github  

Messages by Thread

• [PR] Add `clickbench_pushdown` benchmark [datafusion] via GitHub
• Re: [PR] chore: Remove obsolete supportedSortType function after Arrow updates [datafusion-comet] via GitHub
• [PR] Remove parquet_filter and parquet_sort benchmarks [datafusion] via GitHub
• [PR] share staging infrastructure [datafusion-site] via GitHub
  • Re: [PR] share staging infrastructure [datafusion-site] via GitHub
  • Re: [PR] share staging infrastructure [datafusion-site] via GitHub
  • Re: [PR] share staging infrastructure [datafusion-site] via GitHub
• [I] Add a benchmark for `filter_pushdown` [datafusion] via GitHub
• [I] Update supportedSortType to remove some of the complex type fallbacks [datafusion-comet] via GitHub
  • Re: [I] Update supportedSortType to remove some of the complex type fallbacks [datafusion-comet] via GitHub
  • Re: [I] Update supportedSortType to remove some of the complex type fallbacks [datafusion-comet] via GitHub
• Re: [I] Comet shuffle read size is larger than Spark shuffle [datafusion-comet] via GitHub
• [PR] update python module to latest ballista release (v.47) [datafusion-ballista] via GitHub
• [PR] make: split git clone and checkout commit [datafusion-site] via GitHub
  • Re: [PR] make: split git clone and checkout commit [datafusion-site] via GitHub
  • Re: [PR] make: split git clone and checkout commit [datafusion-site] via GitHub
  • Re: [PR] make: split git clone and checkout commit [datafusion-site] via GitHub
• [PR] Bump the MSRV due to transitive dependencies [datafusion] via GitHub
  • Re: [PR] Bump the MSRV due to transitive dependencies [datafusion] via GitHub
  • Re: [PR] Bump the MSRV due to transitive dependencies [datafusion] via GitHub
  • Re: [PR] Bump the MSRV due to transitive dependencies [datafusion] via GitHub
• [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
  • Re: [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
  • Re: [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
  • Re: [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
  • Re: [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
  • Re: [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
  • Re: [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
  • Re: [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
  • Re: [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
  • Re: [PR] feat: Optimize `collect_left_input` processing [datafusion] via GitHub
• [PR] Improved window and aggregate function signature [datafusion-python] via GitHub
• [PR] Sd reserverd kws tables alias [datafusion-sqlparser-rs] via GitHub
• [I] Comet 0.9.1 Release (July/August 2025) [datafusion-comet] via GitHub
• Re: [I] [EPIC] Complete `datafusion-spark` Spark Compatible Functions [datafusion] via GitHub
• [PR] fix: add `order_requirement` & `dist_requirement` to `OutputRequirementExec` plan display [datafusion] via GitHub
• [PR] Added unquoted identifiers unicode support for mySql, postgreSqp, als… [datafusion-sqlparser-rs] via GitHub
• [I] [Discussion]: show more info for `OutputRequirementExec` display [datafusion] via GitHub
  • Re: [I] [Discussion]: show more info for `OutputRequirementExec` display [datafusion] via GitHub
• [I] Discussion: public some aggregate related function and struct [datafusion] via GitHub
  • Re: [I] Discussion: public some aggregate related function and struct [datafusion] via GitHub
• [I] Implement --test-threads CLI argument for sqllogictest runner [datafusion] via GitHub
  • Re: [I] Implement --test-threads CLI argument for sqllogictest runner [datafusion] via GitHub
