You are viewing a plain text version of this content. The canonical link for it is here.

---

- Re: [PR] fix: report Parquet Bloom filter pruning metrics accurately [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 00:02:03 UTC, 9 replies.
- Re: [PR] fix: match Spark statistical aggregate updates and merges [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 00:15:10 UTC, 11 replies.
- [I] Filtered semi/anti sort-merge join is slow on small key groups and charges each group a whole batch [datafusion] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/01 00:16:48 UTC, 1 replies.
- Re: [I] Investigate nested TPC-H q21 slowdown: Comet 37% slower than Spark at SF1000 [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/01 00:17:02 UTC, 4 replies.
- Re: [PR] fix: fall back when struct field names collide case-insensitively [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 00:24:22 UTC, 0 replies.
- Re: [I] Nested duplicate names in a metadata-free Parquet file bypass the native resolver when the file schema equals the requested schema [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 00:24:23 UTC, 0 replies.
- Re: [PR] [branch-55] Preserve field metadata when coercing INT96 timestamps (#24790) [datafusion] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/01 00:28:32 UTC, 2 replies.
- [I] Assess native (Rust) code generation for fused expression evaluation [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 00:30:45 UTC, 0 replies.
- Re: [PR] feat: write the executor memory usage log to the Spark event log [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 00:32:09 UTC, 0 replies.
- Re: [PR] fix: reject casts involving non-default collated strings [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 00:32:11 UTC, 1 replies.
- Re: [PR] fix: match container field ids that the INT96 coercion drops [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/01 00:32:13 UTC, 2 replies.
- Re: [I] [Doc] CAST collated-string handling on Spark 4.0+ is implicit and untested [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 00:32:15 UTC, 0 replies.
- Re: [PR] fix: Avoid special-casing `count(1)` in `Count::value_from_stats` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 00:35:52 UTC, 0 replies.
- [PR] fix: Fix make_array null input handling [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/01 00:40:40 UTC, 10 replies.
- Re: [PR] fix: bound spill file batches by bytes so external sorts over wide rows can merge [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/01 00:43:54 UTC, 3 replies.
- Re: [I] feat: make `SharedCoalescer` do memory accounting for buffered batches [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/01 00:53:34 UTC, 2 replies.
- Re: [PR] perf: keep the sort-merge join when the forced hash join's build side is too large [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/01 01:13:08 UTC, 5 replies.
- [PR] fix: [branch-1.1] match pre-epoch Iceberg temporal rounding (#6456) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 01:15:18 UTC, 1 replies.
- [PR] fix: [branch-1.1] fall back for rank limits over nested float keys (#6468) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 01:20:24 UTC, 1 replies.
- [PR] fix: [branch-1.1] make adaptive aggregation skipping opt-in (#6474) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 01:26:04 UTC, 2 replies.
- [PR] fix: [branch-1.1] fall back for incompatible regression aggregates (#6451) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 01:26:21 UTC, 1 replies.
- [PR] fix: [branch-1.1] rescale decimals in generated dispatchers (#6455) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 01:26:39 UTC, 2 replies.
- [PR] fix: [branch-1.1] coerce native IF branches to a common type (#6458) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 01:26:56 UTC, 1 replies.
- [PR] test: [branch-1.1] cover sliced boolean arrays in explode (#6473) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 01:27:45 UTC, 1 replies.
- Re: [PR] fix: use build_join_schema for CrossJoinExec output schema metadata [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 01:56:51 UTC, 0 replies.
- Re: [PR] feat: Refactor NLJ into an extensible framework for specialized joins [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 01:56:56 UTC, 0 replies.
- Re: [PR] chore(deps-dev): bump shell-quote from 1.8.3 to 1.10.0 in /datafusion/wasmtest/datafusion-wasm-app [datafusion-sandbox] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 01:59:09 UTC, 1 replies.
- Re: [PR] chore(deps): bump setuptools from 82.0.0 to 83.0.0 [datafusion-sandbox] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 01:59:10 UTC, 1 replies.
- [PR] fix: load the bundled native library only once per class loader [datafusion-comet] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/01 02:12:35 UTC, 4 replies.
- Re: [I] native: `JVMClasses::with_env: JAVA_VM not initialized` aborts a multi-suite JVM [datafusion-comet] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/01 02:13:37 UTC, 1 replies.
- Re: [PR] test: enable SPARK-57298 collect_set tests [datafusion-comet] - posted by "peterxcli (via GitHub)" <gi...@apache.org> on 2026/10/01 02:31:56 UTC, 2 replies.
- [I] Add checked time arithmetic regression coverage for scalar UDF type recovery [datafusion] - posted by "Toby1009 (via GitHub)" <gi...@apache.org> on 2026/10/01 02:37:00 UTC, 2 replies.
- [I] Avoid redundant sorts for scalar subquery expressions [datafusion] - posted by "Toby1009 (via GitHub)" <gi...@apache.org> on 2026/10/01 02:37:14 UTC, 2 replies.
- [PR] chore: move native write configs under spark.comet.write [datafusion-comet] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/01 02:39:04 UTC, 2 replies.
- [PR] test: share collation coverage across Spark 4.x [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 02:42:10 UTC, 1 replies.
- Re: [PR] refactor: separate JNI-free core logic and error classification at the native boundary [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/01 02:52:17 UTC, 1 replies.
- Re: [PR] fix: account for row duplication and padding in join null counts [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/01 03:01:08 UTC, 3 replies.
- Re: [I] Native CASE WHEN names its struct result's fields after the ELSE branch instead of the first THEN branch [datafusion-comet] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/01 03:12:28 UTC, 2 replies.
- Re: [I] Enable TopK dynamic filter pushdown into native Parquet scans [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 03:15:24 UTC, 1 replies.
- Re: [PR] chore(deps): bump pyjwt from 2.13.0 to 2.15.0 [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/01 03:34:19 UTC, 0 replies.
- Re: [PR] chore(deps): bump urllib3 from 2.7.0 to 2.8.0 [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/01 03:35:06 UTC, 0 replies.
- [PR] build(deps): bump pyjwt from 2.13.0 to 2.15.0 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 03:43:20 UTC, 2 replies.
- Re: [PR] perf: avoid quadratic planning for SELECTs with many aggregates [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/01 03:45:38 UTC, 1 replies.
- Re: [PR] fix: preserve compound expression equivalences through projection [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 03:47:26 UTC, 1 replies.
- Re: [PR] chore: gate Parquet opener encryption on `parquet_encryption` [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/01 03:53:00 UTC, 0 replies.
- [PR] perf: reduce Parquet runtime filter schema guard overhead [datafusion-comet] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/01 04:03:39 UTC, 1 replies.
- Re: [PR] Prune hash join probe side via a build-side key range bitmap [datafusion] - posted by "gruuya (via GitHub)" <gi...@apache.org> on 2026/10/01 04:31:27 UTC, 1 replies.
- Re: [PR] docs: add a Celeborn integration guide [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 04:40:51 UTC, 0 replies.
- Re: [I] docs: add a user-facing Celeborn integration guide [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 04:40:53 UTC, 0 replies.
- Re: [PR] feat: evaluate UTF8 array extrema collations natively [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 04:42:31 UTC, 5 replies.
- Re: [PR] fix: preserve positional nested types and named struct nullability [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 04:50:43 UTC, 13 replies.
- [PR] fix: redact credentials in object-store URL diagnostics [datafusion] - posted by "goutamadwant (via GitHub)" <gi...@apache.org> on 2026/10/01 05:15:52 UTC, 2 replies.
- Re: [I] Redact credentials in object-store URL diagnostics [datafusion] - posted by "goutamadwant (via GitHub)" <gi...@apache.org> on 2026/10/01 05:16:50 UTC, 0 replies.
- Re: [I] Native existence join enumerates every duplicate build match (N*M candidates for M markers) [datafusion-comet] - posted by "harshiniiiiiii (via GitHub)" <gi...@apache.org> on 2026/10/01 05:28:54 UTC, 1 replies.
- Re: [PR] perf: emit initial filter output sooner for dynamic pruning [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/01 05:41:09 UTC, 9 replies.
- Re: [PR] perf: optimize levenshtein function [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 05:44:10 UTC, 0 replies.
- Re: [PR] Return provider extensions directly from the statistics walk [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 05:46:32 UTC, 1 replies.
- Re: [PR] feat: Push down offset/skip to TableScan [datafusion] - posted by "martin-g (via GitHub)" <gi...@apache.org> on 2026/10/01 05:48:33 UTC, 1 replies.
- Re: [PR] perf(proto): avoid re-normalizing logical plans [datafusion] - posted by "AnuragRaut08 (via GitHub)" <gi...@apache.org> on 2026/10/01 05:51:56 UTC, 1 replies.
- Re: [PR] Add SECURITY.md for DataFusion [datafusion] - posted by "martin-g (via GitHub)" <gi...@apache.org> on 2026/10/01 06:05:32 UTC, 10 replies.
- Re: [I] Native implementation of `get_json_object` returns last value for duplicate keys, Spark returns first [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 06:07:27 UTC, 0 replies.
- Re: [PR] fix: `get_json_object` returns first value for duplicate keys to match Spark [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 06:07:27 UTC, 0 replies.
- Re: [PR] feat: admit string maps in Spark-to-Comet conversion [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 06:08:18 UTC, 0 replies.
- Re: [PR] fix: restore localReads assertion in AdaptiveQueryExecSuite diffs [datafusion-comet] - posted by "mizulun (via GitHub)" <gi...@apache.org> on 2026/10/01 06:27:34 UTC, 3 replies.
- Re: [PR] chore(deps): bump datafusion-sqllogictest from 55.0.0 to 55.1.0 [datafusion-iceberg] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/01 06:44:13 UTC, 1 replies.
- Re: [PR] chore(deps): bump datafusion-cli from 55.0.0 to 55.1.0 [datafusion-iceberg] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/01 06:44:43 UTC, 1 replies.
- Re: [PR] feat: add builders for `CreateExternalCatalog` and `DropCatalog` [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 06:45:17 UTC, 3 replies.
- [PR] docs: add repository README [datafusion-iceberg] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/01 06:49:07 UTC, 2 replies.
- [PR] chore(deps): bump pyjwt from 2.12.0 to 2.15.0 [datafusion-sandbox] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 06:57:18 UTC, 0 replies.
- Re: [PR] fix(scheduler): read a swapped broadcast partitioned on the probe side [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/01 07:02:08 UTC, 5 replies.
- Re: [PR] fix(physical-plan): replace approximate map_size accounting with exac… [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 07:06:49 UTC, 14 replies.
- Re: [PR] feat: support col reference for percentiles [datafusion] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/01 07:10:38 UTC, 24 replies.
- Re: [PR] fix: deduplicate StringView/BinaryView buffer refs in CollectLeft Has... [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 07:12:27 UTC, 53 replies.
- [I] Implement optimizer hook for combining partial/final aggregate in `AggregateExec` [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/01 07:13:08 UTC, 1 replies.
- Re: [PR] refactor: Make AggregateExec state modeling and public updates safe (part2: topk) [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/01 07:13:40 UTC, 11 replies.
- Re: [I] `CometCast.isSupported` returns the first non-Compatible child, so `Incompatible` can mask `Unsupported` [datafusion-comet] - posted by "liupoyi-1031 (via GitHub)" <gi...@apache.org> on 2026/10/01 07:18:02 UTC, 0 replies.
- Re: [I] Push Down Offset to TableScan [datafusion] - posted by "martin-g (via GitHub)" <gi...@apache.org> on 2026/10/01 07:24:12 UTC, 0 replies.
- Re: [PR] feat: Column statistics support v1 [datafusion-ballista] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/01 07:25:09 UTC, 5 replies.
- [PR] test: cover typed Dataset filters over sliced aggregate batches [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/01 07:31:06 UTC, 2 replies.
- [PR] fix: compact oversized nested list_extract buffers [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/01 07:31:16 UTC, 8 replies.
- Re: [PR] fix: account for every partition in local TopK and limit statistics [datafusion] - posted by "hassaanch23 (via GitHub)" <gi...@apache.org> on 2026/10/01 07:34:59 UTC, 3 replies.
- Re: [PR] fix: keep filters with correlated subqueries above extension nodes [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 07:37:40 UTC, 3 replies.
- Re: [PR] test: cover Iceberg driver commit cleanup [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 07:37:47 UTC, 0 replies.
- [I] Experimental local execution mode that runs a whole query as one DataFusion graph [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/01 07:45:33 UTC, 4 replies.
- [PR] feat: Experimental local execution mode that runs a whole query as one DataFusion graph [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/01 07:46:21 UTC, 4 replies.
- Re: [PR] fix: Validate `execution.time_zone` at `SET` time [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/01 07:58:26 UTC, 2 replies.
- Re: [PR] fix: `AT TIME ZONE` on a timezone-aware timestamp returns a naive timestamp [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 08:10:17 UTC, 2 replies.
- Re: [PR] IN LIST: treat signed zeros as equal [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/01 08:20:05 UTC, 9 replies.
- Re: [PR] perf: prune unused filter output columns [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/01 08:31:19 UTC, 1 replies.
- [PR] fix: prefer Unsupported when combining nested cast support [datafusion-comet] - posted by "liupoyi-1031 (via GitHub)" <gi...@apache.org> on 2026/10/01 08:36:01 UTC, 1 replies.
- [PR] y [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 08:38:34 UTC, 0 replies.
- Re: [PR] feat: add row-count-aware accumulator interfaces [datafusion] - posted by "mhilton (via GitHub)" <gi...@apache.org> on 2026/10/01 08:40:20 UTC, 4 replies.
- Re: [PR] Make StatisticsContext cache entries retain plan nodes [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 08:41:26 UTC, 1 replies.
- Re: [PR] fix: keep the OFFSET of a correlated EXISTS subquery [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 08:44:34 UTC, 1 replies.
- [PR] docs: show array_distinct keeping first-seen order [datafusion] - posted by "rawsun007 (via GitHub)" <gi...@apache.org> on 2026/10/01 08:51:14 UTC, 2 replies.
- Re: [I] Correlated `EXISTS` subquery with `OFFSET` returns wrong results [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 08:57:27 UTC, 0 replies.
- Re: [PR] feat: support NullType output types in codegen dispatch [datafusion-comet] - posted by "grorge123 (via GitHub)" <gi...@apache.org> on 2026/10/01 09:09:18 UTC, 9 replies.
- Re: [PR] feat: run physical requirement enforcement first, as a PhysicalAnalyzer phase [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/01 09:14:20 UTC, 39 replies.
- Re: [PR] fix: bin coarse date_bin timestamps in i128 and restore ordering [datafusion] - posted by "mhilton (via GitHub)" <gi...@apache.org> on 2026/10/01 09:16:30 UTC, 12 replies.
- [PR] fix: read the Iceberg write gate's storage scheme the same way the native factory does [datafusion-comet] - posted by "0lai0 (via GitHub)" <gi...@apache.org> on 2026/10/01 09:36:24 UTC, 3 replies.
- Re: [PR] fix: gate unsupported Iceberg S3 write settings [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 09:43:28 UTC, 6 replies.
- Re: [PR] fix: cast native IF branches to a common type like CASE WHEN [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 09:44:23 UTC, 4 replies.
- Re: [PR] fix: validate Parquet VARIANT annotation against the requested read type [datafusion-comet] - posted by "0lai0 (via GitHub)" <gi...@apache.org> on 2026/10/01 09:51:27 UTC, 5 replies.
- [PR] perf: add fully ordered group values implementation for primitive [datafusion] - posted by "rluvaton (via GitHub)" <gi...@apache.org> on 2026/10/01 09:55:40 UTC, 13 replies.
- Re: [PR] fix: size aggregate spill batches by bytes as well as rows [datafusion] - posted by "EmilyMatt (via GitHub)" <gi...@apache.org> on 2026/10/01 10:08:18 UTC, 14 replies.
- [I] `sum(DISTINCT x)` with `GROUP BY` uses twice the memory or more, unless the query also has `count(*)` [datafusion] - posted by "mkleen (via GitHub)" <gi...@apache.org> on 2026/10/01 10:35:59 UTC, 4 replies.
- Re: [I] Make `AggregateExec` state modeling and public updates safe [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 10:47:05 UTC, 0 replies.
- [PR] Bump bigdecimal from 0.4.10 to 0.4.11 [datafusion-sqlparser-rs] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 10:52:49 UTC, 1 replies.
- [PR] fix: charge semi/anti sort-merge join key groups by their sliced size [datafusion] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/01 11:00:21 UTC, 8 replies.
- Re: [PR] perf(aggregate): specialize fully ordered group keys without hashing [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 11:03:01 UTC, 4 replies.
- Re: [I] Specialized GroupValues Implementation for Ordered Data [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/01 11:13:45 UTC, 0 replies.
- Re: [PR] docs: request changes for correctness and performance findings in the review skill [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 11:29:04 UTC, 0 replies.
- Re: [PR] perf: skip functional dependency work when inputs carry none [datafusion] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/01 11:29:32 UTC, 13 replies.
- Re: [PR] perf: cut schema check and subquery rescan overhead in optimizer [datafusion] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/01 11:29:33 UTC, 11 replies.
- Re: [PR] perf: stop redoing per-chunk setup on the hash join probe path [datafusion] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/01 11:29:35 UTC, 8 replies.
- Re: [I] Split physical optimizer rules into enforcement and optimization phases, with a convergence loop for the optimizers [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 11:40:14 UTC, 0 replies.
- Re: [I] Physical optimizer re-runs rules on plans they have already settled [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 11:41:22 UTC, 0 replies.
- Re: [PR] fix: coalesce shuffle partitions under Comet unions the way Spark does [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 11:44:45 UTC, 3 replies.
- Re: [PR] chore: Hide test-only internal public APIs [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/01 11:59:58 UTC, 3 replies.
- Re: [PR] fix: show results in the nine silent top-level examples [datafusion-python] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/01 12:13:40 UTC, 0 replies.
- [PR] chore(deps): bump pyjwt from 2.13.0 to 2.15.0 in /python [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 12:14:23 UTC, 1 replies.
- Re: [PR] perf: Optimize `array_agg(... IGNORE NULLS)` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 12:17:06 UTC, 1 replies.
- Re: [PR] fix: match Iceberg's rounding for pre-1970 timestamps in native years/months/days/hours [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 12:19:31 UTC, 3 replies.
- Re: [PR] fix: fall back to Spark for regr_* aggregates until their merge matches Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 12:19:33 UTC, 2 replies.
- Re: [PR] perf: mirror compound ASOF key predicates to right [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/01 12:19:37 UTC, 2 replies.
- Re: [PR] fix: keep a subquery correlated when its filter is below a window function [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/01 12:30:22 UTC, 1 replies.
- Re: [PR] refactor: Use cast preimages for cast predicate rewrites [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/01 12:41:31 UTC, 10 replies.
- Re: [PR] fix: rescale decimal results from dispatched functions to the declared type [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 12:42:06 UTC, 10 replies.
- Re: [PR] test: close five mutation-testing gaps in leaf expression pushdown guards [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/01 12:44:04 UTC, 0 replies.
- [I] Record whether a window frame was set explicitly, so `ExprFunctionExt` can build on an existing window function [datafusion] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/01 12:49:27 UTC, 3 replies.
- Re: [PR] refactor: move the remaining PhysicalExpr impls from core into spark-expr [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 12:52:08 UTC, 0 replies.
- Re: [PR] build: bump semanticdb to 4.13.10 so scalafix runs on Spark 4.1 and 4.2 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 12:53:05 UTC, 0 replies.
- Re: [I] Examples of using `TreeNode` APIs to walk and manipulate LogicalPlans [datafusion] - posted by "mattsu2020 (via GitHub)" <gi...@apache.org> on 2026/10/01 12:59:49 UTC, 1 replies.
- [PR] refactor: move the self-contained operators from core into a new operators crate [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:03:25 UTC, 1 replies.
- Re: [PR] docs: promote Spark 4.2 from experimental to supported [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:03:36 UTC, 0 replies.
- Re: [PR] fix: arrays_zip with duplicate field names falls back to Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:04:50 UTC, 0 replies.
- Re: [PR] feat: Use NativeType in get_example_type, information schema [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/01 13:05:51 UTC, 7 replies.
- Re: [PR] Allow the `HLLAccumulator` used by `approx_distinct()` to consume state produced by `HllGroupsAccumulator` [datafusion] - posted by "Dandandan (via GitHub)" <gi...@apache.org> on 2026/10/01 13:16:19 UTC, 8 replies.
- [I] Native Iceberg scan fails on files written before a nested field was added, and since 1.1.0 null checks and explode hit it too [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:17:28 UTC, 1 replies.
- Re: [PR] feat: cost-based join order enumeration [datafusion] - posted by "Dandandan (via GitHub)" <gi...@apache.org> on 2026/10/01 13:19:16 UTC, 7 replies.
- Re: [PR] Make StatisticsContext cache entries node-lifetime safe [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/01 13:24:34 UTC, 5 replies.
- Re: [PR] feat: Use DataFusion date_trunc for compatible trunc and date_trunc paths [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:27:13 UTC, 1 replies.
- Re: [PR] fix: run reverse of a binary value through the codegen dispatcher [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:37:58 UTC, 1 replies.
- Re: [PR] fix: report a cached relation's decoded size to the planner, not its compressed size [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:38:01 UTC, 1 replies.
- Re: [PR] fix: keep Spark's cache scan for a relation whose cached plan records observed metrics [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:38:05 UTC, 1 replies.
- Re: [PR] fix: reject scalar subqueries inside a codegen-dispatch kernel [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:39:37 UTC, 2 replies.
- Re: [PR] perf: optimize JVM columnar-to-row conversion [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:39:39 UTC, 3 replies.
- [I] Crate name `datafusion-iceberg` is taken on crates.io; switch back to `iceberg-datafusion` [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:43:14 UTC, 32 replies.
- [I] Add release infrastructure [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:43:22 UTC, 1 replies.
- Re: [PR] fix: match Spark's float ordering for sort and window keys nested in arrays and structs [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 13:43:35 UTC, 6 replies.
- Re: [PR] refactor: remove unused cast compatibility flag [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:44:45 UTC, 3 replies.
- Re: [PR] feat: custom Rust UDFs via arrow-ffi [experimental] [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/01 13:44:54 UTC, 6 replies.
- Re: [PR] perf(pwmj):settle never-matching streamed rows against the buffered extreme… [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/01 13:52:57 UTC, 13 replies.
- [PR] chore: add release infrastructure and rename crate back to `iceberg-datafusion` [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 13:58:41 UTC, 0 replies.
- [PR] chore(deps): bump urllib3 from 2.7.0 to 2.8.0 in /python [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 14:02:08 UTC, 1 replies.
- Re: [PR] feat: per-location credentials for native Iceberg reads and writes [datafusion-comet] - posted by "snmvaughan (via GitHub)" <gi...@apache.org> on 2026/10/01 14:04:03 UTC, 3 replies.
- [I] Native Parquet scan returns wrong _metadata.file_block_start when Spark splits a file [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:04:34 UTC, 1 replies.
- [I] Native Parquet scan fails on an empty file whose nested field type differs from the read schema [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:04:38 UTC, 1 replies.
- [I] Add an AGENTS.md like other DataFusion repositories [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:05:32 UTC, 1 replies.
- Re: [I] Audit the PRs in 1.1.0 for regressions since 1.0.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:06:06 UTC, 3 replies.
- [PR] fix: build with Rust 1.99, which deprecates the legacy f64 constants and fetch_update [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:06:10 UTC, 1 replies.
- Re: [PR] feat: route map lookups through codegen dispatcher [datafusion-comet] - posted by "LinSimon-901101 (via GitHub)" <gi...@apache.org> on 2026/10/01 14:07:39 UTC, 3 replies.
- Re: [PR] fix: Avoid pushing down sort under limits [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/01 14:08:15 UTC, 9 replies.
- Re: [PR] fix: gate array distinct and union signed-zero semantics by Spark version [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:09:38 UTC, 2 replies.
- [I] S3 credential SPI: honor expirationEpochMillis consistently on the Parquet and Iceberg paths [datafusion-comet] - posted by "snmvaughan (via GitHub)" <gi...@apache.org> on 2026/10/01 14:09:38 UTC, 1 replies.
- [I] Quoted AST values and tokens can serialize to non-equivalent SQL [datafusion-sqlparser-rs] - posted by "alessandro-mizzaro-sonarsource (via GitHub)" <gi...@apache.org> on 2026/10/01 14:12:22 UTC, 0 replies.
- [PR] feat: reuse S3 credentials until shortly before their reported expiry [datafusion-comet] - posted by "snmvaughan (via GitHub)" <gi...@apache.org> on 2026/10/01 14:12:41 UTC, 6 replies.
- [I] why python version older than the rust version [datafusion-python] - posted by "l1t1 (via GitHub)" <gi...@apache.org> on 2026/10/01 14:13:27 UTC, 2 replies.
- [PR] docs: add AGENTS.md for coding agents [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:14:13 UTC, 2 replies.
- [PR] fix: fall back to Spark for _metadata.file_block_start and file_block_length [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:15:22 UTC, 1 replies.
- [PR] fix: [branch-1.1] fall back to Spark for _metadata.file_block_start and file_block_length (#6510) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:16:58 UTC, 1 replies.
- Re: [PR] fix: support zero-field struct group keys in aggregate emit [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/01 14:17:58 UTC, 4 replies.
- Re: [PR] feat: wire native existence join support [datafusion-comet] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/01 14:18:32 UTC, 12 replies.
- Re: [I] Comet 1.1.0 Release (September) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:19:07 UTC, 2 replies.
- Re: [PR] feat: add native support for MergeRowsExec (row-level MERGE INTO) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:19:29 UTC, 6 replies.
- Re: [PR] feat: add parquet_file_metadata and parquet_page_index to datafusion-cli [datafusion] - posted by "jay-dee7 (via GitHub)" <gi...@apache.org> on 2026/10/01 14:29:23 UTC, 6 replies.
- Re: [PR] feat: add native Delta Lake scan contrib module (page/row-group pruning) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:32:21 UTC, 24 replies.
- Re: [PR] fix: keep the recovery projection when leaf pushdown would drop a computed same-name column [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/01 14:36:53 UTC, 0 replies.
- Re: [I] Wrong results: leaf expression pushdown removes a computed column that has the same name as its input column [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/01 14:36:55 UTC, 0 replies.
- Re: [PR] feat: blocked agg with dynamic flat and blocked [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/01 14:45:54 UTC, 15 replies.
- [I] Native Parquet scan assigns row groups to splits differently from Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 14:49:03 UTC, 1 replies.
- Re: [PR] feat: close upstream coverage gaps for DataFusion 55.1.0 [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/01 14:49:13 UTC, 1 replies.
- [PR] chore: Upgrade to Rust 1.99, MSRV to 1.95 [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 14:58:13 UTC, 9 replies.
- [PR] docs: check for behavior changes against the latest release in the review skill [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:05:04 UTC, 2 replies.
- [I] Support native existence sort-merge joins (blocked on DataFusion mark-SMJ output buffering) [datafusion-comet] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/01 15:08:51 UTC, 0 replies.
- [I] Grouped `count(DISTINCT x)` on numbers takes a slower path [datafusion] - posted by "mkleen (via GitHub)" <gi...@apache.org> on 2026/10/01 15:12:10 UTC, 4 replies.
- Re: [I] General framework to decorrelate the subqueries [datafusion] - posted by "mohammadnaqvi04 (via GitHub)" <gi...@apache.org> on 2026/10/01 15:19:43 UTC, 0 replies.
- [I] datafusion-proto: EmptyRelation loses its schema on a logical plan round trip [datafusion] - posted by "bigluck (via GitHub)" <gi...@apache.org> on 2026/10/01 15:21:04 UTC, 2 replies.
- [I] Partitioned INSERT computes partition values from the wrong columns when the input plan ends in a projection [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:27:50 UTC, 0 replies.
- [I] Filter pushdown strips casts on columns, which drops matching rows or fails valid queries [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:27:52 UTC, 0 replies.
- [I] `CREATE TABLE` / `DROP TABLE` hang on a current-thread tokio runtime and panic outside a runtime [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:27:53 UTC, 0 replies.
- [I] INSERT into a partitioned table with fanout disabled always fails: the optimizer removes the partition sort [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:27:55 UTC, 1 replies.
- [I] Clustered (fanout disabled) writes fail on sorted input because batches are split in HashMap order [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:27:58 UTC, 0 replies.
- [I] LIKE prefix pushdown ignores backslash escapes and drops matching rows [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:27:59 UTC, 0 replies.
- [I] Metadata tables ignore the scan projection, so projected and aggregate queries return wrong columns or fail [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:28:01 UTC, 3 replies.
- [I] `SELECT *` fails after a column is added until the next write to the table [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:28:03 UTC, 0 replies.
- [I] INSERT into an unpartitioned table fails when fanout is disabled [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:28:06 UTC, 2 replies.
- [I] `convert_filters_to_predicate` negates a weakened AND, producing a predicate that drops matching rows [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:28:08 UTC, 0 replies.
- [I] Option to assign Parquet row groups to file ranges by midpoint, as Spark does [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 15:28:24 UTC, 1 replies.
- Re: [I] Native Iceberg write merges -0.0 and 0.0 rows into one float/double identity partition [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/01 15:29:21 UTC, 3 replies.
- [PR] docs: add community showcase volumes 4 and 5 [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 15:29:40 UTC, 1 replies.
- [PR] feat: Add option to assign Parquet row groups to file ranges by midpoint [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 15:30:36 UTC, 12 replies.
- [I] Comparing a timestamp cast to a time zone against a literal returns wrong results [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 15:38:48 UTC, 2 replies.
- [I] Spark `negative` returns wrong results for decimal columns [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 15:46:19 UTC, 1 replies.
- [I] Queries with multiple `SUM(expr + literal)` aggregates fail or change result type [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 15:49:44 UTC, 1 replies.
- [PR] fix(proto): preserve EmptyRelation schema across logical plan round trip [datafusion] - posted by "bigluck (via GitHub)" <gi...@apache.org> on 2026/10/01 15:50:28 UTC, 9 replies.
- Re: [I] array_distinct and array_union diverge from Spark on -0.0 for Spark versions without SPARK-54918 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:58:41 UTC, 1 replies.
- Re: [I] A native final aggregate that has spilled can fail the task during its replay [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 15:58:43 UTC, 1 replies.
- [I] SQL unparser drops the time zone from timestamp literals [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 16:00:27 UTC, 1 replies.
- Re: [D] DISCUSSION: San Francisco DataFusion Meetup November 2026 [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 16:01:35 UTC, 1 replies.
- [PR] fix: defer Parquet conversion errors until a row group is decoded, as Spark does [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 16:07:01 UTC, 5 replies.
- Re: [PR] perf: Add an adaptive integer membership prefilter for hash joins [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 16:22:44 UTC, 14 replies.
- [I] `decimal % 1` returns 0 for non-nullable decimal columns [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 16:23:45 UTC, 1 replies.
- Re: [PR] Make `RowValues::compare`'s current-offset assumption self-checking [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 16:23:49 UTC, 1 replies.
- [I] `nvl` / `ifnull` convert decimals to Float64 and timestamps and dates to strings [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 16:26:17 UTC, 3 replies.
- Re: [PR] fix: Route collated instr, substring_index, trim, greatest and least through the codegen dispatcher [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/01 16:27:32 UTC, 1 replies.
- Re: [PR] fix: clamp cosine_distance to enforce metric non-negativity and boundedness [0.0, 2.0] [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 16:28:56 UTC, 1 replies.
- [I] `array_concat` on nested lists panics or fails with type mismatch errors [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 16:29:27 UTC, 1 replies.
- Re: [I] datafusion-proto: logical plan decode re-normalizes already-normalized plans, superlinear on wide plans [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 16:30:43 UTC, 0 replies.
- Re: [I] Release DataFusion `55.2.0` (patch) Release (Oct 2026) [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 16:41:06 UTC, 11 replies.
- Re: [I] date_bin: define the semantics of negative strides [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/01 16:47:39 UTC, 4 replies.
- Re: [PR] Add related source code locations to errors [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 16:57:21 UTC, 2 replies.
- Re: [PR] fix: accept NOT NULL input columns in partitioned INSERT [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 16:58:40 UTC, 4 replies.
- Re: [I] Add AQE to DataFusion [datafusion] - posted by "edmondop (via GitHub)" <gi...@apache.org> on 2026/10/01 16:59:38 UTC, 0 replies.
- Re: [PR] test: consolidate partition metrics tests and clarify snapshot docs [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 17:00:06 UTC, 2 replies.
- Re: [PR] feat(physical-plan): add staged execution boundary contract [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 17:04:01 UTC, 11 replies.
- Re: [PR] Update SECURITY policy to conform to ASF guidelines [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/01 17:06:58 UTC, 2 replies.
- Re: [PR] Bind `->` and `->>` above arithmetic in MySQL and Generic [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/01 17:08:22 UTC, 1 replies.
- Re: [I] Expose driver-controlled stage boundaries in physical plans [datafusion] - posted by "edmondop (via GitHub)" <gi...@apache.org> on 2026/10/01 17:09:08 UTC, 0 replies.
- Re: [I] Update SECURITY policy to conform to ASF rules [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/01 17:09:33 UTC, 0 replies.
- Re: [I] Make RowValues::compare's current-offset assumption self-checking [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 17:09:51 UTC, 0 replies.
- Re: [PR] fix(functions): prevent invalid sort omission in log monotonicity when base <= 1 [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 17:19:07 UTC, 6 replies.
- Re: [PR] bench: add `array_compact` benchmarks [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 17:31:03 UTC, 2 replies.
- [PR] docs: add lessons from the 1.1.0 regression audit to the PR review skills [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 17:33:18 UTC, 0 replies.
- Re: [PR] fix: apply CSV null_regex when reading, not only when inferring the schema [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 17:41:21 UTC, 2 replies.
- Re: [PR] fix: preserve floating-point percentile interpolation precision [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 17:41:57 UTC, 1 replies.
- Re: [PR] fix: avoid Float64 percentile_cont interpolation overflow [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 17:42:06 UTC, 2 replies.
- [PR] docs: cut the release branch before fixing regressions, and add a diagram [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 17:42:24 UTC, 2 replies.
- [PR] fix: keep the time zone when unparsing timestamp literals [datafusion] - posted by "Tyagiquamar (via GitHub)" <gi...@apache.org> on 2026/10/01 17:42:47 UTC, 5 replies.
- Re: [PR] feat: preserve bitmap-backed Parquet row selections [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 17:46:23 UTC, 16 replies.
- [PR] fix: match Spark's float semantics in array_remove and sort_array [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 17:50:11 UTC, 2 replies.
- Re: [I] make_array returns wrong row count for null-array input [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 17:50:29 UTC, 0 replies.
- [PR] build(deps): bump urllib3 from 2.7.0 to 2.8.0 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 17:59:04 UTC, 2 replies.
- [PR] build(deps): bump tornado from 6.5.8 to 6.5.9 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 17:59:05 UTC, 2 replies.
- [PR] build(deps): bump virtualenv from 21.5.0 to 21.7.13 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/01 17:59:06 UTC, 2 replies.
- Re: [I] Add a builder for `CreateExternalCatalog` and `DropCatalog` [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 18:23:45 UTC, 0 replies.
- Re: [PR] Generic: Parse IN lists that start with a parenthesized subquery [datafusion-sqlparser-rs] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 18:26:52 UTC, 1 replies.
- Re: [PR] Generic: Render prefix `!` operator with space before operator characters [datafusion-sqlparser-rs] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 18:29:33 UTC, 1 replies.
- Re: [PR] Gate fuzz oracle targets behind features [datafusion-sqlparser-rs] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 18:30:20 UTC, 0 replies.
- Re: [PR] DuckDB: Support nested block comments [datafusion-sqlparser-rs] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 18:30:22 UTC, 0 replies.
- Re: [PR] Check prefix operator spacing by rendered first char [datafusion-sqlparser-rs] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/01 18:44:21 UTC, 1 replies.
- Re: [PR] SQLite: Support string literals as column names in `CREATE TABLE` [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 19:08:59 UTC, 1 replies.
- Re: [PR] SQLite: support == as assignment operator in UPDATE SET [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 19:09:01 UTC, 2 replies.
- Re: [PR] Parse SQLite's `IS` and `IS NOT` operators [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 19:09:04 UTC, 2 replies.
- Re: [PR] SQLite: Support multi-word type names [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 19:09:09 UTC, 3 replies.
- Re: [PR] SQLite: Support `CAST(expr AS)` without a type name [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 19:09:11 UTC, 1 replies.
- Re: [PR] SQLite: Support signed and decimal numbers in type modifiers [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 19:09:15 UTC, 14 replies.
- Re: [PR] MsSql: Disallow unquoted `FROM` keyword as alias assignment expression [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 19:09:17 UTC, 1 replies.
- Re: [PR] Add support for PostgreSQL `CREATE RULE` [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 19:09:31 UTC, 0 replies.
- [I] Coalesce small batches in the passthrough shuffle writer [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/01 19:12:13 UTC, 1 replies.
- [PR] perf(shuffle-writer): coalesce small batches before writing passthrough shuffle files [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/01 19:12:30 UTC, 7 replies.
- [I] percentile_approx returns different percentiles from Spark when its input holds a NaN with the sign bit set [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 19:13:40 UTC, 4 replies.
- [I] Run array_contains on float elements natively with Spark's equality instead of through the codegen dispatcher [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 19:13:42 UTC, 2 replies.
- Re: [PR] Generic: Add spacing around dot in compound field access adjacent to numbers [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/01 19:15:26 UTC, 0 replies.
- [PR] test: sweep Spark's -0.0 and NaN semantics across operators and float expressions [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 19:16:17 UTC, 1 replies.
- Re: [PR] perf: optimizing take_n for DictionaryGroupValuesColumn [datafusion] - posted by "saadtajwar (via GitHub)" <gi...@apache.org> on 2026/10/01 19:19:49 UTC, 0 replies.
- [I] signum(-0.0) returns 0.0 instead of -0.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 19:20:31 UTC, 2 replies.
- Re: [PR] SQLite: Support identifier characters above U+FFFF [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 19:30:25 UTC, 1 replies.
- [I] `array_repeat` fails on lists with non-nullable elements or a non-default element field name [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/01 19:37:45 UTC, 2 replies.
- [I] Clarify how to run native Comet -> Celeborn shuffle end-to-end [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/01 19:54:33 UTC, 8 replies.
- [I] Let a Dialect override how a table name in FROM is parsed [datafusion-sqlparser-rs] - posted by "edmondop (via GitHub)" <gi...@apache.org> on 2026/10/01 20:17:34 UTC, 1 replies.
- Re: [PR] Hive: Preserve numeric-prefix field access round trips [datafusion-sqlparser-rs] - posted by "efegokdemir (via GitHub)" <gi...@apache.org> on 2026/10/01 20:18:47 UTC, 0 replies.
- [PR] feat: Support Struct type in approx_distinct - #23663 [datafusion] - posted by "mkleen (via GitHub)" <gi...@apache.org> on 2026/10/01 20:19:25 UTC, 0 replies.
- [PR] chore(ci): fix clippy errors from Rust 1.99 [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/01 20:24:11 UTC, 1 replies.
- [I] Performance review: shuffle, executor, scheduler and client findings (tracking) [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/01 20:30:49 UTC, 2 replies.
- Re: [I] Unexpected failure parsing SQLite CREATE TABLE statement [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/01 20:38:45 UTC, 0 replies.
- Re: [PR] docs: add release-behavior checks and the 1.1.0 audit's lessons to the review skills [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 20:41:04 UTC, 1 replies.
- Re: [I] Allow DataSouceExec to have child nodes that supply files at runtime [datafusion] - posted by "OussamaSaoudi (via GitHub)" <gi...@apache.org> on 2026/10/01 20:48:49 UTC, 0 replies.
- Re: [PR] test: cover booleans in native explode output past the first batch [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 20:52:03 UTC, 0 replies.
- Re: [PR] feat: Support RunEndEncoded type in approx_distinct [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 20:53:29 UTC, 3 replies.
- [I] Sort-shuffle writer compacts view columns even when they're already dense [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/01 20:56:14 UTC, 2 replies.
- [PR] perf(sort-shuffle): only gc view columns that are sparse [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/01 20:56:34 UTC, 4 replies.
- [I] Native Iceberg sorted-merge scan rebuilds the delete-file cache per file (shared deletes re-read) [datafusion-comet] - posted by "parthchandra (via GitHub)" <gi...@apache.org> on 2026/10/01 21:02:51 UTC, 0 replies.
- Re: [I] Discussion: release the Python client separately from the Rust crates [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 21:11:46 UTC, 3 replies.
- Re: [PR] fix: make restricted_column run linearly [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/01 21:21:21 UTC, 6 replies.
- [I] Reduce retained buffer allocation when map lookups select short nested values [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 21:26:11 UTC, 1 replies.
- Re: [I] Reconcile the two config namespaces for native writes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 21:42:01 UTC, 0 replies.
- [PR] bench: introduce create_hash benchmarks [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/01 21:51:05 UTC, 8 replies.
- [PR] fix: preserve list element field in array_repeat [datafusion] - posted by "1fanwang (via GitHub)" <gi...@apache.org> on 2026/10/01 22:04:32 UTC, 5 replies.
- Re: [PR] fix: avoid divide-by-zero in `avg` for negative-scale decimals [datafusion] - posted by "AdamGS (via GitHub)" <gi...@apache.org> on 2026/10/01 22:06:52 UTC, 1 replies.
- [PR] docs: add examples for walking and rewriting logical plans [datafusion] - posted by "mattsu2020 (via GitHub)" <gi...@apache.org> on 2026/10/01 22:10:19 UTC, 3 replies.
- Re: [PR] feat: Sort-aware Iceberg reads in Comet via a per-partition streaming merge [datafusion-comet] - posted by "parthchandra (via GitHub)" <gi...@apache.org> on 2026/10/01 22:18:47 UTC, 6 replies.
- [PR] fix: [branch-1.1] build with Rust 1.99, which deprecates the legacy f64 constants and fetch_update (#6507) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 22:25:11 UTC, 1 replies.
- [PR] test: [branch-1.1] fix flaky mixed field id directory test on Spark 3.4 and 3.5 (#6312) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 22:25:15 UTC, 1 replies.
- [I] perf: Comet hash joins use more task time than Spark (skewed SHJ with nested payload, BHJ) [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 22:48:53 UTC, 1 replies.
- [PR] refactor: move write planning into dedicated module [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 22:51:43 UTC, 1 replies.
- [I] AQE skew join split makes the join fall back to Spark with no fallback reason [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/01 22:55:28 UTC, 1 replies.
- [PR] fix: fall back for Iceberg writes with float or double identity partitions [datafusion-comet] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/01 23:15:07 UTC, 5 replies.
- [PR] fix: preserve decimal precision and scale in Spark negative [datafusion] - posted by "mattsu2020 (via GitHub)" <gi...@apache.org> on 2026/10/01 23:18:00 UTC, 1 replies.
- [I] Native CASE WHEN and COALESCE reconcile struct fields by name instead of position [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/01 23:42:54 UTC, 1 replies.
- Re: [I] Comet's in-memory cache reports its compressed size to the planner, which changes join planning [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 00:11:50 UTC, 0 replies.
- Re: [I] instr, substring_index, trim with a trim string, greatest and least ignore string collation [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 00:11:50 UTC, 0 replies.
- Re: [I] Observed metrics (Dataset.observe) on a cached DataFrame are lost with Comet's native cache scan [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 00:13:05 UTC, 0 replies.
- [I] MSSQL: Clarify Synapse final-column trailing-comma support [datafusion-sqlparser-rs] - posted by "dvasdekis (via GitHub)" <gi...@apache.org> on 2026/10/02 01:01:50 UTC, 0 replies.
- [PR] MSSQL: Preserve nonreserved keyword column expressions [datafusion-sqlparser-rs] - posted by "dvasdekis (via GitHub)" <gi...@apache.org> on 2026/10/02 01:06:54 UTC, 1 replies.
- [PR] MSSQL: Support deferred ON clauses in right-nested joins [datafusion-sqlparser-rs] - posted by "dvasdekis (via GitHub)" <gi...@apache.org> on 2026/10/02 01:06:57 UTC, 2 replies.
- [PR] MSSQL: Add typed TRY_PARSE expressions [datafusion-sqlparser-rs] - posted by "dvasdekis (via GitHub)" <gi...@apache.org> on 2026/10/02 01:06:59 UTC, 1 replies.
- Re: [I] Native Iceberg years/months/days/hours differ from Iceberg for some pre-1970 timestamps [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 01:10:00 UTC, 0 replies.
- Re: [PR] fix: normalize float operands in the native comparison builder [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/02 01:17:38 UTC, 19 replies.
- Re: [PR] feat: add native distinct-combined collect_list aggregate support [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/02 01:24:58 UTC, 2 replies.
- Re: [PR] perf: passthrough last stream is `SortPreservingMergeStream` [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:49:50 UTC, 0 replies.
- Re: [PR] feat(spark): add levenshtein with optional threshold support [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:49:54 UTC, 1 replies.
- Re: [PR] fix: coalesce AQE shuffle partitions per alignment group [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:57:58 UTC, 0 replies.
- Re: [PR] feat(core): eagerly reclaim job data when the client finishes consuming results [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:58:01 UTC, 0 replies.
- Re: [PR] fix(scheduler): reclaim intermediate shuffle data under AQE [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:58:03 UTC, 0 replies.
- Re: [PR] feat: spilling hash join operator (opt-in, inner joins) [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:58:05 UTC, 0 replies.
- Re: [PR] WIP: feat(executor): allocator-backed OOM guard behind an opt-in oom-guard feature [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:58:07 UTC, 0 replies.
- Re: [PR] WIP: feat: treat ResourcesExhausted as a retriable task failure [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:58:09 UTC, 0 replies.
- Re: [PR] feat(scheduler): call try_acquire_job on active cache miss in update_task_statuses [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:58:11 UTC, 0 replies.
- Re: [PR] feat: decouple partition location from executor metadata [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:58:13 UTC, 0 replies.
- Re: [PR] Scheduler client reuse [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 01:58:15 UTC, 0 replies.
- Re: [I] Support first_value/last_value aggregates as sliding window aggregates (blocks FILTER + windowed first/last value) [datafusion] - posted by "bhaskargurram-ai (via GitHub)" <gi...@apache.org> on 2026/10/02 02:17:45 UTC, 0 replies.
- Re: [I] Native IF fails with "column types must match schema types" when its branches differ in nested nullability [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 02:24:22 UTC, 0 replies.
- Re: [I] Add ExistenceJoin support to Comet native execution [datafusion-comet] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/02 02:28:01 UTC, 0 replies.
- [PR] fix: validate recursive CTE column coercion [datafusion] - posted by "goutamadwant (via GitHub)" <gi...@apache.org> on 2026/10/02 02:52:53 UTC, 3 replies.
- Re: [I] Recursive CTE silently casts recursive term to the static term's type, producing wrong results or a non-terminating query [datafusion] - posted by "goutamadwant (via GitHub)" <gi...@apache.org> on 2026/10/02 02:53:39 UTC, 1 replies.
- Re: [PR] feat: account JVM UDF Arrow allocations in Spark task memory [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/02 03:12:11 UTC, 2 replies.
- Re: [I] [EPIC] Native Variant Support [datafusion-comet] - posted by "peterxcli (via GitHub)" <gi...@apache.org> on 2026/10/02 03:26:59 UTC, 0 replies.
- Re: [I] LEFT JOIN with struct-field ORDER BY fails ordering validation [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/02 03:46:36 UTC, 0 replies.
- Re: [I] `arrays_except` type mismatch [datafusion-comet] - posted by "contentforge-press (via GitHub)" <gi...@apache.org> on 2026/10/02 04:07:12 UTC, 0 replies.
- [PR] chore(ci): bump taiki-e/install-action from 2.87.21 to 2.87.22 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 04:18:24 UTC, 1 replies.
- Re: [PR] fix(physical-plan): replace approximate `map_size` accounting with exact `HashTable::allocation_size()` in `GroupValuesRows` [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 04:38:59 UTC, 1 replies.
- Re: [I] Use Exact Hash-Table Allocation Accounting in `GroupValuesRows` [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 04:49:38 UTC, 0 replies.
- [I] PiecewiseMergeJoin returns wrong results for List keys with NULL elements and fails on Struct keys [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/02 04:54:01 UTC, 2 replies.
- Re: [PR] fix: clear_shrink(0) on rows should reset to original size + single group by fixes in clear_shrink [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/02 05:00:33 UTC, 7 replies.
- [PR] feat: support first_value/last_value aggregates over sliding window frames [datafusion] - posted by "bhaskargurram-ai (via GitHub)" <gi...@apache.org> on 2026/10/02 05:04:40 UTC, 4 replies.
- [PR] perf: route final aggregate buckets by column [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/02 05:40:27 UTC, 31 replies.
- [PR] Fix array_except type mismatch issue #3646 [datafusion-comet] - posted by "contentforge-press (via GitHub)" <gi...@apache.org> on 2026/10/02 06:05:23 UTC, 6 replies.
- Re: [I] chore: Fix Scala code warnings [datafusion-comet] - posted by "contentforge-press (via GitHub)" <gi...@apache.org> on 2026/10/02 06:07:05 UTC, 0 replies.
- Re: [I] Native regr_* aggregates return wrong results for a constant variable merged from several partitions [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 06:26:10 UTC, 0 replies.
- Re: [I] NestedLoopJoinExec memory-limited fallback returns an empty result (wrong count = 0) instead of spilling or erroring [datafusion] - posted by "Vanzeren (via GitHub)" <gi...@apache.org> on 2026/10/02 06:30:27 UTC, 0 replies.
- [PR] refactor: move the remaining JNI-free entry point logic into core functions [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/02 06:47:46 UTC, 5 replies.
- Re: [PR] fix: Decide NOT IN null-aware joins from expression nullability, not just column nullability [datafusion] - posted by "namanjain24-sudo (via GitHub)" <gi...@apache.org> on 2026/10/02 06:57:38 UTC, 1 replies.
- Re: [I] Wrong results: nullable constant `NOT IN (subquery)` returns every row when the subquery column is `NOT NULL` [datafusion] - posted by "namanjain24-sudo (via GitHub)" <gi...@apache.org> on 2026/10/02 06:57:46 UTC, 2 replies.
- Re: [I] Wrong results: `NOT IN (subquery)` ignores NULLs from a nullable outer expression over `NOT NULL` columns [datafusion] - posted by "namanjain24-sudo (via GitHub)" <gi...@apache.org> on 2026/10/02 06:57:47 UTC, 2 replies.
- [I] Lambda examples in the SQL function docs fail with the default dialect [datafusion] - posted by "rawsun007 (via GitHub)" <gi...@apache.org> on 2026/10/02 08:02:31 UTC, 0 replies.
- Re: [PR] feat: serialize LazyMemoryExec through generator hooks [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 08:35:31 UTC, 4 replies.
- [PR] fix: keep decimal fractions in modulo by one [datafusion] - posted by "1fanwang (via GitHub)" <gi...@apache.org> on 2026/10/02 08:57:23 UTC, 7 replies.
- Re: [PR] fix: use NDV for unresolved scalar subquery selectivity instead of 20% fallback [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/02 09:04:14 UTC, 32 replies.
- Re: [PR] feat: give PhysicalExtensionCodec the full decode context [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 09:04:56 UTC, 12 replies.
- Re: [PR] perf(date_trunc): significantly optimize date_trunc for fixed-offset timezones and coarse granularities binning [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 09:07:44 UTC, 2 replies.
- Re: [PR] feat: stage ORDER BY expression evaluation [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 09:09:07 UTC, 4 replies.
- Re: [PR] Feat(parquet) : Introduce support for optionally writing Distinct Values to statistics [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/02 09:15:18 UTC, 12 replies.
- Re: [PR] chore: guard RangeExpr protobuf fields exhaustively [datafusion] - posted by "Xuanwo (via GitHub)" <gi...@apache.org> on 2026/10/02 09:20:31 UTC, 1 replies.
- Re: [PR] perf: adapt generic hash join allocation to key cardinality [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/02 09:22:47 UTC, 0 replies.
- Re: [PR] feat: add opt-in probe selection for partitioned inner hash joins [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 09:25:29 UTC, 1 replies.
- Re: [PR] fix: infer LIMIT and OFFSET parameter types [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 09:32:07 UTC, 12 replies.
- Re: [PR] chore(release): release the Python client separately from the Rust crates [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 09:39:15 UTC, 0 replies.
- Re: [PR] Add ComposedNamedPhysicalExtensionCodec [datafusion] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/02 09:39:21 UTC, 1 replies.
- [PR] refactor: Implement optimizer hook for combining partial/final aggregate in `AggregateExec` [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/02 09:43:07 UTC, 4 replies.
- Re: [PR] fix: use session statistics registry in dfbench reports [datafusion] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/02 09:48:41 UTC, 8 replies.
- Re: [I] Consolidate built-in statistics estimation in one place [datafusion] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/02 09:50:01 UTC, 2 replies.
- Re: [I] Implement FFI versions of runtime environment and execution properties [datafusion] - posted by "Tom-Newton (via GitHub)" <gi...@apache.org> on 2026/10/02 10:00:08 UTC, 2 replies.
- [PR] chore: Hide internal public utility APIs [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/02 10:07:47 UTC, 7 replies.
- [PR] fix: keep decimal and temporal types in nvl and ifnull [datafusion] - posted by "1fanwang (via GitHub)" <gi...@apache.org> on 2026/10/02 10:13:44 UTC, 16 replies.
- Re: [PR] fix: Set Substrait output_type on window functions and LIKE [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 10:14:26 UTC, 3 replies.
- Re: [PR] feat: enable Comet's in-memory cache by default [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:22:07 UTC, 15 replies.
- [PR] Align statistics cache sharing test comments with reset-free contract [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 10:24:15 UTC, 3 replies.
- Re: [I] Job hangs indefinitely instead of failing when all executors are lost [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:30:36 UTC, 1 replies.
- Re: [I] Distributed execution returns incorrect results for several TPC-DS queries (static planner) [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:30:42 UTC, 1 replies.
- [PR] fix: plan and run repeated SUM(x + literal) on decimals and intervals [datafusion] - posted by "1fanwang (via GitHub)" <gi...@apache.org> on 2026/10/02 10:33:27 UTC, 4 replies.
- [PR] chore: bump Ballista version to 55.0.0 [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:35:41 UTC, 4 replies.
- [PR] refactor: move shuffle planning into dedicated module [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:35:52 UTC, 1 replies.
- [PR] test: strengthen scalar UDF type recovery regression coverage [datafusion] - posted by "Toby1009 (via GitHub)" <gi...@apache.org> on 2026/10/02 10:35:55 UTC, 5 replies.
- Re: [PR] fix: truncate scalar timestamps in their own unit in date_trunc [datafusion] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/02 10:36:05 UTC, 0 replies.
- Re: [I] date_trunc rejects scalar timestamps that array evaluation accepts [datafusion] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/02 10:36:07 UTC, 0 replies.
- Re: [I] Account for partitions in local TopK statistics [datafusion] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/02 10:36:59 UTC, 0 replies.
- [I] S3 credential SPI: follow-ups from #6478 (hostless Iceberg metadata locations, docs, tests) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:38:01 UTC, 0 replies.
- Re: [PR] Plan struct colon access as get_field [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 10:38:49 UTC, 3 replies.
- Re: [PR] fix: publish metrics on the update interval for native blocks without a JVM input [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:39:59 UTC, 0 replies.
- Re: [I] Native blocks without a JVM input publish SQL metrics on every batch, ignoring spark.comet.metrics.updateInterval [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:40:01 UTC, 0 replies.
- Re: [I] Remove `datafusion.proto` and use the `datafusion-proto` api for logical plan serde [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:12 UTC, 1 replies.
- Re: [I] Improve new top-level README for this project [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:16 UTC, 1 replies.
- Re: [I] Ballista should serialize Parquet statistics [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:20 UTC, 1 replies.
- Re: [I] Ballista: Executor must return statistics in CompletedTask / CompletedJob [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:24 UTC, 1 replies.
- Re: [I] Ballista: Fix hacks around concurrency=2 to force hash-partitioned joins [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:28 UTC, 1 replies.
- Re: [I] Implement fast path for QueryStageExec when writing 1 shuffle partition [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:33 UTC, 1 replies.
- Re: [I] Implement hash partitioned aggregation in Ballista [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:39 UTC, 1 replies.
- Re: [I] CI should run Ballista integration tests [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:43 UTC, 1 replies.
- Re: [I] Add "Getting Started" docs to repo [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:47 UTC, 1 replies.
- Re: [I] [Python] Allow configuration options to be set when creating BallistaContext [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:53 UTC, 1 replies.
- Re: [I] Implement memory management in shuffle writer [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:42:57 UTC, 1 replies.
- Re: [I] Optimize shuffle before coalesce [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:01 UTC, 1 replies.
- Re: [I] Provide integration with Grafana / Prometheus [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:05 UTC, 1 replies.
- Re: [I] Enable benchmark data validation for distributed execution [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:09 UTC, 1 replies.
- Re: [I] Proposal for more efficient disk-based shuffle mechanism [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:12 UTC, 1 replies.
- Re: [I] Configuration guide should be generated from code [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:19 UTC, 1 replies.
