github  

Messages by Thread

• • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): `GroupColumn` support for `List` / `LargeList` [datafusion] via GitHub
• [PR] build: enable Spark SQL tests for released Spark 4.2.0 [datafusion-comet] via GitHub
  • Re: [PR] build: enable Spark SQL tests for released Spark 4.2.0 [datafusion-comet] via GitHub
• [I] Spark 4.2: `OneRowRelation` in Union branches forces Union and downstream aggregates off Comet (TPC-DS q77a) [datafusion-comet] via GitHub
• Re: [PR] fix: FilterPushdown incorrectly remaps filters through ProjectionExec with duplicate column names [datafusion] via GitHub
• Re: [PR] perf: avoid per-row copy in Spark hex byte encoding [datafusion] via GitHub
  • Re: [PR] perf: avoid per-row copy in Spark hex byte encoding [datafusion] via GitHub
  • Re: [PR] perf: avoid per-row copy in Spark hex byte encoding [datafusion] via GitHub
  • Re: [PR] perf: avoid per-row copy in Spark hex byte encoding [datafusion] via GitHub
• Re: [PR] feat: add OR pre-selection short-circuit [datafusion] via GitHub
• Re: [PR] feat: Parquet writer logical type narrowing for integers [datafusion] via GitHub
• Re: [PR] Avoid concatenating record batches in joins [datafusion] via GitHub
• [I] Code coverage report not working [datafusion] via GitHub
  • Re: [I] Code coverage report not working [datafusion] via GitHub
  • Re: [I] Code coverage report not working [datafusion] via GitHub
  • Re: [I] Code coverage report not working [datafusion] via GitHub
  • Re: [I] Code coverage report not working [datafusion] via GitHub
  • Re: [I] Code coverage report not working [datafusion] via GitHub
  • Re: [I] Code coverage report not working [datafusion] via GitHub
  • Re: [I] Code coverage report not working [datafusion] via GitHub
  • Re: [I] Code coverage report not working [datafusion] via GitHub
• [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
  • Re: [PR] Add FixedSizeBinary support for MultiGroupBy [datafusion] via GitHub
• [PR] fix: map a task's partition through UnionExec when restricting file scans [datafusion-ballista] via GitHub
  • Re: [PR] fix: map a task's partition through UnionExec when restricting file scans [datafusion-ballista] via GitHub
  • Re: [PR] fix: map a task's partition through UnionExec when restricting file scans [datafusion-ballista] via GitHub
• [I] Multi-Group-By does not support FixedSizeBinary types [datafusion] via GitHub
• [I] Avoid per-file metric registration in `ParquetSource` [datafusion] via GitHub
  • Re: [I] Avoid per-file metric registration in `ParquetSource` [datafusion] via GitHub
  • Re: [I] Avoid per-file metric registration in `ParquetSource` [datafusion] via GitHub
  • Re: [I] Avoid per-file metric registration in `ParquetSource` [datafusion] via GitHub
  • Re: [I] Avoid per-file metric registration in `ParquetSource` [datafusion] via GitHub
  • Re: [I] Avoid per-file metric registration in `ParquetSource` [datafusion] via GitHub
  • Re: [I] Avoid per-file metric registration in `ParquetSource` [datafusion] via GitHub
• [PR] fix: enable the executor client pool by default [datafusion-ballista] via GitHub
  • Re: [PR] fix: enable the executor client pool by default [datafusion-ballista] via GitHub
  • Re: [PR] fix: enable the executor client pool by default [datafusion-ballista] via GitHub
• [I] Executor client pool is disabled by default, so shuffle fetches exhaust ephemeral ports on any multi-executor cluster [datafusion-ballista] via GitHub
  • Re: [I] Executor client pool is disabled by default, so shuffle fetches exhaust ephemeral ports on any multi-executor cluster [datafusion-ballista] via GitHub
  • Re: [I] Executor client pool is disabled by default, so shuffle fetches exhaust ephemeral ports on any multi-executor cluster [datafusion-ballista] via GitHub