  • Re: [I] Implement --test-threads CLI argument for sqllogictest runner [datafusion] via GitHub
• [I] Nested type modifiers/complex type [datafusion-sqlparser-rs] via GitHub
• [PR] [ISSUE-1277] fix: devcontainer protoc:1 feature url [datafusion-ballista] via GitHub
• [I] Could not resolve Feature 'ghcr.io/devcontainers-contrib/features/protoc:1' [datafusion-ballista] via GitHub
• Re: [I] Optimized spill file format [datafusion] via GitHub
  • Re: [I] Optimized spill file format [datafusion] via GitHub
• [I] Use `--test-threads` option properly in sqllogictests.rs [datafusion] via GitHub
• [PR] Use the `test-threads` option in sqllogictests [datafusion] via GitHub
  • Re: [PR] Use the `test-threads` option in sqllogictests [datafusion] via GitHub
• [I] Support memory profiling in benchmarks [datafusion] via GitHub
  • Re: [I] Support memory profiling in benchmarks [datafusion] via GitHub
  • Re: [I] Support memory profiling in benchmarks [datafusion] via GitHub
• Re: [I] [EPIC] Tracking issue of support substrait logical plan [datafusion] via GitHub
• Re: [PR] POC: Eliminate unnecessary group by keys (q35 in clickbench 1.35x faster) [datafusion] via GitHub
• Re: [PR] Add xxhash algorithms in SQL and expression api [datafusion] via GitHub
• Re: [PR] [wip] update list & struct coercion to support incrementality [datafusion] via GitHub
• [PR] feat: Avoid duplicate `PhyscialExpr` evaluation on hash table [datafusion] via GitHub
  • Re: [PR] feat: Avoid duplicate `PhyscialExpr` evaluation on hash table [datafusion] via GitHub
• [PR] fix: Fix CI failing due to #16686 [datafusion] via GitHub
  • Re: [PR] fix: Fix CI failing due to #16686 [datafusion] via GitHub
  • Re: [PR] fix: Fix CI failing due to #16686 [datafusion] via GitHub
  • Re: [PR] fix: Fix CI failing due to #16686 [datafusion] via GitHub
  • Re: [PR] fix: Fix CI failing due to #16686 [datafusion] via GitHub
  • Re: [PR] fix: Fix CI failing due to #16686 [datafusion] via GitHub
  • Re: [PR] fix: Fix CI failing due to #16686 [datafusion] via GitHub
• [I] Some group by query is 6~7x slower than DuckDB [datafusion-python] via GitHub
• [I] Better parallelize large input batches (speed up dataframe access) [datafusion] via GitHub
• [PR] feat: add CopyExec and move CopyExec handling to Spark [datafusion-comet] via GitHub
• [PR] Sf create table as [datafusion-sqlparser-rs] via GitHub
• [I] How to write csv file to disk from a empty dataframe? [datafusion] via GitHub
  • Re: [I] How to write csv file to disk from a empty dataframe? [datafusion] via GitHub
  • Re: [I] How to write csv file to disk from a empty dataframe? [datafusion] via GitHub
  • Re: [I] How to write csv file to disk from a empty dataframe? [datafusion] via GitHub
• Re: [I] Error when use `user` field in where clause [datafusion] via GitHub
• Re: [I] Support u32 indices in HashJoinExec [datafusion] via GitHub
• [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
  • Re: [PR] perf: Optimize hash joins with an empty build side [datafusion] via GitHub
• [PR] fix: Add LogicalTypeAnnotation in ParquetColumnSpec [datafusion-comet] via GitHub
  • Re: [PR] fix: Add LogicalTypeAnnotation in ParquetColumnSpec [datafusion-comet] via GitHub
  • Re: [PR] fix: Add LogicalTypeAnnotation in ParquetColumnSpec [datafusion-comet] via GitHub
  • Re: [PR] fix: Add LogicalTypeAnnotation in ParquetColumnSpec [datafusion-comet] via GitHub
  • Re: [PR] fix: [iceberg] Add LogicalTypeAnnotation in ParquetColumnSpec [datafusion-comet] via GitHub
• [PR] add Makefile and local setup instruction in README [datafusion-site] via GitHub
  • Re: [PR] add Makefile and local setup instruction in README [datafusion-site] via GitHub