- Re: [I] Broadcast join promotion drops a sort order required by a parent SortMergeJoinExec, silently producing wrong results [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:23 UTC, 1 replies.
- Re: [I] Avoid single-task execution for null-aware anti joins (NOT IN subqueries) [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:27 UTC, 1 replies.
- Re: [I] Q10 SF1000 regression after #2315: SortPreservingMergeExec exhausts fair memory pool under AQE default-on [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:30 UTC, 1 replies.
- Re: [I] Add python crate to workspace [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:38 UTC, 1 replies.
- Re: [I] Stop showing very verbose streaming errors [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:44 UTC, 1 replies.
- Re: [I] Scheduler infinite loop after failed/canceled job [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:51 UTC, 1 replies.
- Re: [I] Move ballista-proto to separate module/crate [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:55 UTC, 1 replies.
- Re: [I] Integration test script should test the Python bindings [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:43:59 UTC, 1 replies.
- Re: [I] The type of Timestamp(Nanosecond, None) >= Date32 of binary physical should be same [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:44:05 UTC, 1 replies.
- Re: [I] The type of Float64 >= Int64 of binary physical should be same [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:44:09 UTC, 1 replies.
- [PR] perf: PartitionedTopKRank on the shared store with decide-then-gather [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/02 10:54:05 UTC, 14 replies.
- Re: [I] Preserve primitive Iceberg pruning beside unsupported complex null conjuncts [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/02 10:57:42 UTC, 0 replies.
- Re: [PR] feat: error when the client and scheduler have different major versions [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:58:59 UTC, 5 replies.
- [PR] fix: keep Spark's cache format when Kryo would reject Comet's or Comet disables itself [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 10:59:46 UTC, 2 replies.
- Re: [PR] fix: match Spark's float ordering in min, max, greatest and least [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 11:02:07 UTC, 5 replies.
- [PR] feat: record why Spark scans a relation cached in Comet's format when Comet is off [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 11:03:43 UTC, 2 replies.
- Re: [PR] fix: hash NaN the way Spark does in hash, xxhash64 and native shuffle [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 11:08:20 UTC, 1 replies.
- Re: [PR] fix: preserve sorts for wrapping integer negation [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/02 11:09:06 UTC, 5 replies.
- [I] Support rolling upgrades without an outage window [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 11:09:08 UTC, 1 replies.
- Re: [PR] fix: avoid query failures from inferred numeric cast bounds [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/02 11:11:05 UTC, 3 replies.
- [PR] refactor: deprecate statistics providers that duplicate operator estimates [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/02 11:11:19 UTC, 3 replies.
- [PR] fix: array_concat panics or fails on non-default nested lists [datafusion] - posted by "1fanwang (via GitHub)" <gi...@apache.org> on 2026/10/02 11:11:44 UTC, 5 replies.
- Re: [PR] fix: align nested collection buffer nullability before spilling [datafusion-comet] - posted by "ErikBPF (via GitHub)" <gi...@apache.org> on 2026/10/02 11:26:54 UTC, 7 replies.
- Re: [PR] ci: drop non-existent suites from the Linux and macOS test matrices [datafusion-comet] - posted by "ErikBPF (via GitHub)" <gi...@apache.org> on 2026/10/02 11:26:55 UTC, 1 replies.
- Re: [PR] ci: key TPC dataset caches on pinned generators [datafusion-comet] - posted by "ErikBPF (via GitHub)" <gi...@apache.org> on 2026/10/02 11:26:59 UTC, 2 replies.
- Re: [PR] ci: shard the Iceberg extensions test task [datafusion-comet] - posted by "ErikBPF (via GitHub)" <gi...@apache.org> on 2026/10/02 11:27:02 UTC, 2 replies.
- [PR] fix: hash every NaN like the canonical NaN in Spark xxhash64 [datafusion] - posted by "mrhard9090 (via GitHub)" <gi...@apache.org> on 2026/10/02 11:36:29 UTC, 2 replies.
- Re: [PR] fix: canonicalize NaN in xxhash64 to match Spark behavior (fixes #25913) [datafusion] - posted by "mrhard9090 (via GitHub)" <gi...@apache.org> on 2026/10/02 11:36:39 UTC, 1 replies.
- Re: [PR] fix: gate the power and log rewrites on the base's value, not its nullability [datafusion] - posted by "amitvijapur (via GitHub)" <gi...@apache.org> on 2026/10/02 12:08:09 UTC, 1 replies.
- Re: [PR] fix: skip the null-aware join when a NOT IN correlation duplicates the IN equality [datafusion] - posted by "amitvijapur (via GitHub)" <gi...@apache.org> on 2026/10/02 12:08:13 UTC, 1 replies.
- Re: [I] panic: GROUP BY or SELECT DISTINCT over a zero-field (empty) struct key [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/02 12:13:45 UTC, 0 replies.
- Re: [PR] test: run Comet in Spark SQL and Iceberg suites that build their own sessions [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 12:16:18 UTC, 0 replies.
- Re: [PR] fix: match Spark's whitespace trimming in casts from string to timestamp and timestamp_ntz [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 12:16:18 UTC, 0 replies.
- Re: [I] Some Spark SQL and Iceberg test suites run without Comet in CI [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 12:16:19 UTC, 0 replies.
- Re: [I] [EPIC] cast from string: trim semantics diverge from Spark across all numeric, datetime and boolean targets [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 12:16:19 UTC, 0 replies.
- Re: [I] fix: string-to-timestamp does not trim ISO control characters, and leading '+' returns null under ANSI [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 12:16:20 UTC, 0 replies.
- Re: [I] reverse on a binary column fails with a native UTF-8 error on Spark 4.2 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 12:55:56 UTC, 0 replies.
- Re: [I] Implement dynamic discrete pruning through a join [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/02 13:18:08 UTC, 0 replies.
- [PR] perf: normalize float hash join build keys once [datafusion] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/02 13:23:08 UTC, 3 replies.
- [PR] ci: Enforce PR limit to 3 for non-committers [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/02 13:33:58 UTC, 9 replies.
- [I] PostgreSQL DO statement [datafusion-sqlparser-rs] - posted by "jvatic (via GitHub)" <gi...@apache.org> on 2026/10/02 13:39:46 UTC, 1 replies.
- Re: [I] TPC-H SF1000 results for Ballista main (DataFusion 55.1.0): 0.72x of Spark 3.5, 1.45x of Spark + Comet, 15% of time in planning (#2497) [datafusion-ballista] - posted by "gruuya (via GitHub)" <gi...@apache.org> on 2026/10/02 13:52:46 UTC, 2 replies.
- Re: [PR] PostgreSQL: parse `CREATE GROUP` and `DROP GROUP` [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/02 13:57:26 UTC, 2 replies.
- Re: [PR] Capture the `COPY ... FROM STDIN` payload verbatim [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/02 13:59:57 UTC, 5 replies.
- Re: [PR] Add ordered bind placeholder dialect metadata [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/02 13:59:58 UTC, 4 replies.
- Re: [PR] Support PostgreSQL `ALTER DEFAULT PRIVILEGES` [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/02 14:01:46 UTC, 4 replies.
- Re: [PR] perf: evaluate AND chains as one n-ary conjunction (#25035) [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/02 14:09:48 UTC, 35 replies.
- Re: [PR] perf: bounded distinct count optimization [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 14:11:43 UTC, 4 replies.
- [PR] Show decimal add bug [datafusion] - posted by "kamilk-pal (via GitHub)" <gi...@apache.org> on 2026/10/02 14:18:51 UTC, 0 replies.
- Re: [I] Spark `xxhash64` ignores the running hash for dictionary-encoded values inside structs and lists [datafusion] - posted by "tohuya6 (via GitHub)" <gi...@apache.org> on 2026/10/02 14:24:29 UTC, 1 replies.
- Re: [PR] fix: mark avg, bit_and/or/xor, stddev and variance as order-insensitive [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/02 14:26:30 UTC, 4 replies.
- [PR] Js/store partitioning in dynamic filters [datafusion] - posted by "jayshrivastava (via GitHub)" <gi...@apache.org> on 2026/10/02 14:31:48 UTC, 0 replies.
- [I] Final aggregate under AQE reads its shuffle through the JVM decoder instead of native direct read [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/02 14:35:34 UTC, 1 replies.
- Re: [PR] Add a fuzz target that flags superlinear parsing and printing [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/02 14:42:43 UTC, 2 replies.
- Re: [I] Fuse operations in `equal_rows_arr` [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/02 14:43:45 UTC, 0 replies.
- Re: [PR] perf: apply partition-specific dynamic filters in range scans [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/02 15:00:33 UTC, 1 replies.
- [PR] fix: [branch-1.1] defer Parquet conversion errors until a row group is decoded, as Spark does (#6515) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:03:14 UTC, 1 replies.
- [PR] oss: add benches remaining scalars [datafusion-comet] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/02 15:09:11 UTC, 0 replies.
- Re: [I] Improve performance of first/last aggregates [datafusion-comet] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/02 15:15:49 UTC, 0 replies.
- Re: [PR] feat: support map inputs for explode [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:21:18 UTC, 2 replies.
- Re: [PR] fix: preserve Spark errors for Parquet timestamp overflow [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:21:22 UTC, 2 replies.
- Re: [PR] feat: full native make_interval with 2.6x faster than spark and 1.1x faster than codegen dispatch [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:21:31 UTC, 2 replies.
- Re: [PR] fix: honor Spark’s commit protocol in Spark 3.x native writes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:21:35 UTC, 1 replies.
- Re: [PR] fix: fall back for Parquet datetime rebasing [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:21:39 UTC, 2 replies.
- Re: [PR] fix: enforce null-key rejection and mapKeyDedupPolicy in native map construction [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:21:44 UTC, 3 replies.
- Re: [PR] feat: route date and timestamp interval arithmetic through codegen dispatch [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:21:49 UTC, 2 replies.
- Re: [PR] fix: honor the S3 profile name and file and Hadoop's addressing mode for custom endpoints [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:21:53 UTC, 16 replies.
- Re: [PR] fix: stop gating columnar shuffle on native-serde checks it never uses [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:21:58 UTC, 4 replies.
- Re: [PR] fix: preserve native sliding integer sum overflow semantics [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:12 UTC, 4 replies.
- Re: [PR] fix: refuse codegen dispatch for a TRY cast that can put a null key in a map [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:17 UTC, 5 replies.
- Re: [PR] fix: keep unconverted DPP filters in a scan's canonical form [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:21 UTC, 11 replies.
- Re: [PR] fix: do not resolve DPP subqueries when AQE reads a native scan's partitioning [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:25 UTC, 5 replies.
- Re: [PR] fix: let explicit Hadoop Azure auth outrank ambient AZURE_* environment variables [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:30 UTC, 14 replies.
- Re: [PR] fix: dispatch map lookups with normalized keys and nondeterministic null-guarded children [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:34 UTC, 22 replies.
- Re: [PR] fix: native windows reserve the rows they buffer and buffer one window partition at a time [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:39 UTC, 7 replies.
- Re: [PR] fix: restore Spark write execs when reverting transition-heavy stages [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:43 UTC, 6 replies.
- Re: [PR] fix: check accelerated mapInArrow output against the declared schema [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:47 UTC, 1 replies.
- Re: [PR] fix: preserve duplicate named_struct fields in codegen dispatch [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:52 UTC, 2 replies.
- Re: [PR] fix: support struct-typed scalar subquery results [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:22:56 UTC, 24 replies.
- Re: [PR] Add ExpressionAnalyzer for pluggable expression-level statistics estimation [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/02 15:30:08 UTC, 3 replies.
- [I] Pre-select before cheap conjuncts when the undecided rows form a few long runs [datafusion] - posted by "Abhisheklearn12 (via GitHub)" <gi...@apache.org> on 2026/10/02 15:44:42 UTC, 1 replies.
- [PR] fix: dispatch StaticInvoke and Invoke only into Spark's own classes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 15:46:03 UTC, 2 replies.
- [PR] Add skewness metric to nodes that execute in partitioned mode [datafusion] - posted by "LiaCastaneda (via GitHub)" <gi...@apache.org> on 2026/10/02 15:49:15 UTC, 4 replies.
- Re: [PR] Added derive for arbitrary [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/02 16:02:59 UTC, 0 replies.
- Re: [PR] `PostgreSQL`: Support the `VARIADIC` function call argument marker [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/02 16:05:30 UTC, 2 replies.
- [PR] fix: fall back from the native Iceberg scan when a nested field was added or renamed [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 16:11:53 UTC, 1 replies.
- Re: [PR] Parse the DEFERRABLE transaction mode [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/02 16:22:31 UTC, 2 replies.
- Re: [PR] test: enable `DurationSecond` fuzzing [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/02 16:28:03 UTC, 0 replies.
- Re: [PR] fix: align wide-decimal ANSI overflow value with Spark [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/02 16:33:57 UTC, 1 replies.
- Re: [I] Call for Presentations: Community Showcase: Regular series for sharing what you're building with DataFusion [datafusion] - posted by "wyattwenzel (via GitHub)" <gi...@apache.org> on 2026/10/02 16:37:18 UTC, 2 replies.
- Re: [I] Decide keep-or-lift for each remaining native Iceberg write eligibility restriction [datafusion-comet] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/02 16:39:28 UTC, 0 replies.
- [PR] fix: let a spilled final aggregate read its spill files back past its memory share [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 16:45:21 UTC, 3 replies.
- [PR] feat: [branch-1.1] reuse S3 credentials until shortly before their reported expiry (#6509) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 16:49:42 UTC, 1 replies.
- Re: [PR] fix: make Iceberg delete-file reflection failures fatal [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/02 16:52:19 UTC, 1 replies.
- [I] Native Iceberg scan returns NULL for a nested field renamed after its data file was written [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 16:53:05 UTC, 1 replies.
- [I] Internal error: GROUP BY over UNION ALL fails when a branch projects `coalesce(, FALSE)` (CSE rewrite is physically nullable) [datafusion] - posted by "paul-heyse (via GitHub)" <gi...@apache.org> on 2026/10/02 17:04:55 UTC, 3 replies.
- Re: [PR] test: [branch-1.1] backport the Iceberg write report and the mid-write retry test (#6155, #6111) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 17:17:27 UTC, 0 replies.
- [PR] perf: read the shuffle natively in operators AQE reuses from the initial plan [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/02 17:19:09 UTC, 11 replies.
- [PR] feat: support native wide-decimal hashing [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/02 17:22:59 UTC, 1 replies.
- [I] Native map construction doesn't match Spark 4.0+ float key normalization (-0.0 keys, missing DUPLICATED_MAP_KEY) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 18:03:05 UTC, 0 replies.
- [I] Comet 1.2.0 Release [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 18:14:10 UTC, 2 replies.
- [PR] improve Spark from_utc_timestamp compatibility [datafusion] - posted by "nat-openai (via GitHub)" <gi...@apache.org> on 2026/10/02 18:14:19 UTC, 1 replies.
- [PR] docs: explain which Spark operators Comet leaves in place [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 18:34:31 UTC, 1 replies.
- Re: [PR] feat: add Hudi contrib build gate [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/02 18:56:07 UTC, 0 replies.
- Re: [PR] feat: add build-gated Hudi read integration [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/02 18:56:34 UTC, 0 replies.
- Re: [I] Decimal-returning DSv2 functions lose their scale through the codegen dispatcher [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 19:09:24 UTC, 0 replies.
- Re: [PR] feat: support SortAggregateExec [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/02 19:18:13 UTC, 8 replies.
- [PR] fix: stop struct outputs of the codegen dispatcher from leaking Arrow memory [datafusion-comet] - posted by "peterxcli (via GitHub)" <gi...@apache.org> on 2026/10/02 19:18:22 UTC, 0 replies.
- Re: [PR] The great `Box`-ification experiment [datafusion-sqlparser-rs] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/02 19:22:40 UTC, 2 replies.
- Re: [PR] Update contributor guidelines regarding AI spam [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/02 19:29:06 UTC, 2 replies.
- [PR] feat: add an experimental Comet version of RangeExec [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 19:44:28 UTC, 0 replies.
- [PR] fix: [branch-1.1] dispatch StaticInvoke and Invoke only into Spark's own classes (#6542) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 19:45:18 UTC, 1 replies.
- Re: [PR] docs: add community showcase volumes 4, 5 and 6 [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/02 19:49:01 UTC, 1 replies.
- Re: [PR] fix: respect table timestamp units in Parquet statistics [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/02 20:05:31 UTC, 1 replies.
- Re: [PR] feat: Use DataFusion date_trunc for scalar-format timestamp truncation [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/02 20:08:09 UTC, 7 replies.
- [PR] [branch-55] fix: preserve compound expression equivalences through projection (#25922) [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/02 20:17:11 UTC, 2 replies.
- [I] Support OneRowRelation as a native Comet source [datafusion-comet] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/02 20:18:31 UTC, 1 replies.
- Re: [I] Missing Redshift constructs [datafusion-sqlparser-rs] - posted by "luqmansen (via GitHub)" <gi...@apache.org> on 2026/10/02 20:23:56 UTC, 0 replies.
- Re: [I] `AND` chain pre-selection tests its threshold against the accumulated prefix, not the next conjunct [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/02 20:30:56 UTC, 0 replies.
- Re: [I] Discussion: guidelines for LLM-generated PR reviews [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/02 20:48:30 UTC, 1 replies.
- Re: [PR] ci: grant label runs the contents: write the docs job requests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 21:24:01 UTC, 0 replies.
- Re: [I] ci: every label-triggered CI run fails at startup [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 21:24:05 UTC, 0 replies.
- [PR] fix: return -0.0 for signum(-0.0), as Spark does [datafusion-comet] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/02 21:43:29 UTC, 3 replies.
- [I] spark: array_contains compares floats by bits, where Spark treats -0.0 as 0.0 and all NaNs as equal [datafusion] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/02 22:11:39 UTC, 0 replies.
- Re: [I] S3 credential SPI: per-location credentials for native Iceberg reads and writes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 22:31:33 UTC, 0 replies.
- Re: [PR] fix: reject invalid placeholders in CREATE FUNCTION bodies at definition time [datafusion] - posted by "quwin (via GitHub)" <gi...@apache.org> on 2026/10/02 22:38:18 UTC, 0 replies.
- [PR] docs: note that the peak native aggregate memory metric is not reported [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/02 22:51:13 UTC, 1 replies.
- [PR] fix: run sync catalog calls on a separate runtime [datafusion-iceberg] - posted by "mikamikasuki (via GitHub)" <gi...@apache.org> on 2026/10/02 23:33:36 UTC, 2 replies.
- Re: [PR] fix(cli): respect `sql_parser.recursion_limit` when parsing and validating input [datafusion] - posted by "KassaSana (via GitHub)" <gi...@apache.org> on 2026/10/02 23:49:27 UTC, 3 replies.
- [I] testing [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/02 23:58:10 UTC, 3 replies.
- Re: [PR] chore(`SingleHashAggregateStream`): refactor to async generator implementation [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/03 00:37:09 UTC, 0 replies.
- Re: [PR] Update contributor guidelines regarding AI spam, reviews, code [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/03 00:55:06 UTC, 23 replies.
- Re: [PR] fix: avoid dictionary key overflow in group value output [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/03 01:46:17 UTC, 0 replies.
- Re: [PR] chore(deps-dev): bump webpack-dev-server from 5.2.1 to 5.2.6 in /datafusion/wasmtest/datafusion-wasm-app [datafusion-sandbox] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/03 01:47:51 UTC, 1 replies.
- Re: [PR] feat: add %%sql --limit and --no-display support [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/03 01:52:47 UTC, 0 replies.
- Re: [PR] feat: add docker-compose.quick.yml and fix onboarding docs [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/03 01:52:49 UTC, 0 replies.
- Re: [PR] feat(sort-shuffle): accept Option [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/03 01:52:51 UTC, 0 replies.
- [PR] fix: keep aggregate limits when combining or rebuilding AggregateExec [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 01:56:39 UTC, 5 replies.
- [PR] perf: materialize completed groups once in OrderedSingleAggregateStream [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 02:22:22 UTC, 3 replies.
- Re: [PR] chore: add benches remaining scalars [datafusion-comet] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/03 02:32:09 UTC, 0 replies.
- [I] Native rebase refusals raise CometNativeException instead of SparkUpgradeException [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/03 02:38:25 UTC, 1 replies.
- [PR] fix: handle zero endpoints in division interval bounds [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/03 02:57:20 UTC, 9 replies.
- [PR] fix: release semi/anti/mark sort-merge join reservations before the final output [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 03:00:04 UTC, 3 replies.
- Re: [D] How DataFusion could support other compute engines (libcudf, velox) [datafusion] - posted by "singhpratech (via GitHub)" <gi...@apache.org> on 2026/10/03 05:31:28 UTC, 0 replies.
- [PR] feat(parquet): prune explicitly ordered INT96 timestamps [datafusion] - posted by "Seanium (via GitHub)" <gi...@apache.org> on 2026/10/03 05:36:35 UTC, 0 replies.
- Re: [I] Support pruning on INT96 timestamp columns via `SortOrder::INT96_TIMESTAMP` / `ColumnOrder::INT96_TIMESTAMP_ORDER` [datafusion] - posted by "Seanium (via GitHub)" <gi...@apache.org> on 2026/10/03 05:38:22 UTC, 0 replies.
- [PR] fix: keep grouped integer DISTINCT counts on the native accumulator path [datafusion] - posted by "QinXi-ai (via GitHub)" <gi...@apache.org> on 2026/10/03 06:15:37 UTC, 8 replies.
- [PR] fix: convert native ReadAncientDatetime errors to SparkUpgradeException [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/03 06:15:53 UTC, 1 replies.
- Re: [PR] perf: hash only the selected values of union arrays [datafusion] - posted by "Abhisheklearn12 (via GitHub)" <gi...@apache.org> on 2026/10/03 06:25:09 UTC, 1 replies.
- [I] Rewrite COUNT over non-nullable columns to COUNT(1) [datafusion] - posted by "wudidapaopao (via GitHub)" <gi...@apache.org> on 2026/10/03 06:36:14 UTC, 1 replies.
- [PR] feat: rewrite count over non-nullable columns [datafusion] - posted by "wudidapaopao (via GitHub)" <gi...@apache.org> on 2026/10/03 07:27:37 UTC, 1 replies.
- Re: [PR] feat: optimize count star materialization [datafusion] - posted by "wudidapaopao (via GitHub)" <gi...@apache.org> on 2026/10/03 07:34:09 UTC, 10 replies.
- Re: [I] datafusion-proto: column qualifiers containing `.` are silently corrupted on round-trip [datafusion] - posted by "AnuragRaut08 (via GitHub)" <gi...@apache.org> on 2026/10/03 07:34:44 UTC, 1 replies.
- Re: [I] Potential Optimizations for `hash_union_array` [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/03 07:35:41 UTC, 0 replies.
- [PR] fix(functions): log does not preserve the order of inputs that may be negative [datafusion] - posted by "IgnatiusPang (via GitHub)" <gi...@apache.org> on 2026/10/03 07:38:04 UTC, 0 replies.
- Re: [PR] IN LIST: retain short lists with specialized filters [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/03 07:57:14 UTC, 5 replies.
- Re: [I] Improve shuffle (column) statistics [datafusion-ballista] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/03 08:18:40 UTC, 0 replies.
- Re: [PR] feat: rewrite count(non-nullable column) to count(1) [datafusion] - posted by "wudidapaopao (via GitHub)" <gi...@apache.org> on 2026/10/03 08:28:55 UTC, 2 replies.
- [I] Parallel Parquet writes delay reporting column-worker failures [datafusion] - posted by "Satyr09 (via GitHub)" <gi...@apache.org> on 2026/10/03 08:54:28 UTC, 1 replies.
- [PR] doc: add comments for `LocalLimitExec` and `GlobalLimitExec` [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/03 09:49:22 UTC, 2 replies.
- [PR] Add regression tests for nullable NOT IN expressions [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/03 09:53:07 UTC, 3 replies.
- Re: [PR] ci: Checkout repo first in the Release Version Labeler workflow [datafusion] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/03 12:43:45 UTC, 1 replies.
- [PR] fix: [branch-1.1] fall back from the native Iceberg scan when a nested field was added or renamed (#6543) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 12:50:26 UTC, 1 replies.
- [I] Tighten integer division interval bounds when the divisor has a zero endpoint [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/03 12:51:18 UTC, 0 replies.
- Re: [PR] feat: Arrow Flight SQL frontend for the scheduler + ADBC support [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 12:54:12 UTC, 1 replies.
- Re: [PR] fix: [branch-1.0] revert unsafe partial aggregates after final fallback (#5421) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:02:30 UTC, 0 replies.
- Re: [I] Support more types for `approx_distinct` function [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 13:16:00 UTC, 0 replies.
- Re: [PR] feat: add a native Comet version of RangeExec [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:16:23 UTC, 0 replies.
- [PR] fix: [branch-1.1] gate array distinct and union signed-zero semantics by Spark version (#5750) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:17:34 UTC, 1 replies.
- Re: [PR] fix: keep the running hash for nested dictionaries in Spark xxhash64 [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/03 13:18:15 UTC, 1 replies.
- Re: [I] Accelerated mapInArrow reads Python output at the declared types without checking them [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:28:01 UTC, 0 replies.
- Re: [I] Match Spark ordering and rank semantics for floating values nested in arrays and structs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:28:01 UTC, 0 replies.
- [PR] fix(docker): publish images from release tag pushes [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:30:02 UTC, 1 replies.
- Re: [I] Error when the Python client and the cluster have different major versions [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:30:09 UTC, 0 replies.
- [I] Native Iceberg writer counts NaNs under NULL structs and NULL list or map entries [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:39:06 UTC, 1 replies.
- Re: [PR] fix: compact already-sliced batches before the native Iceberg writer counts NaNs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:40:46 UTC, 2 replies.
- [PR] fix(release): prepare the 55 release process [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:42:39 UTC, 1 replies.
- Re: [PR] Information schema extension [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/03 13:49:52 UTC, 9 replies.
- Re: [PR] fix(scheduler): retire AQE stages cancelled by replan and discard late tasks [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 13:57:08 UTC, 1 replies.
- [PR] feat: normalize floats in native array_distinct and array_union [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 14:08:55 UTC, 19 replies.
- Re: [PR] feat: aggregate a large final hash table as hash buckets (experimental, off by default) [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 14:10:06 UTC, 11 replies.
- [PR] fix: report map_extract on a non-map argument as a plan error [datafusion] - posted by "jackylee-ch (via GitHub)" <gi...@apache.org> on 2026/10/03 14:14:29 UTC, 3 replies.
- [PR] fix: credit changelog co-authors [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 14:19:58 UTC, 1 replies.
- [PR] docs: fix malformed rustdoc for bit_and/bit_or/bit_xor expr fns [datafusion] - posted by "jackylee-ch (via GitHub)" <gi...@apache.org> on 2026/10/03 14:27:00 UTC, 2 replies.
- [I] ORDER BY ... LIMIT returns wrong rows for List/Struct sort keys with NULL elements [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 14:27:59 UTC, 1 replies.
- [PR] fix: do not build TopK dynamic filters from nested sort key thresholds [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 14:28:22 UTC, 4 replies.
- [PR] fix: Only apply SingleDistinctToGroupBy rewrite when it pays (closes #25932) [datafusion] - posted by "mohitgurav20 (via GitHub)" <gi...@apache.org> on 2026/10/03 14:29:31 UTC, 28 replies.
- [I] Sort-merge join outer join with a filter fails on NOT NULL columns: "declared as non-nullable but contains null values" [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 14:39:26 UTC, 2 replies.
- Re: [PR] ClickHouse: Support GLOBAL IN / GLOBAL NOT IN [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/03 14:39:43 UTC, 2 replies.
- [PR] feat: run the operators above a typed Dataset operation natively [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 14:43:28 UTC, 10 replies.
- [I] Sort-merge join ignores a join filter that references no columns (wrong FULL JOIN results) [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 14:46:28 UTC, 1 replies.
- [I] Sort-merge semi/anti/mark joins fail on timezone-aware timestamp, Dictionary, Decimal256 and Time keys: "Unsupported data type in sort merge join comparator" [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 14:54:05 UTC, 0 replies.
- Re: [PR] perf: avoid repeated row comparisons in semi/anti sort-merge joins [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/03 15:00:25 UTC, 1 replies.
- Re: [PR] feat: fuse the typed Dataset map sandwich into a Comet projection [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 15:24:48 UTC, 1 replies.
- [I] [EPIC] Faster Spark-to-Arrow conversion in CometSparkToColumnarExec [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 15:26:54 UTC, 0 replies.
- [PR] 55log [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 15:28:56 UTC, 0 replies.
- [PR] perf: write Spark columns to Arrow in bulk in CometSparkToColumnarExec [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 15:30:15 UTC, 3 replies.
- [PR] Add Ballista 55.0.0 release post [datafusion-site] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 15:42:13 UTC, 1 replies.
- [PR] chore: Update 1.1.0 changelog [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 15:51:48 UTC, 1 replies.
- Re: [PR] chore: [branch-55] Add changelog for 55.0.0 [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 15:59:10 UTC, 0 replies.
- [PR] docs: [branch-1.1] regenerate release docs for 1.1.0-rc2 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 16:00:40 UTC, 1 replies.
- [PR] chore: [branch-1.1] Update changelog [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 16:15:27 UTC, 1 replies.
- [I] Codegen dispatcher initializes kernels with an incorrect partition index under UNION ALL and coalesce [datafusion-comet] - posted by "LinSimon-901101 (via GitHub)" <gi...@apache.org> on 2026/10/03 16:31:10 UTC, 6 replies.
- [PR] fix: validate release build ref before building [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 16:35:07 UTC, 1 replies.
- [PR] docs: add datafusion-arrowmetal to the integrations list [datafusion] - posted by "singhpratech (via GitHub)" <gi...@apache.org> on 2026/10/03 16:35:45 UTC, 4 replies.
- [PR] feat: add Nix flake and direnv support [datafusion] - posted by "VVKot (via GitHub)" <gi...@apache.org> on 2026/10/03 17:02:11 UTC, 5 replies.
- [PR] fix: route sort-merge semi/anti/mark key equality through JoinKeyComparator [datafusion] - posted by "patrickswedish (via GitHub)" <gi...@apache.org> on 2026/10/03 17:46:34 UTC, 4 replies.
- [I] EXPLAIN omits the cached plan under CometInMemoryTableScan [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/03 17:51:21 UTC, 1 replies.
- [PR] feat: track executor allocations and log memory usage [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 18:04:52 UTC, 1 replies.
- Re: [PR] feat: derive per-column pruning guarantees from tuple IN lists [datafusion] - posted by "rgbuilds (via GitHub)" <gi...@apache.org> on 2026/10/03 18:07:13 UTC, 6 replies.
- [PR] dev: Allow new release version to be automatically updated [datafusion] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/03 18:16:10 UTC, 13 replies.
- [I] input_file_name() returns empty values above a converted Spark Parquet scan [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 18:19:20 UTC, 2 replies.
- [PR] fix: draw the cached plan below CometInMemoryTableScan in EXPLAIN [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/03 18:21:17 UTC, 1 replies.
- Re: [PR] feat: route wide-decimal hash and non-literal sha2 through the codege… [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/03 18:23:54 UTC, 1 replies.
- [I] Unparsing the `random` function generates invalid SQL for some dialects [datafusion] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/03 18:24:25 UTC, 1 replies.
- [I] Native scans resolve the AWS SDK ProfileCredentialsProvider names differently from Hadoop [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/03 18:25:59 UTC, 1 replies.
- [PR] fix: Unparse `random` as `rand` for some dialects [datafusion] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/03 18:26:39 UTC, 5 replies.
- Re: [I] `ListingTable` should support scanning against versioned object store files [datafusion] - posted by "HairstonE (via GitHub)" <gi...@apache.org> on 2026/10/03 18:28:42 UTC, 0 replies.
- [I] Adopt DataFusion MemoryDriftTracker after upgrading DataFusion [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 18:34:58 UTC, 0 replies.
- [PR] fix: evaluate sort-merge join filters that reference no columns [datafusion] - posted by "mrhard9090 (via GitHub)" <gi...@apache.org> on 2026/10/03 18:40:58 UTC, 5 replies.
- [I] Arrow struct writer should respect projected schema width [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/03 18:42:46 UTC, 1 replies.
- [PR] fix: draw the cached plan below CometInMemoryTableScan in the SQL tab and event log [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/03 18:44:09 UTC, 4 replies.
- [PR] fix: write columnar structs to Arrow schema width [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/03 18:45:49 UTC, 1 replies.
- [PR] fix(spark): array_contains float equality matches Spark [datafusion] - posted by "mrhard9090 (via GitHub)" <gi...@apache.org> on 2026/10/03 18:46:49 UTC, 5 replies.
- [PR] fix: [branch-1.0] zero sliced boolean offsets at every level before exporting to the JVM (#6339) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 18:53:37 UTC, 1 replies.
- [I] My priorities for 1.2.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 18:55:57 UTC, 0 replies.
- Re: [PR] feat: support multiply_ym_interval with YearMonth interval codegen dispatch [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/03 19:02:17 UTC, 0 replies.
- Re: [I] [Feature] Support Spark expression: multiply_ym_interval [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/03 19:02:18 UTC, 0 replies.
- Re: [PR] fix: pull a correlated filter only through plan nodes known to be safe [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/03 20:22:47 UTC, 0 replies.
- Re: [I] Wrong results: a correlated filter under the right side of an ASOF JOIN is pulled above the join [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/03 20:22:51 UTC, 0 replies.
- Re: [I] Wrong results: a correlated filter under a window function is pulled above the window [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/03 20:22:53 UTC, 0 replies.
- [I] Native Iceberg Write: close cleanup ownership gap during JVM handoff [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/03 20:46:29 UTC, 2 replies.
- [PR] fix: close Iceberg cleanup ownership gap during JVM handoff [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/03 20:52:29 UTC, 1 replies.
- [I] `CASE` with two or more `FixedSizeBinary` WHEN literals panics [datafusion] - posted by "fornwall (via GitHub)" <gi...@apache.org> on 2026/10/03 20:56:26 UTC, 1 replies.
- [I] Remove the spill replay workaround from the memory pools once DataFusion includes apache/datafusion#25383 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/03 21:03:43 UTC, 0 replies.
- Re: [I] Order-insensitive aggregates with an ORDER BY fail in grouped queries (min/max schema mismatch, avg/bit_*/stddev/var panic) [datafusion] - posted by "hassaanch23 (via GitHub)" <gi...@apache.org> on 2026/10/03 21:30:54 UTC, 2 replies.
- [PR] feat: accept column names for aggregate function inputs [datafusion-python] - posted by "richacode007-byte (via GitHub)" <gi...@apache.org> on 2026/10/03 21:37:14 UTC, 10 replies.
- Re: [PR] fix: ignore repeated sort keys in an ordered aggregate's ORDER BY [datafusion] - posted by "hassaanch23 (via GitHub)" <gi...@apache.org> on 2026/10/03 21:41:42 UTC, 3 replies.
- Re: [PR] fix: use session timezone for timestamp subtraction [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/03 21:59:33 UTC, 0 replies.
- [PR] feat: decorrelate a window below a correlated equality filter [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/03 22:14:07 UTC, 13 replies.
- [PR] Add `Dialect::parse_table_factor_name` hook [datafusion-sqlparser-rs] - posted by "edmondop (via GitHub)" <gi...@apache.org> on 2026/10/03 22:24:52 UTC, 10 replies.
- [I] Wrong results: correlated aggregate subquery with a lossy `CAST` in its filter returns one row per inner value [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/03 22:35:11 UTC, 0 replies.
- [I] Proposal: pluggable S3 credential providers [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 00:12:10 UTC, 0 replies.
- [I] Executor keeps a session's first S3 settings after `SET s3.*` changes them [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 00:52:13 UTC, 0 replies.
- [I] S3 object store registry builds a new client on every `get_store` call [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 00:52:15 UTC, 1 replies.
- [I] S3 secret key and session token are written to debug and trace logs [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 00:52:17 UTC, 1 replies.
- Re: [PR] feat(physical-optimizer): support FilterExec with embedded projection in WindowTopN [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/04 02:17:09 UTC, 12 replies.
- Re: [PR] Make Expr::alias and alias_qualified smarter by calling unalias [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/04 02:17:14 UTC, 1 replies.
- Re: [PR] chore(deps): bump cryptography from 46.0.5 to 50.0.0 [datafusion-sandbox] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/04 02:19:17 UTC, 2 replies.
- Re: [PR] chore(deps): bump quinn-proto from 0.11.14 to 0.11.16 [datafusion-sandbox] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/04 02:19:19 UTC, 1 replies.
- Re: [PR] ci: sweep TPC-H/TPC-DS verification over partition counts and empty tables [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/04 02:25:56 UTC, 0 replies.
- Re: [I] Comet writer doesn't respect `OVERWRITE` mode [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 03:39:02 UTC, 2 replies.
- Re: [PR] feat: Support Spark expression: make_dt_interval [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 03:41:33 UTC, 1 replies.
- Re: [I] feat: use `arrays_zip` from DataFusion [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 03:44:35 UTC, 0 replies.
- Re: [PR] chore: move CometCollationSuite to spark-4.1+ test shim [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 03:47:19 UTC, 1 replies.
- Re: [I] Port or enable DateTimeUtilsSuite timestamp format tests in Comet [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 03:50:42 UTC, 0 replies.
- Re: [I] Improve integration of hadoop s3a and comet [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 03:53:35 UTC, 0 replies.
- Re: [I] [Enhancement] Enable mixed partial/final execution for approx_count_distinct (HyperLogLogPlusPlus) [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 03:56:51 UTC, 0 replies.
- Re: [PR] fix: string-to-timestamp does not trim ISO control characters, and leading '+' returns null under ANSI [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 03:59:32 UTC, 2 replies.
- Re: [I] change default Maven profile to Spark 4.0 [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:02:24 UTC, 0 replies.
- Re: [PR] feat: Support Spark Expression Encode [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:05:00 UTC, 1 replies.
- Re: [I] Remove stale dev/diffs test exclusions whose tracking issues are closed [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:07:44 UTC, 4 replies.
- Re: [PR] feat: native RANGE window frames with explicit offset on DATE ORDER BY [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:10:53 UTC, 2 replies.
- Re: [I] Checked TIMESTAMP_MILLIS overflow for nested fields and nested-predicate scans is blocked on DataFusion nested-field pruning [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:13:32 UTC, 1 replies.
- Re: [I] Bug triage results: 2026-08-24 [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:16:56 UTC, 0 replies.
- Re: [I] Spark 3.4 and 3.5 release jars require Java 17 since 0.11.0, though the docs list Java 11 [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:20:20 UTC, 0 replies.
- Re: [PR] Enable mixed approx_count_distinct aggregation [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:23:32 UTC, 0 replies.
- Re: [PR] fix: route length/bit_length/octet_length binary input through codegen dispatcher [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:26:22 UTC, 0 replies.
- Re: [PR] feat: Runtime dynamic filter pushdown for native hash joins [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:29:04 UTC, 0 replies.
- Re: [PR] feat: Implement TimeType support - Infrastructure - sort, min/max [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:32:20 UTC, 0 replies.
- Re: [PR] chore: run CI on contributor forks [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:35:16 UTC, 0 replies.
- Re: [PR] docs: add local-diff mode to review-comet-pr skill and ask about it in the PR template [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:37:51 UTC, 1 replies.
- Re: [PR] feat: native RANGE window frames with explicit offset on " DECIMAL " ORDER BY [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:40:24 UTC, 5 replies.
- Re: [PR] perf: preserve date_trunc ordering for UTC and fixed-offset timestamps [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:42:34 UTC, 0 replies.
- Re: [PR] feat: accelerate scalar Python UDFs with CometArrowEvalPythonExec [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:43:50 UTC, 0 replies.
- Re: [PR] feat: support native Comet scan of plain Delta Lake tables [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:46:32 UTC, 0 replies.
- Re: [I] chore: Separate out extended explain info unit test into spark dependent and spark independent parts [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:49:46 UTC, 0 replies.
- Re: [I] Unaligned memory access in `SparkUnsafeRow` [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:52:39 UTC, 0 replies.
- Re: [PR] feat: extract TimeType to int/decimal [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:55:55 UTC, 0 replies.
- [PR] feat: sort-merge fallback for partitioned hash joins under memory pressure [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:57:54 UTC, 2 replies.
- [PR] perf: keep bounds pruning for hash join partitions that fall back to sort-merge [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:58:19 UTC, 0 replies.
- [PR] feat: add datafusion.execution.hash_join_max_build_size to trigger the sort-merge fallback early [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:58:21 UTC, 2 replies.
- Re: [I] Add date_format support [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 04:58:31 UTC, 1 replies.
- Re: [I] Tracking fs-hdfs issues [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 05:01:35 UTC, 0 replies.
- Re: [I] Enable unit test of hdfs feature in gha [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 05:04:40 UTC, 0 replies.
- [PR] perf: keep the hash join unique-key fast path when the build side has NULL keys [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/04 05:04:49 UTC, 4 replies.
- Re: [I] Handle remainder by zero error in `spark_modulo` function for Spark 4.1 and later. [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 05:07:24 UTC, 0 replies.
- Re: [I] docs: Update "Adding a New Expression" to reference SQL file tests [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 05:10:34 UTC, 0 replies.
- Re: [I] Add jdk21 for spark4.0.1 [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 05:13:47 UTC, 0 replies.
- [PR] Fix CASE literal lookup for fixed-size binary arrays [datafusion] - posted by "jaideeppyne (via GitHub)" <gi...@apache.org> on 2026/10/04 05:18:03 UTC, 3 replies.
- [PR] fix: treat signed zeros as equal in window PARTITION BY [datafusion] - posted by "ShayanGho (via GitHub)" <gi...@apache.org> on 2026/10/04 05:37:23 UTC, 5 replies.
- Re: [PR] fix: handle dictionary nulls in null-aware left mark joins [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/04 05:45:24 UTC, 5 replies.
- Re: [PR] feat: support multi-column NOT IN subqueries with null-aware joins [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/04 05:49:40 UTC, 12 replies.
- Re: [I] ArrowBytesMap and ArrowBytesViewMap undercount memory by not accounting for initial hash table allocation [datafusion] - posted by "yashrb24 (via GitHub)" <gi...@apache.org> on 2026/10/04 06:27:08 UTC, 0 replies.
- Re: [PR] Implement Aggregate function `map_agg` [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/04 06:27:57 UTC, 3 replies.
- Re: [PR] feat: align multi-key equi-join keys with Range partitioning order [datafusion] - posted by "ShayanGho (via GitHub)" <gi...@apache.org> on 2026/10/04 06:31:31 UTC, 6 replies.
- Re: [PR] fix: consider input sizes before reusing join partitioning [datafusion] - posted by "ShayanGho (via GitHub)" <gi...@apache.org> on 2026/10/04 06:31:56 UTC, 2 replies.
- Re: [PR] fix: use session timezone for timestamp subtraction and comparison [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/04 06:41:21 UTC, 2 replies.
- Re: [I] `datafusion.execution.time_zone` is not used for basic time zone inference [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/04 07:15:34 UTC, 0 replies.
- [I] A folded single-entry map literal with a null key fails with NULL_MAP_KEY where Spark returns a value [datafusion-comet] - posted by "Smallfu666 (via GitHub)" <gi...@apache.org> on 2026/10/04 07:40:06 UTC, 2 replies.
- [PR] fix: keep a folded single-entry map literal with a null key on Spark [datafusion-comet] - posted by "Smallfu666 (via GitHub)" <gi...@apache.org> on 2026/10/04 07:58:41 UTC, 1 replies.
- [I] Preserve catalog transactions for split Iceberg writes on Spark 4.2 [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/04 08:29:00 UTC, 2 replies.
- [PR] fix(iceberg): preserve Spark 4.2 write transactions [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/04 08:30:45 UTC, 3 replies.
- [PR] perf: Add a RegexCache type and cache regex for regexp_{replace,instr,count} [datafusion] - posted by "AnthonyZhOon (via GitHub)" <gi...@apache.org> on 2026/10/04 09:16:09 UTC, 4 replies.
- [PR] feat: add opt-in readable column names for SQL results [datafusion] - posted by "haochunchang (via GitHub)" <gi...@apache.org> on 2026/10/04 09:39:40 UTC, 0 replies.
- Re: [I] [Proposal] Readable default column names for SQL query results [datafusion] - posted by "haochunchang (via GitHub)" <gi...@apache.org> on 2026/10/04 11:51:47 UTC, 0 replies.
- Re: [PR] perf: classify string-to-timestamp shapes in one byte scan (up to 5.6x faster) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 12:56:52 UTC, 0 replies.
- [PR] perf: Fix perf regression in `lcm` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/04 13:04:04 UTC, 3 replies.
- [I] `nvl2` result type depends on the type of its first argument [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/04 13:29:16 UTC, 2 replies.
- [PR] docs: add nuthatch to known users [datafusion] - posted by "cargopete (via GitHub)" <gi...@apache.org> on 2026/10/04 13:37:14 UTC, 7 replies.
- [PR] bench: Improve benchmarks for `left`, `right` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/04 13:41:04 UTC, 3 replies.
- [PR] fix: allow NULL-padded rows in sort-merge join filter evaluation [datafusion] - posted by "CuteChuanChuan (via GitHub)" <gi...@apache.org> on 2026/10/04 14:12:13 UTC, 3 replies.
- [I] Add a Presto dialect [datafusion-sqlparser-rs] - posted by "edmondop (via GitHub)" <gi...@apache.org> on 2026/10/04 14:13:22 UTC, 0 replies.
- [I] Explore runtime Iceberg pruning from join, MIN/MAX and TopK [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/04 14:14:53 UTC, 4 replies.
- Re: [I] Preserve bitmap-backed `RowSelection` in `ParquetAccessPlan` [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/04 14:24:50 UTC, 0 replies.
- Re: [I] replace `row_selection_len` in datafusion after arrow-rs release https://github.com/apache/arrow-rs/pull/10704 [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/04 14:24:52 UTC, 0 replies.
- [PR] bench: Fix panic in `power` benchmark [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/04 14:30:29 UTC, 3 replies.
- [I] Title: TopK dynamic filter returns wrong rows when one sort key contains another (DynamicFilterPhysicalExpr remaps the inner column first) [datafusion] - posted by "cargopete (via GitHub)" <gi...@apache.org> on 2026/10/04 14:39:17 UTC, 0 replies.
- [I] Replace manual RowSelection bitmap conversion with force_mask() after arrow-rs release [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/04 14:45:16 UTC, 0 replies.
- [PR] feat: support native Variant columnar-to-row conversion [datafusion-comet] - posted by "peterxcli (via GitHub)" <gi...@apache.org> on 2026/10/04 14:51:01 UTC, 1 replies.
- [PR] perf(core): cache object stores built by the S3 registry [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 14:52:41 UTC, 1 replies.
- [I] Compare floats in Spark's order without normalizing copies of the operands [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:02:12 UTC, 1 replies.
- Re: [PR] fix: fall back to Spark for Parquet field ids on nested fields [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:07:50 UTC, 2 replies.
- [I] Casting to a struct type with repeated field names fails with "ArrowArray struct has 2 children (expected 1)" [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:17:01 UTC, 0 replies.
- [I] Native from_json with a schema that repeats a field name fails with "ArrowArray struct has 2 children (expected 1)" [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:17:16 UTC, 1 replies.
- Re: [I] `named_struct` with duplicate field names falls back to Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:18:20 UTC, 1 replies.
- [PR] fix(core): keep S3 secrets out of debug and trace logs [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:29:04 UTC, 6 replies.
- [I] Give each default Spark-to-Arrow conversion its own spark.comet.convert.* config [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:30:06 UTC, 1 replies.
- [PR] feat: add native Variant null and validity predicates [datafusion-comet] - posted by "peterxcli (via GitHub)" <gi...@apache.org> on 2026/10/04 15:35:36 UTC, 1 replies.
- [PR] feat: support scalar Variant extraction for foldable paths [datafusion-comet] - posted by "peterxcli (via GitHub)" <gi...@apache.org> on 2026/10/04 15:39:56 UTC, 4 replies.
- [I] JVM columnar shuffle spends most of its string and map conversion time on per-value overhead [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:41:28 UTC, 1 replies.
- [I] JVM columnar shuffle's dictionary trial costs about 10 ns per row on high-cardinality strings [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:41:37 UTC, 0 replies.
- [I] Use native shuffle for row input by converting it with CometSparkToColumnarExec [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:41:39 UTC, 1 replies.
- [PR] feat: run array_contains on float elements natively with Spark's equa… [datafusion-comet] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/04 15:47:58 UTC, 7 replies.
- [PR] fix: remap nested TopK filter expressions before their children [datafusion] - posted by "efegokdemir (via GitHub)" <gi...@apache.org> on 2026/10/04 15:53:03 UTC, 5 replies.
- Re: [I] Expr.over() on an aggregate silently drops order_by, null_treatment, filter, and distinct [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/04 15:55:46 UTC, 0 replies.
- Re: [PR] fix: stop the leak of Arrow memory from struct outputs of the codegen dispatcher [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:56:53 UTC, 1 replies.
- [PR] fix: choose get_json_object number-limit behavior from the runtime Jackson version [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 15:57:51 UTC, 1 replies.
- [I] Wrong results: a window function in an `IN` subquery sees every row when the correlated filter repeats the `IN` predicate [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/04 16:03:30 UTC, 0 replies.
- [PR] test: cover speculation and executor loss in multi-task native Iceberg writes [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/04 16:06:24 UTC, 6 replies.
- Re: [PR] perf: stop holding the fair pool lock across blocking memory calls [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 16:07:55 UTC, 16 replies.
- [PR] feat: give each default Spark-to-Arrow conversion its own spark.comet.convert config [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 16:09:25 UTC, 1 replies.
- [I] Correlated `IN` subquery fails with "Projections require unique expression names" when its column is cast [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/04 16:20:09 UTC, 1 replies.
- [PR] docs: note in the 1.1.0 upgrade guide that native Iceberg reads no longer fall back from IRSA [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 16:23:44 UTC, 1 replies.
- Re: [PR] docs: add release notes for 1.1.0 with known regressions and workarounds [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 16:24:29 UTC, 1 replies.
- [PR] perf: speed up string, map and array conversion in JVM columnar shuffle [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 16:24:33 UTC, 3 replies.
- [I] Native Azure credential lookup still differs from Hadoop ABFS in a few configurations [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/04 16:38:13 UTC, 2 replies.
- Re: [PR] fix: add native metrics from every plan a task runs instead of keeping the last [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 16:49:45 UTC, 0 replies.
- Re: [I] Native metrics from several plan instances in one task overwrite each other, so a coalesced scan reports only its last partition [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 16:49:47 UTC, 0 replies.
- [I] Support native MergeRowsExec on Spark 4.1+ with MergeSummary [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/04 16:53:58 UTC, 2 replies.
- [PR] feat: use native shuffle for row input by converting it to Arrow [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 16:59:14 UTC, 13 replies.
- [I] Use RoaringTreemap for MergeRows cardinality tracking [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/04 16:59:30 UTC, 3 replies.
- [I] Substrait roundtrip loses pushed-down TableScan offsets and limits [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/04 17:03:15 UTC, 1 replies.
- [PR] fix(substrait): Preserve pushed-down table scan offsets and limits [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/04 17:06:16 UTC, 12 replies.
- [PR] feat: add experimental cost model for reverting query stages to Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 17:07:35 UTC, 0 replies.
- [I] Wrong ORDER BY results after an outer join when the nullable side equates a column to `coalesce`/`CASE` [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 17:14:52 UTC, 0 replies.
- Re: [PR] feat: support Spark 4.1 TIME type and expressions via codegen dispatch [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 17:16:35 UTC, 2 replies.
- Re: [PR] fix: cancel background batch producers before final metrics [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:19:35 UTC, 1 replies.
- [I] A Spark operator reading a Comet shuffle through AQE's coalesced read gets Spark's ColumnarToRow instead of Comet's [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 17:21:24 UTC, 0 replies.
- Re: [PR] feat: Lambda function support from DataFusion, illustrated with array_filter [datafusion-comet] - posted by "kazantsev-maksim (via GitHub)" <gi...@apache.org> on 2026/10/04 17:24:38 UTC, 3 replies.
- Re: [PR] ci: reuse Linux native libraries across workflow runs [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:29:14 UTC, 3 replies.
- [PR] docs: check open-file limit before release verification [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 17:29:25 UTC, 1 replies.
- Re: [PR] feat: opt in to join filter pushdown through deterministic residuals [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:35:43 UTC, 6 replies.
- Re: [PR] fix: handle null lists with empty children in Spark's `shuffle` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/04 17:37:44 UTC, 3 replies.
- Re: [PR] ci: share one Linux native build across CI workflows [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:39:21 UTC, 2 replies.
- Re: [PR] feat: Extend adaptive partial aggregation to more aggregate functions [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:41:16 UTC, 1 replies.
- Re: [PR] fix: use Spark-compatible shuffle for wide decimal hash keys [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:41:38 UTC, 3 replies.
- Re: [PR] fix: preserve Spark AVG buffer and overflow semantics [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:42:22 UTC, 11 replies.
- Re: [PR] fix: preserve array_join evaluation semantics across Spark versions [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:42:41 UTC, 0 replies.
- Re: [PR] perf: reuse prepared broadcast builds across executor tasks [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:43:04 UTC, 4 replies.
- Re: [PR] feat: carry completed join filters across Union inputs [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:43:06 UTC, 2 replies.
- Re: [PR] perf: specialize scattered Boolean shuffle gathers [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:43:41 UTC, 3 replies.
- Re: [PR] fix: preserve skipped unbase64 rows [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:45:20 UTC, 5 replies.
- Re: [PR] feat: support large Arrow inputs for accelerated Python UDFs [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:45:36 UTC, 0 replies.
- Re: [PR] fix: summarize Bloom literals in filter plan displays [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:45:53 UTC, 3 replies.
- Re: [PR] fix: defer throwing literal casts to Spark at runtime [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:50:49 UTC, 1 replies.
- [I] Optimize MergeRows predicate evaluation and row selection [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/04 17:53:46 UTC, 2 replies.
- [I] Support Spark 4.2 insert-only MERGE execution [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/04 17:54:31 UTC, 1 replies.
- Re: [I] TopKAggregation drops the NULL group under ORDER BY LIMIT n [datafusion] - posted by "HairstonE (via GitHub)" <gi...@apache.org> on 2026/10/04 17:56:55 UTC, 0 replies.
- [I] Array lookup functions evaluate their second argument on rows where the array is NULL, raising ANSI errors that Spark skips [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 17:59:14 UTC, 0 replies.
- Re: [PR] fix: preserve Spark evaluation for next_day and levenshtein [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:59:16 UTC, 8 replies.
- Re: [PR] feat: filter decoded probe batches before intermediate joins [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 17:59:34 UTC, 7 replies.
- [I] Job hangs after losing one executor with AQE: stale tasks can't be cancelled in pull-staged mode, then "Can't find active stage to update stage outputs" [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:00:19 UTC, 0 replies.
- Re: [PR] fix: make wide date-to-timestamp casts safe [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 18:02:06 UTC, 4 replies.
- Re: [PR] test: add regression test for TopKAggregation NULL group preservation (#25850) [datafusion] - posted by "HairstonE (via GitHub)" <gi...@apache.org> on 2026/10/04 18:03:03 UTC, 2 replies.
- [I] Share one Spark-equality match kernel between array_contains, array_position and array_remove [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:11:26 UTC, 0 replies.
- [PR] [branch-55] chore: update version 55.2.0 and add changelog [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/04 18:44:34 UTC, 3 replies.
- [I] [EPIC] Move expression test coverage from Scala suites to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:44:47 UTC, 0 replies.
- [I] test: `query tolerance=` in Comet SQL tests passes when either side is NaN [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:44:57 UTC, 0 replies.
- [I] test: add a Comet SQL test error mode that checks native execution and error-class parity [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:44:59 UTC, 2 replies.
- [I] test: let Comet SQL tests keep ConstantFolding, exclude optimizer rules and change configs mid-file [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:01 UTC, 1 replies.
- [I] docs: document the ways a Comet SQL test can silently miss Comet [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:03 UTC, 2 replies.
- [I] test: move math and arithmetic coverage from Scala suites to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:18 UTC, 0 replies.
- [I] test: move decimal arithmetic coverage from Scala suites to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:21 UTC, 0 replies.
- [I] test: move cast coverage for boolean, integral, floating-point and decimal sources to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:25 UTC, 0 replies.
- [I] test: move cast coverage for string sources to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:29 UTC, 0 replies.
- [I] test: move cast coverage for date, timestamp, binary and complex-type sources to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:32 UTC, 0 replies.
- [I] test: move datetime expression coverage from Scala suites to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:37 UTC, 0 replies.
- [I] test: move string expression coverage from Scala suites to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:41 UTC, 0 replies.
- [I] test: move regex coverage to Comet SQL tests and fix fixtures whose patterns lose their backslashes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:45 UTC, 1 replies.
- [I] test: move array expression coverage from Scala suites to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:48 UTC, 0 replies.
- [I] test: move map and struct expression coverage from Scala suites to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:51 UTC, 0 replies.
- [I] test: move explode/posexplode coverage from CometGenerateExecSuite to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:55 UTC, 0 replies.
