github  

Messages by Thread

• • Re: [PR] feat: support filtered batches in `LimitedBatchCoalescer` [datafusion] via GitHub
  • Re: [PR] feat: support filtered batches in `LimitedBatchCoalescer` [datafusion] via GitHub
  • Re: [PR] feat: support filtered batches in `LimitedBatchCoalescer` [datafusion] via GitHub
• Re: [PR] fix: FilterPushdown incorrectly remaps filters through ProjectionExec with duplicate column names [datafusion] via GitHub
• Re: [PR] In list range pruning [datafusion] via GitHub
• Re: [PR] feat: reuse tree visitor to display tree for `LogicalPlan` [datafusion] via GitHub
• Re: [PR] Introduce dependent join `LogicalPlan` to support complex subquery decorrelation [datafusion] via GitHub
• Re: [PR] feat: Refactor NLJ into an extensible framework for specialized joins [datafusion] via GitHub
• Re: [PR] Per-conjunct pruning stats via PruningPredicateTree + observer [datafusion] via GitHub
• [I] Speed up SortPreservingMerge by caching per-cursor state across all CursorValues types [datafusion] via GitHub
• Re: [PR] feat: Parquet writer logical type narrowing for integers [datafusion] via GitHub
• Re: [PR] Align scalar UDF literal args with coerced return fields [datafusion] via GitHub
• [PR] feat(executor): log per-task memory pool peak usage [datafusion-ballista] via GitHub
  • Re: [PR] feat(executor): log per-task memory pool peak usage [datafusion-ballista] via GitHub
• Re: [I] Add Support for Dynamic SQL Macros for Flexible Column Selection [datafusion] via GitHub
• [I] Allow individual cast conversions to be enabled/disabled [datafusion-comet] via GitHub
• [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
  • Re: [PR] Enable dynamic filters for range-partitioned joins [datafusion] via GitHub
• [I] Can Ballista do S3 prefetching like Spark? [datafusion-ballista] via GitHub
  • Re: [I] Can Ballista do S3 prefetching like Spark? [datafusion-ballista] via GitHub
• [PR] fix: raise CAST_INVALID_INPUT for invalid calendar dates in ANSI cast to date [datafusion-comet] via GitHub
  • Re: [PR] fix: raise CAST_INVALID_INPUT for invalid calendar dates in ANSI cast to date [datafusion-comet] via GitHub
  • Re: [PR] fix: raise CAST_INVALID_INPUT for invalid calendar dates in ANSI cast to date [datafusion-comet] via GitHub
  • Re: [PR] fix: raise CAST_INVALID_INPUT for invalid calendar dates in ANSI cast to date [datafusion-comet] via GitHub
  • Re: [PR] fix: raise CAST_INVALID_INPUT for invalid calendar dates in ANSI cast to date [datafusion-comet] via GitHub
  • Re: [PR] fix: raise CAST_INVALID_INPUT for invalid calendar dates in ANSI cast to date [datafusion-comet] via GitHub
  • Re: [PR] fix: raise CAST_INVALID_INPUT for invalid calendar dates in ANSI cast to date [datafusion-comet] via GitHub
  • Re: [PR] fix: raise CAST_INVALID_INPUT for invalid calendar dates in ANSI cast to date [datafusion-comet] via GitHub
  • Re: [PR] fix: raise CAST_INVALID_INPUT for invalid calendar dates in ANSI cast to date [datafusion-comet] via GitHub
• [I] Native Parquet scan ignores INT96 legacy-calendar rebase, returning silently wrong timestamps [datafusion-comet] via GitHub
  • Re: [I] Native Parquet scan ignores INT96 legacy-calendar rebase, returning silently wrong timestamps [datafusion-comet] via GitHub
  • Re: [I] Native Parquet scan ignores INT96 legacy-calendar rebase, returning silently wrong timestamps [datafusion-comet] via GitHub
• Re: [I] Audit Spark SQL configs that affect query semantics and ensure Comet honors them (or falls back) [datafusion-comet] via GitHub
• [I] Native panic casting to negative-scale decimal when spark.sql.legacy.allowNegativeScaleOfDecimal=true [datafusion-comet] via GitHub
  • Re: [I] Native panic casting to negative-scale decimal when spark.sql.legacy.allowNegativeScaleOfDecimal=true [datafusion-comet] via GitHub
• [I] ANSI mode: cast(string as date) returns NULL instead of throwing for invalid calendar dates [datafusion-comet] via GitHub
  • Re: [I] ANSI mode: cast(string as date) returns NULL instead of throwing for invalid calendar dates [datafusion-comet] via GitHub
