.37% (228/1.02 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/lj_build.parquet]]}, projection=[a, b, c], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=20.19% (196/971)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/lj_probe.parquet]]}, projection=[a, b, e], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= ba AND b@1 <= bb AND struct(a@0, b@1) IN (SET) ([{c0:aa,c1:ba}, {c0:ab,c1:bb}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= ba AND b_null_count@5 != row_count@2 AND b_min@6 <= bb, required_guarantees=[a in (aa, ab), b in (ba, bb)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=22.71% (228/1.00 K)] # LEFT SEMI JOIN: only matching build rows are returned; probe scan still # receives the dynamic filter. @@ -885,8 +885,8 @@ WHERE EXISTS ( ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=LeftSemi, on=[(a@0, a@0), (b@1, b@1)], metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=2, input_rows=4, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/lj_build.parquet]]}, projection=[a, b, c], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=19.88% (196/986)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/lj_probe.parquet]]}, projection=[a, b], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= ba AND b@1 <= bb AND struct(a@0, b@1) IN (SET) ([{c0:aa,c1:ba}, {c0:ab,c1:bb}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= ba AND b_null_count@5 != row_count@2 AND b_min@6 <= bb, required_guarantees=[a in (aa, ab), b in (ba, bb)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=15.11% (154/1.02 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/lj_build.parquet]]}, projection=[a, b, c], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=20.19% (196/971)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/lj_probe.parquet]]}, projection=[a, b], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= ba AND b@1 <= bb AND struct(a@0, b@1) IN (SET) ([{c0:aa,c1:ba}, {c0:ab,c1:bb}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= ba AND b_null_count@5 != row_count@2 AND b_min@6 <= bb, required_guarantees=[a in (aa, ab), b in (ba, bb)], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=15.34% (154/1.00 K)] statement ok reset datafusion.explain.analyze_categories; @@ -955,8 +955,8 @@ FROM hl_probe p INNER JOIN hl_build AS build ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(a@0, a@0), (b@1, b@1)], projection=[a@3, b@4, c@2, e@5], metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=2, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/hl_build.parquet]]}, projection=[a, b, c], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=19.88% (196/986)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/hl_probe.parquet]]}, projection=[a, b, e], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= ba AND b@1 <= bb AND hash_lookup ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= ba AND b_null_count@5 != row_count@2 AND b_min@6 <= bb, required_guarantees=[], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=22.37% (228/1.02 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/hl_build.parquet]]}, projection=[a, b, c], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=20.19% (196/971)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/hl_probe.parquet]]}, projection=[a, b, e], file_type=parquet, predicate=DynamicFilter [ a@0 >= aa AND a@0 <= ab AND b@1 >= ba AND b@1 <= bb AND hash_lookup ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@1 != row_count@2 AND a_max@0 >= aa AND a_null_count@1 != row_count@2 AND a_min@3 <= ab AND b_null_count@5 != row_count@2 AND b_max@4 >= ba AND b_null_count@5 != row_count@2 AND b_min@6 <= bb, required_guarantees=[], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=22.71% (228/1.00 K)] statement ok drop table hl_build; @@ -1004,8 +1004,8 @@ FROM int_build b INNER JOIN int_probe p ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(id1@0, id1@0), (id2@1, id2@1)], projection=[id1@0, id2@1, value@2, data@5], metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=2, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/int_build.parquet]]}, projection=[id1, id2, value], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=18.48% (204/1.10 K)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/int_probe.parquet]]}, projection=[id1, id2, data], file_type=parquet, predicate=DynamicFilter [ id1@0 >= 1 AND id1@0 <= 2 AND id2@1 >= 10 AND id2@1 <= 20 AND hash_lookup ], dynamic_rg_pruning=eligible, pruning_predicate=id1_null_count@1 != row_count@2 AND id1_max@0 >= 1 AND id1_null_count@1 != row_count@2 AND id1_min@3 <= 2 AND id2_null_count@5 != row_count@2 AND id2_max@4 >= 10 AND id2_null_count@5 != row_count@2 AND id2_min@6 <= 20, required_guarantees=[], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=20.67% (221/1.07 K)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/int_build.parquet]]}, projection=[id1, id2, value], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=18.73% (204/1.09 K)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/int_probe.parquet]]}, projection=[id1, id2, data], file_type=parquet, predicate=DynamicFilter [ id1@0 >= 1 AND