  • Re: [PR] add Makefile and local setup instruction in README [datafusion-site] via GitHub
  • Re: [PR] add Makefile and local setup instruction in README [datafusion-site] via GitHub
  • Re: [PR] add Makefile and local setup instruction in README [datafusion-site] via GitHub
  • Re: [PR] add Makefile and local setup instruction in README [datafusion-site] via GitHub
  • Re: [PR] add Makefile and local setup instruction in README [datafusion-site] via GitHub
• [PR] refactor: standardize div_ceil [datafusion-comet] via GitHub
  • Re: [PR] refactor: standardize div_ceil [datafusion-comet] via GitHub
  • Re: [PR] refactor: standardize div_ceil [datafusion-comet] via GitHub
  • Re: [PR] refactor: standardize div_ceil [datafusion-comet] via GitHub
  • Re: [PR] refactor: standardize div_ceil [datafusion-comet] via GitHub
• [I] refactor: use div_ceil instead of bit::ceil [datafusion-comet] via GitHub
  • Re: [I] refactor: use div_ceil instead of bit::ceil [datafusion-comet] via GitHub
  • Re: [I] refactor: use div_ceil instead of bit::ceil [datafusion-comet] via GitHub
• [PR] draft of .slt file. Implemented the basics, need to test with cast ch… [datafusion] via GitHub
  • Re: [PR] [Draft]Add SQL logic tests for Run-End Encoded (REE) [datafusion] via GitHub
• [PR] github: turn on discussion [datafusion-site] via GitHub
  • Re: [PR] github: turn on discussion [datafusion-site] via GitHub
  • Re: [PR] github: turn on discussion [datafusion-site] via GitHub
  • Re: [PR] github: turn on discussion [datafusion-site] via GitHub
  • Re: [PR] github: turn on discussion [datafusion-site] via GitHub
  • Re: [PR] github: turn on discussion [datafusion-site] via GitHub
• [I] ILIKE incorrectly optimized to equality test [datafusion] via GitHub
  • Re: [I] ILIKE incorrectly optimized to equality test [datafusion] via GitHub
  • Re: [I] ILIKE incorrectly optimized to equality test [datafusion] via GitHub
• [PR] minor: improve display output for FFI execution plans [datafusion] via GitHub
  • Re: [PR] minor: improve display output for FFI execution plans [datafusion] via GitHub
  • Re: [PR] minor: improve display output for FFI execution plans [datafusion] via GitHub
• [PR] Add support for automatic join column deduplication in DataFrame joins [datafusion-python] via GitHub
  • Re: [PR] Add support for automatic join column deduplication in DataFrame joins [datafusion-python] via GitHub
  • Re: [PR] Add support for automatic join column deduplication in DataFrame joins [datafusion-python] via GitHub
  • Re: [PR] Add support for automatic join column deduplication in DataFrame joins [datafusion-python] via GitHub
• Re: [I] NoSuchMethodError with Spark 3.5.3 (EMR 7.6) [datafusion-comet] via GitHub
• Re: [I] Filter cache based on the paper "Predicate Caching: Query-Driven Secondary Indexing for Cloud Data" [datafusion] via GitHub
  • Re: [I] Filter cache based on the paper "Predicate Caching: Query-Driven Secondary Indexing for Cloud Data" [datafusion] via GitHub
  • Re: [I] Filter cache based on the paper "Predicate Caching: Query-Driven Secondary Indexing for Cloud Data" [datafusion] via GitHub
  • Re: [I] Filter cache based on the paper "Predicate Caching: Query-Driven Secondary Indexing for Cloud Data" [datafusion] via GitHub
• [PR] feat: reduce duplicate fields on join [datafusion-python] via GitHub
  • Re: [PR] feat: reduce duplicate fields on join [datafusion-python] via GitHub
• Re: [I] Simplify Joins on Shared Column Name [datafusion-python] via GitHub
  • Re: [I] Simplify Joins on Shared Column Name [datafusion-python] via GitHub