• [I] Native Parquet scan ignores legacy-calendar rebase, returning silently wrong dates/timestamps [datafusion-comet] via GitHub
  • Re: [I] Datetime rebase: track the documented scan limitation, and spark.comet.exceptionOnDatetimeRebase is dead code [datafusion-comet] via GitHub
• Re: [PR] PostgreSQL: Support SQL standard `ARRAY` keyword in type declarations [datafusion-sqlparser-rs] via GitHub
  • Re: [PR] PostgreSQL: Support SQL standard `ARRAY` keyword in type declarations [datafusion-sqlparser-rs] via GitHub
  • Re: [PR] PostgreSQL: Support SQL standard `ARRAY` keyword in type declarations [datafusion-sqlparser-rs] via GitHub
  • Re: [PR] PostgreSQL: Support SQL standard `ARRAY` keyword in type declarations [datafusion-sqlparser-rs] via GitHub
  • Re: [PR] PostgreSQL: Support SQL standard `ARRAY` keyword in type declarations [datafusion-sqlparser-rs] via GitHub
  • Re: [PR] PostgreSQL: Support SQL standard `ARRAY` keyword in type declarations [datafusion-sqlparser-rs] via GitHub
  • Re: [PR] PostgreSQL: Support SQL standard `ARRAY` keyword in type declarations [datafusion-sqlparser-rs] via GitHub
  • Re: [PR] PostgreSQL: Support SQL standard `ARRAY` keyword in type declarations [datafusion-sqlparser-rs] via GitHub
• Re: [I] Proto: migrate UnionExec + InterleaveExec [datafusion] via GitHub
• [PR] refactor(proto): migrate HashJoinExec serde [datafusion] via GitHub
  • Re: [PR] refactor(proto): migrate HashJoinExec serde [datafusion] via GitHub
  • Re: [PR] refactor(proto): migrate HashJoinExec serde [datafusion] via GitHub
  • Re: [PR] refactor(proto): migrate HashJoinExec serde [datafusion] via GitHub
• [PR] docs: add upstream-comet-expression skill [datafusion-comet] via GitHub
• Re: [I] [DISCUSS] Add open table format support. [datafusion-ballista] via GitHub
  • Re: [I] [DISCUSS] Add open table format support. [datafusion-ballista] via GitHub
• Re: [I] Proto: migrate CrossJoinExec + NestedLoopJoinExec [datafusion] via GitHub
• Re: [I] Proto: migrate RepartitionExec [datafusion] via GitHub
• [PR] feat: add Spark date_from_unix_date function to datafusion-spark [datafusion] via GitHub
  • Re: [PR] feat: add Spark date_from_unix_date function to datafusion-spark [datafusion] via GitHub
  • Re: [PR] feat: add Spark date_from_unix_date function to datafusion-spark [datafusion] via GitHub
  • Re: [PR] feat: add Spark date_from_unix_date function to datafusion-spark [datafusion] via GitHub
  • Re: [PR] feat: add Spark date_from_unix_date function to datafusion-spark [datafusion] via GitHub
  • Re: [PR] feat: add Spark date_from_unix_date function to datafusion-spark [datafusion] via GitHub
  • Re: [PR] feat: add Spark date_from_unix_date function to datafusion-spark [datafusion] via GitHub
  • Re: [PR] feat: add Spark date_from_unix_date function to datafusion-spark [datafusion] via GitHub
• Re: [I] Release Ballista 54.0.0 [datafusion-ballista] via GitHub
  • Re: [I] Release Ballista 54.0.0 [datafusion-ballista] via GitHub
• Re: [I] Support Meaningful Task ID [datafusion] via GitHub
• Re: [I] Proto: migrate GlobalLimitExec + LocalLimitExec [datafusion] via GitHub
• [PR] Prune parquet row groups using fully dictionary-encoded columns [datafusion] via GitHub
  • Re: [PR] Prune parquet row groups using fully dictionary-encoded columns [datafusion] via GitHub
  • Re: [PR] Prune parquet row groups using fully dictionary-encoded columns [datafusion] via GitHub
• [PR] docs: refresh benchmarking.md with current SF1000 results (Ballista main @ 696ca29b, Spark 3.4 baseline) [datafusion-ballista] via GitHub
  • Re: [PR] docs: refresh benchmarking.md with current SF1000 results (Ballista main @ 696ca29b, Spark 3.4 baseline) [datafusion-ballista] via GitHub
  • Re: [PR] docs: refresh benchmarking.md with current SF1000 results (Ballista main @ 696ca29b, Spark 3.4 baseline) [datafusion-ballista] via GitHub
  • Re: [PR] docs: refresh benchmarking.md with current SF1000 results (Ballista main @ 696ca29b, Spark 3.4 baseline) [datafusion-ballista] via GitHub