- [I] test: move aggregate function coverage from CometAggregateSuite to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:45:59 UTC, 0 replies.
- [I] test: move window function coverage from CometWindowExecSuite to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:46:02 UTC, 1 replies.
- [I] test: move the Spark 4 collation suites to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:46:06 UTC, 0 replies.
- [I] test: move hash and bitwise expression coverage from Scala suites to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:46:09 UTC, 1 replies.
- [I] test: move conditional, JSON, CSV, Variant and other expression coverage to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:46:13 UTC, 0 replies.
- [PR] docs(bench): refresh TPC-H SF1000 results at d6d8bd91 [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:46:17 UTC, 1 replies.
- [I] test: move CometFloatSemanticsSuite's matching cases to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:46:19 UTC, 0 replies.
- [I] test: move expression-level codegen dispatcher tests to Comet SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 18:46:21 UTC, 0 replies.
- [PR] feat: show MERGE INTO details in EXPLAIN [datafusion] - posted by "wirybeaver (via GitHub)" <gi...@apache.org> on 2026/10/04 19:13:17 UTC, 3 replies.
- Re: [D] Native OOM on Large-Scale Joins and Distinct/Deduplication Operations [datafusion-comet] - posted by "arsath7 (via GitHub)" <gi...@apache.org> on 2026/10/04 19:16:59 UTC, 1 replies.
- Re: [PR] test: add seeded fuzz coverage for PyArrow UDFs [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 19:17:51 UTC, 0 replies.
- Re: [I] Support fully-native multi-stage (distinct-combined) collect_list / collect_set [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 19:17:55 UTC, 0 replies.
- Re: [I] The SQL tab and event log lose the cached plan under CometInMemoryTableScan [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/04 19:17:57 UTC, 0 replies.
- Re: [D] I tried benchmarking TPC-DS for Spark vs Datafusion Comet on AWS Glue Catalog Iceberg Tables and Spark was faster. [datafusion-comet] - posted by "NoahKus (via GitHub)" <gi...@apache.org> on 2026/10/04 19:17:58 UTC, 1 replies.
- Re: [I] Wide-decimal overflow reports a different value than Spark [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 19:17:59 UTC, 0 replies.
- Re: [I] Extend windowed aggregate allow-list (collect_set, collect_list, and other natively-supported aggregates) [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 19:18:01 UTC, 0 replies.
- Re: [I] Add randomised fuzz harness for pyarrow UDF vector-copy path [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 19:18:03 UTC, 0 replies.
- Re: [D] Error 134 on SQL regular expressions with Comet 0.12.0 (Spark 3.5.4, Scala 2.13) [datafusion-comet] - posted by "ilia-susanoo (via GitHub)" <gi...@apache.org> on 2026/10/04 19:18:34 UTC, 1 replies.
- [I] Use the release tarball RAT check in CI [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 19:39:58 UTC, 1 replies.
- [PR] ci: check licenses on release source tarball [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 19:40:35 UTC, 1 replies.
- [PR] build(deps): bump taiki-e/install-action from 2.85.5 to 2.87.22 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/04 19:43:52 UTC, 2 replies.
- Re: [PR] build(deps): bump taiki-e/install-action from 2.85.5 to 2.87.20 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/04 19:43:55 UTC, 1 replies.
- [PR] feat: support native MergeSummary on Spark 4.1+ [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/04 19:56:34 UTC, 2 replies.
- [PR] perf: Optimize `left`, `right` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/04 19:58:08 UTC, 12 replies.
- Re: [I] Add native Vortex scan support [datafusion-comet] - posted by "rickard-lundin (via GitHub)" <gi...@apache.org> on 2026/10/04 20:06:43 UTC, 0 replies.
- Re: [PR] fix: preserve DPP filters during transition revert [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 20:27:49 UTC, 0 replies.
- Re: [I] AQE + DPP + spark.comet.exec.transitionRevert.enabled fails with "SubqueryAdaptiveBroadcastExec does not support the execute() code path" [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/04 20:27:51 UTC, 0 replies.
- [I] [EPIC] Adaptive runtime pruning for native Iceberg scans [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/04 20:39:52 UTC, 1 replies.
- [PR] test: compare NaN, infinity sign and row order in tolerance checks [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 20:45:32 UTC, 5 replies.
- [I] Flaky test: CometIcebergWriteActionSuite "a failed write job deletes the data files of tasks that completed" [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 21:07:51 UTC, 1 replies.
- [PR] docs(bench): compare against Spark 4.1.3 and Spark 4.1.3 + Comet 1.1.0-rc2 [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 21:13:08 UTC, 1 replies.
- Re: [PR] perf: choose dictionary encoding like iceberg-java in the native Iceberg writer [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 21:16:42 UTC, 2 replies.
- [PR] docs: explain dialect requirement for lambda examples [datafusion] - posted by "Prajwal-k-tech (via GitHub)" <gi...@apache.org> on 2026/10/04 21:20:51 UTC, 5 replies.
- [PR] test: use the renamed native write flag in the Iceberg 1.11 WAP-branch suite [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 21:36:31 UTC, 1 replies.
- [PR] docs: explain date_bin daylight saving behavior [datafusion] - posted by "Prajwal-k-tech (via GitHub)" <gi...@apache.org> on 2026/10/04 21:45:39 UTC, 4 replies.
- [PR] fix: preserve outer join equivalences for null rows [datafusion] - posted by "Prajwal-k-tech (via GitHub)" <gi...@apache.org> on 2026/10/04 22:20:41 UTC, 10 replies.
- [I] Spark 3.4 SQL test SPARK-34637 fails since #6547 because AQE re-plans flip the DPP join's build side [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 22:38:18 UTC, 1 replies.
- [PR] fix: refresh stale shuffle scans when AQE prepares a stage, not while it re-plans [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 22:38:47 UTC, 1 replies.
- Re: [PR] refactor: separate aggregate group completion from input ordering [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/04 23:00:43 UTC, 4 replies.
- Re: [I] Native Iceberg write gate reads hdfs:/path as file, so the write fails natively instead of falling back [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/04 23:14:28 UTC, 0 replies.
- [PR] oss : add benches for remaining agg functions [datafusion-comet] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/05 01:13:00 UTC, 0 replies.
- Re: [PR] refactor: return Result from fallible catalog and schema methods [datafusion] - posted by "gratus00 (via GitHub)" <gi...@apache.org> on 2026/10/05 01:24:08 UTC, 0 replies.
- Re: [PR] fix: preserve fractional seconds in 'second' and 'millisecond' [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/05 01:56:37 UTC, 0 replies.
- [PR] chore: add benches for remaining comet native kernels [datafusion-comet] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/05 01:58:17 UTC, 1 replies.
- Re: [PR] feat: execute uncorrelated scalar subqueries first instead of rewriting to a join [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/05 02:04:47 UTC, 1 replies.
- Re: [PR] fix: unwrap_cast_in_comparison drops the timezone shift when unwrapping CAST(timestamp AS timestamptz) = literal [datafusion] - posted by "DHRUV6029 (via GitHub)" <gi...@apache.org> on 2026/10/05 03:04:39 UTC, 1 replies.
- [PR] fix: use nested loop join for nested piecewise merge keys [datafusion] - posted by "mikamikasuki (via GitHub)" <gi...@apache.org> on 2026/10/05 03:25:10 UTC, 4 replies.
- [PR] fix: make the native Iceberg per-I/O timeout configurable [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/05 04:04:17 UTC, 1 replies.
- Re: [I] Substrait producer omits output_type on window functions and LIKE expressions [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/05 04:29:05 UTC, 0 replies.
- [PR] chore(deps): bump config from 0.15.26 to 0.15.27 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/05 04:36:03 UTC, 1 replies.
- [PR] chore(deps): bump pyo3-build-config from 0.29.2 to 0.29.3 in /python [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/05 04:37:43 UTC, 1 replies.
- Re: [PR] DRAFT Bench 25188 [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/05 04:46:11 UTC, 0 replies.
- Re: [PR] DRAFT Bench 25044 [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/05 04:46:25 UTC, 0 replies.
- Re: [PR] DRAFT Bench 25150 [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/05 04:46:37 UTC, 0 replies.
- Re: [PR] DRAFT Bench 25010 [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/05 04:46:49 UTC, 0 replies.
- Re: [PR] introduce optional rle reads from parquet [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/05 04:56:39 UTC, 5 replies.
- Re: [PR] test: consolidate ASOF SQL coverage [datafusion] - posted by "Xuanwo (via GitHub)" <gi...@apache.org> on 2026/10/05 05:02:36 UTC, 3 replies.
- Re: [PR] fix: preserve dotted column relation qualifiers [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/05 05:40:52 UTC, 4 replies.
- [PR] fix: requalify LATERAL filters through derived-table aliases [datafusion] - posted by "canyang25 (via GitHub)" <gi...@apache.org> on 2026/10/05 05:49:52 UTC, 7 replies.
- Re: [I] Replace manual `RowSelection` bitmap conversion with `force_mask()` after arrow-rs release [datafusion] - posted by "isabellehuangg (via GitHub)" <gi...@apache.org> on 2026/10/05 06:15:05 UTC, 1 replies.
- [PR] fix: validate temporal display formats [datafusion] - posted by "mikamikasuki (via GitHub)" <gi...@apache.org> on 2026/10/05 07:00:47 UTC, 5 replies.
- [PR] test: add SQL error-class parity checks [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/05 07:04:03 UTC, 1 replies.
- [PR] fix: fall back for duplicate from_json fields [datafusion-comet] - posted by "Samearth17 (via GitHub)" <gi...@apache.org> on 2026/10/05 07:05:22 UTC, 5 replies.
- [PR] bench: Add regexp pattern reuse benchmarks [datafusion] - posted by "AnthonyZhOon (via GitHub)" <gi...@apache.org> on 2026/10/05 07:33:21 UTC, 7 replies.
- [PR] test: move mixed-type shift coverage to SQL fixtures [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/05 07:56:45 UTC, 2 replies.
- [PR] feat: enable native replace for safe inputs [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/05 08:14:50 UTC, 5 replies.
- Re: [PR] fix: reject unsupported DELETE LIMIT [datafusion] - posted by "martin-g (via GitHub)" <gi...@apache.org> on 2026/10/05 08:32:49 UTC, 9 replies.
- Re: [PR] fix: Set Substrait aggregation phase to INITIAL_TO_RESULT [datafusion] - posted by "namanjain24-sudo (via GitHub)" <gi...@apache.org> on 2026/10/05 08:34:37 UTC, 0 replies.
- [PR] fix: preserve types in NVL and IFNULL [datafusion] - posted by "mikamikasuki (via GitHub)" <gi...@apache.org> on 2026/10/05 08:44:14 UTC, 2 replies.
- Re: [PR] Fix GroupValues retained memory accounting [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/05 08:45:16 UTC, 2 replies.
- [PR] docs: mention output_rows_skew on partitioned operators in explain-usage [datafusion] - posted by "LiaCastaneda (via GitHub)" <gi...@apache.org> on 2026/10/05 09:35:30 UTC, 3 replies.
- [I] perf: explore reducing copies in native Celeborn shuffle writes [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/05 09:52:57 UTC, 3 replies.
- Re: [I] Use exponential decay for multi-column join selectivity estimation [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/05 10:31:51 UTC, 0 replies.
- [PR] fix: preserve timezone casts in timestamp comparisons [datafusion] - posted by "mikamikasuki (via GitHub)" <gi...@apache.org> on 2026/10/05 10:32:12 UTC, 0 replies.
- Re: [PR] docs(physical-plan): add doctest examples for StatisticsRegistry, ExtendedStatistics, and compute_extended [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/05 10:35:36 UTC, 4 replies.
- [I] `CoalescePartitionsExec::cardinality_effect` returns `Equal` when `fetch` is set [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/05 11:20:49 UTC, 1 replies.
- [PR] fix: report `LowerEqual` cardinality effect for `CoalescePartitionsExec` with fetch [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/05 11:21:21 UTC, 4 replies.
- [I] Let a Dialect override tokenization [datafusion-sqlparser-rs] - posted by "edmondop (via GitHub)" <gi...@apache.org> on 2026/10/05 11:42:55 UTC, 0 replies.
- [PR] test: move bit_count boundary coverage to SQL fixtures [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/05 11:59:58 UTC, 2 replies.
- Re: [I] CommonSubexprEliminate + leaf-expression pushdown duplicate a UDF call wrapped in get_field [datafusion] - posted by "bert-beyondloops (via GitHub)" <gi...@apache.org> on 2026/10/05 12:03:57 UTC, 0 replies.
- [I] Estimate distinct counts after a filter with the survival formula in `FilterExec` [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/05 12:05:40 UTC, 1 replies.
- Re: [PR] fix: bump DataFusion to 54.1.0 and adapt to RecursiveQuery API change [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/05 12:32:16 UTC, 0 replies.
- Re: [PR] fix: load the Iceberg storage scheme lists from the native factory [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/05 12:36:36 UTC, 2 replies.
- Re: [PR] IN LIST: retain short integer, floating-point, and fixed-size binary lists [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/05 12:40:18 UTC, 30 replies.
- [PR] ci: skip the Rust tests when a change touches nothing under native/ or common/ [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 12:47:45 UTC, 1 replies.
- [PR] Update findepi's affiliation in governance doc [datafusion] - posted by "findepi (via GitHub)" <gi...@apache.org> on 2026/10/05 12:49:13 UTC, 2 replies.
- Re: [PR] fix: forward write_options when write_parquet receives ParquetWriterOptions [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/05 12:49:18 UTC, 1 replies.
- Re: [PR] fix: keep parquet view types out of the shuffle benchmark input [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 12:50:33 UTC, 0 replies.
- Re: [I] shuffle_bench should disable parquet view types so its input matches what Comet produces [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 12:50:34 UTC, 0 replies.
- Re: [PR] perf: fuse Comet cache vector reads into Spark codegen [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 12:50:47 UTC, 3 replies.
- Re: [PR] fix: Make default sort order nulls last [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/05 12:51:32 UTC, 3 replies.
- Re: [I] coalesce(Int, Utf8) coerces to Int [datafusion] - posted by "zyuiop (via GitHub)" <gi...@apache.org> on 2026/10/05 12:54:47 UTC, 1 replies.
- Re: [PR] fix: rethrow the exception a JVM input throws instead of a CometNativeException [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 13:05:58 UTC, 2 replies.
- Re: [PR] fix: report row contents to native write statistics trackers [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 13:06:35 UTC, 5 replies.
- [PR] fix: ship NOTICE.txt as META-INF/NOTICE in the comet-spark jar and sources jar [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 13:08:05 UTC, 1 replies.
- Re: [I] Iceberg scan fails with a hard-wired 10s OpenDAL io_timeout that cannot be configured [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 13:13:32 UTC, 0 replies.
- Re: [PR] refactor: deprecate the bundled statistics providers [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/05 13:14:42 UTC, 8 replies.
- [PR] fix: drop values under NULL parents before the native Iceberg writer counts NaNs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 13:23:30 UTC, 1 replies.
- Re: [I] write_parquet ignores write_options when compression is a ParquetWriterOptions [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/05 13:31:24 UTC, 0 replies.
- [I] Native Iceberg writer's value and null counts for a float under a NULL struct differ from iceberg-java 1.9+ [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 13:37:59 UTC, 2 replies.
- Re: [PR] fix: match Spark ANSI integral overflow errors (#6217) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 13:41:59 UTC, 3 replies.
- [PR] docs: name the AQE query stages on the operator support page [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:03:42 UTC, 1 replies.
- Re: [PR] feat: support bloom filters in native Iceberg writes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:12:22 UTC, 1 replies.
- [I] Recursive CTE: MIN/MAX aggregate dynamic filter survives reset_state, later iterations return wrong results [datafusion] - posted by "alexy (via GitHub)" <gi...@apache.org> on 2026/10/05 14:20:00 UTC, 0 replies.
- [I] ANSI integral SUM overflow reports "integer overflow" without Spark's try_add suggestion [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:22:18 UTC, 2 replies.
- [I] Remove the deprecated bundled statistics providers [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/05 14:30:12 UTC, 4 replies.
- [PR] feat: add a spark.comet.convert config for RowDataSourceScanExec [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:31:16 UTC, 1 replies.
- [PR] feat: enable the Iceberg split-operator write plan by default [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:31:27 UTC, 0 replies.
- [I] Bug triage results: 2026-10-05 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:32:15 UTC, 0 replies.
- [PR] fix: [branch-1.1] stop the leak of Arrow memory from struct outputs of the codegen dispatcher (#6552) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:32:23 UTC, 1 replies.
- [PR] feat: convert OneRowRelation to Arrow by default [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:40:49 UTC, 1 replies.
- Re: [I] [EPIC] Regressions in 1.1.0 since 1.0.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:45:23 UTC, 1 replies.
- [I] Spark 3.4: global aggregate over a single-split Iceberg scan returns no row when DPP prunes the split [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:45:27 UTC, 2 replies.
- [I] Native Iceberg writes: support format-version 3 tables [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:46:19 UTC, 1 replies.
- [I] Native Iceberg writes: write row lineage for copy-on-write DML and compaction on format-version 3 tables [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:46:28 UTC, 1 replies.
- [PR] fix: reset aggregate dynamic filters between recursive iterations [datafusion] - posted by "mikamikasuki (via GitHub)" <gi...@apache.org> on 2026/10/05 14:49:01 UTC, 10 replies.
- Re: [PR] feat: optimize COUNT over constant arguments [datafusion] - posted by "wudidapaopao (via GitHub)" <gi...@apache.org> on 2026/10/05 14:50:57 UTC, 0 replies.
- [PR] feat: [branch-1.1] per-location credentials for native Iceberg reads and writes (#6478) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 14:54:32 UTC, 1 replies.
- [PR] feat: support native Iceberg writes to format-version 3 tables [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:02:09 UTC, 1 replies.
- [PR] fix(cast): fall back for duplicate struct field names [datafusion-comet] - posted by "Samearth17 (via GitHub)" <gi...@apache.org> on 2026/10/05 15:02:59 UTC, 4 replies.
- [I] Kept sort-merge join reads unsorted input after replaceSortMergeJoin rewrites the join below it [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/05 15:21:51 UTC, 1 replies.
- Re: [PR] chore: add benches for remaining agg functions [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:24:46 UTC, 0 replies.
- Re: [PR] test: cover IF branch selection and short-circuiting [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:24:46 UTC, 0 replies.
- Re: [I] [EPIC] Criterion bench coverage for all native expressions [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:24:47 UTC, 0 replies.
- Re: [PR] fix: count the days partition transform in UTC [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:31:16 UTC, 2 replies.
- [I] Codegen dispatcher fails with "Subquery has not finished" when a scalar subquery is inside the dispatched expression [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:31:29 UTC, 0 replies.
- Re: [PR] fix: truncate timestamps around DST transitions the way Spark does [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:31:30 UTC, 0 replies.
- [PR] chore: update the NOTICE copyright year to 2024-2026 [datafusion-comet] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/05 15:32:25 UTC, 1 replies.
- [I] TakeOrderedAndProject fails with "Subquery not found" when the sort order has a scalar subquery and the input has several partitions [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:42:06 UTC, 0 replies.
- [PR] fix: decline native Iceberg writes through a void partition field whose source column was dropped [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:48:31 UTC, 1 replies.
- [PR] build: drop the compiled maven-wrapper.jar by switching to the script-only wrapper [datafusion-comet] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/05 15:51:14 UTC, 4 replies.
- Re: [I] Use Exact Hash-Table Allocation Accounting in `GroupValuesColumn` [datafusion] - posted by "mohitgurav20 (via GitHub)" <gi...@apache.org> on 2026/10/05 15:53:35 UTC, 0 replies.
- [PR] docs: add a contributor guide page on Spark's floating-point semantics [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 15:57:09 UTC, 1 replies.
- [PR] Information schema refactoring [datafusion] - posted by "pepijnve (via GitHub)" <gi...@apache.org> on 2026/10/05 16:13:36 UTC, 0 replies.
- Re: [I] Native Iceberg write fails on a V1 spec that mixes a live field with a void field whose source column was dropped [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 16:18:15 UTC, 2 replies.
- [PR] docs: date the float value and null count divergence to Iceberg 1.9 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 16:19:59 UTC, 1 replies.
- [PR] fix: match Spark's FLOAT and DOUBLE map key rules in native map construction [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 16:32:05 UTC, 4 replies.
- [PR] fix: fall back for nested sort keys whose null elements Spark orders differently [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 16:34:18 UTC, 1 replies.
- [PR] fix: fall back for RANGE frames over nested keys that can hold a null [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 16:34:25 UTC, 1 replies.
- [I] Native shuffle fails with "no more field nodes" on a struct column when it reads converted Spark rows directly [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 16:42:05 UTC, 1 replies.
- [PR] docs: update the timezone page for the fixes from the timezone EPIC [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 16:46:09 UTC, 1 replies.
- [I] Cached AQE queries fail after transition reversion on Spark 4.0+ [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/05 16:56:04 UTC, 0 replies.
- [PR] chore: Add contributor sentiment to contribute [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/05 16:56:31 UTC, 2 replies.
- [PR] SQLite: Reject colon-based semi-structured data traversal [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/05 16:59:50 UTC, 3 replies.
- [I] Wrong results: eliminate_cross_join drops an equi-join key that spans two cross-joined relations [datafusion] - posted by "alexy (via GitHub)" <gi...@apache.org> on 2026/10/05 17:00:05 UTC, 0 replies.
- [PR] fix: have native shuffle read a converted child's Arrow stream [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 17:10:02 UTC, 1 replies.
- Re: [I] Native Iceberg write over-counts NaNs for nested float fields when the input batch is already sliced [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 17:12:31 UTC, 0 replies.
- [PR] chore: raise the native rust-version to 1.95, which iceberg-rust requires [datafusion-comet] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/05 17:16:30 UTC, 1 replies.
- [PR] perf: compare floats in Spark's order without normalizing copies of the operands [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 17:29:18 UTC, 5 replies.
- [I] Plan Iceberg WriteDelta in the split write path and keep it on the JVM DeltaWriter [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/05 17:58:22 UTC, 2 replies.
- [PR] feat(iceberg): plan WriteDelta in the split write path and keep it on the JVM DeltaWriter [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/05 18:02:59 UTC, 3 replies.
- [PR] fix: preserve unassigned inner join keys [datafusion] - posted by "mikamikasuki (via GitHub)" <gi...@apache.org> on 2026/10/05 18:17:22 UTC, 4 replies.
- [I] Support custom vectorized Java UDFs that operate on Arrow vectors [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 18:27:26 UTC, 1 replies.
- Re: [I] Allow users to enable dictionary column reads from parquet files [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/05 18:31:38 UTC, 0 replies.
- [PR] refactor: move the plan entry point logic into core functions [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/05 18:35:45 UTC, 4 replies.
- Re: [PR] test: cover sequence's per-batch element limit and the batch size remedy [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 18:38:43 UTC, 0 replies.
- [PR] feat: support Spark 4.2 insert-only MERGE [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/05 18:42:20 UTC, 2 replies.
- Re: [I] Native Iceberg writer keeps a dictionary page for high-cardinality columns where iceberg-java writes none [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 19:18:19 UTC, 0 replies.
- Re: [PR] Document and enforce compatibility between an aggregate's accumulators [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/05 19:21:07 UTC, 7 replies.
- Re: [I] [EPIC] Substrait: Additional features for producer and consumer for physical plans [datafusion] - posted by "alexandrefimov (via GitHub)" <gi...@apache.org> on 2026/10/05 19:47:24 UTC, 0 replies.
- [PR] Spark, Databricks: allow an interval string without a unit [datafusion-sqlparser-rs] - posted by "moshap-firebolt (via GitHub)" <gi...@apache.org> on 2026/10/05 19:57:42 UTC, 12 replies.
- [PR] feat: custom vectorized Java and Scala UDFs [experimental] [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 20:01:00 UTC, 4 replies.
- [PR] feat: allowlist DataFusion configs, starting with spill compression [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/05 20:11:28 UTC, 2 replies.
- [PR] test: keep the Iceberg job-abort test's wait off Comet's Tokio workers [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 20:15:08 UTC, 2 replies.
- [PR] fix: initialize dispatched kernels with the partition the native plan computes [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/05 20:27:37 UTC, 4 replies.
- Re: [PR] Prototype: physical filter API (PhysicalFilter / FilterConjunct) with optional conjuncts [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/05 20:29:18 UTC, 0 replies.
- [PR] fix: unescape LIKE prefixes before pushing them down as STARTS WITH [datafusion-iceberg] - posted by "CaptainAni187 (via GitHub)" <gi...@apache.org> on 2026/10/05 21:08:55 UTC, 2 replies.
- [PR] fix: preserve DISTINCT semantics in lateral decorrelation [datafusion] - posted by "mikamikasuki (via GitHub)" <gi...@apache.org> on 2026/10/05 21:35:21 UTC, 0 replies.
- [I] Add a "securing DataFusion" documentation [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/05 21:50:54 UTC, 4 replies.
- [PR] perf: Fix performance regression in unary math UDFs [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/05 22:02:01 UTC, 17 replies.
- Re: [I] Add a security policy [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/05 22:33:27 UTC, 0 replies.
- [I] Consider removing the `take` action / open ticket assignment [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/05 22:39:55 UTC, 5 replies.
- [PR] docs: add DataFusion security guidance [datafusion] - posted by "efegokdemir (via GitHub)" <gi...@apache.org> on 2026/10/05 22:52:13 UTC, 12 replies.
- Re: [PR] feat: make the plan nodes inspectable and rebuildable [datafusion-iceberg] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/05 23:19:24 UTC, 12 replies.
- [I] Slow physical planning with many typed NULL struct literals: ScalarValue equality converts nested arrays to ArrayData [datafusion] - posted by "alexy (via GitHub)" <gi...@apache.org> on 2026/10/05 23:34:00 UTC, 1 replies.
- [PR] build(deps): bump rustls from 0.23.44 to 0.23.45 in /native [datafusion-comet] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/05 23:38:27 UTC, 1 replies.
- Re: [I] Fuse the SerializeFromObject / MapElements / DeserializeToObject sandwich into a Comet projection instead of falling back [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 23:41:22 UTC, 0 replies.
- Re: [PR] fix: honor max_row_group_bytes in the parallel Parquet writer [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/05 23:42:05 UTC, 1 replies.
- Re: [I] ANSI integral overflow errors: wrong error class for Byte/Short arithmetic and missing try_ suggestion [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/05 23:48:57 UTC, 0 replies.
- Re: [PR] feat: support `WITH ... AS [NOT] MATERIALIZED` CTEs [datafusion] - posted by "nathanb9 (via GitHub)" <gi...@apache.org> on 2026/10/05 23:52:05 UTC, 17 replies.
- [I] Native Parquet scan: FLOAT and DOUBLE comparisons in data filters don't prune with row-level pushdown [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 00:25:21 UTC, 0 replies.
- Re: [I] RANGE window frames over an array or struct key with a null element span the whole partition [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 00:38:25 UTC, 0 replies.
- Re: [I] Recover date_bin ordering propagation for coarse-precision timestamps [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/06 00:40:20 UTC, 0 replies.
- Re: [I] size, arrays_zip, map_from_arrays and array_append return wrong answers for a nondeterministic child [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/06 00:46:59 UTC, 2 replies.
- [PR] perf: compare nested ScalarValues by type before converting to ArrayData [datafusion] - posted by "alexy (via GitHub)" <gi...@apache.org> on 2026/10/06 00:58:39 UTC, 6 replies.
- [PR] fix: keep a Spark scan unconverted when the plan reads input_file_name [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/06 01:01:35 UTC, 5 replies.
- Re: [I] Remove the per-UDF Mutex serializing Rust UDF batches [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 01:06:29 UTC, 0 replies.
- Re: [I] Add support for custom native UDFs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 01:06:29 UTC, 0 replies.
- Re: [I] A Rust UDF silently answers calls to an ordinary Scala UDF registered under the same name [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 01:06:30 UTC, 0 replies.
- Re: [I] Scope the Rust UDF registry to the session that registered the UDF [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 01:06:30 UTC, 0 replies.
- [PR] fix: handle nested RANGE CURRENT ROW peers [datafusion] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/06 01:38:20 UTC, 12 replies.
- Re: [PR] Allow constant expressions in date_part [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 01:48:09 UTC, 1 replies.
- Re: [PR] Support Preimage for `date_trunc` [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 01:48:13 UTC, 19 replies.
- Re: [PR] feat: native Parquet writes to S3 [datafusion-comet] - posted by "parthchandra (via GitHub)" <gi...@apache.org> on 2026/10/06 01:50:22 UTC, 4 replies.
- Re: [PR] benchmarks: introduce RepartitionExec benchmarks [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/06 02:52:14 UTC, 0 replies.
- [PR] enable flag [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/06 02:58:32 UTC, 16 replies.
- [PR] refactor: Simplify `LimitedDistinctAggregation` optimizer rule [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/06 03:25:02 UTC, 3 replies.
- [I] Codegen dispatcher: run Spark's null guard for a Scala UDF inside the kernel [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 04:06:17 UTC, 1 replies.
- [I] Codegen dispatcher: avoid copying and hashing the serialized expression on every batch [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 04:06:20 UTC, 1 replies.
- [I] Codegen dispatcher: convert boxed primitive Scala UDF parameters without the input encoder [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 04:06:21 UTC, 1 replies.
- [PR] chore(deps): bump insta from 1.48.0 to 1.49.0 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 04:13:54 UTC, 1 replies.
- [PR] chore(deps): bump libc from 0.2.189 to 0.2.190 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 04:14:37 UTC, 1 replies.
- [PR] chore(deps): bump uuid from 1.26.1 to 1.27.0 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 04:14:50 UTC, 1 replies.
- [PR] chore(ci): bump taiki-e/install-action from 2.87.22 to 2.87.23 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 04:16:07 UTC, 1 replies.
- [I] input_file_name() returns empty values over a native Iceberg scan [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 04:30:10 UTC, 2 replies.
- [I] input_file_name() returns empty values above a converted typed Dataset operation [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 04:30:16 UTC, 1 replies.
- [PR] perf: key the codegen dispatcher's kernel cache on a digest of the expression [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 05:03:47 UTC, 5 replies.
- [PR] fix: reject date_bin strides that are not positive [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/06 05:23:22 UTC, 7 replies.
- [I] BaselineMetrics output_bytes converts every column to ArrayData for every batch [datafusion] - posted by "alexy (via GitHub)" <gi...@apache.org> on 2026/10/06 05:28:24 UTC, 1 replies.
- [PR] chore(deps): bump rustls from 0.23.42 to 0.23.45 in /python [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 05:48:28 UTC, 1 replies.
- Re: [I] Substrait decimal arithmetic derives return types that differ from the referenced functions [datafusion] - posted by "alexandrefimov (via GitHub)" <gi...@apache.org> on 2026/10/06 06:19:40 UTC, 0 replies.
- Re: [I] Expression `column_refs` does not return outer referenced columns in subqueries [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 06:20:32 UTC, 0 replies.
- Re: [PR] feat: execute scalar Arrow Python UDFs in native Comet [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/06 06:50:50 UTC, 15 replies.
- Re: [PR] fix: preserve literal metadata and destructure leaf and unary proto hooks [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 06:52:07 UTC, 2 replies.
- Re: [I] Destructure proto hooks for leaf and unary physical expressions [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 07:01:50 UTC, 0 replies.
- Re: [I] Streaming Aggregate operator not being used in deduplication of pre-sorted Parquet files [datafusion] - posted by "cdelmonte-zg (via GitHub)" <gi...@apache.org> on 2026/10/06 07:24:30 UTC, 3 replies.
- Re: [PR] chore(`PartialReduceHashAggregateStream`): convert to async generators and cleanup [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 08:26:36 UTC, 4 replies.
- [I] array_min / array_max fail on a zero-row batch for non-primitive element types [datafusion] - posted by "linuxpi (via GitHub)" <gi...@apache.org> on 2026/10/06 08:30:28 UTC, 0 replies.
- [PR] fix: array_min/array_max on zero rows for non-primitive element types [datafusion] - posted by "linuxpi (via GitHub)" <gi...@apache.org> on 2026/10/06 08:30:34 UTC, 2 replies.
- [PR] Fix GroupOrdering memory descriptor double-counting [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 08:31:50 UTC, 7 replies.
- [PR] chore(deps): bump taiki-e/install-action from 2.87.21 to 2.87.23 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 08:37:50 UTC, 1 replies.
- [PR] chore(deps): bump runs-on/action from 2.3.1 to 2.5.0 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 08:38:31 UTC, 5 replies.
- [PR] chore(deps): bump the all-other-cargo-deps group with 6 updates [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 08:44:34 UTC, 1 replies.
- Re: [I] Rewrite the "Encode metadata, not a handle to a live object" section [datafusion-python] - posted by "Awesome06 (via GitHub)" <gi...@apache.org> on 2026/10/06 08:46:32 UTC, 0 replies.
- [PR] chore(deps): bump proxy-addr from 2.0.7 to 2.0.8 in /datafusion/wasmtest/datafusion-wasm-app [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 09:03:12 UTC, 1 replies.
- [PR] chore(deps): bump compression from 1.8.1 to 1.8.2 in /datafusion/wasmtest/datafusion-wasm-app [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 09:04:21 UTC, 1 replies.
- [PR] docs: rewrite 'Encode metadata, not a handle to a live object' section [datafusion-python] - posted by "Awesome06 (via GitHub)" <gi...@apache.org> on 2026/10/06 09:04:27 UTC, 1 replies.
- Re: [I] Narrowing casts of inferred interval endpoints can reject valid queries [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 09:07:24 UTC, 0 replies.
- Re: [I] Unary negation can eliminate a required sort at the signed minimum [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 09:19:25 UTC, 0 replies.
- [PR] Bench 25413 [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 10:07:31 UTC, 0 replies.
- Re: [PR] DRAFT Bench 25413 [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 10:08:19 UTC, 3 replies.
- Re: [PR] Make `TopKDynamicFilters` public [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 10:18:49 UTC, 4 replies.
- Re: [PR] fix: Emit LIKE the way the Substrait extension defines it [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 10:42:27 UTC, 3 replies.
- Re: [PR] refactor: Simplify `LimitedDistinctAggregation` optimizer rule, push limit in more cases [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/06 11:13:26 UTC, 10 replies.
- [PR] bench: isolate Partial aggregation gains without Final buckets (do not merge) [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/06 11:21:06 UTC, 6 replies.
- Re: [PR] perf: Prune matched right rows in nested loop semi and anti joins [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 11:23:17 UTC, 3 replies.
- [PR] refactor: share one call expression and registration path between native and JVM UDFs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 11:25:13 UTC, 1 replies.
- Re: [PR] test: differential fuzz for leaf expression pushdown and parquet filter pushdown [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 11:46:24 UTC, 2 replies.
- [I] Wrong results from `IN` when a list item is a `CASE` that reads a column [datafusion] - posted by "ranflarion (via GitHub)" <gi...@apache.org> on 2026/10/06 11:53:47 UTC, 1 replies.
- [PR] fix: build the IN list static filter only from literal-only items [datafusion] - posted by "ranflarion (via GitHub)" <gi...@apache.org> on 2026/10/06 11:53:53 UTC, 5 replies.
- Re: [PR] fix: decide the precedence between PushDownFilter and PushDownLeafProjections [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/06 11:57:43 UTC, 3 replies.
- Re: [I] AQE does not coalesce shuffle partitions under a CometUnion when a branch is not a shuffle [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 12:16:40 UTC, 0 replies.
- [I] Proposal: Pluggable SQL statement parsing, planning, and DDL execution [datafusion] - posted by "maver1ck (via GitHub)" <gi...@apache.org> on 2026/10/06 12:20:15 UTC, 2 replies.
- [I] Identical nondeterministic expressions share one codegen dispatcher kernel and continue each other's state [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/06 12:20:26 UTC, 2 replies.
- [PR] fix: give each nondeterministic dispatched expression its own kernel [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/06 12:29:44 UTC, 6 replies.
- Re: [PR] fix: array_sort doesnt respect array inputs for sort order/nulls first [datafusion] - posted by "JSOD11 (via GitHub)" <gi...@apache.org> on 2026/10/06 12:43:40 UTC, 4 replies.
- [PR] fix: [branch-1.1] let a spilled final aggregate read its spill files back past its memory share (#6544) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 12:46:15 UTC, 1 replies.
- Re: [I] BUG: DELETE with a LIMIT clause ignores the LIMIT and deletes every matching row [datafusion] - posted by "martin-g (via GitHub)" <gi...@apache.org> on 2026/10/06 13:15:59 UTC, 0 replies.
- [I] Should `DELETE + LIMIT` be supported by the generic dialect [datafusion-sqlparser-rs] - posted by "martin-g (via GitHub)" <gi...@apache.org> on 2026/10/06 13:22:41 UTC, 0 replies.
- Re: [I] Native sort orders null elements of array and struct keys by the key's null order, unlike Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 13:35:30 UTC, 0 replies.
- Re: [I] Native Iceberg write silently drops S3 settings it cannot honour (credentials provider, SSE, ACL, tags, remote signing) instead of falling back [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 13:48:28 UTC, 0 replies.
- Re: [I] push_down_filter and common_sub_expression_eliminate fight between them [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/06 13:59:52 UTC, 0 replies.
- [PR] fix: `PushDownLeafProjections` yields when the extraction cannot move [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/06 14:04:32 UTC, 4 replies.
- [PR] perf: skip Spark's encoders for boxed primitive Scala UDF values in the codegen dispatcher [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 14:04:37 UTC, 1 replies.
- [PR] perf: run Spark's null guard for a Scala UDF inside the codegen kernel [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 14:05:53 UTC, 8 replies.
- [PR] fix: skip an array or map function's later arguments where the array or map is NULL [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 14:06:14 UTC, 13 replies.
- Re: [I] Let the data source veto `ExpressionPlacement::MoveTowardsLeafNodes` per function [datafusion] - posted by "joseph-isaacs (via GitHub)" <gi...@apache.org> on 2026/10/06 14:48:50 UTC, 1 replies.
- [I] Vectorize the lower-bound check in native date_trunc for fine units [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 14:52:31 UTC, 0 replies.
- Re: [PR] feat: expose per-scan S3 HTTP attempts and retries [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 14:57:19 UTC, 1 replies.
- Re: [PR] docs: check timezone handling against the contributor guide in the PR review skills [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 15:06:17 UTC, 0 replies.
- Re: [I] Spark errors after the first batch of a JVM input stream reach the user as CometNativeException [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 15:06:19 UTC, 0 replies.
- [PR] test: generate NULLs in equivalence fuzz tests [datafusion] - posted by "Nagato-Yuzuru (via GitHub)" <gi...@apache.org> on 2026/10/06 15:06:51 UTC, 3 replies.
- Re: [PR] feat: charge native write buffers to the task's memory pool [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 15:11:17 UTC, 0 replies.
- Re: [I] Account the native Iceberg writer's buffers in Comet's memory pool [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 15:11:19 UTC, 0 replies.
- Re: [I] Charge native write buffers to the shared off-heap memory pool [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 15:11:20 UTC, 0 replies.
- Re: [I] [Epic] Fuzz data generators never produce NULLs [datafusion] - posted by "Nagato-Yuzuru (via GitHub)" <gi...@apache.org> on 2026/10/06 15:17:01 UTC, 0 replies.
- [I] Decide scan parallelism from the estimated row count, not from statistics precision [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/06 15:31:31 UTC, 0 replies.
- [I] Broadcast hash join on string keys drops rows when the build side is a large DISTINCT [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/06 15:44:45 UTC, 4 replies.
- [I] Iceberg data tables whose names end with a metadata-table name fall back to Spark [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/06 15:44:47 UTC, 1 replies.
- Re: [PR] feat: add a spill compression codec config, defaulting to lz4 [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/06 15:50:44 UTC, 3 replies.
- [I] Reuse Arrow buffers across batches in Spark-to-Arrow conversion instead of reallocating and zeroing them [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 16:02:02 UTC, 0 replies.
- [I] Write strings and nested values in bulk when converting Spark rows to Arrow [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 16:02:05 UTC, 1 replies.
- [I] Admit all array and map types in CometSparkToColumnarExec [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 16:02:14 UTC, 0 replies.
- [I] Row-input conversionTime metric includes the time the child spends producing rows [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 16:02:18 UTC, 0 replies.
- Re: [PR] Add Apache DataFusion Comet 1.1.0 release blog post [datafusion-site] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/06 16:20:44 UTC, 1 replies.
- [I] Native Iceberg scan reads every field of a nested column even when Spark prunes it [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/06 16:34:58 UTC, 1 replies.
- [PR] perf: read only the nested fields Spark keeps in the native Iceberg scan [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/06 16:45:39 UTC, 24 replies.
- [I] Narrow multi-column NOT IN UNKNOWN checks by treating NOT NULL tuple elements as scope keys [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/06 16:54:50 UTC, 1 replies.
- [I] Build multi-column null-aware NOT IN on the subquery side (multi-key null-aware RightAnti) [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/06 16:54:51 UTC, 2 replies.
- [PR] feat: admit every array and map type in Spark-to-Comet conversion [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 17:13:17 UTC, 6 replies.
- [I] Explore Kubernetes in-place pod memory resize (Spark 4.2 ExecutorResizePlugin) for Comet's untracked native memory [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 17:31:16 UTC, 0 replies.
- [PR] feature(physical-plan): add NullAwareMode to SortMergeJoinExec [datafusion] - posted by "TinyMurky (via GitHub)" <gi...@apache.org> on 2026/10/06 17:34:24 UTC, 2 replies.
- [PR] docs: add 1.1.0 changelog [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 17:35:38 UTC, 1 replies.
- [I] feat: Treat all NaNs as the same value (`-NaN = NaN`) [datafusion] - posted by "mkleen (via GitHub)" <gi...@apache.org> on 2026/10/06 17:53:13 UTC, 2 replies.
- [PR] perf: reuse Arrow buffers across batches in Spark-to-Arrow conversion [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 17:56:23 UTC, 4 replies.
- [PR] docs(bench): add a Trino 483 column to the TPC-H SF1000 results [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 17:59:36 UTC, 2 replies.
- Re: [I] Consolidate date/timestamp truncation and xxhash64 with upstream DataFusion implementations [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/06 18:06:48 UTC, 0 replies.
- Re: [PR] feat: enable the Iceberg split-operator plan and native writes by default [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 18:10:37 UTC, 7 replies.
- [PR] perf: convert Spark's unsafe rows to Arrow straight from their memory [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 18:14:19 UTC, 14 replies.
- [PR] test: add optimizer controls and config isolation to SQL fixtures [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/06 18:30:27 UTC, 1 replies.
- Re: [PR] fix: resolve Azure ABFS authentication through Hadoop and keep ambient credentials out [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/06 18:31:01 UTC, 8 replies.
- [PR] fix: include try_add suggestion in ANSI SUM overflow error [datafusion-comet] - posted by "DeviousCardi (via GitHub)" <gi...@apache.org> on 2026/10/06 18:45:17 UTC, 7 replies.
- [PR] perf: backport bitmap pruning for runtime join filters [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/06 18:47:13 UTC, 1 replies.
- [PR] docs: add AI-assisted contributions page to the contributor guide [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 18:59:20 UTC, 8 replies.
- [PR] feat: run nullable nested float sort keys natively in strict floating-point mode [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 19:09:30 UTC, 9 replies.
- [PR] chore: update documentation links for 1.1.0 release [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 19:09:57 UTC, 1 replies.
- Re: [PR] perf: retain batched build storage for large hash joins [datafusion] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/06 19:12:06 UTC, 0 replies.
- Re: [PR] [final state] optional filters stack (do not merge) [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/06 19:24:00 UTC, 0 replies.
- [PR] Preserve list element metadata when rebuilding scalar values [datafusion] - posted by "osipovartem (via GitHub)" <gi...@apache.org> on 2026/10/06 19:24:47 UTC, 3 replies.
- Re: [I] Dictionary performance improvement tickets [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/06 19:26:35 UTC, 2 replies.
- Re: [I] Null treatment of `sort` does not follow DataFusion's default [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/06 19:26:39 UTC, 0 replies.
- [PR] chore(deps): bump urllib3 from 2.6.3 to 2.8.0 [datafusion-sandbox] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 19:32:21 UTC, 0 replies.
- Re: [PR] chore(deps): bump urllib3 from 2.6.3 to 2.7.0 [datafusion-sandbox] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/06 19:32:26 UTC, 1 replies.
- Re: [I] Iceberg plan nodes can't be rebuilt by a PhysicalExtensionCodec [datafusion-iceberg] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/06 19:43:47 UTC, 0 replies.
- Re: [PR] feat(datafusion): make IcebergTableProvider::try_new public [datafusion-iceberg] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/06 19:44:30 UTC, 1 replies.
- [PR] Fix/exact hashtable accounting group values column [datafusion] - posted by "mohitgurav20 (via GitHub)" <gi...@apache.org> on 2026/10/06 19:48:40 UTC, 0 replies.
- [I] Design question: long-term, should native Iceberg scans run through DataFusion's ParquetSource instead of iceberg-rust's ArrowReader? [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/06 20:11:33 UTC, 6 replies.
- [I] Native `mode` treats all NaNs as one value on Spark 3.4, where Spark counts each NaN separately [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 20:12:21 UTC, 0 replies.
- Re: [PR] fix: use HashTable::allocation_size() in GroupValuesColumn::size() [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/06 20:16:54 UTC, 0 replies.
- [PR] perf: share one StatisticsContext across all physical optimizer rules [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/06 20:17:56 UTC, 35 replies.
- [PR] fix: project columns correctly when scanning iceberg table metadata [datafusion-iceberg] - posted by "Perseus (via GitHub)" <gi...@apache.org> on 2026/10/06 20:20:33 UTC, 19 replies.
- [I] date_trunc SECOND/MILLISECOND wraps on Spark 4.2, where Spark raises long overflow [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 20:29:28 UTC, 1 replies.
- [PR] fix: match Spark 4.2 date_trunc overflow for SECOND and MILLISECOND [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 20:32:09 UTC, 12 replies.
- [PR] Spark, Databricks: parse multi-unit interval literals [datafusion-sqlparser-rs] - posted by "moshap-firebolt (via GitHub)" <gi...@apache.org> on 2026/10/06 20:59:08 UTC, 1 replies.
- [I] [Bug] Native make_date mishandles Date32 overflow and skipped evaluation [datafusion-comet] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/06 22:37:57 UTC, 1 replies.
- [PR] fix: Return NULL for empty BIT_XOR sliding windows [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/06 22:49:14 UTC, 3 replies.
- [I] warning: package `chacha20 v0.10.1` in Cargo.lock is yanked in registry `crates-io` [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 23:00:58 UTC, 1 replies.
- Re: [I] revertToSpark erases CometIcebergWriteExec / CometNativeWriteExec because originalPlan is the node's own child [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 23:37:33 UTC, 0 replies.
- Re: [I] RevertNativeForTransitionHeavyStages strips transitions in the stage below when AQE is off [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 23:37:34 UTC, 0 replies.
- [I] Scan tasks are skewed when Parquet statistics prune most files: file groups are built before pruning [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 23:38:18 UTC, 1 replies.
- [PR] docs: add 55.0.0 changelog to main [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/06 23:38:52 UTC, 1 replies.
- [PR] feat: add IcebergTableProvider::new_with_schema [datafusion-iceberg] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/07 00:09:44 UTC, 2 replies.
- [PR] perf(bench): register Hive partition columns in the TPC-H runner [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 00:23:18 UTC, 5 replies.
- [I] ShuffleWriterExec doesn't compact Utf8View columns, so small results can exceed the 16 MiB gRPC limit [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 00:45:58 UTC, 1 replies.
- Re: [I] days transform is evaluated in the session timezone, while hours and Iceberg use UTC [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 01:20:49 UTC, 0 replies.
- [PR] fix: downcast to FixedSizeBinaryArray in CASE literal lookup table [datafusion] - posted by "patrickswedish (via GitHub)" <gi...@apache.org> on 2026/10/07 01:22:35 UTC, 4 replies.
- [I] arrays_overlap returns wrong answers or panics with a constant array beside a column [datafusion-comet] - posted by "grorge123 (via GitHub)" <gi...@apache.org> on 2026/10/07 01:23:12 UTC, 0 replies.
- [PR] fix: compare every row when arrays_overlap gets a scalar beside a column [datafusion-comet] - posted by "grorge123 (via GitHub)" <gi...@apache.org> on 2026/10/07 01:23:29 UTC, 2 replies.
- Re: [I] Ballista 55.0.0 Release [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/07 01:49:53 UTC, 1 replies.
- Re: [PR] feat(physical-plan): expose finalized Accumulator state on BoundedWindowAggExec [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 01:54:12 UTC, 0 replies.
- Re: [PR] fix(parquet): cache deferred page index loads [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 01:54:14 UTC, 0 replies.
- Re: [PR] [branch-54] Fix evaluation of lambda with multiple parameters when some are unused (backport of #22853, adapted) [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 01:54:17 UTC, 1 replies.
- Re: [I] Support multi-column (tuple) NOT IN subqueries with null-aware semantics [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/07 02:08:41 UTC, 0 replies.
- [I] Discover Hive partitions like Spark: allow partition columns stored in the files, and infer their types [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 02:31:27 UTC, 0 replies.
- [PR] fix(scheduler): gather Prometheus metrics from the collector's registry [datafusion-ballista] - posted by "Richard-Durkee (via GitHub)" <gi...@apache.org> on 2026/10/07 02:49:19 UTC, 1 replies.
- [PR] fix(core): compact sparse view columns in passthrough shuffle writers [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 03:02:14 UTC, 4 replies.
- [PR] perf: benchmark partial byte threshold on top of #25724 [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/07 03:10:49 UTC, 6 replies.
- [PR] fix(scheduler): prune scan files by statistics and balance file groups [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 04:02:13 UTC, 6 replies.
- [PR] chore(deps): bump tokio from 1.53.1 to 1.53.2 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 04:14:53 UTC, 1 replies.
- [PR] chore(deps): bump tokio from 1.53.1 to 1.53.2 in /python [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 04:15:13 UTC, 1 replies.
- [PR] chore(ci): bump taiki-e/install-action from 2.87.23 to 2.87.24 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 04:16:54 UTC, 1 replies.
- [PR] bench: isolate continuous partial flushing against main [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/07 05:07:58 UTC, 8 replies.
- Re: [I] Improve documentation for StatisticsRegistry, ExtendedStatistics, and StatisticsContext::compute_extended [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/07 06:00:46 UTC, 0 replies.
- [PR] Refactor DataFusion crate folder structure [datafusion-iceberg] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/07 06:26:03 UTC, 2 replies.
- [PR] Migrate Iceberg reads to DataSource [datafusion-iceberg] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/07 06:26:33 UTC, 0 replies.
- Re: [PR] fix(substrait): roundtrip conditionless joins [datafusion] - posted by "bvolpato (via GitHub)" <gi...@apache.org> on 2026/10/07 06:31:00 UTC, 2 replies.
- [I] Account for retained sort-key capacity [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/07 07:14:28 UTC, 1 replies.
- [PR] bench: isolate partial flush row and byte thresholds on main [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/07 07:32:23 UTC, 13 replies.
- [I] Tracked `.envrc` from #26005 silently overwrites contributors' local direnv config [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/07 07:40:00 UTC, 1 replies.
- [I] Nightly CI failed on 2026-10-07 [datafusion-comet] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 07:41:53 UTC, 2 replies.
- Re: [PR] fix: keep a DISTINCT aggregate's arity in `SingleDistinctToGroupBy` [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/07 08:14:02 UTC, 3 replies.
- [PR] doc: Improve docs for configuration 'max_passes' [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/07 08:16:27 UTC, 3 replies.
- [I] Parquet schema inference marks a column NOT NULL when it is missing from some files, making the table unreadable [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/07 08:22:45 UTC, 2 replies.
- [PR] fix: infer a Parquet column as nullable when some files lack it [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/07 08:22:59 UTC, 9 replies.
- [PR] Perf/26071 avoid arraydata conversion [datafusion] - posted by "minhh-nguyen (via GitHub)" <gi...@apache.org> on 2026/10/07 08:29:33 UTC, 0 replies.
- Re: [PR] Add TrinoDialect [datafusion-sqlparser-rs] - posted by "rexminnis (via GitHub)" <gi...@apache.org> on 2026/10/07 08:30:15 UTC, 2 replies.
- Re: [PR] fix: preserve null treatment when unparsing window and aggregate functions [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/07 08:30:52 UTC, 3 replies.
- [I] JoinSelection should skip HashJoinExec nodes that already carry a dynamic filter instead of failing in swap_inputs [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/07 08:41:51 UTC, 8 replies.
- Re: [I] Placeholder datatype not inferred after `LIMIT` clause [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/07 08:43:32 UTC, 0 replies.
- Re: [PR] fix: keep renamed columns intact in leaf projection pushdown [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/07 08:54:42 UTC, 2 replies.
- [PR] test: preserve regex escapes in SQL fixtures [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/07 08:58:09 UTC, 2 replies.
- [PR] doc: Document the physical optimizer contract [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/07 08:58:21 UTC, 18 replies.
- Re: [PR] DataFrame API: allow aggregate functions in select() 2 (#17874) [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/07 09:07:53 UTC, 5 replies.
- Re: [PR] feat: enable native Iceberg writes by default [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 09:08:15 UTC, 18 replies.
- Re: [PR] perf: copy bitmaps a word at a time in `pre_selection_scatter` [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 09:11:36 UTC, 13 replies.
- [I] Preserve ordering through `to_timestamp_micros` and `to_unixtime` [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/07 09:15:39 UTC, 1 replies.
- [PR] perf: reuse StringView storage across partial flushes [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/07 09:18:55 UTC, 5 replies.
- Re: [PR] fix: give a multi-set aggregate the grouping set index Substrait defines [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/07 09:24:46 UTC, 11 replies.
- [PR] fix(executor): cached session runtime ignores SET s3.* changes [datafusion-ballista] - posted by "goingforstudying-ctrl (via GitHub)" <gi...@apache.org> on 2026/10/07 09:27:08 UTC, 5 replies.
- Re: [PR] test: cover CrossJoinExec row metrics across batched inputs [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 09:29:04 UTC, 5 replies.
- [PR] DiskManager: include the description in file names [datafusion] - posted by "Tpt (via GitHub)" <gi...@apache.org> on 2026/10/07 09:47:12 UTC, 13 replies.
- [PR] feat: preserve ordering through to_timestamp_micros and to_unixtime [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/07 10:23:03 UTC, 0 replies.
- [PR] perf: reserve group-key storage across partial flushes [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/07 10:23:23 UTC, 8 replies.
- Re: [PR] feat: preserve ordering through `to_timestamp_micros` and `to_unixtime` [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/07 10:49:51 UTC, 0 replies.
- [PR] ClickHouse: Support ON CLUSTER and SETTINGS in DELETE and UPDATE [datafusion-sqlparser-rs] - posted by "jordiori (via GitHub)" <gi...@apache.org> on 2026/10/07 11:23:58 UTC, 7 replies.
- Re: [PR] Enable more clippy lints (part 1/3) [datafusion] - posted by "emilk (via GitHub)" <gi...@apache.org> on 2026/10/07 11:48:45 UTC, 0 replies.
- [PR] chore(deps): bump the all-other-cargo-deps group with 3 updates [datafusion-iceberg] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 12:25:55 UTC, 4 replies.
- Re: [I] A DELETE or an UPDATE with an IN or an EXISTS subquery in its WHERE clause changes every row [datafusion] - posted by "martin-g (via GitHub)" <gi...@apache.org> on 2026/10/07 12:26:14 UTC, 1 replies.
- [PR] chore(docs): Remove entries for two known limitations which were fixed recently [datafusion] - posted by "martin-g (via GitHub)" <gi...@apache.org> on 2026/10/07 12:33:15 UTC, 3 replies.
- [I] Native Parquet scan reads files from another bucket when one partition spans buckets [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/07 12:47:52 UTC, 2 replies.
- [I] Native CSV scan reads every partition through the first partition's object store [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/07 12:51:34 UTC, 2 replies.
- Re: [PR] Add blog post: The Arrow C Data Interface: Zero-Copy Between Rust and the JVM in DataFusion Comet [datafusion-site] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 13:21:22 UTC, 0 replies.
- Re: [I] Duplicate expression in an ordered aggregate's `ORDER BY` panics (`first_last.rs:602` assertion) or fails with an internal Arrow error [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/07 13:25:52 UTC, 0 replies.
- [PR] bench: Various improvements to trim, substr, split_part benchmarks [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/07 13:38:51 UTC, 0 replies.
- Re: [PR] bench: Various improvements to `trim`, `substr`, `split_part` benchmarks [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/07 14:10:55 UTC, 2 replies.
- [I] SortMergeJoin misses rows for nested float keys containing -0.0 [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/07 14:18:55 UTC, 0 replies.
- [PR] perf: flush partial batches with fixed group capacity (experiment) [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/07 14:28:48 UTC, 51 replies.
- [PR] docs(bench): refresh TPC-H SF1000 results at c76278cd [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 15:04:31 UTC, 1 replies.
- Re: [I] [substrait] Scalar subquery in select not supported [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/07 15:27:45 UTC, 0 replies.
- [PR] ci: add ty type checker and fix existing type errors [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/07 15:29:00 UTC, 5 replies.