• Re: [PR] perf: don't re-inline CSE'd expensive expressions in projection pushdown [datafusion] via GitHub
  • Re: [PR] perf: don't re-inline CSE'd expensive expressions in projection pushdown [datafusion] via GitHub
• [I] UNION ALL silently returns inflated results when the union stage exceeds one wave of executor task slots [datafusion-ballista] via GitHub
  • Re: [I] UNION ALL silently returns inflated results when the union stage exceeds one wave of executor task slots [datafusion-ballista] via GitHub
  • Re: [I] UNION ALL silently returns inflated results when the union stage exceeds one wave of executor task slots [datafusion-ballista] via GitHub
• [PR] fix: restore input ordering a SortMergeJoinExec requires after lowering [datafusion-ballista] via GitHub
  • Re: [PR] fix: restore input ordering a SortMergeJoinExec requires after lowering [datafusion-ballista] via GitHub
  • Re: [PR] fix: restore input ordering a SortMergeJoinExec requires after lowering [datafusion-ballista] via GitHub
  • Re: [PR] fix: restore input ordering a SortMergeJoinExec requires after lowering [datafusion-ballista] via GitHub
  • Re: [PR] fix: restore input ordering a SortMergeJoinExec requires after lowering [datafusion-ballista] via GitHub
  • Re: [PR] fix: restore input ordering a SortMergeJoinExec requires after lowering [datafusion-ballista] via GitHub
• Re: [I] Executor can be OOM-killed because memory accounting misses untracked allocations [datafusion-ballista] via GitHub
• Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
  • Re: [PR] feat(physical-plan): generic Rows-backed GroupColumn keeps mixed schemas on the column-wise path [datafusion] via GitHub
• [I] Broadcast join promotion drops a sort order required by a parent SortMergeJoinExec, silently producing wrong results [datafusion-ballista] via GitHub
  • Re: [I] Broadcast join promotion drops a sort order required by a parent SortMergeJoinExec, silently producing wrong results [datafusion-ballista] via GitHub
• Re: [I] All struct-aware optimizations are hardcoded to `GetFieldFunc` [datafusion] via GitHub
  • Re: [I] All struct-aware optimizations are hardcoded to `GetFieldFunc` [datafusion] via GitHub
• [PR] fix: preserve null_equality so distributed INTERSECT/EXCEPT match NULLs [datafusion-ballista] via GitHub
  • Re: [PR] fix: Enable more TPC-DS queries [datafusion-ballista] via GitHub
• Re: [PR] feat: eliminate LEFT JOINs whose right side is unused [datafusion] via GitHub
  • Re: [PR] feat: eliminate LEFT JOINs whose right side is unused [datafusion] via GitHub
  • Re: [PR] feat: eliminate LEFT JOINs whose right side is unused [datafusion] via GitHub
• [PR] feat: fall back to Spark for collated predicate operands [datafusion-comet] via GitHub
  • Re: [PR] feat: fall back to Spark for collated predicate operands [datafusion-comet] via GitHub
  • Re: [PR] feat: fall back to Spark for collated predicate operands [datafusion-comet] via GitHub
  • Re: [PR] feat: fall back to Spark for collated predicate operands [datafusion-comet] via GitHub
  • Re: [PR] feat: fall back to Spark for collated predicate operands [datafusion-comet] via GitHub
  • Re: [PR] feat: fall back to Spark for collated predicate operands [datafusion-comet] via GitHub
  • Re: [PR] feat: fall back to Spark for collated predicate operands [datafusion-comet] via GitHub
• [PR] refactor: thread SubqueryContext explicitly through physical planning [datafusion] via GitHub
  • Re: [PR] refactor: thread SubqueryContext explicitly through physical planning [datafusion] via GitHub
  • Re: [PR] refactor: thread SubqueryContext explicitly through physical planning [datafusion] via GitHub
  • Re: [PR] refactor: thread SubqueryContext explicitly through physical planning [datafusion] via GitHub