• [I] Replace π-related bound constants with `next_up` / `next_down` [datafusion] via GitHub
• Re: [D] DISCUSSION: DataFusion Meetup in Boston, USA [datafusion] via GitHub
  • Re: [D] DISCUSSION: DataFusion Meetup in Boston, USA [datafusion] via GitHub
  • Re: [D] DISCUSSION: DataFusion Meetup in Boston, USA [datafusion] via GitHub
• Re: [I] [DISCUSSION] Show `predicates` in `DataSourceExec` explain (indent) [datafusion] via GitHub
  • Re: [I] [DISCUSSION] Show `predicates` in `DataSourceExec` explain (indent) [datafusion] via GitHub
• [PR] feat: Upgrade to the official DataFusion 49.0.0 release [datafusion-comet] via GitHub
  • Re: [PR] feat: Upgrade to the official DataFusion 49.0.0 release [datafusion-comet] via GitHub
• [PR] cast_operands_to_double_type_to_fix_arithmetic_overflow [datafusion-comet] via GitHub
  • Re: [PR] cast_operands_to_double_type_to_fix_arithmetic_overflow [datafusion-comet] via GitHub
  • Re: [PR] cast_operands_to_double_type_to_fix_arithmetic_overflow [datafusion-comet] via GitHub
• Re: [PR] feat: expose intersect distinct/except distinct in dataframe api [datafusion] via GitHub
  • Re: [PR] feat: expose intersect distinct/except distinct in dataframe api [datafusion] via GitHub
• Re: [I] Optimize `ColumnarValue::into_array` / `ScalarValue::to_array` / `ScalarValue::to_array_of_size` [datafusion] via GitHub
• Re: [PR] fix: enhance-CLI-query-header-for-cast-expressions-with-literals [datafusion] via GitHub
• Re: [PR] Improve push down limit (logical optimizer rule) [datafusion] via GitHub
• Re: [PR] Support inferring new predicates to push down [datafusion] via GitHub
• Re: [PR] PERF : modify SMJ shuffle file reader to skip validation [datafusion] via GitHub
• Re: [PR] Add `PrimitiveDistinctCountGroupsAccumulator` [datafusion] via GitHub
• Re: [PR] Optimize char expression [datafusion] via GitHub
  • Re: [PR] Optimize char expression [datafusion] via GitHub
• [I] Create CopyExec node on Spark side, move related logic from native [datafusion-comet] via GitHub
• [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
  • Re: [PR] POC: Test DataFusion with experimental Parquet Filter Pushdown (try 4) [datafusion] via GitHub
• [I] Optimize the join operators [datafusion] via GitHub
  • Re: [I] Optimize the join operators [datafusion] via GitHub
  • Re: [I] Optimize the join operators [datafusion] via GitHub
  • Re: [I] Optimize the join operators [datafusion] via GitHub
  • Re: [I] Optimize the join operators [datafusion] via GitHub
  • Re: [I] Optimize the join operators [datafusion] via GitHub
• [I] Add support for SortAggregateExec [datafusion-comet] via GitHub
• [PR] Ci cache [datafusion] via GitHub
• [PR] remove FileSource::with_projection [datafusion] via GitHub
  • Re: [PR] remove FileSource::with_projection [datafusion] via GitHub
  • Re: [PR] remove FileSource::with_projection [datafusion] via GitHub
• [I] Upgrade to DataFusion 49.0.0 [datafusion-comet] via GitHub
• [I] Some group by query is 6~7x slower than DuckDB [datafusion] via GitHub
  • Re: [I] Some group by query is 6~7x slower than DuckDB [datafusion] via GitHub
  • Re: [I] Some group by query is 6~7x slower than DuckDB [datafusion] via GitHub
  • Re: [I] Some group by query is 6~7x slower than DuckDB [datafusion] via GitHub
  • Re: [I] Some group by query is 6~7x slower than DuckDB [datafusion] via GitHub
  • Re: [I] Some group by query is 6~7x slower than DuckDB [datafusion] via GitHub
  • Re: [I] Some group by query is 6~7x slower than DuckDB [datafusion] via GitHub
  • Re: [I] Some group by query is 6~7x slower than DuckDB [datafusion] via GitHub

• Earlier messages