id1@0 <= 2 AND id2@1 >= 10 AND id2@1 <= 20 AND hash_lookup ], dynamic_rg_pruning=eligible, pruning_predicate=id1_null_count@1 != row_count@2 AND id1_max@0 >= 1 AND id1_null_count@1 != row_count@2 AND id1_min@3 <= 2 AND id2_null_count@5 != row_count@2 AND id2_max@4 >= 10 AND id2_null_count@5 != row_count@2 AND id2_min@6 <= 20, required_guarantees=[], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=2, predicate_cache_inner_records=8, predicate_cache_records=4, scan_efficiency_ratio=20.97% (221/1.05 K)] statement ok reset datafusion.explain.analyze_categories; @@ -1056,8 +1056,8 @@ EXPLAIN ANALYZE SELECT nej_build.id, nej_probe.id FROM nej_build JOIN nej_probe ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(id@0, id@0)], NullsEqual: true, metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=2, avg_fanout=100% (2/2), probe_hit_rate=100% (2/2)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nej_build.parquet]]}, projection=[id], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=12.92% (65/503)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nej_probe.parquet]]}, projection=[id], file_type=parquet, predicate=DynamicFilter [ id@0 IS NULL OR id@0 >= 11 AND id@0 <= 11 AND id@0 IN (SET) ([11, NULL]) ], dynamic_rg_pruning=eligible, pruning_predicate=id_null_count@0 > 0 OR id_null_count@0 != row_count@2 AND id_max@1 >= 11 AND id_null_count@0 != row_count@2 AND id_min@3 <= 11 AND (id_null_count@0 != row_count@2 AND id_min@3 <= 11 AND 11 <= id_max@1 OR id_null_count@0 != row_count@2 AND id_min@3 <= NULL AND NULL <= id_max@1), required_guarantees=[], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=3 total → 3 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=1, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=14.45% (74/512)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nej_build.parquet]]}, projection=[id], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=13.32% (65/488)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nej_probe.parquet]]}, projection=[id], file_type=parquet, predicate=DynamicFilter [ id@0 IS NULL OR id@0 >= 11 AND id@0 <= 11 AND id@0 IN (SET) ([11, NULL]) ], dynamic_rg_pruning=eligible, pruning_predicate=id_null_count@0 > 0 OR id_null_count@0 != row_count@2 AND id_max@1 >= 11 AND id_null_count@0 != row_count@2 AND id_min@3 <= 11 AND (id_null_count@0 != row_count@2 AND id_min@3 <= 11 AND 11 <= id_max@1 OR id_null_count@0 != row_count@2 AND id_min@3 <= NULL AND NULL <= id_max@1), required_guarantees=[], metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=3 total → 3 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=1, predicate_cache_inner_records=3, predicate_cache_records=3, scan_efficiency_ratio=14.89% (74/497)] statement ok reset datafusion.explain.analyze_categories; @@ -1099,8 +1099,8 @@ EXPLAIN ANALYZE SELECT mnej_build.a, mnej_build.b, mnej_probe.a, mnej_probe.b FR ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(a@0, a@0), (b@1, b@1)], NullsEqual: true, metrics=[output_rows=2, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=3, avg_fanout=100% (2/2), probe_hit_rate=66.67% (2/3)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/mnej_build.parquet]]}, projection=[a, b], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=16.42% (133/810)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/mnej_probe.parquet]]}, projection=[a, b], file_type=parquet, predicate=DynamicFilter [ a@0 IS NULL OR b@1 IS NULL OR a@0 >= 1 AND a@0 <= 2 AND b@1 >= 10 AND b@1 <= 10 AND struct(a@0, b@1) IN (SET) ([{c0:1,c1:10}, {c0:2,c1:}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@0 > 0 OR b_null_count@1 > 0 OR a_null_count@0 != row_count@3 AND a_max@2 >= 1 AND a_null_count@0 != row_count@3 AND a_min@4 <= 2 AND b_null_count@1 != row_count@3 AND b_max@5 >= 10 AND b_null_count@1 != row_count@3 AND b_min@6 <= 10, required_guarantees=[], metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=6, predicate_cache_records=6, scan_efficiency_ratio=18.16% (148/815)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/mnej_build.parquet]]}, projection=[a, b], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=16.73% (133/795)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/mnej_probe.parquet]]}, projection=[a, b], file_type=parquet, predicate=DynamicFilter [ a@0 IS NULL OR b@1 IS NULL OR a@0 >= 1 AND a@0 <= 2 AND b@1 >= 10 AND b@1 <= 10 AND struct(a@0, b@1) IN (SET) ([{c0:1,c1:10}, {c0:2,c1:}]) ], dynamic_rg_pruning=eligible, pruning_predicate=a_null_count@0 > 0 OR b_null_count@1 > 0 OR a_null_count@0 != row_count@3 AND a_max@2 >= 1 AND a_null_count@0 != row_count@3 AND a_min@4 <= 2 AND b_null_count@1 != row_count@3 AND b_max@5 >= 10 AND b_null_count@1 != row_count@3 AND b_min@6 <= 10, required_guarantees=[], metrics=[output_rows=3, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=3, pushdown_rows_pruned=0, predicate_cache_inner_records=6, predicate_cache_records=6, scan_efficiency_ratio=18.5% (148/800)] statement ok reset datafusion.explain.analyze_categories; @@ -1140,8 +1140,8 @@ EXPLAIN ANALYZE SELECT nnb_build.id, nnb_probe.id FROM nnb_build JOIN nnb_probe ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(id@0, id@0)], NullsEqual: true, metrics=[output_rows=1, output_batches=1, array_map_created_count=1, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=1, avg_fanout=100% (1/1), probe_hit_rate=100% (1/1)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nnb_build.parquet]]}, projection=[id], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=13.71% (68/496)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nnb_probe.parquet]]}, projection=[id], file_type=parquet, predicate=DynamicFilter [ id@0 >= 11 AND id@0 <= 22 AND id@0 IN (SET) ([11, 22]) ], dynamic_rg_pruning=eligible, pruning_predicate=id_null_count@1 != row_count@2 AND id_max@0 >= 11 AND id_null_count@1 != row_count@2 AND id_min@3 <= 22 AND (id_null_count@1 != row_count@2 AND id_min@3 <= 11 AND 11 <= id_max@0 OR id_null_count@1 != row_count@2 AND id_min@3 <= 22 AND 22 <= id_max@0), required_guarantees=[id in (11, 22)], metrics=[output_rows=1, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=3 total → 3 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=1, pushdown_rows_pruned=2, predicate_cache_inner_records=3, predicate_cache_records=1, scan_efficiency_ratio=14.45% (74/512)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nnb_build.parquet]]}, projection=[id], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=14.14% (68/481)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nnb_probe.parquet]]}, projection=[id], file_type=parquet, predicate=DynamicFilter [ id@0 >= 11 AND id@0 <= 22 AND id@0 IN (SET) ([11, 22]) ], dynamic_rg_pruning=eligible, pruning_predicate=id_null_count@1 != row_count@2 AND id_max@0 >= 11 AND id_null_count@1 != row_count@2 AND id_min@3 <= 22 AND (id_null_count@1 != row_count@2 AND id_min@3 <= 11 AND 11 <= id_max@0 OR id_null_count@1 != row_count@2 AND id_min@3 <= 22 AND 22 <= id_max@0), required_guarantees=[id in (11, 22)], metrics=[output_rows=1, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=3 total → 3 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=1, pushdown_rows_pruned=2, predicate_cache_inner_records=3, predicate_cache_records=1, scan_efficiency_ratio=14.89% (74/497)] statement ok reset datafusion.explain.analyze_categories; @@ -1181,8 +1181,8 @@ EXPLAIN ANALYZE SELECT nnp_build.id, nnp_probe.id FROM nnp_build JOIN nnp_probe ---- Plan with Metrics 01)HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(id@0, id@0)], NullsEqual: true, metrics=[output_rows=1, output_batches=1, array_map_created_count=0, build_input_batches=1, build_input_rows=2, input_batches=1, input_rows=1, avg_fanout=100% (1/1), probe_hit_rate=100% (1/1)] -02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nnp_build.parquet]]}, projection=[id], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=12.92% (65/503)] -03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nnp_probe.parquet]]}, projection=[id], file_type=parquet, predicate=DynamicFilter [ id@0 >= 11 AND id@0 <= 11 AND id@0 IN (SET) ([11, NULL]) ], dynamic_rg_pruning=eligible, pruning_predicate=id_null_count@1 != row_count@2 AND id_max@0 >= 11 AND id_null_count@1 != row_count@2 AND id_min@3 <= 11 AND (id_null_count@1 != row_count@2 AND id_min@3 <= 11 AND 11 <= id_max@0 OR id_null_count@1 != row_count@2 AND id_min@3 <= NULL AND NULL <= id_max@0), required_guarantees=[id in (11, NULL)], metrics=[output_rows=1, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=2 total → 2 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=1, pushdown_rows_pruned=1, predicate_cache_inner_records=2, predicate_cache_records=1, scan_efficiency_ratio=13.71% (68/496)] +02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nnp_build.parquet]]}, projection=[id], file_type=parquet, metrics=[output_rows=2, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=0 total → 0 matched, page_index_rows_pruned=0 total → 0 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=0, pushdown_rows_pruned=0, predicate_cache_inner_records=0, predicate_cache_records=0, scan_efficiency_ratio=13.32% (65/488)] +03)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_parquet/nnp_probe.parquet]]}, projection=[id], file_type=parquet, predicate=DynamicFilter [ id@0 >= 11 AND id@0 <= 11 AND id@0 IN (SET) ([11, NULL]) ], dynamic_rg_pruning=eligible, pruning_predicate=id_null_count@1 != row_count@2 AND id_max@0 >= 11 AND id_null_count@1 != row_count@2 AND id_min@3 <= 11 AND (id_null_count@1 != row_count@2 AND id_min@3 <= 11 AND 11 <= id_max@0 OR id_null_count@1 != row_count@2 AND id_min@3 <= NULL AND NULL <= id_max@0), required_guarantees=[id in (11, NULL)], metrics=[output_rows=1, output_batches=1, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=1 total → 1 matched, page_index_pages_pruned=1 total → 1 matched, page_index_rows_pruned=2 total → 2 matched, limit_pruned_row_groups=0 total → 0 matched, batches_split=0, file_open_errors=0, file_scan_errors=0, files_opened=1, files_processed=1, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=1, pushdown_rows_pruned=1, predicate_cache_inner_records=2, predicate_cache_records=1, scan_efficiency_ratio=14.14% (68/481)] statement ok reset datafusion.explain.analyze_categories; diff --git