Apache DataFusion SQL Query Engine
fix: suppress nondeterministic metrics in agg_dyn_e2e sqllogictest (#21657)
Matt Butrovich240fbdb915a2
diff --git a/datafusion/sqllogictest/test_files/push_down_filter_regression.slt b/datafusion/sqllogictest/test_files/push_down_filter_regression.sltindex 51ad998c02..7334054ff2 100644--- a/datafusion/sqllogictest/test_files/push_down_filter_regression.slt+++ b/datafusion/sqllogictest/test_files/push_down_filter_regression.slt@@ -218,21 +218,32 @@ LOCATION 'test_files/scratch/push_down_filter_regression/agg_dyn/';statement okset datafusion.execution.collect_statistics = true;+# Suppress metrics: pruning counts are nondeterministic under parallel+# execution (the order in which Partial aggregates publish dynamic filter+# updates races against when the scan reads each partition). The original+# Rust test only asserted matched < 4; the important invariant here is+# that the DynamicFilter text is correct.statement ok-set datafusion.explain.analyze_categories = 'rows';+set datafusion.explain.analyze_level = summary;++statement ok+set datafusion.explain.analyze_categories = 'none';query TTEXPLAIN ANALYZE select max(column1) from agg_dyn_e2e where column1 > 1;----Plan with Metrics-01)AggregateExec: mode=Final, gby=[], aggr=[max(agg_dyn_e2e.column1)], metrics=[output_rows=1, output_batches=1]-02)--CoalescePartitionsExec, metrics=[output_rows=2, output_batches=2]-03)----AggregateExec: mode=Partial, gby=[], aggr=[max(agg_dyn_e2e.column1)], metrics=[output_rows=2, output_batches=2]-04)------DataSourceExec: file_groups={2 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_regression/agg_dyn/file_0.parquet, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_regression/agg_dyn/file_1.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_regression/agg_dyn/file_2.parquet, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_regression/agg_dyn/file_3.parquet]]}, projection=[column1], file_type=parquet, predicate=column1@0 > 1 AND DynamicFilter [ column1@0 > 4 ], pruning_predicate=column1_null_count@1 != row_count@2 AND column1_max@0 > 1 AND column1_null_count@1 != row_count@2 AND column1_max@0 > 4, required_guarantees=[], metrics=[output_rows=2, output_batches=2, files_ranges_pruned_statistics=4 total → 4 matched, row_groups_pruned_statistics=4 total → 2 matched -> 2 fully matched, row_groups_pruned_bloom_filter=2 total → 2 matched, page_index_pages_pruned=2 total → 2 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=4, files_processed=4, num_predicate_creation_errors=0, predicate_evaluation_errors=0, pushdown_rows_matched=2, pushdown_rows_pruned=0, predicate_cache_inner_records=2, predicate_cache_records=4, scan_efficiency_ratio=25.15% (130/517)]+01)AggregateExec: mode=Final, gby=[], aggr=[max(agg_dyn_e2e.column1)], metrics=[]+02)--CoalescePartitionsExec, metrics=[]+03)----AggregateExec: mode=Partial, gby=[], aggr=[max(agg_dyn_e2e.column1)], metrics=[]+04)------DataSourceExec: file_groups={2 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_regression/agg_dyn/file_0.parquet, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_regression/agg_dyn/file_1.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_regression/agg_dyn/file_2.parquet, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/push_down_filter_regression/agg_dyn/file_3.parquet]]}, projection=[column1], file_type=parquet, predicate=column1@0 > 1 AND DynamicFilter [ column1@0 > 4 ], pruning_predicate=column1_null_count@1 != row_count@2 AND column1_max@0 > 1 AND column1_null_count@1 != row_count@2 AND column1_max@0 > 4, required_guarantees=[], metrics=[]statement okreset datafusion.explain.analyze_categories;+statement ok+reset datafusion.explain.analyze_level;+statement okreset datafusion.execution.collect_statistics;