  • Re: [PR] refactor: thread SubqueryContext explicitly through physical planning [datafusion] via GitHub
  • Re: [PR] refactor: thread SubqueryContext explicitly through physical planning [datafusion] via GitHub
• [I] Adaptive (AQE) execution hangs when a replan cancels an in-flight stage [datafusion-ballista] via GitHub
• [PR] fix: keep EmptyExec partition count intact across stage serialization [datafusion-ballista] via GitHub
  • Re: [PR] fix: keep EmptyExec partition count intact across stage serialization [datafusion-ballista] via GitHub
  • Re: [PR] fix: keep EmptyExec partition count intact across stage serialization [AQE] [datafusion-ballista] via GitHub
  • Re: [PR] fix: keep EmptyExec partition count intact across stage serialization [AQE] [datafusion-ballista] via GitHub
• [PR] fix: preserve EmptyExec and PlaceholderRowExec partition count across proto round-trip [datafusion] via GitHub
  • Re: [PR] fix: preserve EmptyExec and PlaceholderRowExec partition count across proto round-trip [datafusion] via GitHub
  • Re: [PR] fix: preserve EmptyExec and PlaceholderRowExec partition count across proto round-trip [datafusion] via GitHub
  • Re: [PR] fix: preserve EmptyExec and PlaceholderRowExec partition count across proto round-trip [datafusion] via GitHub
  • Re: [PR] fix: preserve EmptyExec and PlaceholderRowExec partition count across proto round-trip [datafusion] via GitHub
  • Re: [PR] fix: preserve EmptyExec and PlaceholderRowExec partition count across proto round-trip [datafusion] via GitHub
  • Re: [PR] fix: preserve EmptyExec and PlaceholderRowExec partition count across proto round-trip [datafusion] via GitHub
  • Re: [PR] fix: preserve EmptyExec and PlaceholderRowExec partition count across proto round-trip [datafusion] via GitHub
• Re: [PR] feat: add Spark-compatible arrays_zip function [datafusion] via GitHub
  • Re: [PR] feat: add Spark-compatible arrays_zip function [datafusion] via GitHub
• Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
  • Re: [PR] fix: `time ± interval` returns a wrapped `time` instead of an interval [datafusion] via GitHub
• [I] datafusion-proto drops EmptyExec partition count on physical plan round-trip [datafusion] via GitHub
  • Re: [I] datafusion-proto drops EmptyExec partition count on physical plan round-trip [datafusion] via GitHub
  • Re: [I] datafusion-proto drops EmptyExec partition count on physical plan round-trip [datafusion] via GitHub
• [PR] fix: handle null date and timestamp format arguments [datafusion] via GitHub
  • Re: [PR] fix: handle null date and timestamp format arguments [datafusion] via GitHub
  • Re: [PR] fix: handle null date and timestamp format arguments [datafusion] via GitHub
  • Re: [PR] fix: handle null date and timestamp format arguments [datafusion] via GitHub
• Re: [I] Decouple the `FileSource` trait from the concrete `FileScanConfig` `DataSource` [datafusion] via GitHub
  • Re: [I] Decouple the `FileSource` trait from the concrete `FileScanConfig` `DataSource` [datafusion] via GitHub
  • Re: [I] Decouple the `FileSource` trait from the concrete `FileScanConfig` `DataSource` [datafusion] via GitHub
• [I] `to_date`, `to_timestamp`, and `to_unixtime` fail on NULL string and format arguments [datafusion] via GitHub
  • Re: [I] `to_date`, `to_timestamp`, and `to_unixtime` fail on NULL string and format arguments [datafusion] via GitHub
  • Re: [I] `to_date`, `to_timestamp`, and `to_unixtime` fail on NULL string and format arguments [datafusion] via GitHub
  • Re: [I] `to_date`, `to_timestamp`, and `to_unixtime` fail on NULL string and format arguments [datafusion] via GitHub
• Re: [I] Add TPC-DS workflow [datafusion-ballista] via GitHub
• [PR] fix: spill sort shuffle writer when the memory pool rejects a reservation grow [datafusion-ballista] via GitHub