  • Re: [PR] docs: refresh benchmarking.md with current SF1000 results (Ballista main @ 696ca29b, Spark 3.4 baseline) [datafusion-ballista] via GitHub
  • Re: [PR] docs: refresh benchmarking.md with current SF1000 results (Ballista main @ 696ca29b, Spark 3.4 baseline) [datafusion-ballista] via GitHub
  • Re: [PR] docs: refresh benchmarking.md with current SF1000 results (Ballista main @ 696ca29b, Spark 3.4 baseline) [datafusion-ballista] via GitHub
  • Re: [PR] docs: refresh benchmarking.md with current SF1000 results (Ballista main @ 696ca29b, Spark 3.4 baseline) [datafusion-ballista] via GitHub
• [I] perf: reuse Arrow IPC CompressionContext across shuffle blocks instead of per-batch allocation [datafusion-comet] via GitHub
  • Re: [I] perf: reuse Arrow IPC CompressionContext across shuffle blocks instead of per-batch allocation [datafusion-comet] via GitHub
• Re: [I] EPIC: complete GroupValuesColumn type coverage (nested types + remaining primitives) [datafusion] via GitHub
• [PR] fix: reproduce function registry deterministically in SessionStateBuilder::new_from_existing [datafusion] via GitHub
  • Re: [PR] fix: reproduce function registry deterministically in SessionStateBuilder::new_from_existing [datafusion] via GitHub
  • Re: [PR] fix: reproduce function registry deterministically in SessionStateBuilder::new_from_existing [datafusion] via GitHub
  • Re: [PR] fix: reproduce function registry deterministically in SessionStateBuilder::new_from_existing [datafusion] via GitHub
  • Re: [PR] fix: reproduce function registry deterministically in SessionStateBuilder::new_from_existing [datafusion] via GitHub
  • Re: [PR] fix: reproduce function registry deterministically in SessionStateBuilder::new_from_existing [datafusion] via GitHub
• Re: [I] Proto: migrate SortExec + SortPreservingMergeExec [datafusion] via GitHub
• [PR] feat: add GroupColumn support for Decimal256 in multi-column GROUP BY [datafusion] via GitHub
  • Re: [PR] feat: add GroupColumn support for Decimal256 in multi-column GROUP BY [datafusion] via GitHub
  • Re: [PR] feat: add GroupColumn support for Decimal256 in multi-column GROUP BY [datafusion] via GitHub
• Re: [I] Comet throws `java.lang.NegativeArraySizeException` [datafusion-comet] via GitHub
• [PR] feat(executor): default to a bounded, auto-sized memory pool [datafusion-ballista] via GitHub
  • Re: [PR] feat(executor): default to a bounded, auto-sized memory pool [datafusion-ballista] via GitHub
  • Re: [PR] feat(executor): default to a bounded, auto-sized memory pool [datafusion-ballista] via GitHub
• [I] CI: non-gating label (e.g. auto-added `performance`) spawns a phantom all-skipped CI run that shadows real checks [datafusion-comet] via GitHub
• Re: [PR] feat: add native GroupsAccumulator for any_value [datafusion] via GitHub
• [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
  • Re: [PR] perf: encode shuffle IPC schema once per writer instead of per block [datafusion-comet] via GitHub
• [PR] perf: reuse zstd context and pre-encode IPC schema in shuffle blocks [experimental] [datafusion-comet] via GitHub
  • Re: [PR] perf: reuse zstd context and pre-encode IPC schema in shuffle blocks [experimental] [datafusion-comet] via GitHub
• [PR] fix: Handle null-aware joins correctly in `FilterNullJoinKeys` when its enabled [datafusion] via GitHub
  • Re: [PR] fix: Handle null-aware joins correctly in `FilterNullJoinKeys` when its enabled [datafusion] via GitHub
  • Re: [PR] fix: Handle null-aware joins correctly in `FilterNullJoinKeys` when its enabled [datafusion] via GitHub
• [I] Optimizer rule `FilterNullJoinKeys` causes null-aware joins to return incorrect results [datafusion] via GitHub
  • Re: [I] Optimizer rule `FilterNullJoinKeys` causes null-aware joins to return incorrect results [datafusion] via GitHub
• Re: [PR] feat: Support null aware hash mark-joins [datafusion] via GitHub
  • Re: [PR] feat: Support null aware hash mark-joins [datafusion] via GitHub
• [PR] chore: remove Github filter `status:success` for `pending PR` shield [datafusion] via GitHub