- [PR] docs(bench): say the Spark, Comet, and Trino harness is not in the repo yet [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 15:29:06 UTC, 1 replies.
- [PR] chore(deps): bump shell-quote from 1.10.0 to 1.12.0 in /datafusion/wasmtest/datafusion-wasm-app [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 15:41:19 UTC, 1 replies.
- [I] Extend per-scan HTTP attempt and retry metrics to native Azure and GCS [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/07 15:44:40 UTC, 0 replies.
- Re: [PR] perf: Concretely typed TopK StringHeap, and StringHashTable slot reuse [datafusion] - posted by "MassivePizza (via GitHub)" <gi...@apache.org> on 2026/10/07 15:54:29 UTC, 8 replies.
- [PR] chore(deps): bump rustls from 0.23.44 to 0.23.45 [datafusion-iceberg] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/07 16:01:15 UTC, 1 replies.
- Re: [PR] feat: expose per-scan S3 HTTP coverage and retries [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/07 16:01:58 UTC, 3 replies.
- Re: [I] Comparison operators on arrays and structs with floating-point leaves do not match Spark for signed zero [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 16:02:03 UTC, 0 replies.
- [I] Spark SQL Writer Tests (manual) never runs Comet's native writer [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 16:03:11 UTC, 0 replies.
- [I] Add an end-to-end HDFS write test for both native Parquet writers [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 16:03:13 UTC, 0 replies.
- [I] Native Parquet writes on Spark 3.4/3.5 ignore maxRecordsPerFile [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 16:03:15 UTC, 0 replies.
- [PR] Preserve required sorts above custom execution plans [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/07 16:03:42 UTC, 3 replies.
- [I] Stop ending Spark-to-Arrow batches at input file boundaries [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 16:18:51 UTC, 0 replies.
- [PR] docs: Update release README examples to 55.2.0 and add SVN download steps [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/07 16:22:08 UTC, 0 replies.
- Re: [PR] fix: preserve only the maintained input ordering in joins [datafusion] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/07 16:23:26 UTC, 1 replies.
- [PR] feat(bench): time TPC-DS queries and share the runner code with TPC-H [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 16:24:01 UTC, 3 replies.
- Re: [PR] fix: align Spark collect aggregate element nullability [datafusion] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/07 16:24:11 UTC, 0 replies.
- [PR] PostgreSQL: Add support for DO statement [datafusion-sqlparser-rs] - posted by "devtechedge (via GitHub)" <gi...@apache.org> on 2026/10/07 16:30:36 UTC, 15 replies.
- Re: [I] Review use of hard-coded UTC assumptions [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 16:40:17 UTC, 1 replies.
- Re: [PR] fix: stop treating arithmetic negation as bitwise NOT [datafusion] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/07 16:46:52 UTC, 0 replies.
- [PR] feat!: remove spark-compat feature and Spark compatibility docs [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 17:05:32 UTC, 3 replies.
- [PR] fix: read each native scan partition through the object store its files live in [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/07 17:06:39 UTC, 15 replies.
- Re: [PR] docs: Update release README examples to 55.2.0 and add SVN commands [datafusion] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/07 17:15:34 UTC, 8 replies.
- Re: [PR] fix: truncate per-row date_trunc formats with the literal-format kernel [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 17:16:02 UTC, 7 replies.
- Re: [I] PartitionedTopKRank over-accounts memory when a single batch has boundary ties across many partitions [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/07 17:31:42 UTC, 1 replies.
- [PR] feat(scheduler): add a cache registry for DataFrame.cache() [datafusion-ballista] - posted by "akshaychitneni (via GitHub)" <gi...@apache.org> on 2026/10/07 17:34:56 UTC, 25 replies.
- [PR] chore: Add "Willingness to contribute" dropdown to issue templates [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/07 17:35:44 UTC, 6 replies.
- [PR] fix: fall back from native V2 scans when the plan reads input_file_name [datafusion-comet] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/07 18:01:15 UTC, 4 replies.
- [PR] perf: Use `sub_view` in `trim`, `substr`, `split_part`, and `substring_index` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/07 18:33:13 UTC, 3 replies.
- Re: [PR] fix: retry a shuffle page allocation that Spark failed after dropping the task's entry [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/07 18:43:05 UTC, 2 replies.
- Re: [PR] fix: retry a native acquire that Spark failed after dropping the task's entry [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/07 18:47:05 UTC, 3 replies.
- Re: [PR] perf: charge the local shuffle writer's buffers to the memory pool [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/07 18:51:32 UTC, 1 replies.
- [I] Codegen dispatcher: run more Scala UDF null-guard shapes inside the kernel [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 19:06:58 UTC, 0 replies.
- [I] spark.comet.expression..enabled has no effect on expressions inside a codegen-dispatched tree [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 19:07:07 UTC, 0 replies.
- [PR] fix: preserve local direnv settings [datafusion] - posted by "VVKot (via GitHub)" <gi...@apache.org> on 2026/10/07 19:24:46 UTC, 9 replies.
- [PR] fix: skip HashJoinExec nodes carrying dynamic filters in JoinSelection [datafusion] - posted by "siddubakka (via GitHub)" <gi...@apache.org> on 2026/10/07 19:26:59 UTC, 27 replies.
- Re: [I] [EPIC] Use blocked / chunked memory management in hash aggregation [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/07 19:27:52 UTC, 11 replies.
- [I] Explore proactive flushing for Partial hash aggregation [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/07 19:38:18 UTC, 0 replies.
- Re: [PR] GC & Deduplicate String View on Spill [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/07 19:39:35 UTC, 0 replies.
- Re: [I] External sort spill GC inflates deduplicated string views [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/07 19:39:37 UTC, 0 replies.
- Re: [I] Implement cache-efficient partial aggregation by Leis et al [datafusion] - posted by "Rachelint (via GitHub)" <gi...@apache.org> on 2026/10/07 19:44:09 UTC, 0 replies.
- [I] perf: converting unsafe arrays of maps to Arrow is up to 1.7x slower when C2 inlines MapWriter.writeEntries [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 19:51:09 UTC, 1 replies.
- Re: [PR] perf: buffer the NestedLoopJoin build side as coalesced chunks instead of one concat_batches allocation [datafusion] - posted by "ranflarion (via GitHub)" <gi...@apache.org> on 2026/10/07 19:59:22 UTC, 1 replies.
- [I] Spark `char` fails on a NULL scalar argument [datafusion] - posted by "ranflarion (via GitHub)" <gi...@apache.org> on 2026/10/07 20:00:12 UTC, 1 replies.
- [PR] fix(spark): return NULL from `char` for a NULL scalar argument [datafusion] - posted by "ranflarion (via GitHub)" <gi...@apache.org> on 2026/10/07 20:00:27 UTC, 2 replies.
- [I] greatest/least compare struct arguments by field name instead of position when names differ only in case [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/07 20:12:55 UTC, 1 replies.
- [I] least orders a null inside a struct or array last, where Spark orders it first [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/07 20:12:57 UTC, 1 replies.
- [PR] fix: compare greatest and least struct arguments by position [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/07 20:13:26 UTC, 4 replies.
- [PR] fix: order nulls inside nested values first in least [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/07 20:13:31 UTC, 11 replies.
- [I] IN treats a column-dependent CASE WHEN / IF candidate as the constant NULL [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/07 20:24:06 UTC, 1 replies.
- [PR] fix: return an empty array from CASE WHEN for an empty batch [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/07 20:24:19 UTC, 8 replies.
- Re: [PR] test: add Iceberg integration fixture [datafusion-iceberg] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/07 20:53:03 UTC, 2 replies.
- [PR] fix: match Spark's ANSI integral SUM overflow error [datafusion-comet] - posted by "0lai0 (via GitHub)" <gi...@apache.org> on 2026/10/07 21:13:52 UTC, 3 replies.
- Re: [I] [Bug] next_day rejects STRING and TIMESTAMP start dates that Spark accepts [datafusion] - posted by "harsh-ande (via GitHub)" <gi...@apache.org> on 2026/10/07 21:14:37 UTC, 0 replies.
- Re: [I] Iceberg native scan claims schemes it cannot execute; three scheme lists disagree [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 21:36:00 UTC, 0 replies.
- [PR] fix(spark): accept STRING and TIMESTAMP start dates in next_day [datafusion] - posted by "harsh-ande (via GitHub)" <gi...@apache.org> on 2026/10/07 21:36:51 UTC, 6 replies.
- Re: [PR] fix: align nested types by position and preserve struct nullability [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/07 21:38:36 UTC, 3 replies.
- Re: [PR] chore(deps): bump pydata-sphinx-theme from 0.20.0 to 0.21.0 in the all-uv-deps group across 1 directory [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/07 21:43:39 UTC, 0 replies.
- [I] [datafusion-spark] unix_millis / unix_seconds truncate toward zero instead of flooring for pre-epoch timestamps [datafusion] - posted by "harsh-ande (via GitHub)" <gi...@apache.org> on 2026/10/07 22:29:32 UTC, 1 replies.
- [I] perf: reuse the nested unsafe views in ArrowWriter's row path, detaching them once per row [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 22:37:55 UTC, 0 replies.
- Re: [I] `LimitPushdown` can return incorrect rows for fetched `SortPreservingMergeExec` over ordered Parquet scans [datafusion] - posted by "sagiba (via GitHub)" <gi...@apache.org> on 2026/10/07 22:39:52 UTC, 1 replies.
- [PR] Parser: fix exponential parse time on nested POSITION calls [datafusion-sqlparser-rs] - posted by "fmcmac (via GitHub)" <gi...@apache.org> on 2026/10/07 22:47:36 UTC, 5 replies.
- [PR] fix(spark): floor instead of truncate in unix_millis/unix_seconds for pre-epoch timestamp [datafusion] - posted by "harsh-ande (via GitHub)" <gi...@apache.org> on 2026/10/07 22:50:49 UTC, 6 replies.
- [PR] chore(deps): bump DataFusion to 55.2.0 [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 23:34:48 UTC, 1 replies.
- [I] Prune files by statistics in `ListingTable` before building file groups [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 23:43:39 UTC, 8 replies.
- [PR] deps: bump to datafusion 55.2.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/07 23:48:12 UTC, 1 replies.
- Re: [PR] fix: align nested piecewise merge join sorting and comparison [datafusion] - posted by "mikamikasuki (via GitHub)" <gi...@apache.org> on 2026/10/07 23:59:37 UTC, 4 replies.
- [I] Warn when unrecognized spark.comet.* configuration keys are set [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 00:03:51 UTC, 0 replies.
- [PR] feat(core): support DESCRIBE table by planning it on the client [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 00:15:57 UTC, 2 replies.
- Re: [PR] fix: Route collated array element comparisons through the codegen dispatcher [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/08 00:28:07 UTC, 1 replies.
- Re: [I] array_contains, arrays_overlap, array_distinct and array_union ignore string collation [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/08 00:28:09 UTC, 0 replies.
- Re: [PR] Brent/query shape viz [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/08 02:03:05 UTC, 1 replies.
- [PR] chore(ci): bump taiki-e/install-action from 2.87.24 to 2.87.25 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/08 04:15:12 UTC, 2 replies.
- [I] Simplify contradictory ranges across AND/OR predicates to prune empty UNION ALL branches [datafusion] - posted by "xudong963 (via GitHub)" <gi...@apache.org> on 2026/10/08 04:43:50 UTC, 1 replies.
- Re: [I] Improve parquet row group pruning metrics display [datafusion] - posted by "xudong963 (via GitHub)" <gi...@apache.org> on 2026/10/08 04:53:36 UTC, 0 replies.
- [PR] feat: simplify contradictory ranges across AND/OR predicates [datafusion] - posted by "xudong963 (via GitHub)" <gi...@apache.org> on 2026/10/08 05:30:03 UTC, 7 replies.
- Re: [PR] refactor: share join input unparsing [datafusion] - posted by "Xuanwo (via GitHub)" <gi...@apache.org> on 2026/10/08 05:56:26 UTC, 1 replies.
- [PR] perf: Partitioned topk emit row number [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/08 06:18:38 UTC, 12 replies.
- Re: [PR] perf: optimize aggregate functions over constant arguments [datafusion] - posted by "wudidapaopao (via GitHub)" <gi...@apache.org> on 2026/10/08 08:23:26 UTC, 0 replies.
- Re: [PR] fix: preserve ABFS container in object store registry keys [datafusion] - posted by "847850277 (via GitHub)" <gi...@apache.org> on 2026/10/08 08:50:08 UTC, 0 replies.
- Re: [I] [EPIC] Add support for all join operators [datafusion-comet] - posted by "judahrand (via GitHub)" <gi...@apache.org> on 2026/10/08 08:56:25 UTC, 0 replies.
- [I] Panic with 64-column GROUPING SETS [datafusion] - posted by "alexandrefimov (via GitHub)" <gi...@apache.org> on 2026/10/08 09:40:27 UTC, 1 replies.
- [I] GROUPING can panic with 65 grouping columns [datafusion] - posted by "alexandrefimov (via GitHub)" <gi...@apache.org> on 2026/10/08 09:40:55 UTC, 1 replies.
- Re: [I] Provide valid extensionUris and extensionUriReferences in Substrait [datafusion] - posted by "alexandrefimov (via GitHub)" <gi...@apache.org> on 2026/10/08 10:14:49 UTC, 0 replies.
- Re: [PR] feat(window-topn): streaming per-partition top-K for pre-sorted input [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/08 10:24:10 UTC, 0 replies.
- [I] Ballista-cli 55.0.0 has not been released [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/08 11:00:14 UTC, 2 replies.
- [PR] fix: avoid shifting zero grouping ordinals by 64 [datafusion] - posted by "alexandrefimov (via GitHub)" <gi...@apache.org> on 2026/10/08 11:13:33 UTC, 5 replies.
- [PR] fix: reject GROUPING masks wider than 64 bits [datafusion] - posted by "alexandrefimov (via GitHub)" <gi...@apache.org> on 2026/10/08 11:15:57 UTC, 6 replies.
- Re: [PR] Add xmlnamespace support mssql [datafusion-sqlparser-rs] - posted by "kfirSatori (via GitHub)" <gi...@apache.org> on 2026/10/08 11:24:39 UTC, 1 replies.
- Re: [I] [EPIC] Attach `Diagnostic` to more errors [datafusion] - posted by "haochunchang (via GitHub)" <gi...@apache.org> on 2026/10/08 11:42:01 UTC, 1 replies.
- Re: [D] Policy on uptick of LLM PRs from new contributors [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/08 12:14:05 UTC, 3 replies.
- Re: [I] Attach `Diagnostic` to "duplicate table name" error [datafusion] - posted by "haochunchang (via GitHub)" <gi...@apache.org> on 2026/10/08 12:21:17 UTC, 1 replies.
- [I] arrays_overlap keeps -0.0 and 0.0 apart on Spark 4.0.5, 4.1.4 and 4.2.1, which merge them (SPARK-59602) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 12:41:56 UTC, 2 replies.
- [I] Native sequence raises "Unreachable code reached." where Spark 4.0.5, 4.1.4 and 4.2.1 return the sequence (SPARK-58821) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 12:41:58 UTC, 0 replies.
- [I] [EPIC] Handle `-0.0` (and NaN) float keys in one place instead of per call site [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/08 12:52:09 UTC, 7 replies.
- [I] forceShuffledHashJoin leaves sortWithinPartitions output unsorted and fails partitioned inserts [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 12:53:32 UTC, 1 replies.
- Re: [PR] fix: preserve ProjectionExec metadata during serialization [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/08 13:22:27 UTC, 1 replies.
- [I] Native fanout Iceberg writes fail when their open partitions outgrow the memory pool [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 13:25:42 UTC, 1 replies.
- [I] Hand natively written Iceberg files' Parquet footers to the JVM instead of reading them back [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 13:25:44 UTC, 1 replies.
- [PR] feat: close fanout partitions early when the memory pool refuses the native Iceberg writer [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 13:26:03 UTC, 15 replies.
- [I] Native Parquet writer starts a new row group for every batch when writing to HDFS [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 13:41:46 UTC, 0 replies.
- Re: [I] Displaying a `Date64` scalar of `i64::MIN` panics [datafusion] - posted by "geographybuff (via GitHub)" <gi...@apache.org> on 2026/10/08 13:42:49 UTC, 1 replies.
- [PR] fix: do not panic when displaying a Date64 scalar of i64::MIN [datafusion] - posted by "geographybuff (via GitHub)" <gi...@apache.org> on 2026/10/08 13:48:03 UTC, 2 replies.
- Re: [PR] feat: adding `elapsed_compute` to the writer [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 13:56:08 UTC, 0 replies.
- [PR] feat: add config to disable or restrict native UDF library loading, and load libraries without a global lock [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 13:58:06 UTC, 2 replies.
- Re: [I] Physical-plan serialization drops ProjectionExec metadata [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/08 13:59:16 UTC, 0 replies.
- Re: [I] Reject oversized GROUPING masks during analysis [datafusion] - posted by "alexandrefimov (via GitHub)" <gi...@apache.org> on 2026/10/08 14:09:09 UTC, 0 replies.
- Re: [I] Execution panic for valid 64-column GROUPING SETS [datafusion] - posted by "alexandrefimov (via GitHub)" <gi...@apache.org> on 2026/10/08 14:09:19 UTC, 1 replies.
- [I] Support releasing batches in RecordBatchMemoryCounter [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/08 14:16:22 UTC, 6 replies.
- Re: [I] [EPIC] Spilling Hash Join — run any join in a bounded memory budget [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/08 14:27:54 UTC, 8 replies.
- Re: [I] Prune unneccessary data from task definition [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 14:43:35 UTC, 1 replies.
- [PR] docs: prefer behavior-named parameters over Spark versions [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 14:49:21 UTC, 3 replies.
- [PR] Fix crate publishing workflow [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 14:59:26 UTC, 2 replies.
- [PR] fix: check native UDF types at registration and explain planning-time evaluation [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 15:05:24 UTC, 2 replies.
- Re: [PR] fix: support CAST/TRY CAST expressions for return_field_from_args [datafusion] - posted by "dd-annarose (via GitHub)" <gi...@apache.org> on 2026/10/08 15:09:31 UTC, 0 replies.
- [PR] docs: add an FAQ page with an answer on vectorized Java/Scala UDFs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 15:10:31 UTC, 1 replies.
- [PR] docs: clarify published Docker image locations [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 15:20:48 UTC, 2 replies.
- Re: [PR] test: add CometExpressionCoverageSuite for runtime expression coverage audit [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 15:41:32 UTC, 0 replies.
- Re: [PR] Let extension bundles declare scalar, aggregate, and window functions [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 15:43:59 UTC, 0 replies.
- Re: [PR] feat: add Grouped equivalence properties [datafusion] - posted by "NGA-TRAN (via GitHub)" <gi...@apache.org> on 2026/10/08 15:49:52 UTC, 1 replies.
- Re: [PR] feat: stream aggregates over grouped input [datafusion] - posted by "NGA-TRAN (via GitHub)" <gi...@apache.org> on 2026/10/08 15:50:11 UTC, 0 replies.
- [I] roadcast hash join produces incorrect results with sliced Arrow string/binary batches [datafusion-comet] - posted by "unikdahal (via GitHub)" <gi...@apache.org> on 2026/10/08 16:23:16 UTC, 0 replies.
- Re: [PR] feat: push window predicates on expression PARTITION BY keys [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/08 16:31:49 UTC, 5 replies.
- Re: [I] Broadcast hash join produces incorrect results with sliced Arrow string/binary batches [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/08 16:42:58 UTC, 1 replies.
- [I] `RepartitionExec` ignores `datafusion.execution.spill_compression` and always spills uncompressed [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/08 16:53:16 UTC, 2 replies.
- [PR] fix: apply `spill_compression` to `RepartitionExec` spill files [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/08 16:53:31 UTC, 3 replies.
- Re: [I] Iceberg serde: delete-file fields fall back to wrong defaults on reflection failure [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 17:05:58 UTC, 0 replies.
- Re: [I] Enable SPARK-57298 collect_set tests when Spark 4.2 SQL diff lands [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 17:06:00 UTC, 0 replies.
- [PR] feat: enable LocalTableScanExec acceleration by default [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 17:08:05 UTC, 0 replies.
- [I] perf: divide once per row in `pmod` and `div_round_half_up` [datafusion-comet] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/08 17:09:33 UTC, 0 replies.
- [I] Native Iceberg scan fails with `field not found` when an equality delete is keyed on a nested field [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 17:30:12 UTC, 1 replies.
- Re: [PR] docs: document the 24-hour review window for non-trivial pull requests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 17:35:03 UTC, 0 replies.
- Re: [PR] perf: keep one shuffle block read buffer per reduce task [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 17:35:56 UTC, 0 replies.
- [PR] docs: expand the FAQ and refresh the Gluten comparison [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 17:49:30 UTC, 4 replies.
- [PR] build(deps): cargo update and roll up open dependabot PRs [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 17:50:52 UTC, 1 replies.
- Re: [PR] build(deps): bump arrow-schema from 59.3.0 to 60.0.0 [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 17:51:17 UTC, 2 replies.
- Re: [PR] build(deps): bump arrow-select from 59.3.0 to 60.0.0 [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 17:51:29 UTC, 2 replies.
- Re: [PR] build(deps): bump arrow-array from 59.3.0 to 60.0.0 [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 17:51:41 UTC, 2 replies.
- Re: [PR] build(deps): bump arrow from 59.3.0 to 60.0.0 [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 17:51:51 UTC, 2 replies.
- Re: [I] A JVM consumer's parked page allocation fails when another consumer of the task empties its balance [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 17:54:36 UTC, 1 replies.
- Re: [I] [Feature] Support Spark expression: date_add_interval [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 17:56:57 UTC, 0 replies.
- Re: [I] [Feature] Support Spark expression: subtract_dates [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:00:06 UTC, 0 replies.
- Re: [I] [Feature] Support Spark expression: subtract_timestamps [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:02:46 UTC, 0 replies.
- [PR] feat: txt file support [datafusion-comet] - posted by "parthchandra (via GitHub)" <gi...@apache.org> on 2026/10/08 18:03:00 UTC, 23 replies.
- [PR] fix: choose the forced shuffled hash join at planning time so Spark keeps its sorts [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:03:28 UTC, 14 replies.
- Re: [I] [Feature] Support Spark expression: timestamp_add_interval [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:05:57 UTC, 0 replies.
- Re: [I] [Feature] Support Spark expression: timestamp_add_ym_interval [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:09:47 UTC, 0 replies.
- [PR] feat: run broadcast joins natively when an unsupported scan is on the build side [datafusion-comet] - posted by "parthchandra (via GitHub)" <gi...@apache.org> on 2026/10/08 18:10:15 UTC, 10 replies.
- [I] Native hash joins lose the streamed side's order when it arrives sorted from outside the native plan [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:12:26 UTC, 3 replies.
- Re: [I] virtual_hosted_style_request bad calculation [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:13:38 UTC, 0 replies.
- [I] Agree on the initial PMC, committers, and chair for Apache Comet [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 18:14:24 UTC, 0 replies.
- [I] Agree on the scope and repositories for Apache Comet [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 18:14:26 UTC, 4 replies.
- [I] Native Iceberg scan returns NULL for nested fields of migrated tables that use a name mapping [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 18:14:34 UTC, 2 replies.
- [I] Draft the Apache Comet proposal and board resolution [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 18:14:45 UTC, 1 replies.
- [I] [EPIC] Set up the Apache Comet project after the board adopts the resolution [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 18:14:48 UTC, 0 replies.
- [I] [EPIC] Promote Comet to a top level Apache project [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 18:15:05 UTC, 0 replies.
- Re: [I] Support fs.s3a.auth.profile.name and fs.s3a.auth.profile.file for ProfileCredentialsProvider [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:17:20 UTC, 0 replies.
- [PR] Use avro for datafiles collection from write-exec [datafusion-iceberg] - posted by "hareshkh (via GitHub)" <gi...@apache.org> on 2026/10/08 18:19:43 UTC, 12 replies.
- [PR] build(deps): bump rustls from 0.23.40 to 0.23.45 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/08 18:21:01 UTC, 2 replies.
- Re: [I] Native Azure store lets ambient AZURE_* environment variables override or corrupt explicit Hadoop auth config [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:21:03 UTC, 1 replies.
- [I] Native Iceberg scan returns nested values that Spark reads as NULL in files without field ids or a name mapping [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 18:22:22 UTC, 2 replies.
- Re: [I] fair_unified: a JVM consumer freeing its last bytes can fail a parked native acquire with NoSuchElementException [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/08 18:24:38 UTC, 1 replies.
- [PR] BigQuery: Allow tokens after a hyphenated identifier ending in a number [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/08 19:02:28 UTC, 5 replies.
- Re: [PR] POC: batch-granular Parquet scans with the push decoder and scan_plan read-ahead [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/08 19:04:09 UTC, 0 replies.
- Re: [I] Move CometCollationSuite into the spark-4.1+ test shim to avoid per-version duplication [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:20:43 UTC, 0 replies.
- Re: [PR] build(deps): bump github/codeql-action/analyze from 4.37.9 to 4.38.2 [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:18 UTC, 1 replies.
- Re: [PR] build(deps): bump astral-sh/setup-uv from 10.0.1 to 10.2.0 [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:20 UTC, 1 replies.
- Re: [PR] build(deps): bump github/codeql-action/init from 4.37.9 to 4.38.2 [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:26 UTC, 1 replies.
- Re: [PR] build(deps): bump soupsieve from 2.8.4 to 2.9 [datafusion-python] - posted by "timsaucer (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:30 UTC, 1 replies.
- [I] test: Spark SQL tests that inspect the physical plan fail when LocalTableScanExec is native [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:44 UTC, 0 replies.
- [I] collect_set / collect_list return elements in a different order than Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:46 UTC, 0 replies.
- [I] Math functions differ from Spark in the last digits [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:48 UTC, 0 replies.
- [I] Native errors surface as SparkException where Spark raises a specific error class [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:50 UTC, 0 replies.
- [I] percentile of -0.0 returns 0.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:54 UTC, 1 replies.
- [I] from_csv: wrong results in permissive modes and failure with a variant schema [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:56 UTC, 1 replies.
- [I] GROUP BY on a struct containing a map fails with CometNativeException [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:24:58 UTC, 0 replies.
- [I] Null-named attribute fails Arrow export with "field name cannot be null" [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:25:00 UTC, 0 replies.
- [I] CometIcebergWriteDetectionSuite assumes a split Iceberg write plan [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:25:01 UTC, 0 replies.
- Re: [I] Enable spark.comet.exec.localTableScan.enabled when running Spark SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 19:25:09 UTC, 0 replies.
- [PR] WIP speed up hashes [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/08 19:55:36 UTC, 22 replies.
- [I] ShuffleScan metrics are dropped under AQE: shuffle read and decode time missing on the direct-read path [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/08 20:01:34 UTC, 0 replies.
- Re: [PR] docs: preserve released documentation during deployment [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/08 20:01:45 UTC, 4 replies.
- [PR] perf: read shuffle blocks in 64 KiB pieces instead of through `Channels.newChannel` [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/08 20:07:04 UTC, 5 replies.
- Re: [PR] fix: Estimate string equality and LIKE filter selectivity [datafusion] - posted by "limadog9 (via GitHub)" <gi...@apache.org> on 2026/10/08 20:07:58 UTC, 3 replies.
- Re: [PR] [asf-site] docs: publish 55.0.0 and 55.1.0 documentation snapshots [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/08 20:20:35 UTC, 2 replies.
- Re: [PR] docs: add version picker and manual release snapshots [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/08 21:09:39 UTC, 2 replies.
- [I] Leaf expression pushdown leaves an unqualified column in an Aggregate's output name, so the plan fails a datafusion-proto round trip [datafusion] - posted by "clintonjrobinson (via GitHub)" <gi...@apache.org> on 2026/10/08 21:10:04 UTC, 0 replies.
- [I] perf: every Comet broadcast hash join probe task re-decodes the whole broadcast in the JVM [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/08 21:23:29 UTC, 3 replies.
- [I] perf: without AQE, native operators read Comet shuffle through a JVM round trip per block, making small reduce tasks up to 4x slower than Spark [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/08 21:23:34 UTC, 0 replies.
- Re: [I] `CASE` expressions drop field metadata, silently stripping Arrow extension types and breaking metadata-aware UDFs [datafusion] - posted by "osipovartem (via GitHub)" <gi...@apache.org> on 2026/10/08 22:08:39 UTC, 2 replies.
- [PR] fix: preserve common field metadata through CASE expressions [datafusion] - posted by "osipovartem (via GitHub)" <gi...@apache.org> on 2026/10/08 22:22:32 UTC, 2 replies.
- [PR] fix: don't let S3A committer, delete and read defaults block native Iceberg writes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/08 23:04:28 UTC, 4 replies.
- [PR] feat: report the sort order of sorted Iceberg scans to DataFusion [datafusion-iceberg] - posted by "anuragmantri (via GitHub)" <gi...@apache.org> on 2026/10/08 23:28:42 UTC, 17 replies.
- [PR] fix: avoid sort-based joins for nested float join keys with negative zeros [datafusion] - posted by "entity-0-0-2 (via GitHub)" <gi...@apache.org> on 2026/10/08 23:58:55 UTC, 1 replies.
- Re: [PR] fix: decorrelate grouping sets that leave out the correlated column when safe [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/09 00:11:01 UTC, 6 replies.
- [PR] feat: support releasing batches in RecordBatchMemoryCounter [datafusion] - posted by "txwyy123 (via GitHub)" <gi...@apache.org> on 2026/10/09 00:16:22 UTC, 28 replies.
- Re: [PR] ci: add performance regression check for PRs / merges [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/09 00:43:33 UTC, 0 replies.
- Re: [PR] docs: document casts involving arrays, structs, and maps [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/09 00:45:48 UTC, 2 replies.
- [I] Joins: one shared protocol for "the last probe partition emits the build-side rows" [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/09 01:01:28 UTC, 0 replies.
- Re: [I] Return `NativeType` instead of `DataType` for `get_example_types` [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/09 01:11:00 UTC, 0 replies.
- Re: [I] Improve NDV statistics for Parquet columns (parquet RLE & Dictionary array focus) [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/09 01:40:26 UTC, 0 replies.
- Re: [I] `RewriteSetComparison` is overly aggressive rewriting some set comparison into multiple mark joins [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/09 01:45:37 UTC, 0 replies.
- Re: [PR] fix: correlated exists/not exists subqueries hit the count bug for groupless aggregates [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/09 01:52:40 UTC, 16 replies.
- Re: [PR] benchmarks: count simulated object store GET requests per query [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/09 01:56:40 UTC, 1 replies.
- Re: [PR] Decouple the `FileSource` trait from the concrete `FileScanConfig` `DataSource` [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/09 01:56:44 UTC, 1 replies.
- Re: [PR] fix: array_position nested lists handling & check index for nulls [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/09 01:56:52 UTC, 1 replies.
- Re: [I] Substrait producer emits LIKE with three arguments and an undefined ilike function [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/09 02:53:11 UTC, 0 replies.
- Re: [I] `corr(DISTINCT x, x)` fails with internal error in `SingleDistinctToGroupBy` [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/09 02:58:46 UTC, 0 replies.
- [PR] test: drain the listener bus before registering Iceberg test listeners [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 03:08:13 UTC, 2 replies.
- Re: [I] Distinguish string equality, LIKE and NOT LIKE estimates [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/09 04:03:48 UTC, 0 replies.
- [PR] chore(ci): bump taiki-e/install-action from 2.87.24 to 2.87.26 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/09 04:22:47 UTC, 1 replies.
- Re: [I] Use `ProbeCompletion` in `NestedLoopJoinExec` [datafusion] - posted by "jeffoodchain (via GitHub)" <gi...@apache.org> on 2026/10/09 05:25:39 UTC, 3 replies.
- Re: [I] date_bin: month strides on s/ms/us timestamps return NULL outside the chrono DateTime range [datafusion] - posted by "ThilakShekharShriyan (via GitHub)" <gi...@apache.org> on 2026/10/09 05:27:10 UTC, 5 replies.
- [PR] fix: match functional dependencies by column position, not by name [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/09 05:36:36 UTC, 13 replies.
- [PR] fix: keep a native hash join's streamed order when Spark drops the sort above it [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 05:58:58 UTC, 6 replies.
- Re: [I] Give the two FFI example crates a runnable entry point [datafusion-python] - posted by "Awesome06 (via GitHub)" <gi...@apache.org> on 2026/10/09 06:32:40 UTC, 0 replies.
- [PR] fix(examples): make csv-read-options self-contained and add output to silent examples [datafusion-python] - posted by "Mola-maker (via GitHub)" <gi...@apache.org> on 2026/10/09 06:51:05 UTC, 0 replies.
- [I] Interrupt a native scalar Arrow UDF when its task is killed [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 06:51:07 UTC, 1 replies.
- [I] Native memory pool requests can fail the task when Spark drops the task's execution memory entry (SPARK-59444) [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 07:21:46 UTC, 3 replies.
- [PR] fix: retry a native memory request that Spark failed after dropping the task's entry [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 07:21:58 UTC, 4 replies.
- [PR] fix: downcast to FixedSizeBinaryArray in CASE bytes lookup table [datafusion] - posted by "jdymitarai (via GitHub)" <gi...@apache.org> on 2026/10/09 07:42:33 UTC, 0 replies.
- [I] Run the sqllogictest corpus under an alternative physical optimizer pipeline [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/09 07:57:44 UTC, 0 replies.
- [PR] fix: bin date_bin month strides outside chrono's range [datafusion] - posted by "ThilakShekharShriyan (via GitHub)" <gi...@apache.org> on 2026/10/09 08:00:04 UTC, 3 replies.
- Re: [PR] fix(physical-optimizer): decline the WindowTopN rewrite when the FilterExec carries a fetch [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/09 08:00:41 UTC, 4 replies.
- Re: [I] Support FilterExec with embedded projections in WindowTopN optimization [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/09 08:00:57 UTC, 0 replies.
- [PR] examples: give the two FFI example crates a runnable entry point [datafusion-python] - posted by "Awesome06 (via GitHub)" <gi...@apache.org> on 2026/10/09 08:44:14 UTC, 1 replies.
- [PR] Fix retained-capacity accounting for grouped byte MIN/MAX [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/09 09:02:56 UTC, 11 replies.
- [PR] fix: preserve empty Iceberg partitions after dynamic pruning [datafusion-comet] - posted by "LinSimon-901101 (via GitHub)" <gi...@apache.org> on 2026/10/09 09:07:21 UTC, 1 replies.
- [PR] Add Arrow IPC format options [datafusion] - posted by "pepijnve (via GitHub)" <gi...@apache.org> on 2026/10/09 09:11:48 UTC, 3 replies.
- Re: [I] SQL unparser drops IGNORE NULLS / RESPECT NULLS on window and aggregate functions [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/09 09:14:46 UTC, 0 replies.
- Re: [I] Overlap DV bitmap and Parquet footer reads during native Delta scan preparation [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 09:51:56 UTC, 0 replies.
- Re: [I] Move cloud compatibility gating into a shared helper beside the object store configuration code [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 09:55:01 UTC, 0 replies.
- Re: [I] Scope object store credentials to execution payloads and selected authorities in the native Delta scan [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 09:57:39 UTC, 0 replies.
- Re: [I] Deepen v2-checkpoint regression coverage for the native Delta scan [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 10:00:31 UTC, 1 replies.
- Re: [I] Native Delta scan: derive the task injection key from a stable scan identity [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 10:01:02 UTC, 1 replies.
- Re: [I] Share the native-reader admission checks between the core Parquet scan and the Delta contrib [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 10:01:23 UTC, 1 replies.
- Re: [I] Reuse the common native scan builder for ordinary columns in the Delta deletion-vector path [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 10:01:45 UTC, 0 replies.
- Re: [I] Make the Delta contrib's file-planning boundary explicit [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 10:02:05 UTC, 1 replies.
- Re: [I] Add envelope and provider contract tests for the Delta plan-data injector [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 10:02:25 UTC, 0 replies.
- Re: [I] Route Delta deletion-vector metadata preparation through the scan's instrumented reader [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 10:02:43 UTC, 1 replies.
- Re: [I] Delegate Delta physical schema preparation to DeltaParquetFileFormat.prepareSchemaForRead [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 10:03:12 UTC, 0 replies.
- Re: [I] Document a capability table for the native Delta reader [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/09 10:04:42 UTC, 0 replies.
- Re: [PR] feat: Implement map-to-string casting [datafusion-comet] - posted by "getChan (via GitHub)" <gi...@apache.org> on 2026/10/09 12:01:36 UTC, 1 replies.
- [PR] perf: resolve aliased field once during metadata inference [datafusion] - posted by "osipovartem (via GitHub)" <gi...@apache.org> on 2026/10/09 12:35:03 UTC, 2 replies.
- Re: [PR] fix: preserve field metadata for simple CASE branches [datafusion] - posted by "osipovartem (via GitHub)" <gi...@apache.org> on 2026/10/09 12:37:21 UTC, 3 replies.
- [PR] perf: speed up Utf8View/BinaryView hashing [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/09 13:13:15 UTC, 11 replies.
- Re: [PR] fix: coalesce the merged key of RIGHT/FULL USING/NATURAL joins [datafusion] - posted by "jonmmease (via GitHub)" <gi...@apache.org> on 2026/10/09 13:27:57 UTC, 8 replies.
- [PR] Preserve field metadata through physical CASE expressions [datafusion] - posted by "osipovartem (via GitHub)" <gi...@apache.org> on 2026/10/09 13:33:23 UTC, 2 replies.
- [I] Non-AQE DPP subquery doesn't reuse the Comet broadcast when the dimension is a UNION [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 14:13:00 UTC, 0 replies.
- [PR] perf: speed up DictionaryArray hashing [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/09 14:15:42 UTC, 42 replies.
- [I] Native timezone conversions stop applying DST after 2099, while Spark keeps applying the zone's rules [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 14:20:33 UTC, 0 replies.
- Re: [I] issues found when publishing crates for 55.0.0 [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 14:31:35 UTC, 0 replies.
- [PR] docs: add draft proposal to establish Apache Comet as a top-level project [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 14:34:32 UTC, 2 replies.
- [PR] chore(python): build the Python client against DataFusion 55 [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 14:57:18 UTC, 6 replies.
- [I] Native fanout Iceberg writes: sort the remaining rows by partition when the memory pool runs short, instead of writing small files [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 15:16:55 UTC, 0 replies.
- [PR] Support equality with one in opt-in WindowTopN rule [datafusion] - posted by "osipovartem (via GitHub)" <gi...@apache.org> on 2026/10/09 16:02:38 UTC, 1 replies.
- Re: [I] Further improve performance of IN list evaluation [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/09 16:10:25 UTC, 3 replies.
- [PR] Introduce a budget for integral sequence byte allocations and improve native kernel performance [datafusion-comet] - posted by "nat-openai (via GitHub)" <gi...@apache.org> on 2026/10/09 16:36:33 UTC, 3 replies.
- Re: [I] push_down_filter does not push window predicates on expression PARTITION BY keys [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/09 16:51:01 UTC, 0 replies.
- [I] Spark 3.x native Parquet writer skips InsertIntoHadoopFsRelationCommand's post-write steps (stale cache, stale table stats) [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 16:55:20 UTC, 1 replies.
- [PR] fix: run InsertIntoHadoopFsRelationCommand's post-write steps in the Spark 3.x native writer [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 16:56:11 UTC, 5 replies.
- [PR] feat: decoupled Result Service for serving query results [datafusion-ballista] - posted by "villebro (via GitHub)" <gi...@apache.org> on 2026/10/09 17:18:42 UTC, 0 replies.
- Re: [PR] feat: use aligned slice access during bulk append in SparkUnsafeArray [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 17:20:49 UTC, 2 replies.
- Re: [PR] fix: [spark34] preserve empty Iceberg partitions after dynamic pruning [datafusion-comet] - posted by "LinSimon-901101 (via GitHub)" <gi...@apache.org> on 2026/10/09 17:23:57 UTC, 4 replies.
- [PR] test: Add regression test for limit / sort [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/09 17:27:15 UTC, 1 replies.
- [I] Native Iceberg scan returns wrong values for a column renamed after a VERSION AS OF snapshot [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 17:27:55 UTC, 2 replies.
- [I] IN evaluates later candidates over the whole batch, so an ANSI error can fire for a row that already matched [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 17:30:54 UTC, 0 replies.
- Re: [I] Track evaluation masks for data-dependent errors beyond unbase64 operator fallback [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 17:31:02 UTC, 0 replies.
- [PR] perf: bulk-append long nullable primitive arrays in SparkUnsafeArray conversion [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 17:32:07 UTC, 7 replies.
- [I] Incorrect results: ORDER BY b, a over a subquery with ORDER BY b LIMIT n is not sorted by (b, a) when SortPreservingMergeExec has a fetch [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/09 17:39:23 UTC, 3 replies.
- Re: [I] [EPIC] Bug fixes to consider backporting to branch-1.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 17:39:39 UTC, 0 replies.
- [PR] fix: correct nullability of AND/OR expressions to resolve plan mismatch in CSE [datafusion] - posted by "siddubakka (via GitHub)" <gi...@apache.org> on 2026/10/09 17:51:08 UTC, 1 replies.
- [PR] Fixes #25978: correct nullability of AND/OR expressions to resolve plan mismatch in CSE [datafusion] - posted by "siddubakka (via GitHub)" <gi...@apache.org> on 2026/10/09 17:55:39 UTC, 18 replies.
- [I] Cast of a literal that fails under ANSI fails the query at planning time, even in a branch no row reaches [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 18:02:26 UTC, 1 replies.
- [I] GroupedHashAggregateStream releases its memory reservation at emit while the output batch is still alive [datafusion] - posted by "pmoust (via GitHub)" <gi...@apache.org> on 2026/10/09 18:04:50 UTC, 5 replies.
- [PR] fix: do not fail planning on a cast of a literal that fails to evaluate [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 18:05:56 UTC, 12 replies.
- [I] RepartitionExec output coalescer buffers are not charged to any memory reservation [datafusion] - posted by "pmoust (via GitHub)" <gi...@apache.org> on 2026/10/09 18:07:49 UTC, 0 replies.
- Re: [I] feat: analyze memory usage for `size` functions [datafusion] - posted by "pmoust (via GitHub)" <gi...@apache.org> on 2026/10/09 18:10:50 UTC, 0 replies.
- [PR] fix: preserve CASE WHEN struct field names from the first THEN branch [datafusion-comet] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/09 18:45:26 UTC, 6 replies.
- Re: [PR] ci: retry the scalafix lint when Maven cannot resolve the plugin [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/09 18:45:29 UTC, 6 replies.
- [PR] docs: list the S3A settings the Iceberg native-write gate ignores [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 18:46:00 UTC, 1 replies.
- Re: [PR] perf: optimize aggregate functions over literal arguments [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/09 18:46:01 UTC, 0 replies.
- Re: [I] Optimize COUNT over constant arguments [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/09 18:46:02 UTC, 0 replies.
- [PR] fix: charge RepartitionExec coalescer buffers to the memory pool [datafusion] - posted by "pmoust (via GitHub)" <gi...@apache.org> on 2026/10/09 19:12:21 UTC, 1 replies.
- Re: [I] timestamp_trunc panics on DST-transition timestamps in a DST timezone [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 19:20:21 UTC, 0 replies.
- Re: [I] Datafusion Native llm.txt [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/09 19:23:01 UTC, 1 replies.
- [I] perf: speed up hash_dictionary_scatter hot loop [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/09 19:28:02 UTC, 1 replies.
- [I] Improve Performance (Polars 2.0 Call to Action) [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/09 19:33:26 UTC, 24 replies.
- Re: [PR] [WIP] feat: decoupled Result Service for serving query results [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/09 19:42:22 UTC, 1 replies.
- [I] substr on Dictionary(_, Utf8) inserts implicit CAST to Utf8View [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/09 19:45:57 UTC, 1 replies.
- Re: [PR] WIP string speed up (hash) [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/09 19:49:54 UTC, 0 replies.
- [PR] fix: match Spark percentile ordering for negative NaNs [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/09 19:50:30 UTC, 3 replies.
- [PR] fix: Native corr, covariance, variance and stddev return wrong values for a constant fractional column merged from several partitions [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/09 20:17:41 UTC, 0 replies.
- Re: [PR] perf: add dict fast path to make_scalar_function [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/09 20:58:18 UTC, 0 replies.
- [PR] fix: handle truncation operands in scalar evaluation and rewrites [datafusion-comet] - posted by "nat-openai (via GitHub)" <gi...@apache.org> on 2026/10/09 23:01:03 UTC, 1 replies.
- [I] Broadcast build-side auto-bridge only accelerates the innermost join when a fact has multiple unsupported-format dimensions [datafusion-comet] - posted by "parthchandra (via GitHub)" <gi...@apache.org> on 2026/10/09 23:19:56 UTC, 0 replies.
- Re: [PR] refactor: share the missing task entry retry between the shuffle allocator and the native pool [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/09 23:48:59 UTC, 0 replies.
- Re: [PR] fix: raise DIVIDE_BY_ZERO from native corr on a zero denominator in ANSI mode [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/09 23:56:02 UTC, 11 replies.
- [PR] Integral sequence optimisation [datafusion-comet] - posted by "nat-openai (via GitHub)" <gi...@apache.org> on 2026/10/10 00:29:25 UTC, 0 replies.
- [I] [EPIC] In-memory cache audit: correctness and performance follow-ups for InMemoryTableScanExec support [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 00:39:12 UTC, 0 replies.
- [PR] fix: keep a streamed side sorted outside the native plan in order through outer hash joins [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 01:06:46 UTC, 33 replies.
- [PR] test: count the partitions and batches the native cache scan reads [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 01:22:12 UTC, 1 replies.
- Re: [PR] Split the partitioned hash join dynamic filter into bounds AND membership [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/10 01:53:45 UTC, 1 replies.
- Re: [PR] parquet: cache per-file ArrowReaderMetadata for wide-schema scans [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/10 01:53:53 UTC, 1 replies.
- Re: [PR] feat: extend interval arithmetic to support scalar functions (UDFs) [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/10 01:53:57 UTC, 1 replies.
- [I] Discussion: Define the Contract for Custom Physical Optimizer Pipelines [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/10 02:03:30 UTC, 12 replies.
- [I] Parquet schema inference keeps missing nested fields non-nullable [datafusion] - posted by "rgbuilds (via GitHub)" <gi...@apache.org> on 2026/10/10 03:18:22 UTC, 2 replies.
- [PR] [DO NOT MERGE] test arrow 59.3.1 [datafusion] - posted by "Jefffrey (via GitHub)" <gi...@apache.org> on 2026/10/10 03:40:01 UTC, 3 replies.
- [I] perf: split sort-shuffle rows by partition as they arrive, when memory allows [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/10 03:44:13 UTC, 0 replies.
- Re: [I] perf: hybrid sort-shuffle buffering: split rows by partition on arrival when memory allows [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/10 04:06:42 UTC, 3 replies.
- [I] CometScanRule reads fs.comet.libhdfs.schemes from SQLConf, but native reads it from the Hadoop conf [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/10 04:13:56 UTC, 2 replies.
- Re: [I] [EPIC] Production-grade Apache Iceberg scans [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/10 04:18:12 UTC, 0 replies.
- Re: [PR] Migrate Iceberg leaf nodes to the DataSource trait [datafusion-iceberg] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/10 04:55:07 UTC, 0 replies.
- [PR] fix: read fs.comet.libhdfs.schemes for the scan rule from the Hadoop conf [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/10 04:59:07 UTC, 10 replies.
- [I] Native string to float/double and decimal casts accept strings Spark rejects [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/10 05:05:50 UTC, 1 replies.
- [I] cast(string as decimal) returns NULL for non-ASCII Unicode digits that Spark accepts [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/10 05:18:03 UTC, 1 replies.
- [PR] fix: accept all BMP Unicode decimal digits in cast(string as decimal) [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/10 05:18:24 UTC, 4 replies.
- [I] Native cast string to date returns NULL for years outside chrono's NaiveDate range [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/10 05:29:56 UTC, 0 replies.
- [I] Native date functions and date-to-string cast return NULL or fail for dates outside chrono's NaiveDate range [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/10 05:39:46 UTC, 1 replies.
- [PR] fix: cast string to date for years outside chrono's NaiveDate range [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/10 05:41:32 UTC, 4 replies.
- Re: [PR] bench: classic pwmj sql benchmark [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/10 06:47:11 UTC, 8 replies.
- [PR] perf: reduce retained buffers for nested map lookups [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/10 06:50:05 UTC, 6 replies.
- [PR] chore: re-enable unused-parameter warnings in strict profile [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/10 06:50:07 UTC, 1 replies.
- [PR] perf: preserve supported Iceberg residual conjuncts [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/10 06:50:09 UTC, 11 replies.
- [PR] fix: do not panic when partitioning a COPY by an out-of-range date [datafusion] - posted by "ODriscollBoys (via GitHub)" <gi...@apache.org> on 2026/10/10 06:59:31 UTC, 0 replies.
- [PR] fix: report nested unnest of a struct as a planning error [datafusion] - posted by "ODriscollBoys (via GitHub)" <gi...@apache.org> on 2026/10/10 06:59:34 UTC, 0 replies.
- [PR] fix: do not preallocate `max_size` centroids when merging a TDigest [datafusion] - posted by "ODriscollBoys (via GitHub)" <gi...@apache.org> on 2026/10/10 06:59:36 UTC, 0 replies.
- [PR] feat!: pass input schema to ExprPlanner::plan_scalar [datafusion] - posted by "fengys1996 (via GitHub)" <gi...@apache.org> on 2026/10/10 07:29:49 UTC, 8 replies.
- [I] Nightly CI failed on 2026-10-10 [datafusion-comet] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/10 07:43:40 UTC, 8 replies.
- [I] Internal error: CAST over an expression simplified to a metadata-carrying column, under UNION ALL + aggregate (physical vs logical field metadata) [datafusion] - posted by "TRO-Wolf (via GitHub)" <gi...@apache.org> on 2026/10/10 09:15:42 UTC, 0 replies.
- [PR] Deprecate CsvSource::newlines_in_values and preserve proto coverage [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/10 10:25:12 UTC, 4 replies.
- Re: [I] EPIC: destructure proto serde hooks in the `datasource` crates [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/10 10:30:00 UTC, 2 replies.
- Re: [PR] fix(proto): preserve physical cast expression state [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/10 10:43:03 UTC, 3 replies.
- [PR] chore(optimizer): remove deprecated `supports_rewrite` [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/10 11:28:16 UTC, 4 replies.
- [I] Clippy fails with all features enabled [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/10 11:44:37 UTC, 1 replies.
- [I] Check the timezone label of every native expression that returns a timestamp [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 12:22:21 UTC, 2 replies.
- Re: [I] [EPIC] Timezone handling bugs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 12:23:37 UTC, 1 replies.
- [I] Follow-ups to native NULL short-circuiting of array and map functions [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 13:00:50 UTC, 0 replies.
- [PR] feat: bump iceberg-rust and write float and double identity partitions natively [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 13:15:59 UTC, 10 replies.
- [PR] fix: preserve columnar output when reverting a cached AQE result stage [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 13:27:13 UTC, 6 replies.
- [PR] perf: read cache statistics null counts from Comet's Arrow vectors [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 14:09:14 UTC, 6 replies.
- [I] Push Iceberg residual predicates on decimal columns into the native scan [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 14:32:02 UTC, 0 replies.
- [I] [EPIC] Nested-type conversion performance: C2R, R2C and JVM shuffle slower than Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 14:45:02 UTC, 2 replies.
- [PR] test: extend C2R and R2C microbenchmarks to cover nested types [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 14:45:19 UTC, 4 replies.
- [PR] refactor: retain hash join build batches after allocation failure [datafusion] - posted by "peterxcli (via GitHub)" <gi...@apache.org> on 2026/10/10 14:48:05 UTC, 5 replies.
- [I] Native PartialMerge aggregate emits duplicate keys under memory pressure, so count(DISTINCT) over-counts [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 14:53:41 UTC, 1 replies.
- [PR] perf: generate the columnar-to-row projection once per executor instead of per partition [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 15:23:11 UTC, 4 replies.
- Re: [PR] perf: add opt-in delta encoding for cached longs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 15:58:50 UTC, 1 replies.
- [PR] feat: add lz4 as an opt-in codec for Comet's in-memory cache [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 16:33:34 UTC, 1 replies.
- [PR] perf: generate the in-memory cache reader's class once per executor [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 16:48:00 UTC, 7 replies.
- [I] Common subexpression elimination evaluates the arguments of an aggregate with `FILTER` for rows that the filter rejects [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/10 17:15:13 UTC, 1 replies.
- [PR] fix: do not extract common subexpressions from the arguments of an aggregate with a FILTER [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/10 17:15:15 UTC, 7 replies.
- [I] DataFrame API: serialize columns to a JSON string column [datafusion] - posted by "cj-zhukov (via GitHub)" <gi...@apache.org> on 2026/10/10 17:20:43 UTC, 6 replies.
- [PR] perf: preserve dictionary encoding through regexp_replace [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/10 17:25:01 UTC, 26 replies.
- [PR] DataFrame API serialize columns to a JSON string column (#26185) [datafusion] - posted by "cj-zhukov (via GitHub)" <gi...@apache.org> on 2026/10/10 17:33:20 UTC, 2 replies.
- [PR] fix: check for nix flake support before trying to load flake [datafusion] - posted by "VVKot (via GitHub)" <gi...@apache.org> on 2026/10/10 17:37:58 UTC, 1 replies.
- Re: [I] Clean up dead ANSI-related plumbing (CometEvalMode helpers, inert allow_incompat on casts) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 17:46:54 UTC, 0 replies.
- [PR] refactor(core): drain and size the sort-shuffle buffer through BufferedBatches [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/10 18:09:35 UTC, 11 replies.
- [I] [EPIC] Support Hive tables for users migrating from Spark [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 18:09:38 UTC, 0 replies.
- Re: [PR] WIP speed up hashes (Primitive) [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/10 18:36:47 UTC, 0 replies.
- [PR] chore: allow clippy mutable_key_type on Expr hash sets in PushDownFilter (#26181) [datafusion] - posted by "patrickswedish (via GitHub)" <gi...@apache.org> on 2026/10/10 18:43:18 UTC, 6 replies.
- Re: [PR] feat: expose bloom filter, page index and sorting metadata in parquet… [datafusion] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/10 19:02:12 UTC, 0 replies.
- [PR] perf(substrait): avoid quadratic field lookup when consuming ReadRel [datafusion] - posted by "ole-baranov (via GitHub)" <gi...@apache.org> on 2026/10/10 19:02:12 UTC, 0 replies.
- [PR] perf: unroll PrimitiveArray hashing for the no-null path [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/10 19:02:41 UTC, 20 replies.
- Re: [PR] fix: share the missing task entry retry and stop retrying it after the task has ended [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/10 19:22:59 UTC, 2 replies.
- [PR] perf: pre-size collections and reuse per-iteration buffers [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/10 19:31:59 UTC, 15 replies.
- [PR] perf: presize collections and reuse buffers in native loops [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/10 19:37:57 UTC, 2 replies.
- Re: [I] Check `PiecewiseMergeJoin` performance for large tables [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/10 20:14:44 UTC, 0 replies.
- [I] `sum` of a decimal returns a wider type than the plan schema declares when the query has a `DISTINCT` aggregate [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/10 21:12:45 UTC, 0 replies.
- Re: [I] Null-aware LeftMark joins miss logical NULLs in dictionary keys [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/10 22:45:00 UTC, 0 replies.
- [I] INSERT fails after a column is added to the table, until the provider is rebuilt [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 23:24:41 UTC, 0 replies.
- [I] Wrong results and panics after a column is dropped and added back under the same name [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 23:24:54 UTC, 0 replies.
- Re: [PR] perf: skip DecimalPrecision.promote's rewrite when there is no decimal arithmetic [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/10 23:27:18 UTC, 1 replies.
- Re: [I] perf: use aligned slice access in SparkUnsafeArray bulk append [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 00:38:04 UTC, 0 replies.
- Re: [PR] fix: reject duplicate projection output names [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/11 01:56:29 UTC, 1 replies.
- Re: [PR] feat: attach Diagnostic to "invalid function argument types" error [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/11 01:56:32 UTC, 1 replies.
- Re: [PR] perf(spark): fold concat_ws plans with literal-NULL separator via simplify [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/11 01:56:34 UTC, 1 replies.
- Re: [PR] fix(proto): logical plan deserialization stack overflow protection [datafusion] - posted by "bvolpato (via GitHub)" <gi...@apache.org> on 2026/10/11 02:40:21 UTC, 2 replies.
- [PR] test: cover container field ids next to INT96 timestamps in the native Parquet scan [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/11 04:35:44 UTC, 2 replies.
- [PR] perf: speed up PrimitiveArray hashing for nullable inputs [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/11 04:42:09 UTC, 9 replies.
- [PR] fix: infer missing nested Parquet fields as nullable [datafusion] - posted by "rgbuilds (via GitHub)" <gi...@apache.org> on 2026/10/11 04:46:14 UTC, 9 replies.
- [PR] feat: mark null-propagating string functions as strict [datafusion] - posted by "DKER2 (via GitHub)" <gi...@apache.org> on 2026/10/11 04:47:00 UTC, 0 replies.
