-
Notifications
You must be signed in to change notification settings - Fork 382
OpenSep 29, 2026
Due by September 30, 2026
•Last updated 76% complete
List view
0 of 29 selected 0 issues of 29 selected
Drop support for Spark 3.4
enhancementNew feature or requestNew feature or requestpriority:lowMinor issues, test failures, tooling, cosmeticMinor issues, test failures, tooling, cosmeticStatus: Open.#4329 In apache/datafusion-comet;Row-level Parquet filter pushdown regresses uncorrelated-predicate scans (TPC-H Q6 +80%)
area:scanParquet scan / data readingParquet scan / data readingenhancementNew feature or requestNew feature or requestStatus: Open.#4988 In apache/datafusion-comet;feat: enable CometLocalTableScanExec by default
area:scanParquet scan / data readingParquet scan / data readingenhancementNew feature or requestNew feature or requestStatus: Draft (not ready).apache/datafusion-cometnumber 4393#4393 In apache/datafusion-comet;[EPIC] Planner, serde, and optimizer rule performance audit
enhancementNew feature or requestNew feature or requestStatus: Open.#5199 In apache/datafusion-comet;Shuffle performance audit: candidate optimizations needing investigation
area:shuffleShuffle (JVM and native)Shuffle (JVM and native)enhancementNew feature or requestNew feature or requestStatus: Open.#5198 In apache/datafusion-comet;[EPIC] cast from string: trim semantics diverge from Spark across all numeric, datetime and boolean targets
area:expressionsExpression evaluationExpression evaluationbugSomething isn't workingSomething isn't workingpriority:criticalData corruption, silent wrong results, security issuesData corruption, silent wrong results, security issuesStatus: Open.#5149 In apache/datafusion-comet;Native Parquet schema-on-read diverges from Spark for ANSI interval targets
area:scanParquet scan / data readingParquet scan / data readingbugSomething isn't workingSomething isn't workingpriority:mediumFunctional bugs, performance regressions, broken featuresFunctional bugs, performance regressions, broken featuresStatus: Open.#5188 In apache/datafusion-comet;fix: string-to-timestamp does not trim ISO control characters, and leading '+' returns null under ANSI
area:expressionsExpression evaluationExpression evaluationbugSomething isn't workingSomething isn't workingpriority:mediumFunctional bugs, performance regressions, broken featuresFunctional bugs, performance regressions, broken featuresStatus: Open.#5165 In apache/datafusion-comet;[Bug] Native make_interval overflows valid time components or loses seconds precision
area:expressionsExpression evaluationExpression evaluationbugSomething isn't workingSomething isn't workingpriority:mediumFunctional bugs, performance regressions, broken featuresFunctional bugs, performance regressions, broken featuresStatus: Open.#5131 In apache/datafusion-comet;[EPIC] ANSI mode audit follow-ups (vs Spark 4.1.1)
area:expressionsExpression evaluationExpression evaluationbugSomething isn't workingSomething isn't workingpriority:mediumFunctional bugs, performance regressions, broken featuresFunctional bugs, performance regressions, broken featuresStatus: Open.#5078 In apache/datafusion-comet;fix: fall back to Spark for negative-scale decimal casts and arithmetic
area:expressionsExpression evaluationExpression evaluationbugSomething isn't workingSomething isn't workingStatus: Open (in progress).RANGE window frame boundary overflow diverges from Spark for DATE and DECIMAL ORDER BY
area:expressionsExpression evaluationExpression evaluationbugSomething isn't workingSomething isn't workingpriority:highCrashes, panics, segfaults, major functional breakageCrashes, panics, segfaults, major functional breakageStatus: Open.#5022 In apache/datafusion-comet;Native panic casting to negative-scale decimal when spark.sql.legacy.allowNegativeScaleOfDecimal=true
