github

Messages by Date

2026/10/28 Re: [I] [dbolympics] Support Nested correlated subquery error with a depth exceeding 1 [datafusion] via GitHub
2026/10/28 Re: [I] Support correlated UNNEST in subquery [datafusion] via GitHub
2026/10/28 Re: [I] [dbolympics] Decorrelate scalar subqueries with more complex filter expressions [datafusion] via GitHub
2026/10/28 Re: [I] [dbolympics] Support correlated scalar subquery without aggregation [datafusion] via GitHub
2026/10/28 Re: [I] [dbolympics] Grandparent column reference in nested subquery causes planner error [datafusion] via GitHub
2026/10/28 Re: [I] Support LATERAL subqueries with HAVING clause [datafusion] via GitHub
2026/10/28 Re: [I] Cached AQE queries fail after transition reversion on Spark 4.0+ [datafusion-comet] via GitHub
2026/10/28 Re: [PR] fix: preserve columnar output when reverting a cached AQE result stage [datafusion-comet] via GitHub
2026/10/28 Re: [I] EPIC: Separate optimizer rules from correctness transformation rules [datafusion] via GitHub
2026/10/28 Re: [I] [dbolympics] Correlated scalar subqueries with `ORDER BY ... LIMIT 1` fail with "Physical plan does not support logical expression ScalarSubquery" [datafusion] via GitHub
2026/10/28 Re: [PR] WIP: Reuse dictionary value hashes in hash joins [datafusion] via GitHub
2026/10/28 Re: [I] [dbolympics] Subqueries in an aggregate (GROUP BY key, aggregate argument or FILTER) fail with "Physical plan does not support logical expression" [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in RepartitionExec [datafusion] via GitHub
2026/10/28 Re: [PR] WIP: Reuse dictionary value hashes in hash joins [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in RepartitionExec [datafusion] via GitHub
2026/10/28 Re: [PR] PostgreSQL: Support ALTER TABLE ATTACH PARTITION [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [PR] WIP: Reuse dictionary value hashes in hash joins [datafusion] via GitHub
2026/10/28 Re: [I] Multi-key null-aware join silently defaults to one NOT IN value key [datafusion] via GitHub
2026/10/28 Re: [I] Wrong results: correlated `NOT IN (subquery)` ignores NULLs in the subquery [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in aggregation [datafusion] via GitHub
2026/10/28 [PR] test: parallelize leaf_pushdown_fuzz with dynamic work-stealing pool (#26759) [datafusion] via GitHub
2026/10/28 Re: [I] Scalar subquery (`Expr::ScalarSubquery`) does not fail when subquery is not scalar [datafusion] via GitHub
2026/10/28 Re: [I] Correlated scalar subquery with `count(*)` returns 0 instead of NULL when `HAVING` references an outer column [datafusion] via GitHub
2026/10/28 Re: [I] Wrong results: LATERAL with SELECT DISTINCT and a non-equality correlated filter returns duplicate rows [datafusion] via GitHub
2026/10/28 Re: [I] Wrong results: correlated `NOT IN` loses the correlation when it is an equality on the `IN` value column [datafusion] via GitHub
2026/10/28 Re: [I] Wrong results: correlated `EXISTS`/`IN` subqueries over a groupless aggregate get the wrong outer rows [datafusion] via GitHub
2026/10/28 Re: [I] Wrong results: correlated scalar subquery with nested aggregates [datafusion] via GitHub
2026/10/28 Re: [I] Wrong results: a window function in an `IN` subquery sees every row when the correlated filter repeats the `IN` predicate [datafusion] via GitHub
2026/10/28 Re: [I] Wrong results: Correlated subquery confuses same-named columns of two of its relations [datafusion] via GitHub
2026/10/28 Re: [PR] docs: [branch-1.2] add #7281 to the 1.2.0 changelog [datafusion-comet] via GitHub
2026/10/28 Re: [I] Executor JVM abort (NMT footer canary broken) when the in-memory cache is enabled on Spark 3.4 [datafusion-comet] via GitHub
2026/10/28 Re: [PR] fix(optimizer): propagate pulled-up correlated state along tree frames [datafusion] via GitHub
2026/10/28 [PR] fix: give zstd the real destination capacity when compressing cached batches [datafusion-comet] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in aggregation [datafusion] via GitHub