  • Re: [PR] chore: remove Github filter `status:success` for `pending PR` shield [datafusion] via GitHub
  • Re: [PR] chore: remove Github filter `status:success` for `pending PR` shield [datafusion] via GitHub
  • Re: [PR] chore: remove Github filter `status:success` for `pending PR` shield [datafusion] via GitHub
• [PR] fix(substrait): handle read filters and projections [datafusion] via GitHub
  • Re: [PR] fix(substrait): handle read filters and projections [datafusion] via GitHub
• [PR] fix: align physical CASE nullability through casts [datafusion] via GitHub
  • Re: [PR] fix: align physical CASE nullability through casts [datafusion] via GitHub
  • Re: [PR] fix: align physical CASE nullability through casts [datafusion] via GitHub
  • Re: [PR] fix: align physical CASE nullability through casts [datafusion] via GitHub
  • Re: [PR] fix: align physical CASE nullability through casts [datafusion] via GitHub
  • Re: [PR] fix: align physical CASE nullability through casts [datafusion] via GitHub
  • Re: [PR] fix: align physical CASE nullability through casts [datafusion] via GitHub
  • Re: [PR] fix: align physical CASE nullability through casts [datafusion] via GitHub
• [PR] refactor join-key equality filtering [datafusion] via GitHub
  • Re: [PR] refactor join-key equality filtering [datafusion] via GitHub
• [PR] Refactor/planner contracts session [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move planning APIs to session crate [datafusion] via GitHub
• [PR] perf: drop redundant concat layer in single-partition shuffle [datafusion-comet] via GitHub
  • Re: [PR] perf: drop redundant concat layer in single-partition shuffle [datafusion-comet] via GitHub
  • Re: [PR] perf: drop redundant concat layer in single-partition shuffle [datafusion-comet] via GitHub
  • Re: [PR] perf: drop redundant concat layer in single-partition shuffle [datafusion-comet] via GitHub
• [I] `to_timestamp_*` discards the timezone of already-timezone-aware inputs [datafusion] via GitHub
  • Re: [I] `to_timestamp_*` discards the timezone of already-timezone-aware inputs [datafusion] via GitHub
  • Re: [I] `to_timestamp_*` discards the timezone of already-timezone-aware inputs [datafusion] via GitHub
  • Re: [I] `to_timestamp_*` discards the timezone of already-timezone-aware inputs [datafusion] via GitHub
• [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
  • Re: [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
  • Re: [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
  • Re: [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
  • Re: [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
  • Re: [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
  • Re: [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
  • Re: [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
  • Re: [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
  • Re: [PR] perf: bypass shuffle BatchCoalescer for already-sized batches [datafusion-comet] via GitHub
• [I] perf: optimize native shuffle writer (redundant copies, per-block allocations) [datafusion-comet] via GitHub
  • Re: [I] perf: optimize native shuffle writer (redundant copies, per-block allocations) [datafusion-comet] via GitHub
  • Re: [I] perf: optimize native shuffle writer (redundant copies, per-block allocations) [datafusion-comet] via GitHub
• Re: [PR] Reduce cloning in LogicalPlanBuilder [datafusion] via GitHub
• [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
  • Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] via GitHub
• [PR] fix(executor): keep heartbeating while all task slots are busy [datafusion-ballista] via GitHub
  • Re: [PR] fix(executor): keep heartbeating while all task slots are busy [datafusion-ballista] via GitHub
  • Re: [PR] fix(executor): keep heartbeating while all task slots are busy [datafusion-ballista] via GitHub
• [I] [DISCUSSION] Rethinking Code Review and Testing in the Agent Era [datafusion] via GitHub
• [PR] test (slt): add memory-limited aggregation sqllogictests [datafusion] via GitHub

• Earlier messages
• Later messages