a/datafusion/sqllogictest/test_files/repartition_scan.slt b/datafusion/sqllogictest/test_files/repartition_scan.slt index e90b13275030f..da777d5a3a1f0 100644 --- a/datafusion/sqllogictest/test_files/repartition_scan.slt +++ b/datafusion/sqllogictest/test_files/repartition_scan.slt @@ -51,7 +51,7 @@ logical_plan 02)--TableScan: parquet_table projection=[column1], partial_filters=[parquet_table.column1 != Int32(42)] physical_plan 01)FilterExec: column1@0 != 42 -02)--DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..131], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:131..262], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:262..393], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:393..521]]}, projection=[column1], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] +02)--DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..127], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:127..254], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:254..381], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:381..506]]}, projection=[column1], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] # disable round robin repartitioning statement ok @@ -66,7 +66,7 @@ logical_plan 02)--TableScan: parquet_table projection=[column1], partial_filters=[parquet_table.column1 != Int32(42)] physical_plan 01)FilterExec: column1@0 != 42 -02)--DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..131], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:131..262], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:262..393], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:393..521]]}, projection=[column1], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] +02)--DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..127], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:127..254], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:254..381], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:381..506]]}, projection=[column1], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] # enable round robin repartitioning again statement ok @@ -90,7 +90,7 @@ physical_plan 01)SortPreservingMergeExec: [column1@0 ASC NULLS LAST] 02)--SortExec: expr=[column1@0 ASC NULLS LAST], preserve_partitioning=[true] 03)----FilterExec: column1@0 != 42 -04)------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..258], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:258..510, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..6], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:6..264], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:264..521]]}, projection=[column1], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] +04)------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..251], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:251..495, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..7], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:7..258], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:258..506]]}, projection=[column1], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] ## Read the files as though they are ordered @@ -125,7 +125,7 @@ logical_plan physical_plan 01)SortPreservingMergeExec: [column1@0 ASC NULLS LAST] 02)--FilterExec: column1@0 != 42 -03)----DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..255], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..260], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:260..521], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:255..510]]}, projection=[column1], output_ordering=[column1@0 ASC NULLS LAST], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] +03)----DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..253], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:253..506], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:247..495]]}, projection=[column1], output_ordering=[column1@0 ASC NULLS LAST], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] # Cleanup statement ok @@ -176,7 +176,7 @@ logical_plan physical_plan 01)SortPreservingMergeExec: [column1@0 ASC NULLS LAST] 02)--FilterExec: column1@0 != 42 -03)----DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/1.parquet:0..258], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/1.parquet:258..516], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/1.parquet:516..521, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/2.parquet:0..253], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/2.parquet:253..510]]}, projection=[column1], output_ordering=[column1@0 ASC NULLS LAST], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] +03)----DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/1.parquet:0..251], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/1.parquet:251..502], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/1.parquet:502..506, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/2.parquet:0..247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/ordered_files/2.parquet:247..495]]}, projection=[column1], output_ordering=[column1@0 ASC NULLS LAST], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)] statement ok DROP TABLE ordered_files;