2026/10/28 Re: [PR] WIP: Reuse dictionary value hashes in hash joins [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in RepartitionExec [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in RepartitionExec [datafusion] via GitHub
2026/10/28 Re: [I] [dbolympics] General framework to decorrelate the subqueries [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in aggregation [datafusion] via GitHub
2026/10/28 Re: [PR] ci: bound sort-axis smoke benchmark inputs [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in aggregation [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in aggregation [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in RepartitionExec [datafusion] via GitHub
2026/10/28 Re: [PR] fix: fall back to Spark for a TRY cast of a map key that can fail [datafusion-comet] via GitHub
2026/10/28 Re: [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] via GitHub
2026/10/28 [PR] fix: publish a CollectLeft join's dynamic filter on the first build report [datafusion] via GitHub
2026/10/28 Re: [I] decorrelate_predicate_subquery removes inner LIMIT inside EXISTS even when a HAVING or WHERE above it depends on the row count [datafusion] via GitHub
2026/10/28 Re: [I] Wrong results: decorrelation loses correlated columns when a subquery contains two equal subplans [datafusion] via GitHub
2026/10/28 [PR] feat: add size-aware join selection for pipelined jobs [datafusion-ballista] via GitHub
2026/10/28 [I] DataFrame::from_columns should derive field nullability from the arrays [datafusion] via GitHub
2026/10/28 Re: [I] [dbolympics] General framework to decorrelate the subqueries [datafusion] via GitHub
2026/10/28 Re: [PR] fix: apply the session's Comet configs in map stages of jobs outside a SQL execution [datafusion-comet] via GitHub
2026/10/28 Re: [PR] feat: charge native Parquet scan memory to the task memory pool [datafusion-comet] via GitHub
2026/10/28 Re: [PR] fix: reject Parquet timestamp columns read as non-timestamp types [datafusion-comet] via GitHub
2026/10/28 Re: [PR] feat: [branch-1.2] support the S3A magic committer in native Parquet writes (#6940) [datafusion-comet] via GitHub
2026/10/28 [PR] deps: bump arrow-java to 19.0.0 [datafusion-comet] via GitHub
2026/10/28 Re: [I] [EPIC] Improve I/O patterns for Parquet scans [datafusion] via GitHub
2026/10/28 [PR] fix: compact view arrays retained by PartitionedTopK [datafusion] via GitHub
2026/10/28 [PR] fix: apply the session's Comet configs in map stages of jobs outside a SQL execution [datafusion-comet] via GitHub
2026/10/28 Re: [PR] perf: reduce small-batch broadcast serialization overhead [datafusion-comet] via GitHub
2026/10/28 Re: [PR] Add a reusable caching array hasher [datafusion] via GitHub
2026/10/28 Re: [I] Cached reads that feed Spark operators are slower than Spark's own cache format [datafusion-comet] via GitHub
2026/10/28 Re: [I] Account for retained sort-key capacity [datafusion] via GitHub
2026/10/28 Re: [PR] feat: run min and max over struct inputs natively [datafusion-comet] via GitHub
2026/10/28 [I] MySQL: `REGEXP`/`RLIKE` followed by `NULL` is rejected or misparsed (regression in 0.59.0) [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [PR] fix: correct NaN grouping and eviction in TopK aggregation [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in RepartitionExec [datafusion] via GitHub
2026/10/28 [PR] DataFrame::from_columns derives field nullability from the array [datafusion] via GitHub
2026/10/28 Re: [PR] PostgreSQL: Parse NULLS [NOT] DISTINCT on column UNIQUE constraints [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [I] DataFrame::from_columns should derive field nullability from the arrays [datafusion] via GitHub
2026/10/28 [I] Let custom ExecutionPlan nodes restrict themselves to a task's partitions [datafusion-ballista] via GitHub
2026/10/28 Re: [I] Call for Presentations: Community Showcase: Regular series for sharing what you're building with DataFusion [datafusion] via GitHub
2026/10/28 Re: [PR] fix: use historic zone offset for extreme-year string-to-timestamp casts [datafusion-comet] via GitHub