  • Re: [PR] fix: spill sort shuffle writer when the memory pool rejects a reservation grow [datafusion-ballista] via GitHub
  • Re: [PR] fix: spill sort shuffle writer when the memory pool rejects a reservation grow [datafusion-ballista] via GitHub
• [I] Sort shuffle writer ignores memory-pool rejection and never spills under pool pressure [datafusion-ballista] via GitHub
  • Re: [I] Sort shuffle writer ignores memory-pool rejection and never spills under pool pressure [datafusion-ballista] via GitHub
• Re: [PR] fix: coalesce the merged key of RIGHT/FULL USING/NATURAL joins [datafusion] via GitHub
• Re: [I] TUI banner renders as garbled glyphs on most fonts [datafusion-ballista] via GitHub
• Re: [PR] [WIP]feat: Support apache uniffle remote shuffle service [datafusion-comet] via GitHub
  • Re: [PR] [WIP]feat: Support apache uniffle remote shuffle service [datafusion-comet] via GitHub
  • Re: [PR] [WIP]feat: Support apache uniffle remote shuffle service [datafusion-comet] via GitHub
• Re: [I] Implement Radix Hash Join [datafusion] via GitHub
• [PR] docs(physical-plan): correct the documentation for `GroupColumn::vectorized_equal_to` [datafusion] via GitHub
  • Re: [PR] docs(physical-plan): correct the documentation for `GroupColumn::vectorized_equal_to` [datafusion] via GitHub
  • Re: [PR] docs(physical-plan): correct the documentation for `GroupColumn::vectorized_equal_to` [datafusion] via GitHub
• [PR] fix: Handle `input_file_name()` pushdown into `ParquetSource` with filter pushdown enabled [datafusion] via GitHub
  • Re: [PR] fix: Handle `input_file_name()` pushdown into `ParquetSource` with filter pushdown enabled [datafusion] via GitHub
  • Re: [PR] fix: Handle `input_file_name()` pushdown into `ParquetSource` with filter pushdown enabled [datafusion] via GitHub
• [PR] docs: add partitioned ClickBench SQL example [datafusion] via GitHub
  • Re: [PR] docs: add partitioned ClickBench SQL example [datafusion] via GitHub
  • Re: [PR] docs: add partitioned ClickBench SQL example [datafusion] via GitHub
  • Re: [PR] docs: add partitioned ClickBench SQL example [datafusion] via GitHub
• [PR] feat(scheduler): Redirect '/' to nighlies.a.o WebTUI [datafusion-ballista] via GitHub
  • Re: [PR] feat(scheduler): Redirect '/' to nighlies.a.o WebTUI [datafusion-ballista] via GitHub
  • Re: [PR] feat(scheduler): Redirect '/' to nighlies.a.o WebTUI [datafusion-ballista] via GitHub
  • Re: [PR] feat(scheduler): Redirect '/' to nighlies.a.o WebTUI [datafusion-ballista] via GitHub
  • Re: [PR] feat(scheduler): Redirect '/' to nighlies.a.o WebTUI [datafusion-ballista] via GitHub
  • Re: [PR] feat(scheduler): Redirect '/' to nighlies.a.o WebTUI [datafusion-ballista] via GitHub
  • Re: [PR] feat(scheduler): Redirect '/' to nighlies.a.o WebTUI [datafusion-ballista] via GitHub
  • Re: [PR] feat(scheduler): Redirect '/' to nighlies.a.o WebTUI [datafusion-ballista] via GitHub
• [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
  • Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] via GitHub
• [PR] minor: Clarify `FunctionalDependence::nullable` and `Dependency` mode docs [datafusion] via GitHub
  • Re: [PR] minor: Clarify `FunctionalDependence::nullable` and `Dependency` mode docs [datafusion] via GitHub
  • Re: [PR] docs: Clarify `FunctionalDependence::nullable` and `Dependency` mode docs [datafusion] via GitHub
• [I] Do not mark GROUP BY derived unique keys as nullable (restores the INTERSECT dedup elimination from #22903) [datafusion] via GitHub
• [PR] Setup dependabot to do `rust-toolchain` updates [datafusion] via GitHub
  • Re: [PR] Setup dependabot to do `rust-toolchain` updates [datafusion] via GitHub
• [PR] Bump MSRV from `1.88.0` to `1.94.0` [datafusion] via GitHub

• Earlier messages
• Later messages