- Re: [I] Eliminate more outer joins by supporting more expressions [datafusion] - posted by "DKER2 (via GitHub)" <gi...@apache.org> on 2026/10/11 04:52:23 UTC, 0 replies.
- [I] `map[key]` fails when the key literal's type differs from the map key type (e.g. `MAP(VARCHAR, ...)` with `m['a']`) [datafusion] - posted by "Ishaan400 (via GitHub)" <gi...@apache.org> on 2026/10/11 04:56:13 UTC, 1 replies.
- Re: [PR] feat: support AtLeastNNonNulls natively [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/11 04:58:14 UTC, 7 replies.
- [PR] fix: validate join_integer_prefilter_min_pruning_ratio at SET time [datafusion] - posted by "Shahzeb-DataEngineer (via GitHub)" <gi...@apache.org> on 2026/10/11 05:04:43 UTC, 0 replies.
- [PR] fix: coerce map lookup keys to the map key type in get_field [datafusion] - posted by "Ishaan400 (via GitHub)" <gi...@apache.org> on 2026/10/11 05:26:48 UTC, 0 replies.
- [PR] test: migrate Java RLIKE semantics and batch coverage to SQL fixtures [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/11 06:07:03 UTC, 1 replies.
- [PR] test: migrate required-child hash regressions to SQL fixtures [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/11 06:07:16 UTC, 1 replies.
- Re: [PR] feat: add IcebergCatalogTableProvider::new_with_schema [datafusion-iceberg] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/11 07:00:58 UTC, 10 replies.
- Re: [PR] feat: mark null-propagating scalar functions as strict [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/11 07:27:29 UTC, 0 replies.
- Re: [PR] feat: improve Spark from_utc_timestamp compatibility [datafusion] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/11 07:34:09 UTC, 5 replies.
- [PR] fix: preserve schema consistency across union and cast [datafusion] - posted by "Amogh-2404 (via GitHub)" <gi...@apache.org> on 2026/10/11 08:09:51 UTC, 4 replies.
- [I] Expose Parquet read-ahead controls for Iceberg SQL scans [datafusion-iceberg] - posted by "terbed (via GitHub)" <gi...@apache.org> on 2026/10/11 08:15:09 UTC, 1 replies.
- Re: [PR] Feat/map sql extension types [datafusion] - posted by "cyberbeam524 (via GitHub)" <gi...@apache.org> on 2026/10/11 08:31:27 UTC, 12 replies.
- [PR] feat: attach Diagnostic to duplicate table name errors [datafusion] - posted by "haochunchang (via GitHub)" <gi...@apache.org> on 2026/10/11 08:32:49 UTC, 2 replies.
- [PR] refactor: replace MapOffset tuple with ProbeOffset enum [datafusion] - posted by "CuteChuanChuan (via GitHub)" <gi...@apache.org> on 2026/10/11 09:53:11 UTC, 4 replies.
- [PR] DRAFT Bench 26133 [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/11 10:03:39 UTC, 13 replies.
- [PR] fix(spark): derive concat_ws nullability from separator [datafusion] - posted by "VVKot (via GitHub)" <gi...@apache.org> on 2026/10/11 10:30:24 UTC, 3 replies.
- [PR] docs: Add Datadog distributed DataFusion blog post to readings page [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/11 10:53:33 UTC, 1 replies.
- Re: [I] Field id matching misses a container id after INT96 coercion drops container metadata [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/11 11:13:30 UTC, 0 replies.
- Re: [PR] perf: integral sequence optimisation [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/11 12:10:07 UTC, 0 replies.
- [PR] fix: preserve filter semantics for casts and negation [datafusion-iceberg] - posted by "terbed (via GitHub)" <gi...@apache.org> on 2026/10/11 13:16:57 UTC, 0 replies.
- [PR] chore: scope mutable-key lint exceptions for window expressions [datafusion] - posted by "VVKot (via GitHub)" <gi...@apache.org> on 2026/10/11 13:30:32 UTC, 2 replies.
- [PR] test: sample current-process RSS before query execution [datafusion] - posted by "VVKot (via GitHub)" <gi...@apache.org> on 2026/10/11 13:31:21 UTC, 2 replies.
- [I] Closing the shuffle direct-read stream early fetches every remaining block [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 14:04:12 UTC, 0 replies.
- [PR] fix: derive string function nullability from inputs [datafusion] - posted by "VVKot (via GitHub)" <gi...@apache.org> on 2026/10/11 14:33:48 UTC, 4 replies.
- [PR] refactor: stop normalizing float divisors now that percentile_approx orders NaN as Spark does [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 14:36:12 UTC, 4 replies.
- Re: [I] chore: Re-enable unused-parameter warnings in the strict-warnings profile [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 14:45:54 UTC, 0 replies.
- [PR] fix: enable Criterion automatically when a benchmark namespace is set [datafusion] - posted by "Omega359 (via GitHub)" <gi...@apache.org> on 2026/10/11 15:00:30 UTC, 1 replies.
- [PR] fix: cast outer projection expr to declared field type in SingleDistinctToGroupBy [datafusion] - posted by "jdymitarai (via GitHub)" <gi...@apache.org> on 2026/10/11 15:31:31 UTC, 7 replies.
- [PR] fix: keep one row per key in a native PartialMerge that runs short of memory [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 15:41:42 UTC, 2 replies.
- Re: [PR] Keep ClickBench SQL in sync across runners [datafusion] - posted by "Omega359 (via GitHub)" <gi...@apache.org> on 2026/10/11 15:46:48 UTC, 2 replies.
- [PR] ci: add Apache RAT license header check [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 15:53:30 UTC, 3 replies.
- [PR] test: fail Comet tests when a native plan mislabels a timestamp's timezone [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 15:58:40 UTC, 1 replies.
- Re: [PR] feat: charge native Parquet scan memory to the task memory pool [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:03:49 UTC, 1 replies.
- Re: [PR] fix: support JVM columnar shuffle with spark.shuffle.checksum.enabled=false [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:04:17 UTC, 1 replies.
- Re: [PR] fix: serialize large-offset string and binary vectors with 32-bit offsets [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:04:19 UTC, 7 replies.
- Re: [PR] docs: add a scan contributor guide and a scan PR review skill [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:04:27 UTC, 1 replies.
- [PR] chore: rename crate back to iceberg-datafusion and start at version 0.12.0 [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:14:49 UTC, 3 replies.
- [PR] Fix local Pelican build [datafusion-site] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/11 16:21:12 UTC, 3 replies.
- [I] Enable page index for Iceberg scans [datafusion-iceberg] - posted by "terbed (via GitHub)" <gi...@apache.org> on 2026/10/11 16:25:19 UTC, 0 replies.
- [PR] fix: [branch-1.1] retry a shuffle page allocation that Spark failed after dropping the task's entry (#6403) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:26:04 UTC, 1 replies.
- [PR] fix: [branch-1.1] match Spark percentile ordering for negative NaNs (#6829) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:28:20 UTC, 1 replies.
- [PR] fix: [branch-1.1] retry a native acquire that Spark failed after dropping the task's entry (#6310) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:29:11 UTC, 1 replies.
- [PR] fix: [branch-1.1] count the days partition transform in UTC (#6348) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:33:28 UTC, 2 replies.
- [PR] Improve UI [datafusion-site] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/11 16:33:37 UTC, 6 replies.
- [PR] fix: [branch-1.1] route collated array element comparisons through the codegen dispatcher (#6471) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:34:41 UTC, 1 replies.
- [PR] fix: [branch-1.1] make Iceberg delete-file reflection failures fatal (#5515) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:36:16 UTC, 1 replies.
- Re: [I] `https://datafusion.apache.org/blog/` routes to a directory listing [datafusion-site] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/11 16:38:09 UTC, 1 replies.
- [PR] fix: [branch-1.1] keep a Spark scan unconverted when the plan reads input_file_name (#6703) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:38:12 UTC, 1 replies.
- [PR] fix: [branch-1.1] initialize dispatched kernels with the partition the native plan computes (#6700) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:41:43 UTC, 3 replies.
- [PR] feat(benchmarks): add plan diagnostics to SQL benchmark runners [datafusion] - posted by "Omega359 (via GitHub)" <gi...@apache.org> on 2026/10/11 16:43:19 UTC, 5 replies.
- [PR] deps: [branch-1.1] bump to datafusion 55.2.0 (#6766, #6862) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 16:46:49 UTC, 0 replies.
- [PR] [branch-1.1] fix: normalize float operands in the native comparison builder [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 17:02:15 UTC, 0 replies.
- [PR] refactor: build IcebergDataSource with a builder [datafusion-iceberg] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/11 17:06:29 UTC, 1 replies.
- [PR] [branch-1.1] fix: restore Spark write execs when reverting transition-heavy stages [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 17:08:14 UTC, 0 replies.
- Re: [PR] chore: add release infrastructure [datafusion-iceberg] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 17:33:31 UTC, 2 replies.
- [PR] test: migrate expect-test snapshots to insta [datafusion-iceberg] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/11 17:36:11 UTC, 1 replies.
- Re: [I] Separate JNI-free core logic and error classification from native JNI entry points [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/11 17:40:42 UTC, 1 replies.
- [PR] feat(executor): report executor memory usage in heartbeats [datafusion-ballista] - posted by "Richard-Durkee (via GitHub)" <gi...@apache.org> on 2026/10/11 17:44:17 UTC, 2 replies.
- Re: [PR] refactor: replace IcebergDataSource::new_with_predicate with a builder [datafusion-iceberg] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/11 17:44:37 UTC, 1 replies.
- [I] Native PartialMerge over input sorted on a prefix of its keys fails to spill on DataFusion 55.2 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/11 17:57:18 UTC, 0 replies.
- Re: [PR] feat(dataframe): add column to a dataframe (#25298) [datafusion] - posted by "cj-zhukov (via GitHub)" <gi...@apache.org> on 2026/10/11 18:02:16 UTC, 3 replies.
- [PR] Enable page-index pruning for Iceberg scans [datafusion-iceberg] - posted by "terbed (via GitHub)" <gi...@apache.org> on 2026/10/11 18:27:37 UTC, 11 replies.
- Re: [PR] feat: decoupled result service for serving query results [datafusion-ballista] - posted by "villebro (via GitHub)" <gi...@apache.org> on 2026/10/11 19:40:28 UTC, 9 replies.
- [PR] build(deps): bump taiki-e/install-action from 2.87.22 to 2.87.26 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/11 19:42:42 UTC, 2 replies.
- [PR] build(deps): bump github/codeql-action/init from 4.38.2 to 4.38.3 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/11 19:43:46 UTC, 2 replies.
- [PR] build(deps): bump github/codeql-action/analyze from 4.38.2 to 4.38.3 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/11 19:44:48 UTC, 2 replies.
- [PR] feat: build multi-column null-aware NOT IN on the subquery side [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/11 20:11:13 UTC, 8 replies.
- Re: [PR] docs: Add distributed DataFusion blog post to readings page [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/11 20:35:40 UTC, 1 replies.
- [PR] fix: use an IcebergCatalog for the test harness [datafusion-iceberg] - posted by "Perseus (via GitHub)" <gi...@apache.org> on 2026/10/11 21:34:04 UTC, 1 replies.
- [PR] perf: read NOT NULL tuple elements of a multi-column NOT IN as scope keys [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/11 22:19:43 UTC, 3 replies.
- Re: [PR] test (aggregation-fuzzer): exercise spilling under a bounded memory pool [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 02:02:49 UTC, 1 replies.
- Re: [PR] perf(sort-merge): cache current-row key per cursor to speed up SortPreservingMerge [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 02:02:52 UTC, 2 replies.
- Re: [PR] feat: support prefix-scoped object stores in the registry [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 02:02:56 UTC, 0 replies.
- Re: [PR] perf: Optimize semi-, anti-join implementation using existence probes [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 02:03:00 UTC, 4 replies.
- Re: [PR] Add transform_values UDF [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 02:03:03 UTC, 1 replies.
- Re: [PR] feat: add approx_top_k aggregate function [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 02:03:10 UTC, 1 replies.
- [PR] perf(sort-merge): skip null checks in ArrayValues when neither cursor has nulls [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/12 02:13:14 UTC, 11 replies.
- [PR] Apply recursion limit to set operation chains [datafusion-sqlparser-rs] - posted by "fengyue-xve (via GitHub)" <gi...@apache.org> on 2026/10/12 03:38:18 UTC, 6 replies.
- [PR] feat: plan Iceberg file tasks before execution using public APIs [datafusion-iceberg] - posted by "alexanderbianchi (via GitHub)" <gi...@apache.org> on 2026/10/12 03:42:53 UTC, 0 replies.
- Re: [PR] perf: opt substr into make_scalar_function dict fast path [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/12 03:46:43 UTC, 34 replies.
- [PR] fix: rewrite decimal-to-integer cast predicates as source-domain ranges [datafusion] - posted by "discord9 (via GitHub)" <gi...@apache.org> on 2026/10/12 03:52:49 UTC, 2 replies.
- [PR] perf: keep freed memory in mimalloc for dfbench and datafusion-cli [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 04:03:12 UTC, 8 replies.
- [PR] perf: push semi joins below inner joins and restrict decorrelated aggregates [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 04:03:59 UTC, 9 replies.
- [PR] test: migrate scalar hash coverage to SQL fixtures [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/12 07:05:30 UTC, 1 replies.
- [PR] test: migrate regex extraction and position coverage to SQL fixtures [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/12 07:05:53 UTC, 1 replies.
- [PR] feat: run admitted local queries as one native graph [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/12 07:25:04 UTC, 14 replies.
- Re: [PR] feat: support filtered batches in `LimitedBatchCoalescer` [datafusion] - posted by "lyne7-sc (via GitHub)" <gi...@apache.org> on 2026/10/12 07:38:10 UTC, 0 replies.
- Re: [PR] perf: avoid scanning `array_agg` state in size [datafusion] - posted by "lyne7-sc (via GitHub)" <gi...@apache.org> on 2026/10/12 07:38:33 UTC, 0 replies.
- [PR] ci: add slt-only test coverage [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/12 08:00:14 UTC, 1 replies.
- [PR] fix: do not drop GROUP BY keys using nullable UNIQUE constraints [datafusion] - posted by "buraksenn (via GitHub)" <gi...@apache.org> on 2026/10/12 08:18:02 UTC, 3 replies.
- [I] Dynamic filter pushdown into IcebergTableScan [datafusion-iceberg] - posted by "jverhoeks (via GitHub)" <gi...@apache.org> on 2026/10/12 08:21:15 UTC, 2 replies.
- Re: [PR] bench: Add benchmarks for ordered `ARRAY_AGG` and `STRING_AGG` [datafusion] - posted by "lyne7-sc (via GitHub)" <gi...@apache.org> on 2026/10/12 08:40:24 UTC, 2 replies.
- [I] Aggregates of `x` and `CAST(x AS ...)` in one query fail with "duplicate unqualified field name", even with aliases [datafusion] - posted by "cblp (via GitHub)" <gi...@apache.org> on 2026/10/12 09:49:58 UTC, 0 replies.
- [I] `sum` and `avg` over sliding window frames return NaN after an infinity leaves the frame [datafusion] - posted by "cblp (via GitHub)" <gi...@apache.org> on 2026/10/12 09:50:44 UTC, 1 replies.
- [I] Rewriting `SUM(x + c)` to `SUM(x) + c * COUNT(x)` changes the result for floating point `x` [datafusion] - posted by "cblp (via GitHub)" <gi...@apache.org> on 2026/10/12 09:51:30 UTC, 8 replies.
- [PR] docs: `#` is bitwise xor only in the PostgreSQL and Redshift dialects [datafusion] - posted by "rawsun007 (via GitHub)" <gi...@apache.org> on 2026/10/12 10:15:33 UTC, 1 replies.
- [I] S3 test suites can no longer pull the minio/minio image [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/12 12:13:49 UTC, 1 replies.
- [I] Native Iceberg writes: count the DataFiles a task keeps in its memory reservation [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 12:33:03 UTC, 0 replies.
- Re: [I] Nightly SNAPSHOT publishing is blocked until ASF Infra provisions Nexus credentials [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 12:40:22 UTC, 1 replies.
- [I] [EPIC] Refactor Operators for Maintainability [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/12 12:59:07 UTC, 12 replies.
- [I] Add a GroupsAccumulator for the native regr_* aggregates [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 13:00:13 UTC, 1 replies.
- [PR] test: run the S3 suites against an available MinIO image [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/12 13:11:25 UTC, 5 replies.
- [I] HashJoinExec loses build-side input order across batches on the hash map path [datafusion] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/12 13:20:43 UTC, 1 replies.
- [PR] build: stop publishing comet-common, the parent pom and comet-spark-integration [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 13:43:08 UTC, 3 replies.
- [I] Write blog post for 1.2.0 release [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 13:47:51 UTC, 1 replies.
- [PR] refactor: Rewrite Hash Join's regular (inner/left/right/full) join path [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/12 13:49:00 UTC, 13 replies.
- [PR] fix: keep build-side input order across batches in hash join [datafusion] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/12 13:54:19 UTC, 13 replies.
- [PR] chore(deps): bump tokio-util from 0.7.19 to 0.7.20 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 14:00:54 UTC, 1 replies.
- [PR] chore(ci): bump the github-codeql group with 2 updates [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 14:03:20 UTC, 3 replies.
- [PR] chore(ci): bump astral-sh/setup-uv from 10.2.0 to 10.3.0 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 14:03:43 UTC, 1 replies.
- [PR] chore(ci): bump actions/setup-node from 7.0.0 to 7.1.0 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 14:03:51 UTC, 1 replies.
- [PR] chore(ci): bump taiki-e/install-action from 2.87.26 to 2.87.27 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/12 14:04:00 UTC, 1 replies.
- [PR] docs: split benchmarking page into results and per-engine pages [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 14:09:33 UTC, 2 replies.
- [I] SQLAppStatusListenerMemoryLeakSuite "no memory leak" is flaky in the Spark SQL tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 14:17:15 UTC, 2 replies.
- [I] Rename Cast.is_spark4_plus and get_json_object_spark34 to describe the behavior they select [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 14:29:06 UTC, 0 replies.
- [I] Bug triage results: 2026-10-12 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 14:52:48 UTC, 0 replies.
- [I] `MaterializedCteExec::reset_state` clears its shared buffer in place [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 14:53:19 UTC, 0 replies.
- [I] Materialized CTE scans report unknown statistics, ordering and partitioning [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 14:53:22 UTC, 0 replies.
- [I] Protobuf serialization for materialized CTE plan nodes [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 14:53:23 UTC, 0 replies.
- [I] Use byte-bounded spill files for materialized CTEs [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 14:53:24 UTC, 1 replies.
- [I] Release the buffer of a materialized CTE when the last scan finishes [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 14:53:25 UTC, 0 replies.
- [I] Wrong results: Correlated subquery confuses same-named columns of two of its relations [datafusion] - posted by "thobe (via GitHub)" <gi...@apache.org> on 2026/10/12 14:56:52 UTC, 0 replies.
- [I] HashJoinExec: declare build-side order for LeftSemi, LeftAnti and LeftMark joins [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 14:57:49 UTC, 1 replies.
- [PR] fix: Keep same-named correlated columns apart when decorrelating subqueries [datafusion] - posted by "thobe (via GitHub)" <gi...@apache.org> on 2026/10/12 14:58:57 UTC, 0 replies.
- [I] Behavior-flag audit: fix Spark version comments on native flags and centralize the CollectSet check [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 15:14:37 UTC, 0 replies.
- [PR] fix: [branch-1.1] report task input metrics after the native iterator closes, and publish native metrics on the update interval (#5880, #6314) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 15:15:34 UTC, 1 replies.
- [I] Decide automatically when to materialize a CTE [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 15:17:06 UTC, 0 replies.
- [I] Make the materialized CTE nodes first-class `LogicalPlan` variants [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 15:17:08 UTC, 1 replies.
- [I] Push filters that all references share into the body of a materialized CTE [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 15:17:12 UTC, 0 replies.
- [I] Prune unused columns from the body of a materialized CTE [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 15:17:16 UTC, 0 replies.
- [I] Parse `WITH ... AS [NOT] MATERIALIZED` in `GenericDialect`, `DuckDbDialect` and `SQLiteDialect` [datafusion-sqlparser-rs] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/12 15:17:18 UTC, 0 replies.
- [PR] perf: [branch-1.1] speed up string, map and array conversion in JVM columnar shuffle (#6604) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 15:28:53 UTC, 1 replies.
- [PR] fix: compare a Remainder divisor with zero in Spark's ordering without ANSI [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 15:29:48 UTC, 1 replies.
- [PR] fix: do not rewrite `SUM(x + literal)` for floating point arguments [datafusion] - posted by "RishavTiwari25 (via GitHub)" <gi...@apache.org> on 2026/10/12 15:43:52 UTC, 4 replies.
- [PR] fix: preserve TPC-DS logical types in Python benchmarks [datafusion-comet] - posted by "ErikBPF (via GitHub)" <gi...@apache.org> on 2026/10/12 15:52:23 UTC, 1 replies.
- [PR] fix: bound parallel batch sorting in SortExec [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/12 15:58:48 UTC, 51 replies.
- Re: [PR] fix: fall back to Spark for NOT IN over an ordered streamed side [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/12 15:59:44 UTC, 7 replies.
- Re: [I] Support multiply and divide on intervals [datafusion] - posted by "RishavTiwari25 (via GitHub)" <gi...@apache.org> on 2026/10/12 16:01:52 UTC, 1 replies.
- [I] `array_concat` with an untyped `NULL` argument fails with "does not support type Int64" [datafusion] - posted by "RishavTiwari25 (via GitHub)" <gi...@apache.org> on 2026/10/12 16:03:47 UTC, 0 replies.
- Re: [I] Three dev/diffs weaken a local-shuffle-read assertion into a contradiction, breaking the Spark-only baseline [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 16:15:23 UTC, 0 replies.
- [I] Native broadcast nested loop joins report the streamed side's order without keeping it [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 16:17:50 UTC, 0 replies.
- [PR] feat: run global aggregates with no grouping keys or functions natively [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 16:18:01 UTC, 7 replies.
- Re: [PR] fix: Let DataFusion handles global aggregate with no grouping keys instead of falling back to Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 16:18:15 UTC, 1 replies.
- Re: [PR] fix: emit one row from a no-grouping aggregate with no aggregate expressions [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 16:29:04 UTC, 1 replies.
- Re: [I] Add an agent skill for datafusion-python extension authors [datafusion-python] - posted by "med9110 (via GitHub)" <gi...@apache.org> on 2026/10/12 16:30:00 UTC, 0 replies.
- [PR] refactor: delegate catalog scans to static table provider [datafusion-iceberg] - posted by "alexanderbianchi (via GitHub)" <gi...@apache.org> on 2026/10/12 16:32:10 UTC, 0 replies.
- [PR] fix: keep the values of sliced batches when coalescing a broadcast [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/12 16:47:13 UTC, 6 replies.
- [I] CometIcebergNativeSuite single-split sort-merge join DPP test fails on Spark 3.5 with AQE [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/12 17:06:01 UTC, 1 replies.
- [PR] fix: remove duplicate predicate benchmark result [datafusion] - posted by "Omega359 (via GitHub)" <gi...@apache.org> on 2026/10/12 17:12:28 UTC, 8 replies.
- [PR] feat(benchmarks): add standalone sort pushdown SQL suite [datafusion] - posted by "Omega359 (via GitHub)" <gi...@apache.org> on 2026/10/12 17:18:32 UTC, 1 replies.
- [PR] test: expect Spark 3.5's empty LocalTableScan in the single-split DPP join test [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/12 17:21:23 UTC, 1 replies.
- [PR] docs: add NestedLoopJoinExec metrics to user-guide metrics page [datafusion] - posted by "nikolas-sapa (via GitHub)" <gi...@apache.org> on 2026/10/12 17:22:42 UTC, 1 replies.
- [I] Joins with join type `Cross` (`CROSS JOIN`, `Dataset.crossJoin`) fall back to Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 17:31:48 UTC, 0 replies.
- [I] Machine-readable report of Comet coverage and fallback reasons [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 17:31:49 UTC, 0 replies.
- [PR] Insert checks for null insertions in required columns [datafusion-iceberg] - posted by "hareshkh (via GitHub)" <gi...@apache.org> on 2026/10/12 17:51:40 UTC, 0 replies.
- [PR] test: Deflake SQLAppStatusListenerMemoryLeakSuite [datafusion-comet] - posted by "LinSimon-901101 (via GitHub)" <gi...@apache.org> on 2026/10/12 17:52:44 UTC, 1 replies.
- [I] canAggregateBeConverted does not mirror doConvert's collated grouping key guard [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 17:53:12 UTC, 0 replies.
- Re: [PR] feat(benchmarks): enable Criterion automatically when a benchmark namespace is set [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/12 18:14:24 UTC, 1 replies.
- [PR] feat: update to datafusion 55 and remove distributed dataframe [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/12 18:15:44 UTC, 3 replies.
- [PR] feat: run joins of type Cross natively [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 18:24:44 UTC, 1 replies.
- [I] Native filter copies its surviving rows, which makes filter-then-aggregate on narrow tables slower than Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 18:25:26 UTC, 0 replies.
- [I] Support `min` and `max` over string and binary columns natively [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/12 18:52:55 UTC, 1 replies.
- [I] Docker entrypoints swallow SIGTERM, so graceful shutdown never runs in the published images [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 19:04:09 UTC, 3 replies.
- [I] MIN/MAX fail with an internal error on RunEndEncoded columns [datafusion] - posted by "grevend (via GitHub)" <gi...@apache.org> on 2026/10/12 19:09:47 UTC, 1 replies.
- [PR] fix: support RunEndEncoded arguments in MIN/MAX [datafusion] - posted by "grevend (via GitHub)" <gi...@apache.org> on 2026/10/12 19:18:58 UTC, 5 replies.
- [PR] test: add an end-to-end Iceberg read, repartition, and write benchmark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 19:37:04 UTC, 1 replies.
- Re: [PR] feat: support PivotFirst aggregate for the optimized PIVOT fast path [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 19:53:51 UTC, 10 replies.
- [I] [EPIC] Performance follow-ups from profiling the end-to-end Iceberg benchmark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:11:33 UTC, 1 replies.
- [I] Native Iceberg writes re-parse Hadoop's XML configuration in every task to re-read footers [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:11:35 UTC, 1 replies.
- [I] Native Iceberg writes do not use shuffle direct read for their input [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:11:41 UTC, 0 replies.
- [I] Make the native Iceberg writer's DictionaryChooser pre-pass cheaper [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:11:46 UTC, 1 replies.
- [I] Native Iceberg write eligibility builds two Hadoop configurations on every planning pass [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:11:50 UTC, 1 replies.
- [I] Reduce the cost of LZ4 compression in native shuffle [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:11:55 UTC, 1 replies.
- [I] Native hash-partitioned shuffle gathers rows one at a time with interleave [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:11:58 UTC, 2 replies.
- [I] Faster Parquet level encoding for nested columns (parquet-rs RleEncoder) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:12:07 UTC, 1 replies.
- [I] Faster string min/max statistics in the parquet-rs writer [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:12:10 UTC, 1 replies.
- [I] Reduce string dictionary interning and level computation cost in the parquet-rs writer [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:12:12 UTC, 1 replies.
- [I] Faster nested Parquet decoding in the native Iceberg scan (parquet-rs) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:12:17 UTC, 1 replies.
- [I] Native outer hash joins still lose a sorted streamed side's order over some caches and checkpoints [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:29:10 UTC, 2 replies.
- Re: [I] Array functions evaluate their second argument on rows where the array is NULL, raising errors that Spark skips [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:31:21 UTC, 0 replies.
- [PR] fix(docker): deliver SIGTERM to the Ballista processes in the images [datafusion-ballista] - posted by "villebro (via GitHub)" <gi...@apache.org> on 2026/10/12 20:31:30 UTC, 6 replies.
- [PR] perf: read native-written Parquet footers without parsing Hadoop's configuration [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:47:51 UTC, 1 replies.
- [I] Native Iceberg writes: pass each data file's footer back instead of re-reading it from storage [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 20:50:52 UTC, 2 replies.
- Re: [I] ClickHouse: Support `GLOBAL IN` / `GLOBAL NOT IN` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/12 21:04:39 UTC, 0 replies.
- [PR] perf: avoid duplicate Hadoop configs in Iceberg write detection [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 21:05:23 UTC, 1 replies.
- [PR] perf: read shuffle blocks directly in native Iceberg writes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 21:11:54 UTC, 0 replies.
- Re: [PR] Databricks: support multipart TABLE queries [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/12 21:18:04 UTC, 0 replies.
- Re: [PR] fix(executor): drain Flight before shutdown cleanup [datafusion-ballista] - posted by "villebro (via GitHub)" <gi...@apache.org> on 2026/10/12 21:39:06 UTC, 13 replies.
- [I] Bound the sorted-scan merge by how many files' key ranges overlap [datafusion-iceberg] - posted by "anuragmantri (via GitHub)" <gi...@apache.org> on 2026/10/12 22:01:56 UTC, 0 replies.
- [I] Merge sorted files in IcebergDataSource only when something above the scan uses their order [datafusion-iceberg] - posted by "anuragmantri (via GitHub)" <gi...@apache.org> on 2026/10/12 22:03:52 UTC, 0 replies.
- [PR] feat: run min and max over string and binary columns natively [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/12 22:14:28 UTC, 7 replies.
- [PR] feat(executor): name the largest memory consumers when a task runs out of memory [datafusion-ballista] - posted by "Richard-Durkee (via GitHub)" <gi...@apache.org> on 2026/10/12 22:19:53 UTC, 1 replies.
- [PR] fix: pick the signed zero Spark ranks first in native percentile [datafusion-comet] - posted by "zhangfengcdt (via GitHub)" <gi...@apache.org> on 2026/10/12 22:39:30 UTC, 12 replies.
- [I] Support the S3A magic committer in native Parquet writes to S3 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/12 22:43:33 UTC, 1 replies.
- [PR] feat(perf): compute routing and lookup hashes for case once [datafusion] - posted by "devanbenz (via GitHub)" <gi...@apache.org> on 2026/10/12 22:50:00 UTC, 1 replies.
- Re: [PR] Fix `Display` of quoted identifiers with a backslash before the quote [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/12 22:53:58 UTC, 1 replies.
- [PR] feat(benchmarks): add dict_encoding_sweep harness [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/13 00:00:43 UTC, 43 replies.
- [PR] SetExpr: apply recursive-protection to Display [datafusion-sqlparser-rs] - posted by "fengyue-xve (via GitHub)" <gi...@apache.org> on 2026/10/13 01:51:09 UTC, 4 replies.
- Re: [PR] fix: keep a projection's schema in step with its simplified expressions [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/13 01:58:43 UTC, 1 replies.
- Re: [PR] perf: optimize non-null FixedSizeBinary grouping [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/13 01:58:45 UTC, 1 replies.
- Re: [PR] bench: model remote object storage faithfully for --simulate-latency [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/13 01:58:47 UTC, 14 replies.
- Re: [PR] perf: elide redundant HashJoin dynamic-filter membership predicates for contiguous integer domains [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/13 01:58:51 UTC, 1 replies.
- Re: [PR] Unify map() list-row handling across list representations [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/13 01:58:53 UTC, 1 replies.
- [PR] refactor: simplify redundant iterator chains [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/13 02:09:37 UTC, 4 replies.
- [I] Select a null-free sort-merge cursor when the schema rules nulls out [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/13 03:15:37 UTC, 0 replies.
- [PR] fix: update quinn-proto to resolve cargo audit failures [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/13 04:03:40 UTC, 4 replies.
- [PR] test: verify native timestamp output timezone labels [datafusion-comet] - posted by "LinSimon-901101 (via GitHub)" <gi...@apache.org> on 2026/10/13 05:34:40 UTC, 1 replies.
- [PR] fix: accept an untyped `NULL` argument in `array_concat` [datafusion] - posted by "RishavTiwari25 (via GitHub)" <gi...@apache.org> on 2026/10/13 06:55:23 UTC, 0 replies.
- Re: [I] DataFrame::fill_null and fill_nan fail on column names with uppercase letters or dots [datafusion] - posted by "RishavTiwari25 (via GitHub)" <gi...@apache.org> on 2026/10/13 06:58:52 UTC, 1 replies.
- [PR] fix: reference columns by qualified name in `DataFrame::fill_null` / `fill_nan` [datafusion] - posted by "RishavTiwari25 (via GitHub)" <gi...@apache.org> on 2026/10/13 07:17:50 UTC, 2 replies.
- [PR] fix: coerce `nvl` / `ifnull` arguments like `coalesce` [datafusion] - posted by "RishavTiwari25 (via GitHub)" <gi...@apache.org> on 2026/10/13 07:28:39 UTC, 2 replies.
- [I] Support Decimal128 literals in predicate pushdown [datafusion-iceberg] - posted by "terbed (via GitHub)" <gi...@apache.org> on 2026/10/13 08:34:20 UTC, 0 replies.
- [I] Slow CI runners [datafusion-iceberg] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/13 09:34:03 UTC, 0 replies.
- Re: [PR] feat(perf): compute routing and lookup hashes once [datafusion] - posted by "tschwarzinger (via GitHub)" <gi...@apache.org> on 2026/10/13 09:45:40 UTC, 13 replies.
- Re: [PR] perf: specialize CASE WHEN for divide-by-zero protection [datafusion] - posted by "vishwanathmuthuraman (via GitHub)" <gi...@apache.org> on 2026/10/13 10:00:43 UTC, 0 replies.
- [I] [DISCUSSION] Is DataFusion's implementation growing too complicated? Are AI assisted PRs to blame? [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/13 10:18:06 UTC, 17 replies.
- Re: [PR] fix: [branch-1.1] normalize float operands in the native comparison builder [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 10:42:40 UTC, 0 replies.
- [PR] feat: support `interval * number`, `number * interval` and `interval / number` [datafusion] - posted by "RishavTiwari25 (via GitHub)" <gi...@apache.org> on 2026/10/13 10:46:40 UTC, 0 replies.
- [I] Changelog generator crashes on commits without a linked GitHub author [datafusion] - posted by "ASVLCII (via GitHub)" <gi...@apache.org> on 2026/10/13 10:54:35 UTC, 1 replies.
- [I] SortMergeJoin: derive sort options from input ordering, and allow it with a single partition when prefer_hash_join=false [datafusion] - posted by "bert-beyondloops (via GitHub)" <gi...@apache.org> on 2026/10/13 11:09:17 UTC, 1 replies.
- [PR] feat: derive SortMergeJoin sort options from input ordering and allow SMJ for a single partition [datafusion] - posted by "bert-beyondloops (via GitHub)" <gi...@apache.org> on 2026/10/13 11:37:04 UTC, 10 replies.
- Re: [D] DISCUSSION: Sep 2026 DataFusion Meetup in London [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/13 12:18:04 UTC, 0 replies.
- [I] FFI_TableProvider methods don't run inside a tokio runtime [datafusion] - posted by "mailmindlin (via GitHub)" <gi...@apache.org> on 2026/10/13 12:24:55 UTC, 0 replies.
- [PR] fix: Enter provider runtime when polling `FFI_TableProvider` methods [datafusion] - posted by "mailmindlin (via GitHub)" <gi...@apache.org> on 2026/10/13 12:29:12 UTC, 2 replies.
- [I] Native Delta scan declines Hadoop's S3A ProfileAWSCredentialsProvider [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/13 13:18:06 UTC, 0 replies.
- [PR] fix: leave memory for others when a spilled sort merges its runs [datafusion] - posted by "MisterRaindrop (via GitHub)" <gi...@apache.org> on 2026/10/13 13:44:14 UTC, 1 replies.
- [I] Postgres: support OVERRIDING { SYSTEM | USER } VALUE in INSERT [datafusion-sqlparser-rs] - posted by "zvonimir-dd (via GitHub)" <gi...@apache.org> on 2026/10/13 14:06:45 UTC, 1 replies.
- [I] Postgres: support WHERE index_predicate in the ON CONFLICT conflict target [datafusion-sqlparser-rs] - posted by "zvonimir-dd (via GitHub)" <gi...@apache.org> on 2026/10/13 14:06:46 UTC, 1 replies.
- [I] Add sqllogictests for scans after a schema change with no write since [datafusion-iceberg] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/13 14:15:03 UTC, 0 replies.
- [PR] Postgres: support OVERRIDING { SYSTEM | USER } VALUE in INSERT [datafusion-sqlparser-rs] - posted by "zvonimir-dd (via GitHub)" <gi...@apache.org> on 2026/10/13 14:25:06 UTC, 5 replies.
- [PR] Postgres: support WHERE index_predicate in the ON CONFLICT target [datafusion-sqlparser-rs] - posted by "zvonimir-dd (via GitHub)" <gi...@apache.org> on 2026/10/13 14:25:10 UTC, 5 replies.
- [PR] fix: end the Delta scan's plan-data key with its plan id [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/13 14:38:42 UTC, 3 replies.
- [PR] ocs: Add det to Known Users [datafusion] - posted by "saurabhr2 (via GitHub)" <gi...@apache.org> on 2026/10/13 14:44:35 UTC, 3 replies.
- [I] Broadcast serialization keeps 64-bit offsets for large_string and large_binary children of nested columns [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 15:06:20 UTC, 0 replies.
- [PR] feat: support Spark-compatible `stack` function [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/13 15:27:36 UTC, 12 replies.
- Re: [PR] deps: use DataFusion main (4a5d580) with Arrow/Parquet 60 and object_store 0.14 [datafusion-comet] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/13 15:37:00 UTC, 1 replies.
- [I] Bump iceberg-rust past apache/iceberg-rust#3255 and narrow the nested schema evolution fallback [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 16:02:12 UTC, 0 replies.
- [I] Wrong results: with `pushdown_filters = true`, a filter on a volatile subquery column is evaluated again in the Parquet scan [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 16:25:10 UTC, 3 replies.
- [I] Spark's task CPU time (`executorCpuTime`) leaves out native execution for plans with no JVM input [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 16:26:42 UTC, 0 replies.
- [I] Native string and binary `min`/`max` under-report memory in hash aggregates [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 16:30:28 UTC, 1 replies.
- [PR] perf: make the native Iceberg writer's dictionary pre-pass 1.6x to 3.1x faster [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 17:08:56 UTC, 0 replies.
- [PR] ignore me [datafusion] - posted by "rluvaton (via GitHub)" <gi...@apache.org> on 2026/10/13 17:13:54 UTC, 19 replies.
- [PR] feat: make the materialized CTE nodes first-class LogicalPlan variants [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 17:29:50 UTC, 2 replies.
- [PR] fix: keep the output of a materialized CTE per run, not in the plan [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 17:29:55 UTC, 1 replies.
- [PR] feat: report statistics, ordering and partitioning of materialized CTE scans [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 17:30:02 UTC, 2 replies.
- [PR] feat: release the output of a materialized CTE when the last scan finishes [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 17:30:04 UTC, 3 replies.
- [PR] feat: protobuf serialization for the materialized CTE plan nodes [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 17:30:07 UTC, 2 replies.
- [PR] feat: prune unused columns from the body of a materialized CTE [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 17:30:09 UTC, 2 replies.
- [PR] feat: push filters that all references share into the body of a materialized CTE [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 17:30:13 UTC, 2 replies.
- [PR] feat: decide automatically when to materialize a CTE [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 17:30:15 UTC, 2 replies.
- Re: [I] Make AggregationFuzzer reproducible [datafusion] - posted by "stantheman0128 (via GitHub)" <gi...@apache.org> on 2026/10/13 17:39:54 UTC, 1 replies.
- [PR] perf: append sort-merge join output pairs in bulk [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 17:44:27 UTC, 9 replies.
- [I] ORDER BY can return NULLs out of order across sorted Parquet files [datafusion] - posted by "rank-p (via GitHub)" <gi...@apache.org> on 2026/10/13 17:57:54 UTC, 1 replies.
- [PR] Fix dictionary LIKE coercion [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/13 18:22:21 UTC, 9 replies.
- [PR] fix: include nulls in file ordering bounds [datafusion] - posted by "rank-p (via GitHub)" <gi...@apache.org> on 2026/10/13 18:22:46 UTC, 5 replies.
- [PR] feat: add support for comet cartesian join [datafusion-comet] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/13 18:35:05 UTC, 2 replies.
- [PR] Sequence invocation ceiling [datafusion-comet] - posted by "nat-openai (via GitHub)" <gi...@apache.org> on 2026/10/13 18:47:24 UTC, 0 replies.
- [PR] feat: support the S3A magic committer in native Parquet writes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 18:59:12 UTC, 11 replies.
- [PR] Assert exact errors in negative tests (1/4): PostgreSQL tests [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/13 19:16:46 UTC, 4 replies.
- [PR] Assert exact errors in negative tests (2/4): common and parser unit tests [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/13 19:23:28 UTC, 3 replies.
- [I] Add `CONTRIBUTING.md` [datafusion-python] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 19:23:32 UTC, 1 replies.
- [PR] Assert exact errors in negative tests (3/4): dialect tests [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/13 19:24:39 UTC, 3 replies.
- [PR] Assert exact errors in negative tests (4/4): deny clippy::assertions_on_result_states [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/13 19:28:28 UTC, 3 replies.
- [I] Store offsets as lengths in shuffle blocks to shrink shuffle files [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 19:33:42 UTC, 0 replies.
- [PR] fix: push filters above a pure extraction projection into the scan below it [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/13 19:34:29 UTC, 1 replies.
- [PR] test: tag the Azure ABFS suites with AzureTest [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/13 19:36:39 UTC, 3 replies.
- Re: [I] Variance and standard deviation return incorrect results for large nearby values [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/13 19:47:36 UTC, 0 replies.
- [PR] perf: store shuffle offsets as lengths with zstd [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 20:18:58 UTC, 7 replies.
- [PR] PostgreSQL: Remove unreachable empty op_types branch in operator FUNCTION items [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/13 20:33:51 UTC, 3 replies.
- [PR] Reject unquoted reserved keywords as table names [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/13 20:46:07 UTC, 6 replies.
- [I] Upload S3A magic committer files natively instead of through the JVM [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 20:47:04 UTC, 0 replies.
- [PR] perf: preserve native DV bitmap compression [datafusion-comet] - posted by "ErikBPF (via GitHub)" <gi...@apache.org> on 2026/10/13 20:49:36 UTC, 4 replies.
- [I] TPC-DS q54/q68: local SF100 results and distributed reproduction limits [datafusion-comet] - posted by "ErikBPF (via GitHub)" <gi...@apache.org> on 2026/10/13 20:50:38 UTC, 0 replies.
- Re: [PR] perf: make the native Iceberg writer's dictionary pre-pass 1.8x to 3.9x faster [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/13 21:16:13 UTC, 10 replies.
- Re: [I] Follow up on post-merge review of the native sequence kernel: perf crossover, unbounded per-batch allocation, and missing ceiling coverage [datafusion-comet] - posted by "nat-openai (via GitHub)" <gi...@apache.org> on 2026/10/13 21:29:23 UTC, 0 replies.
- [PR] MySQL: Add support for LOAD DATA INFILE [datafusion-sqlparser-rs] - posted by "AndreaScotti01 (via GitHub)" <gi...@apache.org> on 2026/10/13 21:32:29 UTC, 0 replies.
- [I] MySQL: Support LOAD DATA ... INFILE [datafusion-sqlparser-rs] - posted by "AndreaScotti01 (via GitHub)" <gi...@apache.org> on 2026/10/13 21:41:55 UTC, 0 replies.
- [PR] ci: purge JAR-less POMs that leave out the packaging element [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 22:08:51 UTC, 0 replies.
- [PR] Sequence try grow [datafusion-comet] - posted by "nat-openai (via GitHub)" <gi...@apache.org> on 2026/10/13 22:21:24 UTC, 3 replies.
- Re: [I] Ranked backlog: native scalar expressions with per-row optimization opportunities [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:01 UTC, 1 replies.
- Re: [I] Shuffle performance audit: candidate optimizations needing investigation [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:05 UTC, 2 replies.
- Re: [I] [EPIC] Planner, serde, and optimizer rule performance audit [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:09 UTC, 0 replies.
- Re: [I] Use end to end microbenchmarks to prevent performance regressions between releases [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:14 UTC, 0 replies.
- Re: [I] array_append: ANSI item error is swallowed when the array is NULL [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:17 UTC, 1 replies.
- Re: [I] Re-enable COUNT for mixed Spark partial / Comet final aggregate execution [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:22 UTC, 0 replies.
- Re: [I] Establish nomenclature style guide and audit operator names for clarity [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:26 UTC, 3 replies.
- Re: [I] Add a docs-review Claude skill to enforce style guide and documentation quality [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:29 UTC, 1 replies.
- Re: [I] Kubernetes guide example never enables Comet because it sets no off-heap memory [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:32 UTC, 0 replies.
- Re: [I] Follow-ups to #6163: correct the `fair_unified` description and prepare `spark.comet.exec.memoryPool.fraction` for removal [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:07:36 UTC, 0 replies.
- [PR] MySQL: Add support for `ZEROFILL` on numeric data types [datafusion-sqlparser-rs] - posted by "davisjc (via GitHub)" <gi...@apache.org> on 2026/10/13 23:09:22 UTC, 2 replies.
- [PR] docs: run Comet SQL in Kubernetes example [datafusion-comet] - posted by "1cbyc (via GitHub)" <gi...@apache.org> on 2026/10/13 23:21:25 UTC, 4 replies.
- [I] The in-memory cache stores small input batches as they arrive, so a cached repartition over many map tasks holds thousands of small batches [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:39:45 UTC, 0 replies.
- [I] Every cached batch allocates a 1 MiB heap chunk, however small its payload [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:39:57 UTC, 0 replies.
- [I] On Spark 4.0+, an adaptive cached plan that ends in a Spark row operator is converted into Spark column vectors and then copied into Arrow [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/13 23:39:58 UTC, 0 replies.
- [PR] perf: reuse input validity buffers instead of rebuilding null masks per row [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/13 23:41:49 UTC, 0 replies.
- [PR] feat: NestedInputAccess capability for nested read pruning and row group / page pruning [datafusion] - posted by "cetra3 (via GitHub)" <gi...@apache.org> on 2026/10/14 00:03:32 UTC, 8 replies.
- Re: [PR] feat: expose UDF field access and input requirements for Parquet pruning [datafusion] - posted by "cetra3 (via GitHub)" <gi...@apache.org> on 2026/10/14 00:07:25 UTC, 0 replies.
- [I] Native Iceberg writes: translate the Parquet settings that have a parquet-rs equivalent [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:43:22 UTC, 0 replies.
- [I] Native Iceberg writes: support the object-storage layout (`write.object-storage.enabled=true`) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:43:24 UTC, 0 replies.
- [I] Native Iceberg writes: stop falling back on settings iceberg-java's writer ignores [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:43:24 UTC, 0 replies.
- [I] Native Iceberg writes: admit S3 settings that cannot change the written object, and translate S3 credential providers and encryption settings [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:43:26 UTC, 0 replies.
- [I] Native Iceberg writes: support `uuid` and `unknown` columns [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:43:29 UTC, 1 replies.
- [I] Native Iceberg writes: support Azure and `oss` data locations, S3-compatible scheme aliases, and `gs` through `HadoopFileIO` [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:43:29 UTC, 0 replies.
- [I] Native Iceberg writes succeed for gzip with a numeric compression level and for brotli, where iceberg-java fails [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:43:31 UTC, 0 replies.
- [PR] docs: record the plan for each native Iceberg write fallback [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:44:43 UTC, 0 replies.
- [PR] feat: make native Iceberg writes opt-in for 1.2.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:55:09 UTC, 1 replies.
- Re: [I] ci: a transient Maven Central failure in lint-java is reported as a scalafix violation [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 00:55:48 UTC, 0 replies.
- [PR] fix: make Comet's in-memory cache opt-in again [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 01:10:30 UTC, 1 replies.
- Re: [PR] feat: Prune complex/nested predicates via statistics propagation [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 01:41:04 UTC, 1 replies.
- Re: [PR] deps: [branch-1.1] bump to datafusion 55.2.0 and iceberg-rust af1da4c (#6766, #6862, #6649) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 01:43:08 UTC, 0 replies.
- Re: [PR] perf: reuse validity buffers and use unary kernels in native expressions [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/14 02:17:40 UTC, 4 replies.
- [I] Label Delta pull requests with an area label [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/14 02:26:19 UTC, 2 replies.
- [PR] ci: label Delta pull requests with area:Delta [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/14 02:41:53 UTC, 2 replies.
- [I] Native string to decimal cast returns zero or NULL where Spark's rescale throws ArithmeticException [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/14 02:53:55 UTC, 0 replies.
- Re: [PR] bench: expand dictionary group-by coverage [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/14 03:39:00 UTC, 1 replies.
- Re: [I] Global aggregate with no grouping keys and no aggregate functions falls back to Spark ("No group by or aggregation") [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 03:50:25 UTC, 0 replies.
- Re: [PR] fix: Not all rows are accounted in RowCursorStream [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 04:02:56 UTC, 2 replies.
- Re: [PR] fix: resolve pass-through columns against the input when merging an extraction projection [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 04:25:05 UTC, 3 replies.
- Re: [PR] fix: do not evaluate a volatile coalesce or nvl argument twice [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 04:41:52 UTC, 9 replies.
- Re: [PR] fix: validate cast target type in interval check_support [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 04:43:21 UTC, 6 replies.
- [I] Pass a scan's Hadoop options to libhdfs [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/14 04:51:14 UTC, 0 replies.
- Re: [PR] Full join output partitioning [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 04:53:19 UTC, 0 replies.
- Re: [PR] fix: preserve grouping set member names during type coercion [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/14 05:15:57 UTC, 0 replies.
- Re: [I] Group by rollup/cube/etc.. fails with new type_coercion [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/14 05:15:59 UTC, 0 replies.
- Re: [I] Destructure proto hooks for cast physical expressions [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 06:05:38 UTC, 0 replies.
- Re: [PR] ci: run the Rust workflow for fork pull requests on the fork [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 06:10:25 UTC, 26 replies.
- Re: [PR] perf: avoid capturing unused evicted rows in TopK [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 06:11:33 UTC, 2 replies.
- Re: [PR] fix: validate parquet.coerce_int96 when it is set [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 06:13:34 UTC, 4 replies.
- [I] SanityCheckPlan error when ordering by a literal column from the probe side of a hash join [datafusion] - posted by "acbokade (via GitHub)" <gi...@apache.org> on 2026/10/14 06:18:25 UTC, 1 replies.
- [I] Correlated `EXISTS` on a `CASE` or `UNION ALL` column fails with "Can't compare arrays of different types" [datafusion] - posted by "acbokade (via GitHub)" <gi...@apache.org> on 2026/10/14 06:18:35 UTC, 1 replies.
- [I] Internal error (nullability mismatch) when aggregating over `CASE WHEN a < b THEN a ELSE ... END` [datafusion] - posted by "acbokade (via GitHub)" <gi...@apache.org> on 2026/10/14 06:18:37 UTC, 0 replies.
- [PR] fix: preserve Spark nested null ordering in native sort [datafusion-comet] - posted by "Weijun-H (via GitHub)" <gi...@apache.org> on 2026/10/14 06:18:54 UTC, 7 replies.
- Re: [PR] fix: carry across component bounds when stepping composite interval values [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 06:45:15 UTC, 2 replies.
- Re: [PR] feat: add opt-in strict predicate short-circuit evaluation [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 06:50:25 UTC, 1 replies.
- [PR] Account for TopK common-prefix converter memory [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 07:03:58 UTC, 5 replies.
- Re: [PR] fix: plan aggregates over CASE conditions with multiple columns [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 07:09:24 UTC, 4 replies.
- [PR] perf(pwmj): build output batches from buffered runs and one streamed … [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/14 07:27:58 UTC, 4 replies.
- Re: [PR] docs: document ^ as the bitwise xor operator [datafusion] - posted by "Jefffrey (via GitHub)" <gi...@apache.org> on 2026/10/14 07:30:05 UTC, 1 replies.
- Re: [PR] fix: guard against out-of-bounds column statistics in count's fast path [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/14 07:31:47 UTC, 3 replies.
- Re: [I] Avoid inferring full anti-join coverage from range bounds [datafusion] - posted by "LDM-A (via GitHub)" <gi...@apache.org> on 2026/10/14 08:03:50 UTC, 0 replies.
- [PR] perf: vectorize int, decimal, float and boolean casts to timestamp [datafusion-comet] - posted by "Ersa-tech (via GitHub)" <gi...@apache.org> on 2026/10/14 09:15:33 UTC, 1 replies.
- [I] Native element_at and map_from_arrays skip a shared subexpression on NULL rows under ANSI [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/14 09:29:56 UTC, 3 replies.
- [PR] Fix volatile projection filter pushdown [datafusion] - posted by "Tiancheng-Xu (via GitHub)" <gi...@apache.org> on 2026/10/14 09:56:43 UTC, 0 replies.
- [I] `unwrap_cast_in_comparison` does not unwrap `CAST(date_col AS TIMESTAMP) timestamp_literal` [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 11:13:58 UTC, 2 replies.
- [I] MIN/MAX don't unwrap nested encodings inside Dictionary columns [datafusion] - posted by "grevend (via GitHub)" <gi...@apache.org> on 2026/10/14 11:38:45 UTC, 0 replies.
- [PR] docs: show runnable query examples in API documentation [datafusion] - posted by "Harshil-1603 (via GitHub)" <gi...@apache.org> on 2026/10/14 11:59:44 UTC, 4 replies.
- [I] JVM codegen dispatch skips a shared subexpression on NULL rows under ANSI [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/14 12:06:07 UTC, 1 replies.
- Re: [I] Release DataFusion `54.2.0` (minor/patch) Release [datafusion] - posted by "lilic (via GitHub)" <gi...@apache.org> on 2026/10/14 12:20:45 UTC, 6 replies.
- [I] Native null short-circuit evaluates shared arguments eagerly when subexpression elimination is off [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/14 12:39:03 UTC, 2 replies.
- [PR] [DO NOT MERGE] test(executor): exercise DataFusion StageBoundary API [datafusion-ballista] - posted by "edmondop (via GitHub)" <gi...@apache.org> on 2026/10/14 13:17:09 UTC, 0 replies.
- [I] Merge queue times out PRs whose checks are still running, so merging takes many manual attempts and CI is re-run from scratch [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 13:48:48 UTC, 8 replies.
- [I] Planner panics instead of returning errors for out-of-range Decimal128 list literals and unsupported ANSI binary operators [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:25 UTC, 2 replies.
- [I] Deduplicate spark_ceil and spark_floor and port floor's decimal boundary tests to ceil [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:30 UTC, 1 replies.
- [I] Extract a shared metrics-preserving exec wrapper from CometFilterExec and CometProjectionExec [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:32 UTC, 2 replies.
- [I] Deduplicate Legacy/Ansi/Try integer SUM accumulators in sum_int.rs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:34 UTC, 0 replies.
- [I] Deduplicate field-major struct append paths in shuffle spark_unsafe/row.rs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:35 UTC, 0 replies.
- [I] Share Parquet field-ID and name resolution between remap_physical_schema and match_struct_fields [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:37 UTC, 1 replies.
- [I] [EPIC] Finish moving PhysicalPlanner::create_plan and create_expr onto the operator and expression registries [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:40 UTC, 0 replies.
- [I] Deduplicate ASCII and char paths in levenshtein_distance_with_threshold [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:42 UTC, 1 replies.
- [I] Extract a variable-length slot writer from TypedElements::write_elements_slow in columnar_to_row.rs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:45 UTC, 1 replies.
- [I] Replace duplicated scalar/array broadcast match in math_funcs with a shared helper [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:47 UTC, 1 replies.
- [I] Extract shared list-array construction from the split_* functions in split.rs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:50 UTC, 1 replies.
- [I] Reuse hash_list_primitive! for string/binary list elements and factor out map-entry hashing loops [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 13:55:51 UTC, 1 replies.
- Re: [I] CI: Merge queue rejects PR even after all tests pass [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 13:56:04 UTC, 0 replies.
- [PR] ci: raise the merge queue status check timeout to 360 minutes [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 13:57:48 UTC, 11 replies.
- [PR] perf: write a cached batch under the chunk size into one chunk of its exact size [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:06:30 UTC, 0 replies.
- [PR] docs: explain timestamp timezone comparisons [datafusion] - posted by "Harshil-1603 (via GitHub)" <gi...@apache.org> on 2026/10/14 14:11:04 UTC, 0 replies.
- [I] Unparser silently drops CASE operand and ELSE branch when they fail to unparse [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:16:56 UTC, 1 replies.
- [I] Struct union type coercion takes field nullability from the wrong field when field order differs [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:16:58 UTC, 1 replies.
- [I] gcd benchmarks pass number_rows: 0 for 100k-row inputs [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:00 UTC, 2 replies.
- [I] Split Unparser::select_to_sql_recursively into per-plan-node methods [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:03 UTC, 2 replies.
- [I] Break up ensure_distribution_with_stats and enforce_distribution_relationships in EnforceDistribution [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:05 UTC, 1 replies.
- [I] Move large LogicalPlan arms out of DefaultPhysicalPlanner::map_logical_node_to_physical [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:07 UTC, 1 replies.
- [I] Move large Statement arms out of SqlToRel::sql_statement_to_plan_with_context_impl [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:09 UTC, 1 replies.