2026/10/28 [I] JVM columnar shuffle writers use Comet defaults in map stages of jobs outside a SQL execution [datafusion-comet] via GitHub
2026/10/28 Re: [PR] build: format the generated release docs with the latest prettier [datafusion-comet] via GitHub
2026/10/28 Re: [PR] PostgreSQL: Support ALTER TABLE ATTACH PARTITION [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [PR] fix: propagate field metadata through coalesce, nvl, and nvl2 [datafusion] via GitHub
2026/10/28 Re: [PR] fix: preserve columnar output when reverting a cached AQE result stage [datafusion-comet] via GitHub
2026/10/28 Re: [PR] fix: propagate field metadata through coalesce, nvl, and nvl2 [datafusion] via GitHub
2026/10/28 Re: [PR] feat: reuse range partitioning for audited date_bin aggregation [datafusion] via GitHub
2026/10/28 [I] Executor JVM abort (NMT footer canary broken) when the in-memory cache is enabled on Spark 3.4 [datafusion-comet] via GitHub
2026/10/28 Re: [PR] perf: remove per-partition tail copy and flush from the native shuffle writer [datafusion-comet] via GitHub
2026/10/28 Re: [PR] MySQL: Parse USING index type before PRIMARY KEY and UNIQUE columns [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [PR] docs: add the 1.2.0 changelog and known differences to the upgrade guide [datafusion-comet] via GitHub
2026/10/28 Re: [PR] Bump libsqlite3-sys from 0.38.2 to 0.39.0 in /fuzz [datafusion-sqlparser-rs] via GitHub
2026/10/28 [I] Speed up nullable dictionary hash scattering [datafusion] via GitHub
2026/10/28 Re: [PR] fix: publish a CollectLeft join's dynamic filter on the first build report [datafusion] via GitHub
2026/10/28 Re: [PR] fix: keep a constant sort key when a projection reads a duplicate alias [datafusion] via GitHub
2026/10/28 Re: [PR] docs: add version picker and manual release snapshots [datafusion] via GitHub
2026/10/28 Re: [PR] Postgres: Accept generated columns with no mode keyword or VIRTUAL [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] Add a reusable caching array hasher [datafusion] via GitHub
2026/10/28 Re: [PR] perf: reuse projection schema in `OptimizeProjections` instead of recomputing it [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 [PR] docs: add the 1.2.0 changelog and known differences to the upgrade guide [datafusion-comet] via GitHub
2026/10/28 Re: [I] Versioned documentation [datafusion] via GitHub
2026/10/28 [PR] Speed up nullable dictionary hash scattering [datafusion] via GitHub
2026/10/28 Re: [PR] PostgreSQL: Support DROP and COMMENT ON FOREIGN TABLE [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [I] Account for retained sort-key capacity [datafusion] via GitHub
2026/10/28 Re: [PR] fix: decode invalid UTF-8 in nested Parquet BINARY values read as strings [datafusion-comet] via GitHub
2026/10/28 Re: [PR] MySQL: Parse USING index type before PRIMARY KEY and UNIQUE columns [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [PR] perf: resolve aliased field once during metadata inference [datafusion] via GitHub
2026/10/28 Re: [I] this recursive CTE SQL runs slower than SQLite [datafusion-python] via GitHub
2026/10/28 Re: [PR] fix: preserve field metadata for simple CASE branches [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] fix: validate sort pushdown through custom execution plans [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [I] Unify list-like row decomposition for map construction [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] fix: support struct-typed scalar subquery results [datafusion-comet] via GitHub
2026/10/28 [I] `SHOW ... ILIKE '<pattern>'` is displayed without quotes [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [PR] fix: write a sliced batch to the in-memory cache without the rows before it [datafusion-comet] via GitHub
2026/10/28 Re: [PR] fix: apply the session's Comet configs in map stages of jobs outside a SQL execution [datafusion-comet] via GitHub
2026/10/28 [PR] ci: run the Docker image build nightly instead of on every PR [datafusion-ballista] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 [PR] fix(expr-common): resolve struct union field nullability by name matching (#26296) [datafusion] via GitHub