area:expressionsExpression evaluationExpression evaluationbugSomething isn't workingSomething isn't workingcrashNative engine crash/panic/segfaultNative engine crash/panic/segfaultpriority:highCrashes, panics, segfaults, major functional breakageCrashes, panics, segfaults, major functional breakageStatus: Open.#5013 In apache/datafusion-comet;Native implementation of
get_json_objectreturns last value for duplicate keys, Spark returns firstarea:expressionsExpression evaluationExpression evaluationbugSomething isn't workingSomething isn't workingpriority:highCrashes, panics, segfaults, major functional breakageCrashes, panics, segfaults, major functional breakageStatus: Open.#4947 In apache/datafusion-comet;Ranked backlog: native scalar expressions with per-row optimization opportunities
enhancementNew feature or requestNew feature or requestStatus: Open.#4942 In apache/datafusion-comet;[Bug] map_from_arrays / map_from_entries do not enforce null-key rejection or spark.sql.mapKeyDedupPolicy
area:expressionsExpression evaluationExpression evaluationbugSomething isn't workingSomething isn't workingpriority:mediumFunctional bugs, performance regressions, broken featuresFunctional bugs, performance regressions, broken featuresStatus: Open.#4680 In apache/datafusion-comet;Add a docs-review Claude skill to enforce style guide and documentation quality
documentationImprovements or additions to documentationImprovements or additions to documentationpriority:lowMinor issues, test failures, tooling, cosmeticMinor issues, test failures, tooling, cosmeticStatus: Open.#4420 In apache/datafusion-comet;Establish nomenclature style guide and audit operator names for clarity
documentationImprovements or additions to documentationImprovements or additions to documentationpriority:lowMinor issues, test failures, tooling, cosmeticMinor issues, test failures, tooling, cosmeticStatus: Open.#4419 In apache/datafusion-comet;Enable spark.comet.exec.localTableScan.enabled when running Spark SQL tests
priority:lowMinor issues, test failures, tooling, cosmeticMinor issues, test failures, tooling, cosmeticspark sql testsSpark SQL test failuresSpark SQL test failuresStatus: Open.#4347 In apache/datafusion-comet;native_datafusion: ParquetSchemaConvert error does not include the file path
native_datafusionSpecific to native_datafusion scan typeSpecific to native_datafusion scan typeStatus: Open.#4316 In apache/datafusion-comet;Re-enable COUNT for mixed Spark partial / Comet final aggregate execution
area:aggregationHash aggregates, aggregate expressionsHash aggregates, aggregate expressionspriority:mediumFunctional bugs, performance regressions, broken featuresFunctional bugs, performance regressions, broken featuresStatus: Open.#4242 In apache/datafusion-comet;Audit Spark SQL configs that affect query semantics and ensure Comet honors them (or falls back)
area:expressionsExpression evaluationExpression evaluationarea:scanParquet scan / data readingParquet scan / data readingenhancementNew feature or requestNew feature or requestpriority:mediumFunctional bugs, performance regressions, broken featuresFunctional bugs, performance regressions, broken featuresStatus: Open.#4180 In apache/datafusion-comet;Register CometArrowAllocator as a Spark MemoryConsumer for JVM-UDF dispatch
area:expressionsExpression evaluationExpression evaluationarea:ffiArrow FFI / JNI boundaryArrow FFI / JNI boundarypriority:mediumFunctional bugs, performance regressions, broken featuresFunctional bugs, performance regressions, broken featuresStatus: Open.#4174 In apache/datafusion-comet;Consistent debug logging levels and messages
enhancementNew feature or requestNew feature or requestStatus: Open.#3445 In apache/datafusion-comet;[hdfs-opendal] Got an
reader got too little dataerror on hdfs-opendalarea:scanParquet scan / data readingParquet scan / data readingbugSomething isn't workingSomething isn't workingnative_datafusionSpecific to native_datafusion scan typeSpecific to native_datafusion scan typepriority:mediumFunctional bugs, performance regressions, broken featuresFunctional bugs, performance regressions, broken featuresStatus: Open.#2400 In apache/datafusion-comet;