- [I] Deduplicate copy-pasted rule families in Simplifier::f_up [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:11 UTC, 2 replies.
- [I] Share a single pad kernel between lpad and rpad [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:15 UTC, 3 replies.
- [I] Deduplicate Concat string and binary builders in datafusion-functions [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:17 UTC, 1 replies.
- [I] Split PushDownFilter::rewrite into per-plan-node pushdown helpers [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:18 UTC, 1 replies.
- [I] Use the shared aggr_test_schema in CSV scan tests instead of a local copy [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:22 UTC, 5 replies.
- [I] Deduplicate bucket computation in width_bucket_interval_mdn_exact [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:22 UTC, 5 replies.
- [I] Merge duplicated wildcard arms in LogicalPlanBuilder project_with_validation [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:24 UTC, 1 replies.
- [I] [EPIC] Reduce complexity and duplication hotspots in DataFusion [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:17:42 UTC, 4 replies.
- [I] Executor never honours scheduler_connect_timeout_seconds and retries the scheduler connection forever [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:42:35 UTC, 0 replies.
- [PR] fix: honor subexpression elimination off in the native null short-circuit [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/14 14:42:36 UTC, 3 replies.
- [I] AQE: resolve_stage and rollback_*_stage drop the stage from the graph when the conversion fails [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:42:38 UTC, 1 replies.
- [I] [EPIC] Share execution graph logic between StaticExecutionGraph and AdaptiveExecutionGraph [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:42:49 UTC, 1 replies.
- Re: [I] AQE: handle executor failure on the adaptive execution path [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:42:57 UTC, 0 replies.
- [I] Split QueryStageScheduler::on_receive into per-event handlers [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:00 UTC, 0 replies.
- [I] Break start_executor_process_inner into startup phases [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:02 UTC, 0 replies.
- [I] Deduplicate execute_query_pull and execute_query_push in DistributedQueryExec [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:03 UTC, 1 replies.
- [I] Extract shared execute/handoff logic from the three shuffle writer execs [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:05 UTC, 0 replies.
- [I] AQE: split SelectJoinRule::optimize into per-action methods and flatten its nesting [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:10 UTC, 0 replies.
- [I] TUI: unify App::on_key and App::on_key_sync so key handling lives in one place [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:11 UTC, 0 replies.
- [I] Deduplicate the TPC-H table schema across scheduler tests and benchmarks [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:13 UTC, 2 replies.
- [I] BallistaClient: share retry logic between execute_do_get and execute_do_action_with_header, and don't panic when io_retries_times is 0 [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:16 UTC, 0 replies.
- [I] TUI: collapse repeated sort-order blocks in JobsData::sort_jobs and share table scrolling helpers [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:18 UTC, 4 replies.
- [I] Share the binding driver between bind_task_bias and bind_task_round_robin [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:22 UTC, 1 replies.
- [I] [EPIC] Reduce complexity and duplication hotspots in Ballista [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 14:43:35 UTC, 2 replies.
- [PR] fix: extract bundled native libraries into private directories [datafusion-comet] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/14 14:48:56 UTC, 6 replies.
- [PR] fix: read Hive's null partition placeholder as NULL [datafusion] - posted by "xanderbailey (via GitHub)" <gi...@apache.org> on 2026/10/14 14:49:07 UTC, 11 replies.
- [PR] fix(executor): honour scheduler_connect_timeout_seconds [datafusion-ballista] - posted by "samuel7james (via GitHub)" <gi...@apache.org> on 2026/10/14 14:58:35 UTC, 5 replies.
- [PR] fix: propagate CASE unparser errors [datafusion] - posted by "1cbyc (via GitHub)" <gi...@apache.org> on 2026/10/14 15:04:09 UTC, 3 replies.
- [PR] perf: combine small columnar batches before caching them [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 15:08:42 UTC, 1 replies.
- [PR] refactor: share the REPLACE and validation steps of the wildcard arms in project_with_validation [datafusion] - posted by "ozenyunus35 (via GitHub)" <gi...@apache.org> on 2026/10/14 15:09:32 UTC, 2 replies.
- [PR] fix: treat -0.0 and 0.0 as one value in arrays_overlap on Spark 4.0.5, 4.1.4 and 4.2.1 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 15:29:05 UTC, 5 replies.
- [PR] refactor: share Parquet field-id and name resolution between root and nested fields [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 15:29:15 UTC, 3 replies.
- [I] SQL planner calls `LogicalPlan::using_columns()` once per SELECT item, making wide nested SELECTs quadratic [datafusion] - posted by "JoeryH (via GitHub)" <gi...@apache.org> on 2026/10/14 15:44:38 UTC, 0 replies.
- [I] `DFSchema` column lookup is a linear scan, making logical planning and type coercion quadratic in schema width [datafusion] - posted by "JoeryH (via GitHub)" <gi...@apache.org> on 2026/10/14 15:45:00 UTC, 1 replies.
- [PR] perf: build an AQE cache that ends in a Spark operator straight into Arrow [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 15:52:43 UTC, 1 replies.
- [PR] fix: share Ballista client retry handling [datafusion-ballista] - posted by "1cbyc (via GitHub)" <gi...@apache.org> on 2026/10/14 15:56:03 UTC, 2 replies.
- [PR] feat(parquet): add NDV cap for dictionary reads [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/14 16:04:48 UTC, 60 replies.
- [I] Unparser turns NULL list literals into `[]` and fails on NULL struct/map literals [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 16:07:54 UTC, 1 replies.
- [PR] fix: stop building maps natively when the key type holds a FLOAT or DOUBLE [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 16:11:31 UTC, 7 replies.
- [PR] perf: compute using columns once per SELECT, not per item [datafusion] - posted by "JoeryH (via GitHub)" <gi...@apache.org> on 2026/10/14 16:18:53 UTC, 0 replies.
- [PR] refactor: deduplicate `concat` string and binary builders [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 16:28:45 UTC, 8 replies.
- [I] Native Iceberg scan fails a VERSION AS OF read of a column whose type was promoted after the snapshot [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 16:33:29 UTC, 1 replies.
- [PR] [branch-54] fix: prevent LEAD/LAG IGNORE NULLS panic without null bitmap (#23706) [datafusion] - posted by "lilic (via GitHub)" <gi...@apache.org> on 2026/10/14 16:36:39 UTC, 3 replies.
- [PR] chore(deps): bump uuid from 1.27.0 to 1.28.0 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 16:39:01 UTC, 1 replies.
- [PR] chore(deps): bump serde_json from 1.0.151 to 1.0.154 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 16:40:31 UTC, 1 replies.
- [PR] chore(deps): bump pydata-sphinx-theme from 0.21.0 to 0.23.0 in the all-uv-deps group [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 17:35:47 UTC, 1 replies.
- [PR] chore(deps): bump the codeql-actions group across 1 directory with 2 updates [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 17:36:37 UTC, 3 replies.
- [PR] chore(deps): bump taiki-e/install-action from 2.87.23 to 2.87.27 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 17:37:35 UTC, 1 replies.
- [PR] chore(deps): bump astral-sh/setup-uv from 10.2.0 to 10.3.0 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 17:38:14 UTC, 1 replies.
- [PR] chore(deps): bump actions/upload-artifact from 7.0.1 to 7.0.2 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 17:38:23 UTC, 1 replies.
- [PR] chore(deps): bump actions/download-artifact from 8.0.1 to 8.0.2 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 17:39:07 UTC, 1 replies.
- [PR] chore(deps): bump actions/setup-node from 7.0.0 to 7.1.0 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 17:39:35 UTC, 3 replies.
- Re: [I] Proposal: Decoupled Result Service for Ballista [datafusion-ballista] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/14 17:40:42 UTC, 0 replies.
- [PR] refactor: share one TPC-H schema across scheduler tests and benchmarks [datafusion-ballista] - posted by "cestercian (via GitHub)" <gi...@apache.org> on 2026/10/14 17:43:09 UTC, 1 replies.
- [PR] chore(deps): bump the all-other-cargo-deps group with 7 updates [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 17:46:21 UTC, 0 replies.
- [I] Nested field-id reads give one file column to both an id match and a name match; the root returns null [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 18:13:24 UTC, 1 replies.
- [PR] feat(benchmarks): prototype adaptive hash join mode selection (AQE) [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 18:30:51 UTC, 0 replies.
- [I] A cached aggregate stores each output slice with the bytes of the slices before it, inflating its size statistics and memory [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 18:37:22 UTC, 0 replies.
- [PR] Bump serde_json from 1.0.151 to 1.0.154 [datafusion-sqlparser-rs] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 18:37:40 UTC, 1 replies.
- [PR] fix: fall back for brotli Iceberg writes when Hadoop's BrotliCodec cannot be loaded [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 18:49:48 UTC, 1 replies.
- [PR] ci: raise the merge queue status check timeout to 360 minutes [datafusion-sqlparser-rs] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 19:08:51 UTC, 3 replies.
- Re: [I] Enable page index pruning for Iceberg scans [datafusion-iceberg] - posted by "terbed (via GitHub)" <gi...@apache.org> on 2026/10/14 19:48:56 UTC, 0 replies.
- Re: [PR] feat(optimizer): coalesce peer first_value / last_value into a single struct aggregate [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 20:37:08 UTC, 0 replies.
- Re: [PR] feat: skip hash shuffle for date_bin/date_trunc on Range([timestamp]) [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 20:37:52 UTC, 2 replies.
- Re: [PR] feat: allow extension `ExecutionPlan`s to decode via a per-type registry instead of `PhysicalExtensionCodec` [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 20:38:38 UTC, 4 replies.
- Re: [PR] refactor: use group clustering terminology in aggregate execution [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 20:40:25 UTC, 10 replies.
- [I] Howard Hinnant civil-date algorithms hand-written 7 times across 3 crates [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 21:02:56 UTC, 0 replies.
- Re: [I] ListingTable handling of missing partition values [datafusion] - posted by "xanderbailey (via GitHub)" <gi...@apache.org> on 2026/10/14 21:03:06 UTC, 0 replies.
- [PR] build: use a single jni version across the native workspace [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 21:10:08 UTC, 1 replies.
- [PR] fix: report OneOf signature mismatches as planning errors [datafusion] - posted by "SingletonYe (via GitHub)" <gi...@apache.org> on 2026/10/14 21:13:30 UTC, 4 replies.
- Re: [PR] docs: add proposal to establish Apache Comet as a top-level project [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 21:14:15 UTC, 0 replies.
- [PR] [WIP][Experimental] feat: add `datafusion.execution.isolated_partitions` for distributed-safe join selection [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 21:23:48 UTC, 3 replies.
- [PR] [WIP][Experimental] feat: use DataFusion's `isolated_partitions` option for broadcast-safe join selection [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 21:23:56 UTC, 0 replies.
- Re: [PR] fix: [branch-1.1] restore Spark write execs when reverting transition-heavy stages [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/14 21:40:42 UTC, 2 replies.
- [I] unnest drops the list item field's metadata (e.g. Arrow extension types) [datafusion] - posted by "jiayuasu (via GitHub)" <gi...@apache.org> on 2026/10/14 21:42:02 UTC, 1 replies.
- [PR] chore(deps): bump datafusion from 55.1.0 to 55.2.0 [datafusion-iceberg] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 22:06:56 UTC, 0 replies.
- [PR] test: use WITH ORDER tables for date_bin/date_trunc ordering plan tests [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/14 22:10:51 UTC, 4 replies.
- [I] Lower and upper window-frame bound serialization are near-identical copies [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 22:27:59 UTC, 2 replies.
- Re: [PR] feat: pick hash join mode at runtime from the build side (AQE without stages) [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/14 22:41:09 UTC, 9 replies.
- [PR] build: remove Guava dependency [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 22:46:47 UTC, 1 replies.
- Re: [PR] feat: add extension to support `DataFrame::checkpoint()` [datafusion-ballista] - posted by "akshaychitneni (via GitHub)" <gi...@apache.org> on 2026/10/14 22:48:52 UTC, 1 replies.
- Re: [PR] feat: use datafusion python FFI for integration (native datafusion python support) [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/14 22:49:30 UTC, 16 replies.
- Re: [I] Support Configuring arrow_ipc::FileWriter via ArrowWriterOptions [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 22:55:35 UTC, 0 replies.
- Re: [I] Replace the `MapOffset` tuple with an enum [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 22:55:37 UTC, 0 replies.
- Re: [PR] fix: surface SparkArithmeticException(DIVIDE_BY_ZERO) for divide-by-zero in dispatched ScalaUDF path [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:08:20 UTC, 4 replies.
- Re: [PR] fix: Account for buffered rows in `RowCursorStream` [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 23:22:20 UTC, 1 replies.
- Re: [I] Document and enforce compatibility of the intermediate state produced by an `AggregateUDFImpl`'s `Accumulator` and `GroupsAccumulator` [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 23:22:21 UTC, 0 replies.
- Re: [PR] fix: count buffers shared between sort input batches once [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 23:23:40 UTC, 0 replies.
- Re: [PR] Add tests fpr nullability of AND/OR expressions [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/14 23:24:06 UTC, 0 replies.
- [I] [Bug] atan2 does not normalize -0.0 the way Spark does [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:25:11 UTC, 0 replies.
- [I] [Bug] pow differs from Spark for -0.0, NaN and infinite exponents [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:25:34 UTC, 2 replies.
- [I] ANSI NaN and infinity use the wrong exception for cast to timestamp [datafusion-comet] - posted by "Ersa-tech (via GitHub)" <gi...@apache.org> on 2026/10/14 23:25:38 UTC, 0 replies.
- [I] Negative-scale decimal cast to timestamp panics [datafusion-comet] - posted by "Ersa-tech (via GitHub)" <gi...@apache.org> on 2026/10/14 23:25:41 UTC, 0 replies.
- [I] [Bug] round on a DECIMAL keeps the input type, Spark reduces the scale of the result [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:25:45 UTC, 1 replies.
- [I] [Bug] date_part('SECOND', ts) drops the fractional seconds, Spark returns decimal(8,6) [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:25:56 UTC, 0 replies.
- [I] Legacy cast of an overflowing finite double to timestamp returns NULL [datafusion-comet] - posted by "Ersa-tech (via GitHub)" <gi...@apache.org> on 2026/10/14 23:26:03 UTC, 1 replies.
- [I] [Bug] format_string prints the unscaled value for %s of a DECIMAL and strips trailing zeros for %g [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:26:05 UTC, 0 replies.
- [I] [Bug] trunc and date_trunc handle unsupported, NULL and non-literal formats differently from Spark [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:26:14 UTC, 1 replies.
- [I] [Bug] last_day, monthname, weekday, round and unbase64 reject arguments that Spark implicitly casts [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:26:24 UTC, 1 replies.
- [I] [Bug] unbase64 rejects input that Spark's MIME decoder accepts [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:26:33 UTC, 0 replies.
- [I] [Bug] parse_url raises on a malformed URL when ANSI mode is off, Spark returns NULL [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/14 23:26:44 UTC, 0 replies.
- [I] array_repeat fails for array inputs with nonnullable elements [datafusion] - posted by "nat-openai (via GitHub)" <gi...@apache.org> on 2026/10/14 23:28:37 UTC, 3 replies.
- Re: [I] Allow extension `ExecutionPlan`s to decode via a per-type registry instead of `PhysicalExtensionCodec` [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/14 23:39:49 UTC, 0 replies.
- [I] Planning fails with "Conflicting types" when one placeholder is inferred with two types [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/15 00:43:55 UTC, 3 replies.
- [PR] fix(spark): return NULL from parse_url for a malformed URL unless ANSI [datafusion] - posted by "ozenyunus35 (via GitHub)" <gi...@apache.org> on 2026/10/15 00:49:11 UTC, 0 replies.
- [PR] fix(spark): decode unbase64 input like Spark's MIME Base64 decoder [datafusion] - posted by "ozenyunus35 (via GitHub)" <gi...@apache.org> on 2026/10/15 00:55:35 UTC, 0 replies.
- [PR] fix(spark): format_string %s of a DECIMAL and %g like Java's Formatter [datafusion] - posted by "ozenyunus35 (via GitHub)" <gi...@apache.org> on 2026/10/15 01:02:56 UTC, 0 replies.
- [I] Add a GroupsAccumulator for array_agg(DISTINCT) [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/15 01:36:26 UTC, 1 replies.
- Re: [PR] fix: Validate file cache identity and isolate object stores [datafusion] - posted by "limadog9 (via GitHub)" <gi...@apache.org> on 2026/10/15 02:21:17 UTC, 0 replies.
- Re: [PR] fix: Preserve column identifiers in DataFrame fill methods [datafusion] - posted by "limadog9 (via GitHub)" <gi...@apache.org> on 2026/10/15 02:21:40 UTC, 5 replies.
- Re: [PR] fix: preserve functional dependencies across unnest [datafusion] - posted by "limadog9 (via GitHub)" <gi...@apache.org> on 2026/10/15 02:21:55 UTC, 5 replies.
- [PR] bench: test Arrow RLE dictionary reader optimization [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/15 03:06:24 UTC, 128 replies.
- [I] Optimize inner joins with a proven single constant row into Filter/Projection [datafusion] - posted by "xudong963 (via GitHub)" <gi...@apache.org> on 2026/10/15 03:15:32 UTC, 1 replies.
- [PR] fix: handle aggregate name collisions from casts [datafusion] - posted by "DeviousCardi (via GitHub)" <gi...@apache.org> on 2026/10/15 03:19:37 UTC, 1 replies.
- [PR] chore: bump rustls to fix audit [datafusion] - posted by "Jefffrey (via GitHub)" <gi...@apache.org> on 2026/10/15 03:51:18 UTC, 3 replies.
- [PR] feat: add `SessionConfig::update_extension` so libraries can share one `ProtoDecoderRegistry` [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/15 03:53:22 UTC, 7 replies.
- [PR] fix(scheduler): keep AQE stage in the graph when a stage transition fails [datafusion-ballista] - posted by "DeviousCardi (via GitHub)" <gi...@apache.org> on 2026/10/15 04:03:02 UTC, 0 replies.
- [I] Memory limit test `smj_with_mem_limit_1` is flaky [datafusion] - posted by "mzabaluev (via GitHub)" <gi...@apache.org> on 2026/10/15 04:10:37 UTC, 0 replies.
- [PR] chore(ci): bump taiki-e/install-action from 2.87.27 to 2.87.28 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/15 04:14:40 UTC, 1 replies.
- Re: [PR] feat: allow extension `PhysicalExpr`s to decode via a per-type registry [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/15 04:29:02 UTC, 5 replies.
- [PR] perf: resolve parquet leaf columns in O(1) during statistics collection [datafusion] - posted by "cetra3 (via GitHub)" <gi...@apache.org> on 2026/10/15 05:57:44 UTC, 12 replies.
- [PR] fix: keep EliminateGroupByConstant from requalifying group expressions [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/15 05:58:50 UTC, 8 replies.
- [PR] perf: add a GroupsAccumulator for array_agg(DISTINCT) [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/15 06:03:55 UTC, 11 replies.
- [I] Physical CastExpr display hides nullability changes, so union coercion casts look like no-ops [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/15 06:46:57 UTC, 1 replies.
- [PR] Show nullability of an explicit CastExpr target in its display [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/15 06:47:13 UTC, 4 replies.
- [PR] PoC: Explicit Invariant Regions in the Physical Optimizer [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/15 07:31:34 UTC, 2 replies.
- Re: [I] Align multi-key equi-join conditions to match Range ordering [datafusion] - posted by "blaginin (via GitHub)" <gi...@apache.org> on 2026/10/15 08:00:35 UTC, 0 replies.
- [I] Refactor `HashJoinExec` by splitting regular/existence join into dedicated streams [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/15 08:03:35 UTC, 0 replies.
- Re: [PR] fix: validate parquet encoding when configured [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/15 08:39:51 UTC, 11 replies.
- [I] Validate Parquet INT96 timezone values when configuration is assigned [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/15 09:00:43 UTC, 2 replies.
- [I] how to get full result of the sql() function [datafusion-python] - posted by "l1t1 (via GitHub)" <gi...@apache.org> on 2026/10/15 09:12:00 UTC, 3 replies.
- [I] Piecewise merge join: semi/anti joins fail with an internal error on RunEndEncoded keys [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/15 09:12:43 UTC, 0 replies.
- [I] Window referencing a named window with an added frame, OVER (w ROWS ...), silently drops PARTITION BY and ORDER BY [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/15 10:05:03 UTC, 1 replies.
- Re: [PR] fix: preserve negative zero in trunc [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/15 10:16:16 UTC, 4 replies.
- Re: [PR] Snowflake: Add CREATE and DROP EXTERNAL VOLUME [datafusion-sqlparser-rs] - posted by "sabir-akhadov-localstack (via GitHub)" <gi...@apache.org> on 2026/10/15 10:22:17 UTC, 1 replies.
- Re: [PR] Snowflake: Add DESC[RIBE] EXTERNAL VOLUME [datafusion-sqlparser-rs] - posted by "sabir-akhadov-localstack (via GitHub)" <gi...@apache.org> on 2026/10/15 10:22:18 UTC, 1 replies.
- Re: [PR] Snowflake: Add SHOW EXTERNAL VOLUMES [datafusion-sqlparser-rs] - posted by "sabir-akhadov-localstack (via GitHub)" <gi...@apache.org> on 2026/10/15 10:22:20 UTC, 2 replies.
- [PR] Snowflake: Support ALTER TABLE ADD COLUMN IF NOT EXISTS [datafusion-sqlparser-rs] - posted by "sabir-akhadov-localstack (via GitHub)" <gi...@apache.org> on 2026/10/15 10:25:57 UTC, 4 replies.
- Re: [PR] perf: Optimize `array_filter` [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/15 10:26:43 UTC, 19 replies.
- [PR] refactor: deduplicate split list-array construction [datafusion-comet] - posted by "arminazimi (via GitHub)" <gi...@apache.org> on 2026/10/15 10:42:19 UTC, 2 replies.
- [PR] feat: let `SpillCompression::Zstd` carry a compression level [datafusion] - posted by "KonaeAkira (via GitHub)" <gi...@apache.org> on 2026/10/15 10:45:32 UTC, 2 replies.
- [PR] fix: avoid quadratic row-buffer accounting in sort merges [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/15 10:49:51 UTC, 22 replies.
- Re: [PR] feat: drop a stream task's future in place when its stream is dropped [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/15 11:16:40 UTC, 12 replies.
- [PR] refactor: share a single pad kernel between lpad and rpad [datafusion] - posted by "shazilkhan (via GitHub)" <gi...@apache.org> on 2026/10/15 11:29:54 UTC, 9 replies.
- [PR] DRAFT Bench 25767 [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/15 12:04:52 UTC, 9 replies.
- Re: [PR] perf: speed up INTERSECT ALL and EXCEPT ALL on mostly distinct rows [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/15 12:24:52 UTC, 11 replies.
- [I] Double-negated child check and an always-true guard in the shuffle support logic [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 12:35:01 UTC, 2 replies.
- [I] Native Parquet scan fails on a duplicate field id in a column the query does not read [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 12:44:17 UTC, 0 replies.
- Re: [I] Improve internal worker parallelism support [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/15 12:51:06 UTC, 0 replies.
- Re: [I] Incorrect AVG result from empty native partial buffers [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 12:51:46 UTC, 1 replies.
- [I] Native decimal AVG returns NULL for large sums at high scale, such as DECIMAL(38,18) above 1.7e16 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 12:51:55 UTC, 1 replies.
- [I] Maintainer availability update [datafusion-sqlparser-rs] - posted by "iffyio (via GitHub)" <gi...@apache.org> on 2026/10/15 12:58:33 UTC, 3 replies.
- [I] Native Iceberg writes accept write.parquet.compression-codec=none, which iceberg-java rejects [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 13:07:11 UTC, 0 replies.
- [PR] docs: correct native Iceberg write docs that drifted from the code [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 13:07:47 UTC, 2 replies.
- [I] Extend fully ordered aggregation to temporal, decimal, and fixed-size binary keys [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/15 13:22:07 UTC, 1 replies.
- Re: [PR] feat: preserve ordering through `to_timestamp_seconds/millis/micros/nanos` and `to_unixtime` [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/15 13:24:41 UTC, 9 replies.
- [PR] refactor: move MergeRows planning into dedicated module [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 13:30:33 UTC, 2 replies.
- [PR] refactor: move Explode planning into dedicated module [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 13:30:43 UTC, 2 replies.
- [PR] refactor: move hash aggregate planning into dedicated module [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 13:30:54 UTC, 2 replies.
- [PR] refactor: move join planning into dedicated module [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 13:31:03 UTC, 2 replies.
- [PR] refactor: move window planning into dedicated module [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 13:31:15 UTC, 0 replies.
- [PR] perf: extend fully ordered aggregation to more scalar types [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/15 13:43:18 UTC, 13 replies.
- [PR] fix: unwrap nested encodings inside Dictionary arguments to MIN/MAX [datafusion] - posted by "grevend (via GitHub)" <gi...@apache.org> on 2026/10/15 14:13:18 UTC, 2 replies.
- Re: [PR] docs: add a regression check against the latest release tag to bug triage [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 14:19:14 UTC, 0 replies.
- [PR] fix: bound Parquet Variant nesting depth [datafusion-comet] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/15 14:22:57 UTC, 0 replies.
- [I] Substrait producer does not support LogicalPlan::Unnest [datafusion] - posted by "1fanwang (via GitHub)" <gi...@apache.org> on 2026/10/15 14:23:49 UTC, 0 replies.
- Re: [PR] fix: keep nested inner joins with a different null equality in EliminateCrossJoin [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/15 14:32:17 UTC, 3 replies.
- [PR] docs: fix SQL examples that the default dialect cannot parse [datafusion] - posted by "rawsun007 (via GitHub)" <gi...@apache.org> on 2026/10/15 14:48:18 UTC, 2 replies.
- [PR] refactor(optimizer): deduplicate boolean literal comparison rules [datafusion] - posted by "emanuele-em (via GitHub)" <gi...@apache.org> on 2026/10/15 14:50:10 UTC, 4 replies.
- [PR] perf: share one decoded copy of a broadcast among the tasks of an executor [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 15:03:24 UTC, 17 replies.
- [PR] fix(expr): differentiate aggregate functions with and without explicit cast in output schema (#26221) [datafusion] - posted by "Subodh-17 (via GitHub)" <gi...@apache.org> on 2026/10/15 15:03:26 UTC, 0 replies.
- [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/15 15:06:20 UTC, 22 replies.
- [PR] DRAFT: add a generic test suite for `ExecutionPlan`s [datafusion] - posted by "masonh22 (via GitHub)" <gi...@apache.org> on 2026/10/15 15:20:41 UTC, 1 replies.
- [PR] fix: fall back to Spark for decimal AVG cases that return wrong results [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 15:31:47 UTC, 2 replies.
- Re: [I] Graceful executor shutdown terminates active Flight streams [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/15 15:37:01 UTC, 0 replies.
- Re: [I] Hash partitioning not falling back to Spark for high precision decimal partition keys [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 15:41:35 UTC, 1 replies.
- Re: [PR] fix: fall back to Spark for negative-scale decimal casts and arithmetic [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 15:41:46 UTC, 13 replies.
- [PR] fix: [branch-1.1] fall back from native V2 scans when the plan reads input_file_name (#6754) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 15:45:53 UTC, 1 replies.
- [I] Native Iceberg scan reads its full schema when a partition source is nested in a struct the query prunes [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/15 15:46:46 UTC, 0 replies.
- [PR] fix: [branch-1.1] keep one row per key in a native PartialMerge that runs short of memory (#6867) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 16:08:00 UTC, 2 replies.
- [I] Use one shared check and reason string for negative-scale decimals across the serdes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 16:13:04 UTC, 0 replies.
- [I] Native decimal cast kernels compute `10^scale` without checking for a negative scale [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 16:13:06 UTC, 0 replies.
- [I] Negative-scale decimal `/`, `div`, `ceil` and `floor` fall back to Spark while `round` dispatches [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 16:13:07 UTC, 0 replies.
- [PR] fix(functions-nested): preserve element field in array_repeat [datafusion] - posted by "patrickswedish (via GitHub)" <gi...@apache.org> on 2026/10/15 16:18:59 UTC, 3 replies.
- Re: [PR] refactor: move MergeRows, Explode, aggregate, join and window planning into dedicated modules [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/15 17:28:37 UTC, 3 replies.
- [I] Support MIN/MAX over StructType in native aggregates [datafusion-comet] - posted by "parthchandra (via GitHub)" <gi...@apache.org> on 2026/10/15 17:32:46 UTC, 0 replies.
- [PR] chore: Add Decimal128 benchmarks for gcd [datafusion] - posted by "CLCK0622 (via GitHub)" <gi...@apache.org> on 2026/10/15 17:55:33 UTC, 0 replies.
- [I] PartitionedTopKExec keeps whole Utf8View input buffers alive for the rows it retains [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/15 17:55:56 UTC, 0 replies.
- [PR] fix(spark): return NaN and -Infinity from `pow` where Spark does [datafusion] - posted by "abp002 (via GitHub)" <gi...@apache.org> on 2026/10/15 18:03:30 UTC, 1 replies.
- Re: [PR] fix: declare Hive partitioned scans as Range [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/15 18:20:15 UTC, 5 replies.
- [I] CrossJoinExec buffers the entire left input without spilling (OOM under memory pressure) [datafusion] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/15 18:35:15 UTC, 1 replies.
- [PR] fix: evaluate the array_append item on rows whose array is NULL [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/15 18:43:24 UTC, 7 replies.
- [PR] [DO NOT MERGE] Test DataFusion against arrow-rs main (pre-release testing, 2026-10-15) [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/15 18:49:15 UTC, 5 replies.
- [PR] Fix literal projection distinct count statistics [datafusion] - posted by "masonh22 (via GitHub)" <gi...@apache.org> on 2026/10/15 18:53:36 UTC, 7 replies.
- [PR] Fuzz window nulls [datafusion] - posted by "Nagato-Yuzuru (via GitHub)" <gi...@apache.org> on 2026/10/15 18:53:45 UTC, 0 replies.
- Re: [PR] fix: support binaryAsString in the native Parquet scan [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/15 18:56:26 UTC, 8 replies.
- Re: [PR] fix: wait for the whole NULL peer group before emitting RANGE `N PRECEDING` window results [datafusion] - posted by "Nagato-Yuzuru (via GitHub)" <gi...@apache.org> on 2026/10/15 19:02:20 UTC, 1 replies.
- [PR] WIP: Add parquet `progressive_io` option using `ParquetPushDecoder::scan_plan` (one-shot row group I/O with pushdown filters) [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/15 19:03:17 UTC, 18 replies.
- [I] `translate` panics when output would exceed 2GB [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/15 19:06:34 UTC, 0 replies.
- Re: [I] Represent Hive/value partitioning without claiming Partitioning::Hash [datafusion] - posted by "jayshrivastava (via GitHub)" <gi...@apache.org> on 2026/10/15 19:14:13 UTC, 9 replies.
- [PR] fix [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/15 19:37:54 UTC, 0 replies.
- [PR] fix: fall back for Iceberg write settings that iceberg-java rejects [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 20:13:14 UTC, 1 replies.
- Re: [PR] WIP: NOT READY FOR REVIEW: Add parquet `progressive_io` option to keep one-shot row group I/O with pushdown filters [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/15 20:20:24 UTC, 0 replies.
- Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/15 20:21:06 UTC, 0 replies.
- Re: [PR] WIP: DO NOT REVIEW: Benchmark enabling parquet filter pushdown by default with one-shot row group I/O [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/15 20:21:23 UTC, 1 replies.
- Re: [PR] [DO NOT MERGE] Test apache/arrow-rs#10852 (adaptive RowSelection construction) with ClickBench [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/15 20:22:03 UTC, 1 replies.
- [PR] feat: bump iceberg-rust past #3255 and narrow the nested schema evolution fallback [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 20:35:19 UTC, 0 replies.
- Re: [PR] test: add NULL values to Fuzz window [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/15 20:46:57 UTC, 3 replies.
- Re: [I] Add documentation for `cast` support for complex types [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 20:58:36 UTC, 0 replies.
- [PR] refactor: recompute retained merge-row reservation on release [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/15 21:07:56 UTC, 11 replies.
- [I] Native Parquet scan returns wrong INT96 timestamps inside legacy-format lists [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:45:55 UTC, 0 replies.
- [I] Native Parquet scan returns a non-null array or struct of NULLs where Spark returns NULL because no requested nested field is in the file [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:45:59 UTC, 1 replies.
- [I] Native Parquet scan returns NULL for nested BINARY values that are not valid UTF-8 when they are read as STRING [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:46:00 UTC, 0 replies.
- [I] Spark 3.4: native Parquet scan returns NULL for a struct matched by field id under a new name when Spark prunes its fields [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:46:00 UTC, 2 replies.
- [I] Native Iceberg scan fails when a data file omits an optional nested field [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:46:15 UTC, 0 replies.
- [I] Native Parquet scan reads TIMESTAMP(NANOS) columns as timestamp where Spark rejects them [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:46:17 UTC, 0 replies.
- [I] Native Parquet scan cannot read a file whose schema has a nested encoding arrow-rs rejects, even in a column the query does not read [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:46:18 UTC, 0 replies.
- [I] Native Parquet scan reads the whole nested column for maps, field ids, case-insensitive names and leaf type changes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:46:20 UTC, 0 replies.
- [I] Native Parquet scan does not prune row groups or pages with predicates on struct fields [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:46:21 UTC, 0 replies.
- [I] Push Iceberg residual predicates on struct fields into the native scan [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:46:24 UTC, 0 replies.
- [I] Native Iceberg scan reads every column of a file when it needs none of them [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:46:25 UTC, 0 replies.
- [I] [EPIC] Nested types in the native Parquet and Iceberg scans: correctness and performance follow-ups [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 21:47:55 UTC, 0 replies.
- Re: [I] Make datafusion support materializing option for CTE [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/15 22:00:28 UTC, 0 replies.
- [I] Native panic backtrace can be attached to another thread's CometNativeException [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/15 22:12:44 UTC, 1 replies.
- [PR] fix(sql): inherit partition and order by when window spec references named window (#26364) [datafusion] - posted by "patrickswedish (via GitHub)" <gi...@apache.org> on 2026/10/15 22:19:23 UTC, 2 replies.
- [I] SanityCheckPlan error: a constant sort key is lost when a projection reads a duplicate alias [datafusion] - posted by "cetra3 (via GitHub)" <gi...@apache.org> on 2026/10/15 22:21:09 UTC, 1 replies.
- [PR] fix: keep each native panic's backtrace with its own thread [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/15 22:22:33 UTC, 2 replies.
- [PR] refactor(sql): extract large statement arms from SqlToRel [datafusion] - posted by "Theodus (via GitHub)" <gi...@apache.org> on 2026/10/15 22:27:43 UTC, 1 replies.
- [I] coerce_int96 does not coerce INT96 inside legacy Parquet list layouts (bag/array, two-level lists) [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 22:35:27 UTC, 0 replies.
- [PR] fix(spark): normalize -0.0 in atan2 like Spark [datafusion] - posted by "spicysharkco (via GitHub)" <gi...@apache.org> on 2026/10/15 22:45:28 UTC, 0 replies.
- [PR] fix: fall back to Spark when Iceberg reports an output ordering [datafusion-comet] - posted by "parthchandra (via GitHub)" <gi...@apache.org> on 2026/10/15 22:59:19 UTC, 8 replies.
- Re: [I] Reduce retained buffer allocation when list_extract selects short nested arrays [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 23:14:41 UTC, 0 replies.
- Re: [I] Native corr, covariance, variance and stddev return wrong values for a constant fractional column merged from several partitions [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/15 23:14:42 UTC, 0 replies.
- Re: [I] Native Parquet writes report row counts but not row contents to WriteTaskStatsTrackers [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/15 23:14:48 UTC, 0 replies.
- [PR] fix(parquet): support int96 coercion in legacy list layouts [datafusion] - posted by "patrickswedish (via GitHub)" <gi...@apache.org> on 2026/10/15 23:27:32 UTC, 3 replies.
- [I] ProjectionPushdown fails on a nested-loop join whose lambda captures a column from the other input [datafusion] - posted by "xudong963 (via GitHub)" <gi...@apache.org> on 2026/10/16 00:41:36 UTC, 1 replies.
- [PR] fix: keep a constant sort key when a projection reads a duplicate alias [datafusion] - posted by "cetra3 (via GitHub)" <gi...@apache.org> on 2026/10/16 00:54:18 UTC, 1 replies.
- [PR] fix: support RunEndEncoded keys in min/max and piecewise merge join (#26363) [datafusion] - posted by "patrickswedish (via GitHub)" <gi...@apache.org> on 2026/10/16 00:56:25 UTC, 3 replies.
- [PR] fix: preserve lambda bindings in nested-loop join projection pushdown [datafusion] - posted by "xudong963 (via GitHub)" <gi...@apache.org> on 2026/10/16 01:07:41 UTC, 3 replies.
- [PR] PostgreSQL: Parse CREATE TRIGGER function arguments as expressions [datafusion-sqlparser-rs] - posted by "DeviousCardi (via GitHub)" <gi...@apache.org> on 2026/10/16 01:17:20 UTC, 1 replies.
- [PR] Resolve named windows referenced inside OVER (...) [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/16 01:27:35 UTC, 6 replies.
- [PR] feat: add nested benchmark derived from TPC-H [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/16 01:33:05 UTC, 1 replies.
- Re: [PR] fix: preserve precision in log() with mixed-width float arguments [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/16 01:40:47 UTC, 2 replies.
- [PR] add_flight_passthrough_serve_bench [datafusion-ballista] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/16 01:41:21 UTC, 0 replies.
- [PR] serve_shuffle_partition_via_ipc_passthrough [datafusion-ballista] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/16 01:41:28 UTC, 0 replies.
- Re: [PR] perf: serve shuffle partition via ipc passthrough [datafusion-ballista] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/16 01:48:03 UTC, 0 replies.
- Re: [PR] chore: add flight passthrough serve bench [datafusion-ballista] - posted by "coderfender (via GitHub)" <gi...@apache.org> on 2026/10/16 01:48:06 UTC, 0 replies.
- [PR] fix(spark): return decimal(8, 6) with fractional seconds for date_part('SECOND', ts) [datafusion] - posted by "patrickswedish (via GitHub)" <gi...@apache.org> on 2026/10/16 02:16:37 UTC, 3 replies.
- [PR] fix(physical-plan): compact view buffers in PartitionedTopK (#26381) [datafusion] - posted by "patrickswedish (via GitHub)" <gi...@apache.org> on 2026/10/16 02:41:54 UTC, 4 replies.
- Re: [PR] docs: fix dead heading anchors and fail the docs build on warnings [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/16 03:02:37 UTC, 0 replies.
- [PR] refactor: extract aggregate physical planning [datafusion] - posted by "1cbyc (via GitHub)" <gi...@apache.org> on 2026/10/16 04:12:27 UTC, 2 replies.
- [PR] feat: rewrite inner joins against a single constant row into a filter [datafusion] - posted by "xudong963 (via GitHub)" <gi...@apache.org> on 2026/10/16 05:30:18 UTC, 4 replies.
- [PR] perf: avoid building a DFSchema for every pruning comparison [datafusion] - posted by "cetra3 (via GitHub)" <gi...@apache.org> on 2026/10/16 05:31:17 UTC, 6 replies.
- Re: [I] The config values aren't checked [datafusion] - posted by "AdiXgit (via GitHub)" <gi...@apache.org> on 2026/10/16 06:03:50 UTC, 0 replies.
- [I] Migrate workflows away from `pull_request_target` [datafusion] - posted by "Jefffrey (via GitHub)" <gi...@apache.org> on 2026/10/16 06:21:46 UTC, 1 replies.
- [PR] perf: decode Parquet footers for statistics in parallel during planning [datafusion] - posted by "cetra3 (via GitHub)" <gi...@apache.org> on 2026/10/16 06:30:59 UTC, 11 replies.
- Re: [I] Backport workflow-hardening fix (unpinned-uses) to `maint-16.x` [datafusion] - posted by "Jefffrey (via GitHub)" <gi...@apache.org> on 2026/10/16 06:40:42 UTC, 0 replies.
- [I] Use zizmor to harden actions workflows [datafusion] - posted by "Jefffrey (via GitHub)" <gi...@apache.org> on 2026/10/16 06:44:07 UTC, 0 replies.
- [I] Add a GroupsAccumulator for array_agg with ORDER BY [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/16 07:17:59 UTC, 1 replies.
- [I] `[]` after a nested `STRUCT<…>` closed by `>>` attaches to the inner struct [datafusion-sqlparser-rs] - posted by "kdn36 (via GitHub)" <gi...@apache.org> on 2026/10/16 07:21:56 UTC, 0 replies.
- [PR] Revert #25363 due to overlapping optimizations [datafusion] - posted by "2010YOUY01 (via GitHub)" <gi...@apache.org> on 2026/10/16 08:01:44 UTC, 4 replies.
- [PR] Parser: Fix array suffixes after a `>>` that closes two nested types [datafusion-sqlparser-rs] - posted by "kdn36 (via GitHub)" <gi...@apache.org> on 2026/10/16 08:10:09 UTC, 4 replies.
- [I] SortExec merge lookahead can retain batches without memory reservations [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/16 08:10:32 UTC, 1 replies.
- [PR] fix: restore floating-point rounding mode after panic [datafusion] - posted by "emanuele-em (via GitHub)" <gi...@apache.org> on 2026/10/16 09:26:48 UTC, 3 replies.
- [PR] refactor: simplify shuffle support predicates [datafusion-comet] - posted by "0lai0 (via GitHub)" <gi...@apache.org> on 2026/10/16 09:31:28 UTC, 1 replies.
- [PR] build(deps): bump actions/setup-python from 6 to 7 [datafusion-comet] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/16 09:35:09 UTC, 1 replies.
- Re: [PR] Encode MemTable as durable metadata in the FFI example logical codec [datafusion-python] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/16 11:29:18 UTC, 0 replies.
- Re: [PR] PostgreSQL: Support CREATE FOREIGN DATA WRAPPER [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/16 11:41:34 UTC, 2 replies.
- [I] following sql reports Exception: DataFusion error: type_coercion caused by Execution error: Cannot access field at argument 1: type Utf8 is not Struct, Map, or Null [datafusion-python] - posted by "l1t1 (via GitHub)" <gi...@apache.org> on 2026/10/16 12:17:53 UTC, 2 replies.
- [PR] bench: non-ASCII cases for left and right [datafusion] - posted by "mightsleep (via GitHub)" <gi...@apache.org> on 2026/10/16 12:33:19 UTC, 3 replies.
- Re: [PR] fix: reject statistics whose column count does not match the schema [datafusion] - posted by "jackylee-ch (via GitHub)" <gi...@apache.org> on 2026/10/16 13:47:09 UTC, 2 replies.
- Re: [PR] perf: build spark_size LargeList lengths from i64 offsets [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 13:47:21 UTC, 0 replies.
- Re: [I] Use Exact Hash-Table Allocation Accounting in `GroupValuesPrimitive` [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/16 14:22:07 UTC, 0 replies.
- [PR] Deny `clippy::manual_assert_eq` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/16 14:30:54 UTC, 8 replies.
- [I] Native Parquet writer ignores the datetime rebase modes, so Spark rejects or shifts its pre-1582 dates [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 14:37:23 UTC, 0 replies.
- [I] Native Parquet writer ignores outputTimestampType and writeLegacyFormat, and omits Spark's schema metadata [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 14:37:48 UTC, 0 replies.
- [I] Native Iceberg writes into NOT NULL columns fall back on Spark 3.5+ because Comet has no native AssertNotNull [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 14:37:52 UTC, 1 replies.
- [I] Iceberg write docs say the float/double null-count difference can't change IS NULL pruning, but it can [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 14:37:54 UTC, 1 replies.
- Re: [I] Native Parquet writer ignores Spark's Parquet writer properties (block size, page size, dictionary, writer version, statistics) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 14:37:58 UTC, 0 replies.
- [I] [EPIC] Nested types in the native Parquet and Iceberg writers: correctness and performance follow-ups [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 14:38:24 UTC, 0 replies.
- Re: [PR] chore(ci): Register the substrait check job with runs-on, route spark checks through xtask [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/16 14:53:49 UTC, 0 replies.
- [PR] docs: list known Parquet and Iceberg correctness issues and add a data source audit log [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 15:02:40 UTC, 0 replies.
- [PR] fix: preserve input strictness in from_unixtime [datafusion] - posted by "haohuaijin (via GitHub)" <gi...@apache.org> on 2026/10/16 15:04:45 UTC, 0 replies.
- [PR] fix: write the Spark version into the footer of natively written Parquet files [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 15:07:40 UTC, 3 replies.
- Re: [I] Spark 4.1 NullType parquet: parquet-rs rejects BOOLEAN + Unknown logical type [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 15:29:12 UTC, 1 replies.
- [PR] perf: stop at the first match in RightSemi/RightAnti hash joins [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 15:30:00 UTC, 6 replies.
- [PR] test: re-enable the NullType Parquet read tests that #4199 skipped [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 15:37:37 UTC, 0 replies.
- Re: [PR] fix: preserve input strictness in `from_unixtime` [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/16 15:39:12 UTC, 2 replies.
- [I] enable_window_topn returns wrong results when a projection under the filter drops a column (wrong ranking function chosen) [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/16 15:45:41 UTC, 1 replies.
- [PR] fix: WindowTopN resolves the filter column through intermediate proje… [datafusion] - posted by "SubhamSinghal (via GitHub)" <gi...@apache.org> on 2026/10/16 15:52:53 UTC, 4 replies.
- [PR] WIP: Enable parquet `pushdown_filters` and `progressive_io` by default [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/16 15:59:21 UTC, 3 replies.
- Re: [I] [] after a >> that closes two nested types attaches to the inner type [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/16 16:12:22 UTC, 0 replies.
- [PR] test: fold set_comparison test into core_integration binary [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/16 16:12:52 UTC, 0 replies.
- Re: [I] Include residual predicates in join estimates [datafusion] - posted by "rgbuilds (via GitHub)" <gi...@apache.org> on 2026/10/16 16:14:09 UTC, 3 replies.
- Re: [PR] SQLite: Support comma-separated WITHOUT ROWID and STRICT table options [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/16 16:16:21 UTC, 2 replies.
- [I] ClickHouse: Add fuzz target comparing the tokenizer with ClickHouse's lexer [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/16 16:27:39 UTC, 0 replies.
- [PR] ClickHouse: Add fuzz target comparing the tokenizer with ClickHouse's lexer [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/16 16:28:32 UTC, 6 replies.
- [PR] fix: validate parquet.coerce_int96_tz when it is set. [datafusion] - posted by "akashjainn (via GitHub)" <gi...@apache.org> on 2026/10/16 16:30:15 UTC, 8 replies.
- [PR] fix: [branch-1.1] return an empty array from CASE WHEN for an empty batch (#6763) [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/16 16:36:13 UTC, 2 replies.
- Re: [PR] feat: support Set Comparison Subquery [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/16 16:44:34 UTC, 0 replies.
- [PR] fix: align Union inputs after leaf expression pushdown [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/16 16:46:48 UTC, 6 replies.
- [PR] test: fold tpcds_planning test into core_integration binary [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/16 16:49:38 UTC, 0 replies.
- [PR] test: combine datafusion-ffi test binaries into ffi_integration [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/16 16:53:45 UTC, 1 replies.
- Re: [PR] minor: combine `set_comparison` test into `core_integration` binary [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/16 16:57:59 UTC, 2 replies.
- Re: [I] [EPIC] Subplan Materalization [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/16 16:59:31 UTC, 1 replies.
- [PR] refactor: share filter and projection metrics wrapper [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/16 17:03:48 UTC, 2 replies.
- [I] Report the ordering and partitioning of MATERIALIZED CTE scans by optimizing each CTE body first [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/16 17:12:21 UTC, 0 replies.
- [D] [RFC/Discussion] Partition-at-a-Time Streaming Evaluation in WindowAggExec [datafusion] - posted by "Subodh-17 (via GitHub)" <gi...@apache.org> on 2026/10/16 17:18:12 UTC, 2 replies.
- [PR] refactor(scheduler): share the binding driver between bind_task_bias and bind_task_round_robin [datafusion-ballista] - posted by "cestercian (via GitHub)" <gi...@apache.org> on 2026/10/16 17:27:33 UTC, 0 replies.
- Re: [PR] minor: fold tpcds_planning test into core_integration binary [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/16 17:48:22 UTC, 3 replies.
- [PR] Issue 26388 [datafusion] - posted by "rishabh1244 (via GitHub)" <gi...@apache.org> on 2026/10/16 17:54:14 UTC, 1 replies.
- [PR] issue fix 26388 [datafusion] - posted by "rishabh1244 (via GitHub)" <gi...@apache.org> on 2026/10/16 18:08:11 UTC, 3 replies.
- [PR] feat: spilling shuffled hash join (research draft) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 18:09:03 UTC, 0 replies.
- Re: [I] Map growth in aggregate can be 3x of size [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 18:30:37 UTC, 0 replies.
- Re: [PR] minor: combine datafusion-ffi test binaries into ffi_integration [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/16 18:44:18 UTC, 2 replies.
- [I] perf: the bypass JVM columnar shuffle writer writes one-row blocks when its partitions' pages don't fit in a task's memory [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 18:50:56 UTC, 1 replies.
- Re: [I] Share Parquet footer and page index metadata across tasks in an executor [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 19:31:54 UTC, 0 replies.
- [PR] feat: report the ordering and partitioning of materialized CTE scans [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/16 19:46:21 UTC, 1 replies.
- [PR] perf: start bypass shuffle partition writers on small pages that grow [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 19:47:17 UTC, 5 replies.
- [I] perf: every native plan creates and deletes a temp directory on each Spark local disk, even when it never spills [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 19:50:11 UTC, 1 replies.
- [I] perf: the sort-based JVM columnar shuffle is 2x slower than Spark at 2,000 partitions because every partition write pays builder, file and codec setup [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 19:51:04 UTC, 1 replies.
- Re: [I] Cancelling a task doesn't stop its native plan until the plan produces its next batch [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 19:51:24 UTC, 0 replies.
- [I] JVM columnar shuffle panics on a struct column with a NullType field [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 19:52:58 UTC, 1 replies.
- [I] Native hashing of NullType and ANSI interval values fails with "Unsupported data type in hasher" [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 19:53:07 UTC, 0 replies.
- [I] perf: Arrow IPC write paths still copy through Channels.newChannel's 8 KiB buffer [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 19:54:11 UTC, 0 replies.
- [PR] perf: write every partition of a JVM shuffle spill in one native call [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 19:56:53 UTC, 5 replies.
- [PR] perf: share one DiskManager per executor across native plans [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:01:46 UTC, 3 replies.
- [PR] Commit the fuzz crate's Cargo.lock [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/16 20:05:40 UTC, 3 replies.
- [PR] Deny `clippy::should_panic_without_expect` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/16 20:06:09 UTC, 3 replies.
- [PR] Parser: Move CREATE statement parsing into parser/create.rs [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/16 20:08:26 UTC, 0 replies.
- [I] perf: a stage that reads shuffle and ends in columnar-to-row crosses the FFI boundary twice per batch [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:12:55 UTC, 0 replies.
- [I] perf: the shuffle reader builds a new decompressor and zeroes a fresh body buffer for every block [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:12:55 UTC, 0 replies.
- [I] perf: investigate decoding shuffle blocks ahead of the consumer in native shuffle read [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:02 UTC, 0 replies.
- [I] perf: NativeBatchDecoderIterator discards its direct buffer after every block over 128 KiB [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:04 UTC, 0 replies.
- [I] perf: the native multi-partition shuffle writer copies each partition's tail batch and flushes the output file once per partition [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:07 UTC, 0 replies.
- [I] perf: use extend when buffering partition row indices in the native shuffle writer [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:14 UTC, 4 replies.
- [I] perf: a shuffle over a native plan takes the JVM row shuffle for round-robin and nested hash partitioning [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:16 UTC, 0 replies.
- [I] perf: the JVM columnar shuffle insert loop boxes, locks and copies every row more than once [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:19 UTC, 0 replies.
- [I] perf: the JVM shuffle's native radix sort always runs six passes, and the JVM reserves scratch it never uses [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:20 UTC, 1 replies.
- [I] perf: the native Celeborn writer reserves about 7x a batch and holds it through the network round trip [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:22 UTC, 1 replies.
- [I] perf: the native Celeborn writer sends one frame per partition chunk with no coalescing [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:23 UTC, 1 replies.
- [I] perf: the native Celeborn writer pays a large fixed cost per frame (admission, schema, estimates, re-encodes) [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:25 UTC, 1 replies.
- [I] bench: add the shuffle benchmark cases that the #5905 review found missing [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:28 UTC, 1 replies.
- [I] perf: Celeborn push completion is polled every 10 ms and the transport hook proxies every channel of the shared factory [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:28 UTC, 1 replies.
- Re: [PR] [WIP]Parser: Move CREATE statement parsing into parser/create.rs [datafusion-sqlparser-rs] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/16 20:13:30 UTC, 1 replies.
- [PR] fix: reserve hash table growth before aggregating a batch [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 20:14:44 UTC, 3 replies.
- [I] SanityCheckPlan error when sorting by a function of a product above a projection with a computed column [datafusion] - posted by "JoeryH (via GitHub)" <gi...@apache.org> on 2026/10/16 20:15:02 UTC, 2 replies.
- [PR] fix: preserve Parquet root field IDs after nested pruning [datafusion-comet] - posted by "LinSimon-901101 (via GitHub)" <gi...@apache.org> on 2026/10/16 20:20:37 UTC, 4 replies.
- [I] `ORDER BY ... LIMIT 0` panics in TopK (`assertion failed: k > 0`) when `eliminate_limit` does not run [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/16 20:42:20 UTC, 0 replies.
- Re: [PR] perf: avoid ArrayData conversion in BaselineMetrics for every column [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/16 20:43:47 UTC, 4 replies.
- [I] Parser: target module layout for splitting src/parser/mod.rs [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/16 20:49:37 UTC, 1 replies.
- Re: [I] Numeric-to-string cast interval inference can reject valid filters with reversed bounds [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/16 21:00:10 UTC, 0 replies.
- [PR] fix: return no rows from TopK with LIMIT 0 instead of panicking [datafusion] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/16 21:16:07 UTC, 3 replies.
- Re: [PR] MySQL: Bind && with the precedence of AND [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/16 21:18:01 UTC, 1 replies.
- Re: [PR] SQLite: Support `$` inside identifiers [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/16 21:19:32 UTC, 2 replies.
- Re: [I] Internal error: CSE-extracted `__common_expr_1` has mismatched nullability between logical and physical plans when the expression is under an aggregate [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/16 21:20:12 UTC, 0 replies.
- [PR] perf: share Parquet footer and page index metadata across the tasks of a stage [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 21:46:45 UTC, 23 replies.
- Re: [PR] PostgreSQL: parse `ALTER TRIGGER RENAME TO` and `DEPENDS ON EXTENSION` [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/16 21:56:07 UTC, 0 replies.
- Re: [PR] Postgres: Support aliases for JOIN USING [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/16 21:59:01 UTC, 0 replies.
- [PR] fix: UNNEST now preserves item fields in expression inference and logical-plan schemas [datafusion] - posted by "quwin (via GitHub)" <gi...@apache.org> on 2026/10/16 22:14:08 UTC, 6 replies.
- [PR] fix: keep file order for scans that advertise an output ordering [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/16 22:14:50 UTC, 7 replies.
- [PR] [branch-55] fix: frame IPC messages when reading spill files so batches pin only their own bytes (#24592) [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 22:17:20 UTC, 2 replies.
- Re: [PR] fix: preserve scan order during sort-preserving merge limit pushdown [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/16 22:31:39 UTC, 2 replies.
- Re: [I] AQE reuses one exchange for scans with different dynamic pruning filters and drops rows [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/16 22:33:32 UTC, 0 replies.
- Re: [PR] docs: list known Parquet and Iceberg issues and add a data source audit log [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/16 22:44:21 UTC, 4 replies.
- Re: [I] Support dynamic filters and work-table plans state reset [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/16 22:49:19 UTC, 2 replies.
- Re: [PR] Partition information schema content per catalog [datafusion] - posted by "pepijnve (via GitHub)" <gi...@apache.org> on 2026/10/16 23:42:12 UTC, 11 replies.
- [PR] fix: compact sparse string views in FilterExec coalescing [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/16 23:53:22 UTC, 12 replies.
- Re: [PR] feat: Prune ListingTable file groups for range-key filters [datafusion] - posted by "stuhood (via GitHub)" <gi...@apache.org> on 2026/10/17 00:02:17 UTC, 2 replies.
- [PR] Add `Dialect::supports_cte_materialization` and enable it for DuckDB [datafusion-sqlparser-rs] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/17 00:05:00 UTC, 4 replies.
- [PR] Allow a SessionState to carry a custom sqlparser dialect [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/17 00:32:41 UTC, 1 replies.
- Re: [PR] feat: stream aggregates when group keys are partition-disjoint [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/17 01:39:02 UTC, 1 replies.
- Re: [PR] fix: reject zero parallel parquet row group writers [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/17 01:39:04 UTC, 1 replies.