2026/10/28 Re: [PR] feat: add a physical analyzer phase that hands the optimizer a valid plan [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] feat: report the ordering and partitioning of materialized CTE scans [datafusion] via GitHub
2026/10/28 Re: [I] [EPIC] Handle `-0.0` (and NaN) float keys in one place instead of per call site [datafusion] via GitHub
2026/10/28 Re: [PR] feat: report statistics of materialized CTE scans [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] PostgreSQL: Parse hexadecimal, octal and binary integer literals [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [PR] perf: use native distinct accumulator for COUNT(DISTINCT) on Decimal32/Decimal64 [datafusion] via GitHub
2026/10/28 Re: [PR] docs: add a docs-review skill [datafusion-comet] via GitHub
2026/10/28 Re: [PR] docs: add a documentation style guide and apply it to the remaining pages [datafusion-comet] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [I] Account for retained sort-key capacity [datafusion] via GitHub
2026/10/28 Re: [PR] Check the final physical plan in the planner and name the rule that broke it [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] fix: keep the output of a materialized CTE per run, not in the plan [datafusion] via GitHub
2026/10/28 [PR] feat: trim the native heap when an executor's last native plan finishes [datafusion-comet] via GitHub
2026/10/28 Re: [PR] fix: preserve make_date evaluation across lazy operators [datafusion-comet] via GitHub
2026/10/28 Re: [PR] feat: add grouping equivalence properties [datafusion] via GitHub
2026/10/28 Re: [PR] perf: use native distinct accumulator for COUNT(DISTINCT) on Decimal32/Decimal64 [datafusion] via GitHub
2026/10/28 Re: [PR] feat: add grouping equivalence properties [datafusion] via GitHub
2026/10/28 Re: [PR] fix: keep Iceberg residual pushdown within Spark semantics [datafusion-comet] via GitHub
2026/10/28 Re: [PR] feat: charge native Parquet scan memory to the task memory pool [datafusion-comet] via GitHub
2026/10/28 Re: [PR] feat: add comet-scheduler and comet-executor for Comet Native Executors [datafusion-comet] via GitHub
2026/10/28 Re: [PR] Rename `LogicalPlan::DescribeTable` to `LogicalPlan::Show` move statement implementations out of `sql` module [datafusion] via GitHub
2026/10/28 Re: [PR] fix: decode invalid UTF-8 in nested Parquet BINARY values read as strings [datafusion-comet] via GitHub
2026/10/28 Re: [I] Support custom vectorized Java UDFs that operate on Arrow vectors [datafusion-comet] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [I] Add optional fully-native deployment mode (Ballista-backed) [datafusion-comet] via GitHub
2026/10/28 Re: [PR] perf: use native distinct accumulator for COUNT(DISTINCT) on Decimal32/Decimal64 [datafusion] via GitHub
2026/10/28 Re: [PR] docs: publish older version docs from versions.json with a workflow and build script [datafusion] via GitHub
2026/10/28 Re: [PR] fix: preserve field metadata for simple CASE branches [datafusion] via GitHub
2026/10/28 Re: [PR] fix: keep Iceberg residual pushdown within Spark semantics [datafusion-comet] via GitHub
2026/10/28 Re: [PR] test: generate the taxi fixture instead of committing it [datafusion-iceberg] via GitHub
2026/10/28 Re: [PR] test: generate the taxi fixture instead of committing it [datafusion-iceberg] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 [PR] feat: give logical plan columns an identity (ColumnId) [datafusion] via GitHub
2026/10/28 [PR] build: format the generated release docs with the latest prettier [datafusion-comet] via GitHub
2026/10/28 Re: [I] SanityCheckPlan error: a constant sort key is lost when a projection reads a duplicate alias [datafusion] via GitHub
2026/10/28 Re: [PR] build(deps-dev): bump com.google.guava:guava from 33.2.1-jre to 33.7.1-jre [datafusion-comet] via GitHub
2026/10/28 Re: [PR] fix: publish a CollectLeft join's dynamic filter on the first build report [datafusion] via GitHub
2026/10/28 [PR] fix: clear groupings when clearing orderings [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [I] [EPIC] Reimplement Scala expression microbenchmarks so they measure expression cost, not scan and result transfer [datafusion-comet] via GitHub
2026/10/28 Re: [PR] fix: don't declare Unique group keys for partial aggregation output [datafusion] via GitHub
2026/10/28 Re: [PR] Pipeline non-null dictionary hash scatter on AArch64 [datafusion] via GitHub
2026/10/28 Re: [PR] feat: run min and max over struct inputs natively [datafusion-comet] via GitHub
2026/10/28 [PR] fix(physical-expr): preserve constant equivalence class and scalar subquery in EquivalenceGroup projection (#26624) [datafusion] via GitHub
2026/10/28 Re: [PR] fix: keep sort below OFFSET when the sort columns are projected away [datafusion] via GitHub
2026/10/28 Re: [I] Native Iceberg scan returns nested values that Spark reads as NULL in files without field ids or a name mapping [datafusion-comet] via GitHub
2026/10/28 Re: [I] Centralize dynamic-filter expression policy outside shared accumulator finalization [datafusion] via GitHub
2026/10/28 [PR] PostgreSQL: Parse hexadecimal, octal and binary integer literals [datafusion-sqlparser-rs] via GitHub
2026/10/28 Re: [PR] feat: add pipelined exchange operators [datafusion-ballista] via GitHub
2026/10/28 [PR] fix: validate window ordering before removing sort [datafusion] via GitHub
2026/10/28 Re: [PR] feat: add pipelined exchange operators [datafusion-ballista] via GitHub
2026/10/28 Re: [I] Call for Presentations: Community Showcase: Regular series for sharing what you're building with DataFusion [datafusion] via GitHub
2026/10/28 Re: [PR] perf: reuse projection schema in `OptimizeProjections` instead of recomputing it [datafusion] via GitHub
2026/10/28 Re: [PR] Speed up nullable dictionary hash scattering [datafusion] via GitHub
2026/10/28 Re: [PR] fix: coerce correlated subqueries against the outer column's coerced … [datafusion] via GitHub
2026/10/28 Re: [PR] perf: reduce small-batch broadcast serialization overhead [datafusion-comet] via GitHub
2026/10/28 Re: [PR] Speed up nullable dictionary hash scattering [datafusion] via GitHub
2026/10/28 Re: [I] Incorrect ORDER BY results after sort pushdown through custom execution plans [datafusion] via GitHub
2026/10/28 Re: [PR] feat: add grouping equivalence properties [datafusion] via GitHub
2026/10/28 [I] Let hash shuffles assign rows to partitions with a client's own hash function [datafusion-ballista] via GitHub
2026/10/28 [I] Map stages of RDD-level jobs run Comet with default settings instead of the session's [datafusion-comet] via GitHub
2026/10/28 Re: [PR] perf: avoid quadratic metadata merging in union schemas [datafusion] via GitHub
2026/10/28 Re: [PR] Speed up nullable dictionary hash scattering [datafusion] via GitHub
2026/10/28 Re: [PR] perf: reuse projection schema in `OptimizeProjections` instead of recomputing it [datafusion] via GitHub
2026/10/28 Re: [PR] refactor: pin satisfied sort keys in a walk instead of adding them as constants [datafusion] via GitHub
2026/10/28 Re: [PR] Speed up nullable dictionary hash scattering [datafusion] via GitHub
2026/10/28 Re: [PR] refactor: pin satisfied sort keys in a walk instead of adding them as constants [datafusion] via GitHub
2026/10/28 Re: [PR] Speed up nullable dictionary hash scattering [datafusion] via GitHub
2026/10/28 Re: [PR] fix: validate sort pushdown through custom execution plans [datafusion] via GitHub
2026/10/28 Re: [PR] Speed up nullable dictionary hash scattering [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in aggregation [datafusion] via GitHub
2026/10/28 Re: [PR] feat: add a physical analyzer phase that hands the optimizer a valid plan [datafusion] via GitHub
2026/10/28 [I] Parquet scan drops field metadata (extension types) of columns at execution time [datafusion] via GitHub
2026/10/28 Re: [PR] feat: add a physical analyzer phase that hands the optimizer a valid plan [datafusion] via GitHub
2026/10/28 Re: [PR] Reuse dictionary value hashes in RepartitionExec [datafusion] via GitHub
2026/10/28 Re: [PR] docs: [branch-1.2] generate docs for the 1.2.0 release [datafusion-comet] via GitHub