- [PR] perf: share a scan's pruning predicates between its files' FilePruners [datafusion] - posted by "asg0451 (via GitHub)" <gi...@apache.org> on 2026/10/17 01:56:26 UTC, 2 replies.
- [I] map_from_entries dispatches a calendar-interval result into the microsecond overflow [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/17 03:20:33 UTC, 1 replies.
- [PR] fix: hash NullType and ANSI interval values natively [datafusion-comet] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/17 03:43:11 UTC, 3 replies.
- [I] array_agg(DISTINCT x ORDER BY x) returns values in reverse order when another aggregate orders by x DESC [datafusion] - posted by "raams95 (via GitHub)" <gi...@apache.org> on 2026/10/17 05:13:47 UTC, 2 replies.
- [PR] fix: respect ORDER BY in array_agg(DISTINCT) when the aggregate is reversed [datafusion] - posted by "raams95 (via GitHub)" <gi...@apache.org> on 2026/10/17 05:14:23 UTC, 3 replies.
- [PR] fix: match Spark nullness for missing nested Parquet fields [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/17 06:25:58 UTC, 3 replies.
- [PR] perf: prune ListingTable files before grouping [datafusion] - posted by "rgbuilds (via GitHub)" <gi...@apache.org> on 2026/10/17 06:28:15 UTC, 4 replies.
- [PR] perf: replace the routed hash join dynamic filter with one global filter (InList or bloom filter) [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/17 06:54:36 UTC, 25 replies.
- Re: [I] trunc(x) on a column turns -0.0 into 0.0 [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/17 07:00:35 UTC, 0 replies.
- Re: [PR] Postgres: Support SUBSTRING SIMILAR/ESCAPE syntax and reversed FOR/FROM order [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 08:08:10 UTC, 0 replies.
- [PR] refactor(unparser): move the Join arm of select_to_sql_recursively into join_to_sql [datafusion] - posted by "ahlag (via GitHub)" <gi...@apache.org> on 2026/10/17 08:39:37 UTC, 1 replies.
- [PR] Deny `clippy::ignore_without_reason` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 08:54:05 UTC, 3 replies.
- [PR] Deny `clippy::allow_attributes` and `allow_attributes_without_reason` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 09:55:02 UTC, 4 replies.
- [PR] Deny `clippy::dbg_macro and clippy::todo` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 10:35:51 UTC, 3 replies.
- [I] Replace remaining unwrap calls on protobuf input in the native planner with errors [datafusion-comet] - posted by "0lai0 (via GitHub)" <gi...@apache.org> on 2026/10/17 13:03:31 UTC, 1 replies.
- [PR] fix: return errors instead of panicking in native planner [datafusion-comet] - posted by "0lai0 (via GitHub)" <gi...@apache.org> on 2026/10/17 13:06:35 UTC, 1 replies.
- [I] fair_unified's per-consumer limit does not bind when tasks run concurrently, so one consumer can starve another [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 13:16:16 UTC, 1 replies.
- [PR] fix: reject TIMESTAMP(NANOS) Parquet columns read as timestamp [datafusion-comet] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/17 13:17:58 UTC, 11 replies.
- Re: [PR] PostgreSQL: add support for CREATE AGGREGATE [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 13:20:27 UTC, 4 replies.
- [I] TopK aggregation duplicates NaN groups and can panic during eviction [datafusion] - posted by "bvolpato (via GitHub)" <gi...@apache.org> on 2026/10/17 13:29:07 UTC, 0 replies.
- [PR] docs: consolidate Parquet and Iceberg documentation into one page each [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 13:34:13 UTC, 5 replies.
- Re: [PR] fix: size the native runtime for standalone executors without spark.executor.cores [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 13:39:39 UTC, 1 replies.
- [PR] fix: handle NaN grouping keys in TopK aggregation [datafusion] - posted by "bvolpato (via GitHub)" <gi...@apache.org> on 2026/10/17 13:39:47 UTC, 1 replies.
- Re: [PR] Fix Hive SKEWED BY display [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/17 13:50:54 UTC, 0 replies.
- [PR] ClickHouse, MySQL: Keep the quoting of the CREATE TABLE ENGINE name [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 13:51:47 UTC, 4 replies.
- Re: [I] TPC-DS query 72 slow on modest (10) scale factors [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 13:56:43 UTC, 3 replies.
- [PR] DuckDB: Always render the macro argument list parentheses [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 13:57:43 UTC, 4 replies.
- [I] DiskManager in Directories mode creates its temp directories when it is built, even if nothing spills [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 14:04:45 UTC, 2 replies.
- [I] Spill limit error tells Comet users to raise datafusion.runtime.max_temp_directory_size [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 14:04:50 UTC, 1 replies.
- Re: [PR] perf: create a native plan's spill directories on its first spill [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 14:05:03 UTC, 4 replies.
- [PR] SQLite: Support `<<` and `>>` bitwise shift operators [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 14:20:38 UTC, 3 replies.
- [PR] SQLite: Support a parenthesized table name in `FROM` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 14:34:48 UTC, 3 replies.
- [I] BoundedWindowAggExec reserves no memory for the rows its window frames keep [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 14:45:48 UTC, 4 replies.
- [PR] Tokenize `~~` as `LIKE` only in PostgreSQL, Redshift and DuckDB [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 14:52:23 UTC, 2 replies.
- [I] perf: native Parquet scans fetch each file and row group only after the previous one is decoded [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 14:56:20 UTC, 1 replies.
- [PR] perf: store the build rows of repeated hash join keys together [datafusion] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 15:30:30 UTC, 8 replies.
- [PR] perf: load the next Parquet file's footer and page index while the current file is read [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 15:33:16 UTC, 17 replies.
- [PR] SQLite, DuckDB: Support aggregate `ORDER BY` without arguments [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 15:47:00 UTC, 4 replies.
- [I] Avoid aggregate repartitioning for audited `date_trunc` on single-key timestamp ranges [datafusion] - posted by "benbellick (via GitHub)" <gi...@apache.org> on 2026/10/17 15:53:17 UTC, 1 replies.
- [PR] Add 'Best Practices for Single Row Lookups' post [datafusion-site] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/17 15:57:03 UTC, 20 replies.
- [PR] SQLite: Accept a block comment left open at end of input [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 15:58:32 UTC, 2 replies.
- [PR] fix: scope fallback reasons to the current conversion [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/17 16:12:28 UTC, 3 replies.
- [PR] chore(deps-dev): bump compression from 1.8.1 to 1.8.2 in /datafusion/wasmtest/datafusion-wasm-app [datafusion-sandbox] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/17 16:16:33 UTC, 0 replies.
- [PR] feat: reuse range partitioning for date_trunc aggregation [datafusion] - posted by "benbellick (via GitHub)" <gi...@apache.org> on 2026/10/17 16:19:27 UTC, 2 replies.
- [PR] Accept `VALUE` as a synonym of `VALUES` only in MySQL [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 16:23:55 UTC, 3 replies.
- [PR] PostgreSQL: Display the index operator class before the sort options [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 16:33:25 UTC, 2 replies.
- [PR] SQLite: Parse the `BETWEEN` lower bound up to its `AND` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 16:46:16 UTC, 1 replies.
- [PR] PostgreSQL, DuckDB, Spark, Databricks: Accept a comparison in the `BETWEEN` lower bound [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 16:57:40 UTC, 1 replies.
- [PR] SQLite: Support `ON` and `USING` after a comma join [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 17:16:54 UTC, 2 replies.
- [PR] fix: make fair_unified's per-consumer limit bind when tasks run concurrently [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 17:34:34 UTC, 20 replies.
- [PR] fix: count negative split_part positions from forward delimiter matches [datafusion] - posted by "vera-rubin (via GitHub)" <gi...@apache.org> on 2026/10/17 17:52:44 UTC, 0 replies.
- [I] Incorrect Parquet pruning for timestamp-to-time casts across midnight [datafusion] - posted by "rgbuilds (via GitHub)" <gi...@apache.org> on 2026/10/17 18:03:31 UTC, 1 replies.
- [PR] perf: use extend instead of push loop in shuffle row buffering [datafusion-comet] - posted by "Jbansal2 (via GitHub)" <gi...@apache.org> on 2026/10/17 18:11:55 UTC, 2 replies.
- [PR] PostgreSQL: Reject string literals as aliases [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 18:22:48 UTC, 3 replies.
- [PR] fix: avoid pruning timestamp-to-time casts [datafusion] - posted by "rgbuilds (via GitHub)" <gi...@apache.org> on 2026/10/17 18:59:31 UTC, 7 replies.
- [PR] DuckDB, MySQL, Spark, Databricks, Hive, ClickHouse: Accept string literal aliases only where each engine does [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 19:00:19 UTC, 2 replies.
- [PR] perf: Optimize `array_sort` to count bits while compacting [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/17 19:06:00 UTC, 0 replies.
- Re: [PR] perf: Optimize `array_sort` to count validity bits while compacting [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/17 19:36:43 UTC, 5 replies.
- Re: [I] Optimize JVM columnar-to-row conversion [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/17 19:40:10 UTC, 0 replies.
- [PR] build(deps): bump tokio from 1.53.2 to 1.53.3 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/17 19:42:46 UTC, 0 replies.
- [PR] build(deps): bump serde_json from 1.0.151 to 1.0.154 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/17 19:42:52 UTC, 0 replies.
- [PR] MsSql: Keep the comma separator when displaying DECLARE lists [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 20:03:20 UTC, 4 replies.
- [PR] PostgreSQL, SQLite, DuckDB, MySQL: Accept keyword-like base window names in `OVER` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 20:29:04 UTC, 2 replies.
- [I] ClickHouse: # comments are not recognized [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/17 20:42:44 UTC, 1 replies.
- [PR] replaces the hard-coded dialect list in the tokenizer with a `supports_hash_comment` dialect method [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/17 20:44:11 UTC, 2 replies.
- [PR] PostgreSQL: Parse an empty SELECT target list without FROM [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 20:53:40 UTC, 2 replies.
- [I] Wrong results: UNION ALL ... ORDER BY ... LIMIT when a sort key is constant per arm (partitioned TopK shares a threshold over a shortened key) [datafusion] - posted by "cning112 (via GitHub)" <gi...@apache.org> on 2026/10/17 20:57:27 UTC, 1 replies.
- [PR] fix: point the spill limit error at spark.comet.maxTempDirectorySize [datafusion-comet] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/17 21:03:58 UTC, 1 replies.
- [PR] fix: keep per-partition constant sort keys in a partitioned TopK [datafusion] - posted by "cning112 (via GitHub)" <gi...@apache.org> on 2026/10/17 21:09:27 UTC, 5 replies.
- [PR] PostgreSQL, ClickHouse: Keep custom data type modifiers re-parseable with a typed list [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/17 21:24:27 UTC, 2 replies.
- [PR] feat: stream the output of a materialized CTE to its scans [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/17 21:59:28 UTC, 1 replies.
- [PR] fix: handle NullType struct fields in JVM columnar shuffle [datafusion-comet] - posted by "jadenfix (via GitHub)" <gi...@apache.org> on 2026/10/17 22:08:38 UTC, 1 replies.
- Re: [I] Decorrelate subqueries whose grouping sets leave out the correlated column [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 01:24:11 UTC, 0 replies.
- Re: [PR] fix: scope HashJoinExec build_time to hash-table construction only [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/18 01:43:16 UTC, 0 replies.
- Re: [PR] perf(scheduler): run one stage when the plan asks for the same stage twice [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/18 01:50:30 UTC, 0 replies.
- Re: [PR] test(scheduler): freeze the plan each TPC-H query ends on, under both planners [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/18 01:50:32 UTC, 0 replies.
- [PR] feat: write top-level Iceberg unknown columns natively [datafusion-comet] - posted by "yunchipang (via GitHub)" <gi...@apache.org> on 2026/10/18 02:07:37 UTC, 8 replies.
- [I] Scans of tables with a declared ordering use count-based file groups, so uneven files make them up to 3x slower [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 02:30:42 UTC, 2 replies.
- [PR] perf: balance file groups by size for scans with an output ordering [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 02:30:50 UTC, 6 replies.
- [PR] fix: keep a sort in EnsureRequirements when the ordering cannot be proven [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 02:52:49 UTC, 2 replies.
- [I] Physical plan check does not cover appended optimizer rules and does not name the rule that broke the plan [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 02:52:56 UTC, 0 replies.
- [PR] Check the final physical plan in the planner and name the rule that broke it [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 02:53:11 UTC, 13 replies.
- [I] Draft: duplicate output names (decision 3) [datafusion] - posted by "fmcmac (via GitHub)" <gi...@apache.org> on 2026/10/18 03:43:42 UTC, 0 replies.
- Re: [I] Support columns having the same alias [datafusion] - posted by "fmcmac (via GitHub)" <gi...@apache.org> on 2026/10/18 03:45:37 UTC, 0 replies.
- [I] coerce_int96 leaves INT96 in two-level and legacy Parquet lists as nanoseconds [datafusion] - posted by "ranflarion (via GitHub)" <gi...@apache.org> on 2026/10/18 04:30:53 UTC, 0 replies.
- [PR] fix: coerce INT96 in two-level and legacy Parquet lists [datafusion] - posted by "ranflarion (via GitHub)" <gi...@apache.org> on 2026/10/18 04:33:14 UTC, 1 replies.
- [PR] fix(functions): pass correct number_rows in gcd benchmarks [datafusion] - posted by "Subodh-17 (via GitHub)" <gi...@apache.org> on 2026/10/18 06:39:21 UTC, 2 replies.
- [I] Aliased aggregate functions fail in sliding window frames [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 08:15:31 UTC, 3 replies.
- [PR] SQLite, DuckDB, PostgreSQL: Accept `._name` after whitespace in a qualified name [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/18 08:17:50 UTC, 2 replies.
- [PR] feat: support `RLIKE` and `REGEXP` operators [datafusion] - posted by "fmcmac (via GitHub)" <gi...@apache.org> on 2026/10/18 08:37:33 UTC, 5 replies.
- [PR] feat: support `[NOT] [I]LIKE ANY (...)` with a list of patterns [datafusion] - posted by "fmcmac (via GitHub)" <gi...@apache.org> on 2026/10/18 08:37:37 UTC, 0 replies.
- [I] docs: update Scala comments that reference the removed iceberg-writes.md page [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/18 09:04:10 UTC, 0 replies.
- Re: [I] Wrong results: window aggregates over `RANGE ... N PRECEDING` depend on batch boundaries when the ORDER BY value is NULL [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 09:32:23 UTC, 0 replies.
- Re: [I] alter_fp_rounding_mode Is Not Panic Safe [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 09:46:22 UTC, 0 replies.
- [I] Internal error: CAST to an extension-type field over a non-null column, under an aggregate (logical vs physical nullability) [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 09:52:24 UTC, 0 replies.
- [PR] SQLite: Bind <, <=, > and >= tighter than = [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/18 10:00:21 UTC, 2 replies.
- [I] `bit_xor` over a sliding window frame returns 0 instead of NULL when the frame has only NULLs [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 10:01:59 UTC, 2 replies.
- [I] `corr`, `covar_pop`, `covar_samp` and `regr_*` silently ignore `DISTINCT` [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/18 10:02:05 UTC, 2 replies.
- [PR] docs: fix missing word in BytesLikeIndexMap field comment [datafusion] - posted by "aarushkandukoori (via GitHub)" <gi...@apache.org> on 2026/10/18 10:11:10 UTC, 2 replies.
- [I] Planning a query with many aggregate or window expressions slows down quadratically [datafusion] - posted by "Braedon-Wooding-Displayr (via GitHub)" <gi...@apache.org> on 2026/10/18 10:18:23 UTC, 0 replies.
- [PR] perf: deduplicate found expressions with an IndexSet [datafusion] - posted by "Braedon-Wooding-Displayr (via GitHub)" <gi...@apache.org> on 2026/10/18 10:19:24 UTC, 3 replies.
- [I] Parquet scans still set up a reader for files whose row groups are all pruned [datafusion] - posted by "Braedon-Wooding-Displayr (via GitHub)" <gi...@apache.org> on 2026/10/18 10:20:37 UTC, 1 replies.
- [I] Python client: plug into DataFusion Python natively through a custom FFI query planner [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/18 10:21:14 UTC, 0 replies.
- [PR] perf: don't build a parquet stream for a file range with no row group left [datafusion] - posted by "Braedon-Wooding-Displayr (via GitHub)" <gi...@apache.org> on 2026/10/18 10:21:53 UTC, 7 replies.
- [PR] Refactoring: Merge the `IN` expression variants into `Expr::In` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/18 10:29:30 UTC, 2 replies.
- [PR] SQLite: Support `IN` with a table name or table-valued function [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/18 10:30:36 UTC, 5 replies.
- Re: [I] `ORDER BY` on a source column fails when a select item is aliased to that column's name [datafusion] - posted by "paoValle (via GitHub)" <gi...@apache.org> on 2026/10/18 10:46:15 UTC, 0 replies.
- [PR] fix: plan ORDER BY on a source column hidden by a select alias [datafusion] - posted by "paoValle (via GitHub)" <gi...@apache.org> on 2026/10/18 10:46:21 UTC, 0 replies.
- Re: [I] Optimize the evaluation of `DATE_TRUNC() == )` when pushed down [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/18 11:40:00 UTC, 0 replies.
- [I] Support hash-partitioned execution in AsOfJoinExec for memory-bounded joins [datafusion] - posted by "Kristofferjoha (via GitHub)" <gi...@apache.org> on 2026/10/18 11:55:51 UTC, 1 replies.
- [PR] docs: Explain the role of `EnsureRequirements` in the physical optimizer pipeline [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/18 12:18:13 UTC, 1 replies.
- Re: [PR] docs(minor): Explain the role of `EnsureRequirements` in the physical optimizer pipeline [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/18 12:44:12 UTC, 1 replies.
- [PR] fix: forward `create_sliding_accumulator` to the inner UDAF when aliased [datafusion] - posted by "cool9850311 (via GitHub)" <gi...@apache.org> on 2026/10/18 12:59:51 UTC, 2 replies.
- Re: [I] Invalid parquet writer options (e.g. `max_row_group_size = 0`, `bloom_filter_fpp = 1.5`) panic in `COPY` instead of returning an error [datafusion] - posted by "tripleaceme (via GitHub)" <gi...@apache.org> on 2026/10/18 13:08:12 UTC, 1 replies.
- [I] EPIC: Separate optimizer rules from correctness transformation rules [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/18 13:15:26 UTC, 4 replies.
- [PR] SQLite: Accept fallback keywords as implicit column aliases [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/18 13:31:04 UTC, 4 replies.
- [PR] fix: return NULL from bit_xor when a sliding frame has no non-NULL values [datafusion] - posted by "choksi2212 (via GitHub)" <gi...@apache.org> on 2026/10/18 13:44:35 UTC, 3 replies.
- [PR] bench: add ASOF join benchmark with a large unfiltered right input [datafusion] - posted by "Kristofferjoha (via GitHub)" <gi...@apache.org> on 2026/10/18 13:45:16 UTC, 4 replies.
- [PR] feat(python): Add Python UDF support to Ballista Python bindings [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/18 15:40:29 UTC, 6 replies.
- [PR] SQLite: Parse `&` and `|` at the same precedence [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/18 16:01:04 UTC, 2 replies.
- [PR] fix: reject DISTINCT in corr, covar and regr_* instead of ignoring it [datafusion] - posted by "abp002 (via GitHub)" <gi...@apache.org> on 2026/10/18 16:10:30 UTC, 5 replies.
- Re: [I] RANGE window frame boundary overflow diverges from Spark for DATE and DECIMAL ORDER BY [datafusion-comet] - posted by "0lai0 (via GitHub)" <gi...@apache.org> on 2026/10/18 16:21:54 UTC, 2 replies.
- [PR] fix: return NULL from `bit_xor` when a sliding frame has no non-NULL values [datafusion] - posted by "cool9850311 (via GitHub)" <gi...@apache.org> on 2026/10/18 16:45:00 UTC, 4 replies.
- [I] External sort OOM error tells Comet users to change `datafusion.runtime.memory_limit` and `datafusion.execution.sort_spill_reservation_bytes` [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/18 16:54:29 UTC, 0 replies.
- [PR] test: write ancient dates with CORRECTED rebase mode in the DATE RANGE window test [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/18 17:39:32 UTC, 1 replies.
- [PR] fix(aqe): preserve stages when transitions fail [datafusion-ballista] - posted by "SIBTAIN-ASAD (via GitHub)" <gi...@apache.org> on 2026/10/18 18:01:29 UTC, 0 replies.
- Re: [PR] feat: allow configuring datafusion-cli history file location [datafusion] - posted by "ratmice (via GitHub)" <gi...@apache.org> on 2026/10/18 18:14:39 UTC, 0 replies.
- [PR] build: Publish abi3t wheels for Python 3.15+ [datafusion-python] - posted by "edgarrmondragon (via GitHub)" <gi...@apache.org> on 2026/10/18 18:18:14 UTC, 0 replies.
- Re: [I] Comet starts a single Tokio worker on standalone executors when spark.executor.cores is unset [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/18 18:53:42 UTC, 0 replies.
- [PR] fix: point the external sort OOM error at Comet's memory settings [datafusion-comet] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/18 19:00:00 UTC, 7 replies.
- Re: [I] Update PyO3 to 0.29 and explore abi3t support [datafusion-python] - posted by "edgarrmondragon (via GitHub)" <gi...@apache.org> on 2026/10/18 19:08:30 UTC, 0 replies.
- [PR] refactor: derive the catalog provider's schema from its table [datafusion-iceberg] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/18 19:17:34 UTC, 4 replies.
- [PR] chore: Update "Maximizing CPU Usage" link format in README.md [datafusion-python] - posted by "edgarrmondragon (via GitHub)" <gi...@apache.org> on 2026/10/18 19:37:01 UTC, 0 replies.
- [PR] build(deps): bump github/codeql-action/init from 4.38.2 to 4.39.0 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/18 19:43:24 UTC, 0 replies.
- [PR] build(deps): bump taiki-e/install-action from 2.87.22 to 2.87.28 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/18 19:43:33 UTC, 0 replies.
- [PR] build(deps): bump github/codeql-action/analyze from 4.38.2 to 4.39.0 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/18 19:44:43 UTC, 0 replies.
- [PR] build(deps): bump astral-sh/setup-uv from 10.2.0 to 10.3.0 [datafusion-python] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/18 19:45:03 UTC, 0 replies.
- [PR] fix: preserve ExprFunctionExt options when chaining [datafusion] - posted by "goutamadwant (via GitHub)" <gi...@apache.org> on 2026/10/18 20:37:40 UTC, 1 replies.
- [PR] feat(executor): report metrics from pull-based executors [datafusion-ballista] - posted by "Richard-Durkee (via GitHub)" <gi...@apache.org> on 2026/10/18 20:54:13 UTC, 0 replies.
- [I] Bug triage results: 2026-10-18 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/18 21:24:09 UTC, 0 replies.
- [I] Run a job's final commit step on the scheduler, not an executor [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/18 22:19:25 UTC, 1 replies.
- Re: [PR] Perf/19938 grouped flat array [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 01:47:04 UTC, 0 replies.
- Re: [PR] feat: add IEJoin for joins with two range predicates [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 01:47:10 UTC, 0 replies.
- Re: [PR] perf: improve splitting of the offset vector in `GroupColumn::take_n` implementations, adding a new helper fn [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 01:47:13 UTC, 0 replies.
- Re: [PR] Setup dependabot to do `rust-toolchain` updates [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 01:47:15 UTC, 0 replies.
- [PR] Fix retained memory accounting for ExprIntervalGraph [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/19 03:30:43 UTC, 1 replies.
- [PR] chore(deps): bump rustls from 0.23.45 to 0.23.46 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 04:47:35 UTC, 1 replies.
- [PR] chore(deps): bump pyo3-build-config from 0.29.3 to 0.30.1 in /python [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 04:47:38 UTC, 2 replies.
- [PR] chore(deps): bump arrow-flight from 59.3.0 to 59.3.1 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 04:48:08 UTC, 1 replies.
- [PR] fix: decode invalid UTF-8 in nested Parquet BINARY values read as strings [datafusion-comet] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/19 04:48:21 UTC, 7 replies.
- [I] Physical optimizer drops SortExec below OFFSET when an aggregate consumes the subquery [datafusion] - posted by "Fly-a-Kite (via GitHub)" <gi...@apache.org> on 2026/10/19 04:48:32 UTC, 1 replies.
- [PR] chore(deps): bump arrow from 59.3.0 to 59.3.1 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 04:48:42 UTC, 1 replies.
- [PR] chore(deps): bump tokio from 1.53.2 to 1.53.3 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 04:48:58 UTC, 1 replies.
- [PR] chore(deps): bump tokio from 1.53.2 to 1.53.3 in /python [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 04:49:03 UTC, 2 replies.
- [PR] chore(ci): bump taiki-e/install-action from 2.87.28 to 2.87.29 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 04:50:25 UTC, 1 replies.
- [PR] refactor(spark): deduplicate bucket computation in width_bucket_interval_mdn_exact [datafusion] - posted by "Shahzeb-DataEngineer (via GitHub)" <gi...@apache.org> on 2026/10/19 04:56:30 UTC, 3 replies.
- [I] Plain `SELECT` of a Parquet float column returns wrong values: NaN rows are replaced by the statistics constant when min == max [datafusion] - posted by "hanke580 (via GitHub)" <gi...@apache.org> on 2026/10/19 06:18:10 UTC, 0 replies.
- [I] Parquet bloom filter pruning drops rows holding the other signed zero: `WHERE c = 0.0` misses `-0.0` rows (and vice versa) [datafusion] - posted by "hanke580 (via GitHub)" <gi...@apache.org> on 2026/10/19 06:18:50 UTC, 1 replies.
- [I] `COPY … PARTITIONED BY` writes partition values containing `=` unescaped (`p0=x=y`); DuckDB and Polars cannot read the dataset or silently drop the partition column [datafusion] - posted by "hanke580 (via GitHub)" <gi...@apache.org> on 2026/10/19 06:19:43 UTC, 1 replies.
- [I] `COPY … STORED AS JSON` (and `INSERT INTO` a JSON table) drops every `MAP` entry whose value is NULL: `{color: red, size: NULL}` is written as `{"color":"red"}` [datafusion] - posted by "hanke580 (via GitHub)" <gi...@apache.org> on 2026/10/19 06:21:15 UTC, 1 replies.
- [PR] refactor: share window frame bound offset serialization between lower and upper bounds [datafusion-comet] - posted by "0lai0 (via GitHub)" <gi...@apache.org> on 2026/10/19 06:30:51 UTC, 1 replies.
- [I] Executor is OOM-killed while Comet's pool and allocation counter stay under the limit: glibc keeps several GiB of freed native memory [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/19 06:33:30 UTC, 0 replies.
- Re: [I] Investigate charging native Iceberg scan memory to the task memory pool [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/19 06:33:44 UTC, 0 replies.
- [PR] fix: do not treat float min==max Parquet statistics as constant columns [datafusion] - posted by "charan-rathore (via GitHub)" <gi...@apache.org> on 2026/10/19 07:27:51 UTC, 1 replies.
- [PR] PostgreSQL: Parse schema-qualified keyword function calls [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/19 08:50:28 UTC, 2 replies.
- Re: [PR] feat: report statistics of materialized CTE scans [datafusion] - posted by "asolimando (via GitHub)" <gi...@apache.org> on 2026/10/19 08:58:23 UTC, 0 replies.
- Re: [I] Supporting analytics over large amounts of pre‑partitioned data [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/19 08:59:40 UTC, 0 replies.
- [I] NativeUtil.exportBatch rejects large_string and large_binary vectors [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 09:11:47 UTC, 0 replies.
- Re: [PR] fix: count grouped integer SUM state in the aggregate's memory reservation [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 09:13:12 UTC, 1 replies.
- Re: [PR] chore(deps): bump the all-other-cargo-deps group across 1 directory with 7 updates [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 09:13:50 UTC, 1 replies.
- [PR] chore(deps): bump the all-other-cargo-deps group across 1 directory with 9 updates [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/19 09:15:05 UTC, 2 replies.
- [I] this recursive CTE SQL runs slower than SQLite [datafusion-python] - posted by "l1t1 (via GitHub)" <gi...@apache.org> on 2026/10/19 10:40:07 UTC, 0 replies.
- [PR] ClickHouse: Allow $ inside identifiers [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/19 11:21:09 UTC, 2 replies.
- [I] Null-aware `NOT IN` hash join in `Partitioned` mode returns rows when the subquery contains NULL [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/19 12:17:38 UTC, 2 replies.
- Re: [I] Attach `Diagnostic` to "invalid function argument types" error [datafusion] - posted by "aruadecarvalho (via GitHub)" <gi...@apache.org> on 2026/10/19 12:25:06 UTC, 4 replies.
- Re: [I] Attach `Diagnostic` to "wrong number of arguments" error [datafusion] - posted by "aruadecarvalho (via GitHub)" <gi...@apache.org> on 2026/10/19 12:25:35 UTC, 0 replies.
- [PR] SQLite: Support `INDEXED BY` and `NOT INDEXED` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/19 13:03:15 UTC, 2 replies.
- [PR] MySQL: Keep literal prefixes as identifiers after a period [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/19 13:26:59 UTC, 2 replies.
- [PR] PostgreSQL: Parse custom typed string literals [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/19 13:34:40 UTC, 2 replies.
- [I] `nth_value` and `approx_percentile_cont` silently ignore `DISTINCT` [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/19 13:48:31 UTC, 2 replies.
- [PR] chore: fix compiler warnings in the spark module [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 13:48:52 UTC, 1 replies.
- [PR] ci: give the Delta contrib Maven cache its own key prefix [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 14:03:35 UTC, 2 replies.
- Re: [PR] fix: build release jars from the same commit as the native libraries [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 14:07:14 UTC, 0 replies.
- Re: [I] Release build script builds JVM components from wrong branch [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 14:07:15 UTC, 0 replies.
- Re: [PR] chore(ci): bump the github-codeql group across 1 directory with 2 updates [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/19 14:09:51 UTC, 0 replies.
- [PR] docs: publish the newest release at user-guide/latest and main at user-guide/dev [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 14:24:26 UTC, 3 replies.
- [PR] fix: nvl2 result type should not depend on its first argument [datafusion] - posted by "CuteChuanChuan (via GitHub)" <gi...@apache.org> on 2026/10/19 14:37:16 UTC, 8 replies.
- [I] Support join runtime reader filters through column-only projections [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/19 14:48:24 UTC, 0 replies.
- [PR] test: move the float semantics sweep to SQL file tests [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 14:59:05 UTC, 1 replies.
- Re: [PR] Accept `CREATE SEQUENCE` options in any order [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/19 15:07:17 UTC, 4 replies.
- [PR] fix: fall back to Spark for mode on FLOAT and DOUBLE before Spark 3.5.2 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 15:29:50 UTC, 1 replies.
- [PR] Docs: Require a fuzz seed per bug fix in AGENTS.md [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/19 15:37:06 UTC, 2 replies.
- [PR] feat(scheduler): graceful shutdown for the scheduler's gRPC and embedded Flight-proxy server [datafusion-ballista] - posted by "villebro (via GitHub)" <gi...@apache.org> on 2026/10/19 15:46:29 UTC, 0 replies.
- [PR] Add `Comments::find_before` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/19 15:57:04 UTC, 5 replies.
- Re: [I] Grouped integer SUM doesn't count its per-group state in the aggregate's memory reservation [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 16:12:54 UTC, 0 replies.
- Re: [I] Wrong results: a list `unnest` keeps its input's GROUP BY key, so a later DISTINCT or GROUP BY drops rows [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/19 16:17:22 UTC, 0 replies.
- [I] Keep wide-decimal scalar AVG native with a wider running sum [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/19 16:18:58 UTC, 0 replies.
- Re: [PR] fix: experiments with large types for aggregated values [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/19 16:55:17 UTC, 0 replies.
- [PR] fix: preserve make_date overflow and skipped evaluation [datafusion-comet] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/19 17:15:34 UTC, 11 replies.
- [PR] fix(cli): preserve multiline literals in SQL files [datafusion] - posted by "vera-rubin (via GitHub)" <gi...@apache.org> on 2026/10/19 18:11:55 UTC, 0 replies.
- Re: [I] Bug: unexpected behavior with special characters in input [datafusion] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/19 18:20:14 UTC, 0 replies.
- Re: [I] Instantiate an `AggregateExec` with no group columns + no aggregates triggers `must either specify a row count or at least one column` from RecordBatch [datafusion] - posted by "hsiang-c (via GitHub)" <gi...@apache.org> on 2026/10/19 18:31:00 UTC, 0 replies.
- [PR] fix: keep NULL-valued MAP entries when writing JSON [datafusion] - posted by "shantanutheone (via GitHub)" <gi...@apache.org> on 2026/10/19 18:46:05 UTC, 1 replies.
- Re: [I] Window sort pushdown below LIMIT/OFFSET prevents early termination [datafusion] - posted by "blaginin (via GitHub)" <gi...@apache.org> on 2026/10/19 19:07:37 UTC, 0 replies.
- [PR] fix: reject invalid parquet writer options when they are set [datafusion] - posted by "tripleaceme (via GitHub)" <gi...@apache.org> on 2026/10/19 19:23:33 UTC, 4 replies.
- Re: [I] Large-offset Arrow vectors from PyArrow UDFs cannot be serialized for broadcast or collect [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 19:33:43 UTC, 0 replies.
- [PR] docs: update committer list in governance page [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/19 19:50:52 UTC, 3 replies.
- [I] Correlated scalar subquery with `count(*)` returns 0 instead of NULL when `HAVING` references an outer column [datafusion] - posted by "fornwall (via GitHub)" <gi...@apache.org> on 2026/10/19 20:10:24 UTC, 2 replies.
- [I] Correlated subquery fails when filtering an aliased derived table on an outer column [datafusion] - posted by "fornwall (via GitHub)" <gi...@apache.org> on 2026/10/19 20:16:38 UTC, 1 replies.
- [I] Correlated scalar subquery ignores `HAVING` that is true for empty input [datafusion] - posted by "fornwall (via GitHub)" <gi...@apache.org> on 2026/10/19 20:30:02 UTC, 3 replies.
- [I] Named window in `HAVING` is silently ignored and the query returns results instead of an error [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/19 20:30:36 UTC, 2 replies.
- [PR] perf: Optimize repeated counting of set bits [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/19 20:43:59 UTC, 9 replies.
- [I] Wrong results: correlated scalar subquery with nested aggregates [datafusion] - posted by "fornwall (via GitHub)" <gi...@apache.org> on 2026/10/19 21:02:41 UTC, 1 replies.
- [I] Text broadcast build sides and string min/max apply the invalid UTF-8 decode where 1.1.0 stayed on Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 21:29:51 UTC, 1 replies.
- [PR] docs: note that Text broadcast build sides decode invalid UTF-8 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 21:30:25 UTC, 2 replies.
- Re: [I] Casting existing timestamp to timestamp again strips timezone information [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/19 21:37:16 UTC, 0 replies.
- [PR] chore: fix stddev accumulator size and resolve session libhdfs schemes once per scan rule [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/19 21:53:09 UTC, 2 replies.
- Re: [I] `push_down_leaf_projections` fails with an ambiguous schema when a sub-query projection renames columns [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/19 22:16:56 UTC, 0 replies.
- [PR] docs: name the invalid UTF-8 cases that 1.1.0 kept in Spark [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 22:32:22 UTC, 2 replies.
- Re: [PR] feat(python): Plug into DataFusion Python natively through a custom FFI query planner [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/19 22:51:18 UTC, 3 replies.
- [I] store start and end bounds in Partitioning::Range [datafusion] - posted by "jayshrivastava (via GitHub)" <gi...@apache.org> on 2026/10/19 23:00:08 UTC, 0 replies.
- Re: [PR] feat: finish scheduler jobs on shutdown and unify signal handling [datafusion-ballista] - posted by "villebro (via GitHub)" <gi...@apache.org> on 2026/10/20 00:04:23 UTC, 5 replies.
- Re: [PR] perf(parquet): preserve RLE dictionaries for binary_as_string scans [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/20 00:28:30 UTC, 15 replies.
- [PR] fix: redact Parquet key configuration Debug output [datafusion] - posted by "autoCAT6 (via GitHub)" <gi...@apache.org> on 2026/10/20 00:35:27 UTC, 0 replies.
- [PR] fix: fall back when an Iceberg equality delete is keyed on a nested field [datafusion-comet] - posted by "yunchipang (via GitHub)" <gi...@apache.org> on 2026/10/20 00:46:34 UTC, 2 replies.
- [I] MySQL caret binds below multiplication, changing a DataFusion query result [datafusion-sqlparser-rs] - posted by "pbottine (via GitHub)" <gi...@apache.org> on 2026/10/20 00:48:56 UTC, 2 replies.
- [I] SQLite parser dialect returns different rows for bitwise filter than SQLite [datafusion] - posted by "pbottine (via GitHub)" <gi...@apache.org> on 2026/10/20 00:49:14 UTC, 0 replies.
- Re: [PR] ci: run extended tests on aggregate and window function changes [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 01:43:22 UTC, 0 replies.
- Re: [PR] feat(pruning): prune containers through `CASE` predicates [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 01:43:24 UTC, 0 replies.
- Re: [PR] fix: union coercion coerces to string instead of number [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 01:43:30 UTC, 0 replies.
- Re: [PR] feat: Enable expressions as default value in lead/lag function [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 01:43:40 UTC, 0 replies.
- Re: [PR] Introduce way to customize prefix of multi file outputs [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 01:43:47 UTC, 0 replies.
- Re: [PR] fix: summarize Bloom literals in filter and projection plan displays [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/20 02:11:23 UTC, 1 replies.
- [PR] fix: default broadcast build side conversion to off and document invalid UTF-8 cases [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 02:21:32 UTC, 2 replies.
- [I] Amortize state compaction in DistinctArrayAggGroupsAccumulator on EmitTo::First [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/20 02:43:39 UTC, 0 replies.
- [PR] fix: preserve Parquet column key metadata associations [datafusion] - posted by "autoCAT6 (via GitHub)" <gi...@apache.org> on 2026/10/20 02:50:48 UTC, 0 replies.
- [I] CSV `ESCAPE` option is used when reading but ignored when writing: `INSERT`/`COPY` files cannot be read back with the same options (rows merged, backslashes dropped) [datafusion] - posted by "hanke580 (via GitHub)" <gi...@apache.org> on 2026/10/20 03:07:57 UTC, 3 replies.
- Re: [PR] fix: cap native projection input before collect limits [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/20 03:54:33 UTC, 8 replies.
- [PR] chore(deps): bump libc from 0.2.190 to 0.2.191 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 04:31:34 UTC, 1 replies.
- [PR] fix: write each batch's partitions in first-row order for the clustered writer [datafusion-iceberg] - posted by "CaptainAni187 (via GitHub)" <gi...@apache.org> on 2026/10/20 04:43:24 UTC, 0 replies.
- Re: [I] Native UDFs: config to disable or restrict library loading [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 05:03:22 UTC, 0 replies.
- Re: [I] Rust UDF library cache holds its write lock across dlopen [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 05:03:23 UTC, 0 replies.
- Re: [I] Support Spark-compatible native hash and xxhash64 for decimals with precision >18 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 05:14:59 UTC, 0 replies.
- Re: [PR] fix: log native panic backtraces instead of attaching them to the exception [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/20 05:37:08 UTC, 6 replies.
- Re: [PR] perf: stop re-pairing marked build rows in the scope-key null-aware join [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/20 05:38:33 UTC, 0 replies.
- [PR] fix: export large_string and large_binary vectors with 32-bit offsets [datafusion-comet] - posted by "afterincomparableyum (via GitHub)" <gi...@apache.org> on 2026/10/20 05:39:13 UTC, 2 replies.
- Re: [PR] perf: preserve and process Parquet dictionaries efficiently [datafusion] - posted by "adriangbot (via GitHub)" <gi...@apache.org> on 2026/10/20 05:40:20 UTC, 26 replies.
- [PR] perf: sort JVM shuffle spill pointers in the sorter's scratch space [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/20 06:38:59 UTC, 2 replies.
- [PR] fix: fall back when an outer hash join's streamed order cannot be checked [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/20 07:25:33 UTC, 6 replies.
- Re: [PR] fix: preserve duplicate counts in INTERSECT ALL and EXCEPT ALL [datafusion] - posted by "1fanwang (via GitHub)" <gi...@apache.org> on 2026/10/20 07:52:59 UTC, 0 replies.
- [PR] fix: keep URL passwords and SAS queries out of Azure store errors and logs [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/20 08:02:28 UTC, 0 replies.
- [I] Native object-store errors and debug logs print whole URLs outside the Azure store [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/20 08:05:14 UTC, 1 replies.
- [PR] Resolve named windows in HAVING [datafusion] - posted by "zhuqi-lucas (via GitHub)" <gi...@apache.org> on 2026/10/20 08:15:18 UTC, 3 replies.
- [I] Native Iceberg scan applies equality deletes to the wrong column when column names differ only in case [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/20 08:34:41 UTC, 0 replies.
- Re: [PR] feat: estimate Decimal filter selectivity with interval analysis [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/20 08:39:57 UTC, 7 replies.
- Re: [PR] perf: evaluate Parquet Bloom filters incrementally during row group pruning [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/20 08:41:26 UTC, 10 replies.
- [I] MySQL: compound time units (`YEAR_MONTH`, `DAY_HOUR`...) fail in `EXTRACT` and `INTERVAL` [datafusion-sqlparser-rs] - posted by "sfaut (via GitHub)" <gi...@apache.org> on 2026/10/20 08:46:28 UTC, 0 replies.
- Re: [PR] feat(parquet): add `coerce_binary_to_string` option to read binary file columns as binary [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/20 09:10:23 UTC, 4 replies.
- Re: [I] Iceberg native scan fails queries on tables whose column names are case-distinct to Java but not to Rust [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/20 09:14:36 UTC, 0 replies.
- [PR] fix: match Iceberg column names exactly in the native scan [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/20 09:14:53 UTC, 9 replies.
- [I] `optimize_projections` fails with "No field named ..." after `propagate_empty_relation` removes the first branch of a UNION [datafusion] - posted by "moraistejerina (via GitHub)" <gi...@apache.org> on 2026/10/20 09:15:41 UTC, 1 replies.
- [I] [EPIC] Variant on DataFusion [datafusion] - posted by "raghuvanshraj (via GitHub)" <gi...@apache.org> on 2026/10/20 09:18:21 UTC, 4 replies.
- Re: [PR] fix: Reject negative RANGE window frame offsets [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/20 09:25:30 UTC, 1 replies.
- Re: [PR] feat: allow COPY to be disabled independently [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/20 09:48:26 UTC, 3 replies.
- Re: [PR] test: run microbenchmarks in extended CI [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/20 09:50:19 UTC, 9 replies.
- [PR] docs: update libhdfs thread-destructor notes now that the fix is released [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 09:56:07 UTC, 3 replies.
- [PR] perf: default the native Iceberg scan to two concurrent data files [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 10:15:50 UTC, 1 replies.
- [I] Discuss limiting open PRs per contributor without write access [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 10:33:48 UTC, 7 replies.
- Re: [PR] fix(ffi): forward distinct_handling through FFI_AggregateUDF [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/20 10:36:45 UTC, 5 replies.
- [PR] test: use shared aggr_test_schema in csv tests (#26306) [datafusion] - posted by "nishant4671 (via GitHub)" <gi...@apache.org> on 2026/10/20 10:58:34 UTC, 0 replies.
- Re: [PR] MSSQL: Support multiple columns after ALTER TABLE ADD [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/20 11:08:07 UTC, 0 replies.
- [PR] Fix changelog generation for unlinked authors [datafusion] - posted by "krishnagp97 (via GitHub)" <gi...@apache.org> on 2026/10/20 11:08:59 UTC, 0 replies.
- Re: [I] preserve ordering through `to_timestamp_seconds/millis/micros/nanos` and `to_unixtime` [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/20 11:12:50 UTC, 0 replies.
- [PR] chore(deps-dev): bump webpack from 5.111.1 to 5.112.0 in /datafusion/wasmtest/datafusion-wasm-app in the all-npm-deps group [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 11:18:42 UTC, 1 replies.
- [PR] chore(deps): bump the all-other-cargo-deps group with 3 updates [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 11:19:15 UTC, 1 replies.
- [PR] chore(deps): bump taiki-e/install-action from 2.87.27 to 2.87.29 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 11:19:36 UTC, 1 replies.
- [PR] chore(deps): bump rustyline from 18.0.1 to 19.0.0 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 11:19:42 UTC, 1 replies.
- [PR] chore(deps): bump tomlkit from 0.15.1 to 0.15.2 in the all-uv-deps group [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 11:19:43 UTC, 1 replies.
- [I] Native Iceberg scan reads the wrong struct child for name-mapped files whose nested names differ in case [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/20 11:23:23 UTC, 0 replies.
- Re: [PR] fix: keep Text build sides on Spark by default and add Text conversion configs [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 11:24:17 UTC, 10 replies.
- [PR] perf(sort): continues sort and merge every x batches in background [datafusion] - posted by "rluvaton (via GitHub)" <gi...@apache.org> on 2026/10/20 12:01:20 UTC, 35 replies.
- [I] TRY_CAST rejects valid struct casts at planning time [datafusion] - posted by "ahlag (via GitHub)" <gi...@apache.org> on 2026/10/20 12:09:13 UTC, 1 replies.
- Re: [I] [Iceberg] Run a job's final commit step on the scheduler, not an executor [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/20 12:18:40 UTC, 3 replies.
- [PR] fix: plan TRY_CAST struct casts by field name like CAST [datafusion] - posted by "ahlag (via GitHub)" <gi...@apache.org> on 2026/10/20 12:29:39 UTC, 1 replies.
- Re: [PR] fix: keep probe-side constants in join equivalence properties [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/20 12:31:59 UTC, 14 replies.
- Re: [PR] [branch-55] perf: Avoid copying when materializing output in OrderedPartialAggregateStream (#25312) [datafusion] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/20 12:41:49 UTC, 0 replies.
- Re: [PR] fix: keep URL passwords and SAS queries out of Azure and object store errors, keys and logs [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/20 12:58:22 UTC, 3 replies.
- Re: [I] Support named placeholders wherever numeric ones are allowed [datafusion] - posted by "colinmarc (via GitHub)" <gi...@apache.org> on 2026/10/20 14:32:57 UTC, 0 replies.
- [I] Parquet binary_as_string expands RLE dictionaries before rebuilding them [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/20 15:05:14 UTC, 1 replies.
- [PR] perf: create DiskManager Directories mode temp dirs on first spill [datafusion] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/20 15:10:57 UTC, 0 replies.
- Re: [I] chore: Improve cast MapType to String [datafusion-comet] - posted by "getChan (via GitHub)" <gi...@apache.org> on 2026/10/20 15:12:35 UTC, 0 replies.
- Re: [I] A way to specify constant/scalar arguments in UDFs [datafusion] - posted by "getChan (via GitHub)" <gi...@apache.org> on 2026/10/20 15:14:40 UTC, 0 replies.
- Re: [I] partitioning: store start and end bounds in Partitioning::Range [datafusion] - posted by "jayshrivastava (via GitHub)" <gi...@apache.org> on 2026/10/20 15:34:36 UTC, 0 replies.
- Re: [I] Allow a Parquet scan to read binary columns as binary when the table schema declares a string type [datafusion] - posted by "manuzhang (via GitHub)" <gi...@apache.org> on 2026/10/20 15:41:35 UTC, 0 replies.
- [PR] feat: support DataFrame::cache() with pinned shuffle output and recovery [datafusion-ballista] - posted by "akshaychitneni (via GitHub)" <gi...@apache.org> on 2026/10/20 15:43:12 UTC, 5 replies.
- [I] `LAST_VALUE ... IGNORE NULLS` is quadratic in the partition size [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 16:11:02 UTC, 1 replies.
- [PR] perf: make `LAST_VALUE ... IGNORE NULLS` linear in the partition size [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 16:11:46 UTC, 10 replies.
- [PR] chore: limit open PRs for users without write access to 3 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 16:17:17 UTC, 3 replies.
- [PR] Accept identifiers that start with a digit + Refactoring [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/20 16:54:45 UTC, 1 replies.
- Re: [PR] Add support for PostgreSQL `DROP RULE` [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/20 16:57:11 UTC, 1 replies.
- [PR] wip [datafusion] - posted by "jayshrivastava (via GitHub)" <gi...@apache.org> on 2026/10/20 17:06:35 UTC, 1 replies.
- [PR] feat: support reference relations in the Substrait consumer [datafusion] - posted by "alexanderbianchi (via GitHub)" <gi...@apache.org> on 2026/10/20 17:28:34 UTC, 1 replies.
- [D] On self-hosted CI [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/20 17:40:30 UTC, 3 replies.
- Re: [I] CI takes hours to start [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/20 18:01:53 UTC, 37 replies.
- [I] Native Iceberg scan drops -0.0 rows for floating-point predicates [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/20 18:23:17 UTC, 0 replies.
- [I] Native Iceberg scan drops NULL rows for NOT (col <=> value) [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/20 18:23:20 UTC, 0 replies.
- [I] Native Iceberg scan drops rows from data files that store a narrower type than the column [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/20 18:23:26 UTC, 0 replies.
- [I] Fuzz testing takes more CI time than all the other tests combined [datafusion-sqlparser-rs] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/20 18:28:22 UTC, 1 replies.
- [PR] CI: Keep ClusterFuzzLite fuzzing on the daily schedule [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/20 18:41:47 UTC, 0 replies.
- Re: [PR] CI: Remove ClusterFuzzLite from PR, daily schedule only. [datafusion-sqlparser-rs] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/20 18:50:23 UTC, 3 replies.
- Re: [PR] Snowflake: Add ALTER EXTERNAL VOLUME [datafusion-sqlparser-rs] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/20 18:54:45 UTC, 0 replies.
- [PR] perf(aggregate): read the first/last value scoreboard a word at a time [datafusion] - posted by "tanmay442 (via GitHub)" <gi...@apache.org> on 2026/10/20 19:16:27 UTC, 8 replies.
- Re: [PR] feat: Fix output bytes metric in hash agg [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/20 19:42:47 UTC, 0 replies.
- Re: [PR] feat(benchmarks): add sql benchmark sort pushdown SQL suite [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/20 19:44:43 UTC, 1 replies.
- [PR] test: add window operator benchmarks [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 19:48:51 UTC, 1 replies.
- Re: [I] Allow extension `PhysicalExpr`s to decode via a per-type registry instead of `PhysicalExtensionCodec` [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/20 19:53:12 UTC, 0 replies.
- [PR] fix: report output rows and time of the native window operator [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 20:00:32 UTC, 3 replies.
- [I] Memoize `LAST_VALUE` and `NTH_VALUE` with `IGNORE NULLS` so `BoundedWindowAggExec` can prune its buffer [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 20:03:51 UTC, 1 replies.
- [I] `NTH_VALUE(expr, -n) IGNORE NULLS` is quadratic in the partition size [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 20:12:41 UTC, 1 replies.
- [I] `LAST_VALUE` and `NTH_VALUE` with `IGNORE NULLS` keep the whole partition buffered [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 20:12:45 UTC, 1 replies.
- [I] `FIRST_VALUE`, `LAST_VALUE` and `NTH_VALUE` build a `ScalarValue` for every row [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 20:12:52 UTC, 1 replies.
- [I] `BoundedWindowAggExec` has a high fixed cost per partition when partitions are small [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 20:12:54 UTC, 0 replies.
- Re: [PR] perf: optimize dictionary float-zero normalization [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/20 20:25:45 UTC, 0 replies.
- [I] [DISCUSS] Proposal to donate `distributed-datafusion` to Apache DataFusion [datafusion-ballista] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/20 20:33:15 UTC, 2 replies.
- [I] Simplify `IN` lists containing `NULL` literals under filter semantics in `EliminateFilter` [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/20 20:44:48 UTC, 1 replies.
- [PR] [DO NOT MERGE] Test DataFusion against arrow/parquet 60.1.0 release candidate (apache/arrow-rs#11750) [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/20 20:48:52 UTC, 11 replies.
- [PR] fix: keep a subquery correlated when an aggregate sits above a pulled up scalar aggregate [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/20 20:49:39 UTC, 13 replies.
- [I] Wrong results: a filter on a constant column keeps the row of an aggregate without GROUP BY [datafusion] - posted by "ameyypawar (via GitHub)" <gi...@apache.org> on 2026/10/20 20:55:31 UTC, 1 replies.
- [I] Dejadoc & code duplication [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/20 21:09:43 UTC, 0 replies.
- Re: [PR] fix: clear error instead of panic on mismatched column statistics [datafusion] - posted by "jackylee-ch (via GitHub)" <gi...@apache.org> on 2026/10/20 21:42:48 UTC, 0 replies.
- [PR] Parser: fix exponential parse time on `(x) ->` lambda chains [datafusion-sqlparser-rs] - posted by "moshap-firebolt (via GitHub)" <gi...@apache.org> on 2026/10/20 22:15:56 UTC, 1 replies.
- [PR] chore(deps): bump certifi from 2026.1.4 to 2026.10.19 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 23:53:45 UTC, 1 replies.
- [PR] chore(deps): bump launch-editor from 2.14.1 to 2.14.2 in /datafusion/wasmtest/datafusion-wasm-app [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/20 23:54:07 UTC, 1 replies.
- Re: [PR] fix: decline native scans whose S3 configuration diverges from Hadoop's [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/21 00:08:33 UTC, 9 replies.
- Re: [PR] fix(substrait): preserve nested nullability [datafusion] - posted by "huymq1710 (via GitHub)" <gi...@apache.org> on 2026/10/21 00:10:36 UTC, 1 replies.
- [PR] test: pin localTableScan off in Iceberg write detection helpers [datafusion-comet] - posted by "yunchipang (via GitHub)" <gi...@apache.org> on 2026/10/21 00:36:59 UTC, 0 replies.
- Re: [PR] datafusion-physical-expr: add `DynamicFilterPhysicalExpr::update_from(Self)` method [datafusion] - posted by "codecov-commenter (via GitHub)" <gi...@apache.org> on 2026/10/21 01:01:36 UTC, 5 replies.
- Re: [I] Allow COPY to be disabled independently in SQLOptions [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/21 01:14:04 UTC, 0 replies.
- Re: [PR] perf(scheduler): merge a task's sorted partitions before the shuffle write [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/21 02:01:58 UTC, 0 replies.
- Re: [PR] feat(python): integrate Ballista through DataFusion FFI [datafusion-ballista] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/21 02:02:02 UTC, 0 replies.
- [I] refactor: consolidate make_date and shared evaluation guards [datafusion-comet] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/21 02:58:39 UTC, 0 replies.
- [I] perf: retain native make_date filters behind redundant NULL checks [datafusion-comet] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/21 02:58:49 UTC, 0 replies.
- [I] test: move make_date SQL regressions into SQL fixtures [datafusion-comet] - posted by "pingzh (via GitHub)" <gi...@apache.org> on 2026/10/21 02:58:53 UTC, 0 replies.
- [I] Tune nested take compaction threshold with a query-level benchmark [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/21 03:54:18 UTC, 0 replies.
- [PR] MySQL: Support compound time units in EXTRACT and INTERVAL [datafusion-sqlparser-rs] - posted by "princejain756 (via GitHub)" <gi...@apache.org> on 2026/10/21 04:03:55 UTC, 0 replies.
- [PR] MySQL: Bind bitwise XOR (^) tighter than multiplication [datafusion-sqlparser-rs] - posted by "princejain756 (via GitHub)" <gi...@apache.org> on 2026/10/21 04:08:35 UTC, 0 replies.
- Re: [PR] SQLite: Tokenize parameters the way SQLite does [datafusion-sqlparser-rs] - posted by "sabir-akhadov-localstack (via GitHub)" <gi...@apache.org> on 2026/10/21 04:47:35 UTC, 0 replies.
- [PR] chore(deps): bump rustyline from 18.0.1 to 19.0.0 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/21 04:59:30 UTC, 1 replies.
- [PR] fix: simplify IN lists containing NULL literals in EliminateFilter [datafusion] - posted by "raghavyadav01 (via GitHub)" <gi...@apache.org> on 2026/10/21 05:04:50 UTC, 5 replies.
- [I] Security audit CI failing: RUSTSEC-2026-0382 (rustls-webpki) and RUSTSEC-2026-0383 (webpki-root-certs) [datafusion] - posted by "yashaggarwal85d (via GitHub)" <gi...@apache.org> on 2026/10/21 05:20:11 UTC, 3 replies.
- [PR] chore(deps): bump rustls-webpki and webpki-root-certs to fix security… [datafusion] - posted by "yashaggarwal85d (via GitHub)" <gi...@apache.org> on 2026/10/21 05:22:56 UTC, 2 replies.
- [PR] fix(optimizer): preserve correlated columns when removing filter above SubqueryAlias [datafusion] - posted by "princejain756 (via GitHub)" <gi...@apache.org> on 2026/10/21 05:24:37 UTC, 5 replies.
- [PR] feat: add session-scoped secrets and CREATE/DROP SECRET [datafusion] - posted by "autoCAT6 (via GitHub)" <gi...@apache.org> on 2026/10/21 05:52:29 UTC, 0 replies.
- [PR] refactor: extract join physical planning [datafusion] - posted by "LiXuanqi (via GitHub)" <gi...@apache.org> on 2026/10/21 06:23:48 UTC, 0 replies.
- [PR] bench: add first_value/last_value cases for a group-by with many groups [datafusion] - posted by "tanmay442 (via GitHub)" <gi...@apache.org> on 2026/10/21 07:14:10 UTC, 1 replies.
- Re: [PR] perf(aggregate): collect the first/last value winners from the touched groups [datafusion] - posted by "tanmay442 (via GitHub)" <gi...@apache.org> on 2026/10/21 07:17:03 UTC, 11 replies.
- [PR] feat: allow extension DataSources to decode via a per-type registry [datafusion] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/21 07:50:53 UTC, 10 replies.
- [PR] fix: reject DISTINCT for aggregates with DistinctHandling::Unsupported [datafusion] - posted by "PreetiToppo (via GitHub)" <gi...@apache.org> on 2026/10/21 08:00:33 UTC, 1 replies.
- Re: [I] Support column reference as percentile arg for `percentile_cont` and `approx_percentile_cont` [datafusion] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/21 08:00:38 UTC, 0 replies.
- [PR] fix: map remaining union input by position in `propagate_empty_relation` [datafusion] - posted by "moraistejerina (via GitHub)" <gi...@apache.org> on 2026/10/21 09:23:50 UTC, 3 replies.
- [PR] MsSql: Serialize DECLARE variable lists and WITH NAME role renames correctly [datafusion-sqlparser-rs] - posted by "princejain756 (via GitHub)" <gi...@apache.org> on 2026/10/21 09:55:41 UTC, 2 replies.
- [PR] fix: coerce correlated subqueries against the outer column's coerced … [datafusion] - posted by "yashaggarwal85d (via GitHub)" <gi...@apache.org> on 2026/10/21 11:14:04 UTC, 1 replies.
- [PR] CI: Reduce redundant Rust checks [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/21 11:53:02 UTC, 3 replies.
- [PR] CI: Prepare required checks for lint consolidation [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/21 12:01:27 UTC, 2 replies.
- [I] Make datafusion-ffi a plain rlib by moving the cdylib integration tests into their own crate [datafusion] - posted by "jprochazk (via GitHub)" <gi...@apache.org> on 2026/10/21 12:23:27 UTC, 1 replies.
- [I] Allow coerce_primitives in Json source [datafusion] - posted by "ion-elgreco (via GitHub)" <gi...@apache.org> on 2026/10/21 12:25:37 UTC, 0 replies.
- [PR] feat: add coerce_primitive in json [datafusion] - posted by "ion-elgreco (via GitHub)" <gi...@apache.org> on 2026/10/21 12:27:06 UTC, 0 replies.
- [PR] test: cover the memory accounting paths of the grouped aggregate streams that no test reaches [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/21 12:30:51 UTC, 9 replies.
- [PR] refactor: share the memory accounting of the grouped aggregate streams [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/21 12:32:06 UTC, 2 replies.
- [PR] chore: move datafusion-ffi integration tests into their own crate [datafusion] - posted by "jprochazk (via GitHub)" <gi...@apache.org> on 2026/10/21 12:44:46 UTC, 1 replies.
- [PR] refactor: register proto decoders with `T::register` instead of a free function [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/21 12:56:18 UTC, 3 replies.
- [I] Identify the plan node that owns each `MemoryConsumer` [datafusion] - posted by "adriangb (via GitHub)" <gi...@apache.org> on 2026/10/21 12:58:49 UTC, 0 replies.
- Re: [PR] refactor: drive `datafusion.runtime.*` config from a `ConfigField` schema [datafusion] - posted by "ByteBaker (via GitHub)" <gi...@apache.org> on 2026/10/21 13:13:50 UTC, 5 replies.
- Re: [I] chore: Explore combining `SessionConfig` and `RuntimeConfig` into same framework [datafusion] - posted by "ByteBaker (via GitHub)" <gi...@apache.org> on 2026/10/21 13:17:36 UTC, 0 replies.
- [PR] chore: Use `value_field` to fetch list element field [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/21 14:21:18 UTC, 1 replies.
- [PR] chore: Move more CI jobs to run on `ubuntu-slim` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/21 15:49:40 UTC, 2 replies.
- [I] Run SortAggregateExec as a native hash aggregate without its input sort [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/21 16:31:48 UTC, 1 replies.
- Re: [I] Null-aware anti join keeps rows whose dictionary build key points at a NULL value [datafusion] - posted by "abp002 (via GitHub)" <gi...@apache.org> on 2026/10/21 16:38:02 UTC, 1 replies.
- [I] Regression: `ORDER BY col, (scalar subquery) LIMIT` over a `RIGHT JOIN` fails in `SanityCheckPlan` [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/21 16:38:24 UTC, 0 replies.
- [I] `= ANY (subquery)` in a `JOIN ... ON` over an aliased table fails: "No field named x.a" [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/21 16:43:30 UTC, 4 replies.
- [PR] chore: run the circular dependency check on the fork for fork PRs [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/21 16:46:26 UTC, 3 replies.
- [PR] chore(deps): bump parquet from 59.3.0 to 59.3.1 [datafusion-iceberg] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/21 16:50:14 UTC, 0 replies.
- [PR] chore(deps): bump the all-other-cargo-deps group across 1 directory with 4 updates [datafusion-iceberg] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/21 16:51:02 UTC, 0 replies.
- [I] Partial aggregate over fully sorted input fails with ResourcesExhausted instead of emitting completed groups [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/21 17:10:19 UTC, 1 replies.
- [PR] fix: emit completed groups when a fully sorted partial aggregate runs out of memory [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/21 17:45:35 UTC, 1 replies.
- [PR] chore: Skip `datafusion-sqllogictest` in semver check [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/21 17:49:46 UTC, 3 replies.
- [PR] fix: drop build rows with a dictionary NULL key in null-aware anti joins [datafusion] - posted by "abp002 (via GitHub)" <gi...@apache.org> on 2026/10/21 17:57:47 UTC, 2 replies.
- [I] Native filters and non-collect limits can evaluate ANSI casts on rows Spark skips [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/21 18:45:38 UTC, 2 replies.
- [PR] fix: coerce INT96 timestamps inside legacy-format lists in the native Parquet scan [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/21 18:47:26 UTC, 2 replies.
- [PR] test: cover positional struct reconciliation in native CASE WHEN and COALESCE [datafusion-comet] - posted by "kazuyukitanimura (via GitHub)" <gi...@apache.org> on 2026/10/21 18:52:10 UTC, 4 replies.
- [PR] build(deps): bump webpki-root-certs and rustls-webpki to drop compromised emSign root [datafusion-ballista] - posted by "avantgardnerio (via GitHub)" <gi...@apache.org> on 2026/10/21 19:27:34 UTC, 9 replies.
- [PR] fix(parquet): decode binary dictionaries as strings [datafusion] - posted by "Rich-T-kid (via GitHub)" <gi...@apache.org> on 2026/10/21 19:50:41 UTC, 10 replies.
- [I] Support opt-in uppercase folding of unquoted SQL identifiers [datafusion] - posted by "osipovartem (via GitHub)" <gi...@apache.org> on 2026/10/21 20:13:04 UTC, 0 replies.
- [PR] MsSql: Preserve ALTER ROLE ... WITH NAME = on display [datafusion-sqlparser-rs] - posted by "princejain756 (via GitHub)" <gi...@apache.org> on 2026/10/21 20:23:24 UTC, 0 replies.
- [PR] feat(python): Improve ballista session config [datafusion-ballista] - posted by "milenkovicm (via GitHub)" <gi...@apache.org> on 2026/10/21 20:34:55 UTC, 0 replies.
- Re: [PR] Clickhouse: Clickhouse assume table constraint [datafusion-sqlparser-rs] - posted by "pelovett (via GitHub)" <gi...@apache.org> on 2026/10/21 20:52:57 UTC, 0 replies.
- [I] `CASE WHEN` copies a whole struct column on every branch when a branch reads one of its fields [datafusion] - posted by "mzabaluev (via GitHub)" <gi...@apache.org> on 2026/10/21 22:21:37 UTC, 0 replies.
- [I] Run the MinIO-backed S3 suites in CI, starting with ParquetWriteWithMagicCommitterSuite [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/21 22:48:02 UTC, 0 replies.
- [PR] feat(iceberg): scan Iceberg tables in Ballista [datafusion-ballista] - posted by "NoahKusaba (via GitHub)" <gi...@apache.org> on 2026/10/21 23:08:36 UTC, 0 replies.
- [PR] docs: add a terminology style guide for contributor docs [datafusion-comet] - posted by "Abhishek-Mohan (via GitHub)" <gi...@apache.org> on 2026/10/22 00:14:27 UTC, 0 replies.
- [PR] docs: adopt issue #4419 terminology in remaining contributor docs [datafusion-comet] - posted by "Abhishek-Mohan (via GitHub)" <gi...@apache.org> on 2026/10/22 00:14:30 UTC, 0 replies.
- [PR] docs: add a docs-review skill [datafusion-comet] - posted by "Abhishek-Mohan (via GitHub)" <gi...@apache.org> on 2026/10/22 00:14:35 UTC, 1 replies.
- [PR] Deduplicate ASCII and char paths in levenshtein_distance_with_threshold [datafusion-comet] - posted by "EyobelG (via GitHub)" <gi...@apache.org> on 2026/10/22 00:34:33 UTC, 0 replies.
- [PR] chore: check for circular dependencies with a publish dry run [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/22 00:46:41 UTC, 0 replies.
- [PR] perf: create DiskManager Directories-mode working dirs lazily [datafusion] - posted by "raghavyadav01 (via GitHub)" <gi...@apache.org> on 2026/10/22 01:30:05 UTC, 2 replies.
- Re: [PR] Cache reusable Parquet pruning setup across files with the same schema [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/22 01:43:57 UTC, 1 replies.
- [PR] feat: support native AssertNotNull for DataSource V2 writes [datafusion-comet] - posted by "LinSimon-901101 (via GitHub)" <gi...@apache.org> on 2026/10/22 03:07:52 UTC, 6 replies.
- Re: [PR] chore: check for circular dependencies with `cargo publish` [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/22 03:19:44 UTC, 3 replies.
- Re: [PR] chore: migrate HawkEye to v7 [datafusion-sandbox] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/22 04:01:15 UTC, 0 replies.
- [PR] fix: keep sort below OFFSET when the sort columns are projected away [datafusion] - posted by "yashaggarwal85d (via GitHub)" <gi...@apache.org> on 2026/10/22 04:08:15 UTC, 1 replies.
- [PR] DRAFT Bench 25811 [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/22 04:30:34 UTC, 3 replies.
- Re: [I] DataFrame API: allow aggregate functions in `select()` [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/22 04:55:24 UTC, 0 replies.
- [PR] chore(deps): bump lru from 0.18.5 to 0.19.0 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/22 05:20:38 UTC, 1 replies.
- [PR] chore(deps): bump rstest from 0.27.0 to 0.28.0 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/22 05:21:00 UTC, 1 replies.
- [PR] fix: keep Iceberg residual pushdown within Spark semantics [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/22 05:52:00 UTC, 0 replies.
- Re: [I] Multi-key null-aware join silently defaults to one NOT IN value key [datafusion] - posted by "siddubakka (via GitHub)" <gi...@apache.org> on 2026/10/22 07:46:25 UTC, 0 replies.
- Re: [PR] feat: add opt-in readable column labels for SQL results [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/22 07:57:36 UTC, 0 replies.
- [PR] refactor: limit the package root to the common entry points- #1771 [datafusion-python] - posted by "Awesome06 (via GitHub)" <gi...@apache.org> on 2026/10/22 08:20:34 UTC, 0 replies.
- [PR] fix: reject null-aware `LeftAnti` hash join in `Partitioned` mode [datafusion] - posted by "cool9850311 (via GitHub)" <gi...@apache.org> on 2026/10/22 08:21:21 UTC, 2 replies.
- [PR] perf: try bucket sort [datafusion] - posted by "rluvaton (via GitHub)" <gi...@apache.org> on 2026/10/22 10:10:17 UTC, 20 replies.
- Re: [I] Test our microbenchmarks as part of CI [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/22 10:46:38 UTC, 0 replies.
- [PR] Refactoring: Move DCL parsing into `src/parser/dcl.rs` [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/22 10:51:21 UTC, 3 replies.
- Re: [I] ClickHouse: tuple element access followed by a field changes meaning after round-trip [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/22 10:58:45 UTC, 2 replies.
- Re: [I] Enable Bloom-filter pruning for joins on multiple columns [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/22 11:32:14 UTC, 0 replies.
- [PR] fix(parquet): coerce INT96 inside legacy Parquet list layouts [datafusion] - posted by "DsThakurRawat (via GitHub)" <gi...@apache.org> on 2026/10/22 11:41:08 UTC, 0 replies.
- [PR] CI: Use a Python release available on Ubuntu 26.04 for RAT [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/22 11:53:25 UTC, 3 replies.
- Re: [I] [DISCUSSION] Rethinking Code Review and Testing in the Agent Era [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/22 12:00:03 UTC, 2 replies.
- Re: [PR] feat: plan Iceberg file tasks before execution [datafusion-iceberg] - posted by "gabotechs (via GitHub)" <gi...@apache.org> on 2026/10/22 12:28:21 UTC, 0 replies.
- Re: [PR] test: run the libhdfs suite in CI again now that the thread-destructor fix is released [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/22 12:36:28 UTC, 0 replies.
- [PR] perf: Precompute simple column-derived expressions for `ProjectedCaseBody` [datafusion] - posted by "mzabaluev (via GitHub)" <gi...@apache.org> on 2026/10/22 13:09:00 UTC, 0 replies.
- Re: [PR] fix: use null counts to estimate IS NULL and IS NOT NULL [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/22 13:40:50 UTC, 9 replies.
- [I] Support multiple output partitions for lazy file discovery [datafusion-iceberg] - posted by "alexanderbianchi (via GitHub)" <gi...@apache.org> on 2026/10/22 13:53:35 UTC, 0 replies.
- [PR] fix: restore all-features Clippy for DataFrame aggregate rewrites [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/22 13:59:59 UTC, 3 replies.
- [PR] ci: check all features with Clippy [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/22 14:22:32 UTC, 4 replies.
- [PR] feat: support partitioned execution for ASOF joins [datafusion] - posted by "Kristofferjoha (via GitHub)" <gi...@apache.org> on 2026/10/22 14:58:48 UTC, 2 replies.
- [PR] chore: skip slow test under `force_hash_collisions` [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/22 16:24:30 UTC, 1 replies.
- Re: [I] `min` / `max` over a list of lists (or of structs) fails with "Internal error: Uncomparable values" [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/22 16:42:46 UTC, 0 replies.
- [I] Release DataFusion Iceberg `0.12.0` (??? 2026) [datafusion-iceberg] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/22 16:51:08 UTC, 1 replies.
- [PR] feat: read Iceberg tables on HDFS natively through iceberg-rust's hdfs-native backend [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/22 17:09:37 UTC, 0 replies.
- Re: [PR] feat(iceberg): support HDFS storage via iceberg-rust hdfs-native backend [NOT FOR MERGE: pending apache/iceberg-rust#3111] [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/22 17:09:58 UTC, 1 replies.
- [PR] Centralize float canonicalization [datafusion] - posted by "mkleen (via GitHub)" <gi...@apache.org> on 2026/10/22 17:11:35 UTC, 0 replies.
- [PR] fix: keep filters with subqueries correlated on an alias above the SubqueryAlias [datafusion] - posted by "abp002 (via GitHub)" <gi...@apache.org> on 2026/10/22 17:25:49 UTC, 3 replies.
- [I] docs: add DataFrame aggregation example (select vs aggregate) [datafusion] - posted by "cj-zhukov (via GitHub)" <gi...@apache.org> on 2026/10/22 17:59:36 UTC, 1 replies.
- [PR] chore: speedup semver check using shared target directory [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/22 18:02:21 UTC, 1 replies.
- [PR] perf: faster character boundary scan for non-ASCII left and right [datafusion] - posted by "mightsleep (via GitHub)" <gi...@apache.org> on 2026/10/22 18:16:01 UTC, 3 replies.
- [PR] add DataFrame aggregation example (#26597) [datafusion] - posted by "cj-zhukov (via GitHub)" <gi...@apache.org> on 2026/10/22 18:18:36 UTC, 0 replies.
- [PR] bench: add float canonicalization benchmark [datafusion] - posted by "mkleen (via GitHub)" <gi...@apache.org> on 2026/10/22 18:23:01 UTC, 1 replies.
- [I] Improve Substrait JOIN and UNION planning for async table providers [datafusion] - posted by "alexanderbianchi (via GitHub)" <gi...@apache.org> on 2026/10/22 18:27:09 UTC, 0 replies.
- [PR] feat(substrait): consume independent JOIN and UNION inputs concurrently [datafusion] - posted by "alexanderbianchi (via GitHub)" <gi...@apache.org> on 2026/10/22 18:27:56 UTC, 0 replies.
- [PR] chore: use shallow checkout for semver check [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/22 19:10:27 UTC, 2 replies.
- Re: [I] Release DataFusion `56.0.0` (Oct/Nov 2026) [datafusion] - posted by "jayshrivastava (via GitHub)" <gi...@apache.org> on 2026/10/22 19:37:23 UTC, 1 replies.
- [I] date_bin should error when the computed timestamp bin is out of range [datafusion] - posted by "benbellick (via GitHub)" <gi...@apache.org> on 2026/10/22 19:40:01 UTC, 2 replies.
- Re: [PR] fix: rebase lambda params after projection schema changes [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/22 19:58:39 UTC, 0 replies.
- Re: [PR] feat: push immutable scalar functions into CASE branches with literal outputs [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/22 19:59:29 UTC, 0 replies.
- [I] Joins with string view columns can become extremely slow [datafusion] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/22 20:06:28 UTC, 0 replies.
- Re: [PR] refactor: Centralize float canonicalization [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/22 20:25:55 UTC, 0 replies.
- [PR] fix(datetime): error on out-of-range date_bin timestamp bins [datafusion] - posted by "benbellick (via GitHub)" <gi...@apache.org> on 2026/10/22 21:13:46 UTC, 4 replies.
- [PR] fix: apply a pulled up HAVING in scalar subqueries whose aggregate is NULL for empty input [datafusion] - posted by "abp002 (via GitHub)" <gi...@apache.org> on 2026/10/22 21:25:28 UTC, 0 replies.
- [I] Native Parquet scan: casts the planner inserts into pushed-down filters are rejected as Parquet type promotions (Spark 3.x, row-level filter pushdown) [datafusion-comet] - posted by "snmvaughan (via GitHub)" <gi...@apache.org> on 2026/10/22 21:54:41 UTC, 0 replies.
- [PR] fix: don't treat planner-inserted casts as Parquet schema conversions [datafusion-comet] - posted by "snmvaughan (via GitHub)" <gi...@apache.org> on 2026/10/22 21:54:58 UTC, 4 replies.
- [PR] perf: look up few CASE literals by linear comparison [datafusion] - posted by "mzabaluev (via GitHub)" <gi...@apache.org> on 2026/10/22 22:12:06 UTC, 0 replies.
- [PR] chore(deps-dev): bump webpack-dev-server from 6.0.0 to 6.1.0 in /datafusion/wasmtest/datafusion-wasm-app in the all-npm-deps group [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/22 22:16:35 UTC, 1 replies.
- [PR] chore(deps): bump setuptools from 84.0.0 to 84.2.0 in the all-uv-deps group [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/22 22:17:37 UTC, 1 replies.
- [PR] chore(deps): bump the all-other-cargo-deps group with 2 updates [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/22 22:26:27 UTC, 1 replies.
- [PR] chore(deps): bump rstest from 0.27.0 to 0.28.0 [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/22 22:26:53 UTC, 1 replies.
- [PR] perf: defer CASE columns not read by WHEN expressions [datafusion] - posted by "mzabaluev (via GitHub)" <gi...@apache.org> on 2026/10/22 23:23:19 UTC, 0 replies.
- Re: [I] Decorrelate a window function below a correlated equality filter by extending `PARTITION BY` [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/22 23:29:38 UTC, 0 replies.
- [I] Wrong result: `count(*) OVER ()` sees only the LIMIT rows when ORDER BY ... LIMIT sits on top of another window (target_partitions > 1) [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 00:14:59 UTC, 2 replies.
- [I] Wrong results: `ORDER BY , ... LIMIT n` drops `-0.0` rows when 0.0 arrives in an earlier batch (TopK dynamic filter) [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 00:19:27 UTC, 0 replies.
- [I] `push_down_filter` substitutes the wrong expression when `col` and `CAST(col AS ...)` share a schema name (HAVING and correlated IN give type errors) [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 00:31:00 UTC, 0 replies.
- Re: [PR] fix: reverse ordering and range in NegativeExpr::get_properties [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/23 00:37:03 UTC, 1 replies.
- [I] Panic "all window expressions shall have the same sort keys" when two window functions share `ORDER BY a + 1` (debug builds) [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 00:43:18 UTC, 1 replies.
- [I] `GROUP BY CAST(a AS VARCHAR), a` with a common subexpression fails in `optimize_projections` ("No field named t.a", sometimes a panic) [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 00:47:36 UTC, 1 replies.
- [I] `x > ALL (subquery)` in the SELECT list fails with an internal schema error unless it is aliased [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 00:52:14 UTC, 2 replies.
- [I] SanityCheckPlan error with sort-merge join when a filter says `a + b = a` [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 00:55:19 UTC, 0 replies.
- [I] SanityCheckPlan error with sort-merge join when a filter makes a sort or join key constant (constant lost in `EquivalenceGroup` projection) [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 00:59:24 UTC, 0 replies.
- [I] SanityCheckPlan error for `UNION ALL ... ORDER BY` when each arm selects the same column twice [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 01:02:20 UTC, 1 replies.
- [I] SanityCheckPlan error for two window functions with `target_partitions = 1` (`WindowAggExec` loses `can_repartition` when its children are replaced) [datafusion] - posted by "alpaylan (via GitHub)" <gi...@apache.org> on 2026/10/23 01:07:27 UTC, 0 replies.
- [I] Spill files are mostly `Utf8` offsets, which zstd and lz4 barely compress [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/23 01:09:43 UTC, 0 replies.
- [I] Final and Single aggregates over fully sorted input fail with ResourcesExhausted instead of emitting completed groups [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/23 01:30:45 UTC, 1 replies.
- Re: [PR] docs(dataframe): add dataframe aggregation example (#26597) [datafusion] - posted by "neilconway (via GitHub)" <gi...@apache.org> on 2026/10/23 01:43:16 UTC, 2 replies.
- [I] decorrelate_predicate_subquery removes inner LIMIT inside EXISTS even when a HAVING or WHERE above it depends on the row count [datafusion] - posted by "wjjc1017 (via GitHub)" <gi...@apache.org> on 2026/10/23 01:55:44 UTC, 0 replies.
- [PR] perf: index DFSchema field names to avoid quadratic lookups on wide schemas [datafusion] - posted by "cetra3 (via GitHub)" <gi...@apache.org> on 2026/10/23 02:21:20 UTC, 5 replies.
- [PR] refactor: derive cross join equivalence properties as an inner join [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 03:55:09 UTC, 2 replies.
- [I] Nested loop join filter pushdown evaluates CASE branches, OR/AND operands and coalesce arguments on every row [datafusion] - posted by "morristai (via GitHub)" <gi...@apache.org> on 2026/10/23 04:23:33 UTC, 0 replies.
- [I] Allow downcasting `ParquetFileReaderFactory` like `FileSource` and `DataSource` [datafusion] - posted by "morristai (via GitHub)" <gi...@apache.org> on 2026/10/23 04:27:10 UTC, 0 replies.
- [PR] fix: keep conditionally evaluated parts of nested loop join filters in the filter [datafusion] - posted by "morristai (via GitHub)" <gi...@apache.org> on 2026/10/23 04:31:10 UTC, 0 replies.
- [PR] feat: allow downcasting `ParquetFileReaderFactory` [datafusion] - posted by "morristai (via GitHub)" <gi...@apache.org> on 2026/10/23 04:31:12 UTC, 1 replies.
- [PR] fix: preserve equivalence classes in union output properties [datafusion] - posted by "princejain756 (via GitHub)" <gi...@apache.org> on 2026/10/23 04:34:45 UTC, 0 replies.
- [PR] fix: emit completed groups when fully sorted final and single aggrega… [datafusion] - posted by "yashaggarwal85d (via GitHub)" <gi...@apache.org> on 2026/10/23 04:43:51 UTC, 9 replies.
- [PR] fix: preserve expression names in RewriteSetComparison [datafusion] - posted by "yashaggarwal85d (via GitHub)" <gi...@apache.org> on 2026/10/23 04:49:45 UTC, 1 replies.
- Re: [PR] fix: make csv-read-options.py example self-contained (#1728) [datafusion-python] - posted by "dedsec-terminal (via GitHub)" <gi...@apache.org> on 2026/10/23 05:07:00 UTC, 0 replies.
- [PR] chore(ci): bump swatinem/rust-cache from 2.9.2 to 2.9.3 [datafusion-ballista] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/23 05:31:35 UTC, 1 replies.
- [I] Discuss unifying NVL and IFNULL coercion with COALESCE [datafusion] - posted by "1fanwang (via GitHub)" <gi...@apache.org> on 2026/10/23 05:41:46 UTC, 0 replies.
- [PR] fix: keep a LIMIT inside EXISTS that an operator above it can empty [datafusion] - posted by "raghavyadav01 (via GitHub)" <gi...@apache.org> on 2026/10/23 05:56:43 UTC, 0 replies.
- [I] Hash join dynamic filters don't prune inside recursive CTEs [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 06:24:29 UTC, 3 replies.
- [I] TopK dynamic filters don't prune inside recursive CTEs [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 06:24:34 UTC, 1 replies.
- Re: [I] Conslidate benchmark runner documentation [datafusion] - posted by "yiaany (via GitHub)" <gi...@apache.org> on 2026/10/23 06:56:42 UTC, 0 replies.
- [PR] refactor: one rule for the equivalence properties of a merge of partitions [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 07:07:16 UTC, 1 replies.
- Re: [PR] test: add planner tests for ordering, constant and equality facts [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 07:09:22 UTC, 1 replies.
- [PR] test: compute the nested loop join reference once per join fuzz case [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 07:17:31 UTC, 0 replies.
- [I] `Cannot execute pipeline breaking queries` error prints the whole operator struct [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 07:21:34 UTC, 0 replies.
- [I] Wrong results: `SortPreservingMergeExec` keeps orderings of its input that do not hold after the merge [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 07:32:40 UTC, 2 replies.
- [PR] docs: replace "DataFusion native engine" on the docs landing page [datafusion-comet] - posted by "Abhishek-Mohan (via GitHub)" <gi...@apache.org> on 2026/10/23 07:36:20 UTC, 2 replies.
- [PR] docs: adopt the #4419 terminology in the native shuffle guide [datafusion-comet] - posted by "Abhishek-Mohan (via GitHub)" <gi...@apache.org> on 2026/10/23 07:36:22 UTC, 2 replies.
- [PR] docs: adopt the #4419 terminology in the JVM shuffle guide [datafusion-comet] - posted by "Abhishek-Mohan (via GitHub)" <gi...@apache.org> on 2026/10/23 07:36:25 UTC, 2 replies.
- [PR] docs: adopt the #4419 terminology in the Gluten comparison [datafusion-comet] - posted by "Abhishek-Mohan (via GitHub)" <gi...@apache.org> on 2026/10/23 07:36:28 UTC, 2 replies.
- [PR] docs: finish the #4419 terminology in Understanding Comet Plans [datafusion-comet] - posted by "Abhishek-Mohan (via GitHub)" <gi...@apache.org> on 2026/10/23 07:36:32 UTC, 2 replies.
- [PR] refactor: move the NOT IN marking helpers into hash_join/not_in.rs [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 07:52:30 UTC, 0 replies.
- [I] sum() over DECIMAL silently wraps on overflow instead of erroring [datafusion] - posted by "Shahzeb-DataEngineer (via GitHub)" <gi...@apache.org> on 2026/10/23 08:04:52 UTC, 2 replies.
- [PR] ci: stop re-running the workspace test suite in the extended tests job [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 08:09:03 UTC, 4 replies.
- [PR] fix: print DisplayAs form in pipeline-breaking SanityCheckPlan errors [datafusion] - posted by "ninglinLiu (via GitHub)" <gi...@apache.org> on 2026/10/23 08:10:40 UTC, 0 replies.
- Re: [PR] refactor: Centralize float semantics [datafusion] - posted by "mkleen (via GitHub)" <gi...@apache.org> on 2026/10/23 08:11:59 UTC, 0 replies.
- [I] Minimum-value integer literal with postfix cast fails: SELECT -2147483648::INT errors in the optimizer [datafusion] - posted by "Shahzeb-DataEngineer (via GitHub)" <gi...@apache.org> on 2026/10/23 08:17:38 UTC, 0 replies.
- Re: [PR] docs: update the plugin overview for current scans and #4419 terminology [datafusion-comet] - posted by "Abhishek-Mohan (via GitHub)" <gi...@apache.org> on 2026/10/23 08:25:27 UTC, 1 replies.
- [PR] fix: error on overflow in sum() over DECIMAL instead of silently wrapping [datafusion] - posted by "Shahzeb-DataEngineer (via GitHub)" <gi...@apache.org> on 2026/10/23 08:34:35 UTC, 0 replies.
- [PR] fix: fold unary minus into a number literal before a postfix cast [datafusion] - posted by "Shahzeb-DataEngineer (via GitHub)" <gi...@apache.org> on 2026/10/23 08:34:46 UTC, 0 replies.
- Re: [PR] refactor: Centralize float normalization [datafusion] - posted by "mkleen (via GitHub)" <gi...@apache.org> on 2026/10/23 08:54:13 UTC, 18 replies.
- [PR] fix: SortPreservingMergeExec drops input orderings when merging partitions [datafusion] - posted by "HarshilMital (via GitHub)" <gi...@apache.org> on 2026/10/23 09:03:29 UTC, 1 replies.
- Re: [I] Estimate Decimal filter selectivity [datafusion] - posted by "kosiew (via GitHub)" <gi...@apache.org> on 2026/10/23 09:34:25 UTC, 0 replies.
- [PR] docs: list the \i and \pset commands in the CLI usage guide [datafusion] - posted by "rawsun007 (via GitHub)" <gi...@apache.org> on 2026/10/23 09:41:44 UTC, 0 replies.
- Re: [PR] fix: Correct ANY/ALL results for unaliased subqueries on the same table [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 09:50:14 UTC, 3 replies.
- Re: [I] Support scalar PySpark Arrow UDFs in Comet native execution via PyO3 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 09:55:25 UTC, 0 replies.
- Re: [I] Support Spark's `AtLeastNNonNulls` natively [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 10:41:31 UTC, 0 replies.
- [PR] chore: [branch-1.2] change version from 1.2.0-SNAPSHOT to 1.2.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 11:01:30 UTC, 1 replies.
- [PR] docs: list contrib/delta-spark/pom.xml in the release version bump [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 11:02:44 UTC, 0 replies.
- [PR] chore: start 1.3.0 development [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 11:04:59 UTC, 1 replies.
- [PR] docs: Add changelog for 1.2.0 [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 11:26:39 UTC, 0 replies.
- Re: [PR] feat: support non-foldable sha2 through codegen dispatch [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/23 11:30:36 UTC, 3 replies.
- [PR] chore: refresh the native dependencies with cargo update [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 11:34:10 UTC, 1 replies.
- [PR] Add Apache DataFusion Comet 1.2.0 release blog post (draft) [datafusion-site] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 11:35:45 UTC, 0 replies.
- Re: [I] Run replace natively by default when the search string is a non-empty literal [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/23 11:37:18 UTC, 0 replies.
- Re: [I] Sliding-window SUM(BIGINT) ignores ANSI and TRY overflow semantics [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 11:56:27 UTC, 0 replies.
- [I] Sort pushdown through a custom execution plan [datafusion] - posted by "geoffreyclaude (via GitHub)" <gi...@apache.org> on 2026/10/23 12:10:04 UTC, 0 replies.
- Re: [I] Track provenance of fallback reasons copied through shared expression nodes [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 12:14:43 UTC, 0 replies.
- [PR] fix: keep a projection's field names when decorrelating a predicate s… [datafusion] - posted by "SingletonYe (via GitHub)" <gi...@apache.org> on 2026/10/23 12:23:40 UTC, 1 replies.
- Re: [I] Failure-injection tests for native Iceberg writes [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/23 12:30:48 UTC, 0 replies.
- [I] `LimitPushPastWindows` panics with "attempt to add with overflow" for a large `ROWS ... FOLLOWING` bound [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 12:45:37 UTC, 0 replies.
- [I] `LimitPushPastWindows` only pushes a limit past the first window in a plan [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 12:45:51 UTC, 1 replies.
- Re: [I] [DISCUSSION] Making it easier to use DataFusion (lessons from GlareDB) [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 12:53:14 UTC, 1 replies.
- Re: [I] [EPIC] A collection of items to improve DataFuson stability (reduce effort required to upgrade) [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 12:54:08 UTC, 1 replies.
- [PR] refactor: one vocabulary for moving LIMIT through the physical plan [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 13:08:14 UTC, 1 replies.
- Re: [PR] docs: list contrib/delta-spark/pom.xml in the version bump and add a dependency refresh step [datafusion-comet] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/23 13:08:56 UTC, 1 replies.
- [I] Review "db olympics" results [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 13:13:21 UTC, 14 replies.
- [PR] fix: saturate window frame lookahead instead of overflowing on huge FOLLOWING bounds [datafusion] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/23 13:14:58 UTC, 0 replies.
- Re: [I] Codegen dispatcher writes a null map key as the key type's default value [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 13:32:00 UTC, 0 replies.
- Re: [PR] Remove information schema references from `sql` module [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/23 13:36:07 UTC, 0 replies.
- [I] sequence and string to decimal cast don't match Spark 4.0.5, 4.1.4 and 4.2.1 (SPARK-58821, SPARK-60118) [datafusion-comet] - posted by "snmvaughan (via GitHub)" <gi...@apache.org> on 2026/10/23 14:30:50 UTC, 0 replies.
- [PR] fix: match SPARK-58821 and SPARK-60118 in sequence and string to decimal cast [datafusion-comet] - posted by "snmvaughan (via GitHub)" <gi...@apache.org> on 2026/10/23 14:31:38 UTC, 2 replies.
- Re: [I] Wrong results: correlated `EXISTS`/`IN` subqueries over a groupless aggregate get the wrong outer rows [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 14:37:29 UTC, 0 replies.
- [PR] fix: support RunEndEncoded keys in piecewise merge join existence joins [datafusion] - posted by "pujitha24 (via GitHub)" <gi...@apache.org> on 2026/10/23 15:12:26 UTC, 0 replies.
- [PR] perf: memoize `LAST_VALUE` and `NTH_VALUE` with `IGNORE NULLS`, gather results with `take` [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/23 15:17:37 UTC, 0 replies.
- [I] Bloom aggregate merge panics on batched states and ignores sliced offsets [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/23 15:26:33 UTC, 0 replies.
- [PR] fix: merge all Bloom filter states and respect sliced offsets [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/23 15:27:23 UTC, 3 replies.
- [I] [Substrait] Substrait consumer honours function declared output types [datafusion] - posted by "dd-annarose (via GitHub)" <gi...@apache.org> on 2026/10/23 15:35:45 UTC, 1 replies.
- [PR] Fix security advisory [datafusion] - posted by "AdamGS (via GitHub)" <gi...@apache.org> on 2026/10/23 15:36:56 UTC, 0 replies.
- Re: [PR] fix: fall back to Spark for a TRY cast of a map key that can fail [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/23 15:51:17 UTC, 2 replies.
- Re: [PR] Support partitioning of information schema content per catalog [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 15:53:15 UTC, 9 replies.
- [I] Nested Parquet pruning reads every leaf through FixedSizeList, ListView and Dictionary wrappers [datafusion] - posted by "ranflarion (via GitHub)" <gi...@apache.org> on 2026/10/23 15:55:38 UTC, 0 replies.
- [PR] fix: apply nested Parquet leaf pruning through FixedSizeList, ListView and Dictionary [datafusion] - posted by "ranflarion (via GitHub)" <gi...@apache.org> on 2026/10/23 15:55:53 UTC, 0 replies.
- [PR] fix: preserve hash join dynamic filters across recursive CTE iterations [datafusion] - posted by "Kristofferjoha (via GitHub)" <gi...@apache.org> on 2026/10/23 16:25:23 UTC, 4 replies.
- [PR] Fix/topk recursive 26642 [datafusion] - posted by "Kristofferjoha (via GitHub)" <gi...@apache.org> on 2026/10/23 16:26:44 UTC, 0 replies.
- Re: [I] When performing set comparison subqueries (such as > ANY / > ALL / = ANY, etc.) on the same table (without using aliases), silently returns wrong results (0 rows or all rows). [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/23 16:29:51 UTC, 0 replies.
- [I] Concurrent unified pool try_grow calls can both ask Spark for the same overcommit [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/23 16:48:20 UTC, 0 replies.
- [I] A short grant stays with Spark when handing it back fails, but the pool records nothing [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/23 16:49:41 UTC, 0 replies.
- [I] CometTaskMemoryManager.releaseMemory lowers used before Spark accepts the release [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/23 16:51:10 UTC, 0 replies.
- [PR] refactor(scheduler): split SelectJoinRule::optimize into per-action methods [datafusion-ballista] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/23 17:06:19 UTC, 0 replies.
- Re: [PR] refactor: keep the hash join NOT IN rules in one module [datafusion] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 17:10:08 UTC, 13 replies.
- [I] Comparing a `Duration` to an `Interval` with a days field returns wrong results (e.g. `ts - ts <= INTERVAL '3 days'`) [datafusion] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/23 17:14:56 UTC, 0 replies.
- [I] Surface native scalar Arrow UDF errors as Spark's `PythonException` [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 17:19:41 UTC, 1 replies.
- [I] Keep native Arrow UDFs on Spark's path when the embedded Python version differs [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 17:19:44 UTC, 1 replies.
- [PR] feat: keep native Arrow UDFs on Spark's path when the embedded Python version differs [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 17:21:48 UTC, 2 replies.
- [I] [EPIC] A Collection of Wrong Results Bugs - Q4 2026 [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 17:25:56 UTC, 4 replies.
- Re: [I] `UnwrapCastInComparison` produces incorrect results [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 17:33:48 UTC, 1 replies.
- [PR] perf: overlap the deletion vector and footer reads in Delta scan preparation [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/23 17:36:58 UTC, 0 replies.
- [I] `EXTRACT EPOCH` inconsistently extracts fractional seconds [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 17:44:27 UTC, 6 replies.
- [PR] fix: saturate LimitPushPastWindows and ROWS frame bounds for huge FOLLOWING [datafusion] - posted by "ninglinLiu (via GitHub)" <gi...@apache.org> on 2026/10/23 17:49:30 UTC, 0 replies.
- Re: [I] Support `date_bin` on timestamps with timezone, properly accounting for Daylight Savings Time [datafusion] - posted by "Omega359 (via GitHub)" <gi...@apache.org> on 2026/10/23 18:24:53 UTC, 0 replies.
- [PR] feat: interrupt a native scalar Arrow UDF when its task is killed [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 18:26:04 UTC, 3 replies.
- [PR] fix: preserve can_repartition in WindowAggExec::replace_children (#26626) [datafusion] - posted by "XiaoMingFa (via GitHub)" <gi...@apache.org> on 2026/10/23 18:28:43 UTC, 0 replies.
- [PR] fix: keep fractional seconds in EXTRACT(EPOCH) for Duration [datafusion] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/23 18:36:55 UTC, 16 replies.
- [PR] feat: Surface native scalar Arrow UDF errors as Spark's PythonException [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 18:49:29 UTC, 2 replies.
- Re: [I] Make fair_unified account for spillable consumers [datafusion-comet] - posted by "andygrove (via GitHub)" <gi...@apache.org> on 2026/10/23 18:59:36 UTC, 0 replies.
- [PR] reject correlated IN/NOT IN over a groupless aggregate [datafusion] - posted by "mohammadnaqvi04 (via GitHub)" <gi...@apache.org> on 2026/10/23 18:59:46 UTC, 0 replies.
- Re: [I] [Epic] High cardinality aggregation performance wishlist [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 19:02:19 UTC, 1 replies.
- [PR] refactor(scheduler): split QueryStageScheduler::on_receive into per-event handlers [datafusion-ballista] - posted by "ump45nose (via GitHub)" <gi...@apache.org> on 2026/10/23 19:04:20 UTC, 0 replies.
- Re: [PR] ci: halve extended test fuzz time by computing the join fuzz reference once [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 19:18:27 UTC, 1 replies.
- [I] `EXTRACT(NANOSECOND)` on `Duration` and `Interval` counts whole seconds twice [datafusion] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/23 19:19:36 UTC, 0 replies.
- Re: [I] date_part returning wrong results due to overflows [datafusion] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/23 19:20:12 UTC, 0 replies.
- [PR] feat(substrait): add a hook for consuming relation inputs [datafusion] - posted by "alexanderbianchi (via GitHub)" <gi...@apache.org> on 2026/10/23 19:24:34 UTC, 1 replies.
- [PR] feat(substrait): consume default JOIN and UNION inputs concurrently [datafusion] - posted by "alexanderbianchi (via GitHub)" <gi...@apache.org> on 2026/10/23 19:36:52 UTC, 0 replies.
- Re: [PR] Fix new security advisory: RUSTSEC-2026-0385 [datafusion] - posted by "AdamGS (via GitHub)" <gi...@apache.org> on 2026/10/23 19:38:21 UTC, 0 replies.
- Re: [PR] feat(iceberg): native Iceberg scans of HDFS-backed tables via iceberg-rust's hdfs-native backend [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/23 19:45:59 UTC, 1 replies.
- Re: [PR] fix: preserve narrowing TRY_CAST comparison semantics [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 19:53:46 UTC, 1 replies.
- Re: [PR] fix: reject correlated IN/NOT IN over a groupless aggregate [datafusion] - posted by "mohammadnaqvi04 (via GitHub)" <gi...@apache.org> on 2026/10/23 20:29:26 UTC, 3 replies.
- [PR] chore(csv): use shared aggr_test_schema in CSV scan tests [datafusion] - posted by "ninglinLiu (via GitHub)" <gi...@apache.org> on 2026/10/23 20:44:48 UTC, 1 replies.
- [I] Malformed JNI arguments panic instead of returning an error [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 20:53:08 UTC, 1 replies.
- [I] Raise native UDF validation failures as typed exceptions instead of matching message text [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 20:53:51 UTC, 1 replies.
- [PR] refactor: raise native UDF validation failures as typed exceptions [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 20:53:59 UTC, 2 replies.
- [PR] fix: return errors instead of panicking on malformed JNI arguments [datafusion-comet] - posted by "viirya (via GitHub)" <gi...@apache.org> on 2026/10/23 20:55:29 UTC, 2 replies.
- [I] [EPIC] Improve I/O patterns for Parquet scans [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 21:07:14 UTC, 1 replies.
- [PR] ci: migrate pull_request_target workflows to workflow_run [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/23 21:14:34 UTC, 7 replies.
- [I] [DISCUSSION] 2026 Q4 Roadmap [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 21:15:51 UTC, 8 replies.
- Re: [I] [EPIC] Decouple logical from physical types [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 21:19:13 UTC, 0 replies.
- Re: [I] [DISCUSSION] 2026 Q3-Q4 Roadmap Discussion [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 21:20:34 UTC, 1 replies.
- Re: [PR] Prefetch Parquet row groups with a bounded I/O budget [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/23 21:21:32 UTC, 0 replies.
- [I] `date_part` declares a non-nullable result for non-null input, but can return NULL [datafusion] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/23 21:27:08 UTC, 0 replies.
- [PR] fix: date_part sub-second parts and result nullability, reusing arrow kernels [datafusion] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/23 21:32:49 UTC, 34 replies.
- [I] Native string to negative-scale decimal cast doesn't match Spark 4.0.5, 4.1.4 and 4.2.1 (SPARK-60119) [datafusion-comet] - posted by "snmvaughan (via GitHub)" <gi...@apache.org> on 2026/10/23 21:37:19 UTC, 0 replies.
- [I] Spill files are validated again on read since 55.0.0 [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/23 21:39:56 UTC, 1 replies.
- [PR] fix: skip validating spilled record batches again [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/23 21:40:24 UTC, 1 replies.
- [I] Native string to decimal cast raises the wrong error under ANSI for values with more than 38 integral digits [datafusion-comet] - posted by "snmvaughan (via GitHub)" <gi...@apache.org> on 2026/10/23 21:48:41 UTC, 0 replies.
- [I] GROUPS frames and bounded rank split peers with logically equal nested dictionary nulls [datafusion] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/23 23:25:15 UTC, 0 replies.
- [I] Reduce duplicate right-side keys before sorting a native left-semi join [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/24 00:26:29 UTC, 0 replies.
- [PR] perf: reduce duplicate right-side rows before sorting left-semi joins [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/24 00:34:05 UTC, 1 replies.
- Re: [PR] bench: improve Iceberg TPC workflow and plan capture [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/24 01:09:30 UTC, 0 replies.
- [PR] feat: run min and max over struct inputs natively [datafusion-comet] - posted by "parthchandra (via GitHub)" <gi...@apache.org> on 2026/10/24 01:19:47 UTC, 0 replies.
- [I] `ORDER BY ... LIMIT` over an `OFFSET` subquery returns too few rows when the table is sorted and has several files [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 01:36:47 UTC, 0 replies.
- [I] TopK aggregation keeps the wrong groups when a projection computes a new column with the aggregate's name [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 01:36:48 UTC, 1 replies.
- Re: [PR] Derive total_byte_size for join statistics [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/24 01:42:57 UTC, 0 replies.
- Re: [PR] perf: return Utf8View from Spark hex with inline short path [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/24 01:43:01 UTC, 0 replies.
- Re: [PR] Parallel bounded RANGE-frame window functions without PARTITION BY (draft) [datafusion] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/24 01:43:13 UTC, 0 replies.
- Re: [PR] chore(deps): bump postgres-protocol from 0.6.10 to 0.6.12 [datafusion-sandbox] - posted by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2026/10/24 01:44:35 UTC, 0 replies.
- [I] Wrong results: decorrelation loses correlated columns when a subquery contains two equal subplans [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 02:15:40 UTC, 0 replies.
- [PR] fix(optimizer): emit bare CSE columns inside window expressions [datafusion] - posted by "princejain756 (via GitHub)" <gi...@apache.org> on 2026/10/24 02:33:33 UTC, 0 replies.
- [PR] ci: gate extended test targets as a whole instead of filtering by name [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 02:43:18 UTC, 0 replies.
- [I] Wrong results: correlated `EXISTS` over a groupless aggregate ignores a predicate on outer columns only [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 02:55:24 UTC, 1 replies.
- [I] Hash aggregate output slices keep the whole dictionary, so downstream work grows with the group count [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 03:11:29 UTC, 2 replies.
- [I] [EPIC] Custom ExecutionPlan nodes: correct results, and the same optimizations as built-in nodes [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 03:46:39 UTC, 0 replies.
- Re: [I] Allow user defined ExecutionPlans to benefit from pushdown behavior [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 03:46:44 UTC, 2 replies.
- [I] Broadcast exchange fails with `OversizedAllocationException` when a string or binary column holds more than 1 GiB [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/24 04:00:20 UTC, 0 replies.
- [PR] perf: write offsets to compressed spill files as lengths [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/24 04:17:27 UTC, 2 replies.
- Re: [PR] perf: memoize `LAST_VALUE` and `NTH_VALUE` with `IGNORE NULLS` [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 04:18:07 UTC, 7 replies.
- [PR] fix(optimizer): propagate pulled-up correlated state along tree frames [datafusion] - posted by "princejain756 (via GitHub)" <gi...@apache.org> on 2026/10/24 04:36:52 UTC, 1 replies.
- [PR] fix: split a coalesced broadcast before a string or binary vector passes 1 GiB [datafusion-comet] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/24 04:47:02 UTC, 0 replies.
- [I] Run the sqllogictest corpus across a matrix of batch sizes [datafusion] - posted by "comphead (via GitHub)" <gi...@apache.org> on 2026/10/24 05:02:38 UTC, 7 replies.
- [I] Final hash aggregate fails with ResourcesExhausted when its materialized output is larger than its table [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 05:34:13 UTC, 0 replies.
- [PR] fix: keep the qualified column in the CSE projection when a CAST group key shares its name [datafusion] - posted by "Sriram-PR (via GitHub)" <gi...@apache.org> on 2026/10/24 06:32:44 UTC, 0 replies.
- [PR] perf: add grouped accumulators for regression aggregates [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/24 06:37:32 UTC, 0 replies.
- [PR] fix: cap projection input beneath local and global limits [datafusion-comet] - posted by "rich7420 (via GitHub)" <gi...@apache.org> on 2026/10/24 07:52:45 UTC, 0 replies.
- [PR] fix: resolve conflicting Parquet field claims consistently [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/24 08:12:10 UTC, 0 replies.
- Re: [I] Incorrect results for NOT IN subqueries with nulls [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/24 08:19:12 UTC, 1 replies.
- Re: [PR] feat: make the materialized CTE nodes a first-class LogicalPlan variant [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 08:29:55 UTC, 3 replies.
- [PR] perf: bound work over dictionary values by the batch's row count [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 08:39:31 UTC, 14 replies.
- Re: [PR] PostgreSQL: accept CREATE SEQUENCE options in any clause order [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/24 08:48:44 UTC, 1 replies.
- [I] Subqueries in an aggregate (GROUP BY key, aggregate argument or FILTER) fail with "Physical plan does not support logical expression" [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 09:30:38 UTC, 0 replies.
- [I] Partial aggregate state reaches the final aggregate without a memory reservation (median, array_agg) [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 09:58:56 UTC, 0 replies.
- Re: [I] Cannot cast `Large` Types to normal arrow types [datafusion] - posted by "ion-elgreco (via GitHub)" <gi...@apache.org> on 2026/10/24 09:59:18 UTC, 0 replies.
- Re: [PR] feat[functions]: use `placement` to pushdown `bit/octet/''_length` [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 10:04:24 UTC, 0 replies.
- Re: [I] Incorrect results: GROUP BY column dropped based on a nullable UNIQUE constraint [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 10:11:56 UTC, 0 replies.
- Re: [I] ForeignAggregateUDF does not forward distinct handling [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 10:13:25 UTC, 0 replies.
- Re: [I] Substrait: the grouping set column holds `__grouping_id`, not the set's index [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 10:40:26 UTC, 2 replies.
- Re: [PR] feat(optimizer): logical rewrite Filter(row_number() = 1) over PARTITION BY → Aggregate(FIRST_VALUE(... ORDER BY)) [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 10:44:40 UTC, 0 replies.
- [PR] PostgreSQL: parse `DROP GROUP` [datafusion-sqlparser-rs] - posted by "LucaCappelletti94 (via GitHub)" <gi...@apache.org> on 2026/10/24 10:54:24 UTC, 1 replies.
- [I] Support reusing the physical plan in prepared statements [datafusion] - posted by "nuno-faria (via GitHub)" <gi...@apache.org> on 2026/10/24 11:01:49 UTC, 0 replies.
- Re: [PR] docs: add a documentation style guide and apply it to the remaining pages [datafusion-comet] - posted by "sunchao (via GitHub)" <gi...@apache.org> on 2026/10/24 11:16:17 UTC, 0 replies.
- [I] WindowAggExec and BoundedWindowAggExec reserve no memory, so a memory limit does not bound them [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 11:55:25 UTC, 0 replies.
- [PR] chore(deps-dev): bump serialize-javascript from 7.0.5 to 7.1.4 in /datafusion/wasmtest/datafusion-wasm-app [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/24 11:59:19 UTC, 0 replies.
- [PR] chore(deps-dev): bump fast-uri from 3.1.7 to 3.1.9 in /datafusion/wasmtest/datafusion-wasm-app [datafusion] - posted by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/10/24 11:59:20 UTC, 0 replies.
- Re: [PR] fix: preserve TopK dynamic filters across recursive CTE iterations [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 12:02:24 UTC, 1 replies.
- [PR] Docs: Assert exact parser errors in some negative tests [datafusion-sqlparser-rs] - posted by "s5dsn-eqee (via GitHub)" <gi...@apache.org> on 2026/10/24 12:02:39 UTC, 4 replies.
- [I] Correlated scalar subqueries with `ORDER BY ... LIMIT 1` fail with "Physical plan does not support logical expression ScalarSubquery" [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 12:32:26 UTC, 2 replies.
- Re: [I] CSV null_regex is applied to schema inference but never to the reader, so matching values are not null [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 12:38:12 UTC, 0 replies.
- Re: [I] beautify default column names [datafusion] - posted by "haochunchang (via GitHub)" <gi...@apache.org> on 2026/10/24 12:45:07 UTC, 0 replies.
- [I] [EPIC] Simplify memory-limited (spilling) execution [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 12:46:01 UTC, 0 replies.
- [I] fair_unified: a sort fails on its first request when consumers that cannot spill hold the task's share [datafusion-comet] - posted by "dwsmith1983 (via GitHub)" <gi...@apache.org> on 2026/10/24 12:48:37 UTC, 0 replies.
- Re: [I] Join per-column stats not scaled with estimated row count [datafusion] - posted by "jayzhan211 (via GitHub)" <gi...@apache.org> on 2026/10/24 12:52:16 UTC, 1 replies.
- [PR] feat: support native Iceberg UUID writes [datafusion-comet] - posted by "sam-1112 (via GitHub)" <gi...@apache.org> on 2026/10/24 13:07:51 UTC, 0 replies.
- Re: [I] `date_part` returning wrong results due to overflows [datafusion] - posted by "mbutrovich (via GitHub)" <gi...@apache.org> on 2026/10/24 13:23:12 UTC, 0 replies.
- [PR] fix: preserve sort column identity in TopK aggregation [datafusion] - posted by "xgbtxy (via GitHub)" <gi...@apache.org> on 2026/10/24 13:44:09 UTC, 0 replies.
- Re: [I] [dbolympics] Subqueries in an aggregate (GROUP BY key, aggregate argument or FILTER) fail with "Physical plan does not support logical expression" [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:44:22 UTC, 0 replies.
- Re: [I] [dbolympics] Correlated scalar subqueries with `ORDER BY ... LIMIT 1` fail with "Physical plan does not support logical expression ScalarSubquery" [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:11 UTC, 0 replies.
- Re: [I] [dbolympics] Decorrelate scalar subqueries with more complex filter expressions [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:14 UTC, 0 replies.
- Re: [I] [dbolympics] General framework to decorrelate the subqueries [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:17 UTC, 0 replies.
- Re: [I] [dbolympics] Support correlated scalar subquery without aggregation [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:20 UTC, 0 replies.
- Re: [I] [dbolympics] Support Nested correlated subquery error with a depth exceeding 1 [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:23 UTC, 0 replies.
- Re: [I] [dbolympics] Grandparent column reference in nested subquery causes planner error [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:25 UTC, 0 replies.
- Re: [I] [dbolympics] Support multiply and divide on intervals [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:27 UTC, 0 replies.
- Re: [I] [dbolympics] SanityCheckPlan error when sorting by a function of a product above a projection with a computed column [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:29 UTC, 0 replies.
- Re: [I] [dbolympics] `sum` of a decimal returns a wider type than the plan schema declares when the query has a `DISTINCT` aggregate [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:33 UTC, 0 replies.
- Re: [PR] [dbolympics] fix: cast outer projection expr to declared field type in SingleDistinctToGroupBy [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:35 UTC, 0 replies.
- Re: [I] [dbolympics] Comparing a `Duration` to an `Interval` with a days field returns wrong results (e.g. `ts - ts <= INTERVAL '3 days'`) [datafusion] - posted by "alamb (via GitHub)" <gi...@apache.org> on 2026/10/24 13:45:39 UTC, 0 replies.
- [PR] bench: add a compressed high-partition writer case (#7080) [datafusion-comet] - posted by "HarshilMital (via GitHub)" <gi...@apache.org> on 2026/10/24 13:51:53 UTC, 0 replies.
- [PR] bench: add nested-column gather cases (#7080) [datafusion-comet] - posted by "HarshilMital (via GitHub)" <gi...@apache.org> on 2026/10/24 14:02:50 UTC, 0 replies.
- [PR] bench: add string, Map and nullable row-to-columnar cases (#7080) [datafusion-comet] - posted by "HarshilMital (via GitHub)" <gi...@apache.org> on 2026/10/24 14:10:48 UTC, 0 replies.
- [I] [Minor docs update] Known users list, Parseable description is outdated [datafusion] - posted by "yashdotrv (via GitHub)" <gi...@apache.org> on 2026/10/24 14:50:34 UTC, 0 replies.
- [PR] Update Parseable description in user guide [datafusion] - posted by "yashdotrv (via GitHub)" <gi...@apache.org> on 2026/10/24 14:55:48 UTC, 1 replies.
- [PR] ci: draft inactive PRs awaiting author action [datafusion] - posted by "kumarUjjawal (via GitHub)" <gi...@apache.org> on 2026/10/24 15:09:43 UTC, 0 replies.