Skip to content

Pull requests: apache/datafusion-comet

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

feat: remove memory accounting from Comet's on-heap mode area:memory Memory pools, reservations, OOM handling area:shuffle Shuffle (JVM and native) enhancement New feature or request run-iceberg-tests run-spark-3.4-tests Run the Spark 3.4 SQL tests on this PR run-spark-3.5-tests Run the Spark 3.5 SQL tests on this PR run-spark-4.0-tests run-spark-4.1-tests Run the Spark 4.1 SQL tests on this pull request instead of waiting for the merge queue
#6066 opened Sep 20, 2026 by andygrove Member Draft
fix: load the Iceberg storage scheme lists from the native factory area:Iceberg area:scan Parquet scan / data reading area:writer Native Parquet writer bug Something isn't working
#6065 opened Sep 20, 2026 by dwsmith1983 Contributor Loading…
fix: restore the site's mermaid diagrams and make a dropped one fail CI bug Something isn't working
#6064 opened Sep 20, 2026 by andygrove Member Loading…
2
1
ci: retry the scalafix lint when Maven cannot resolve the plugin area:ci CI/CD, GitHub Actions, build tooling build Build environment enhancement New feature or request
#6061 opened Sep 20, 2026 by andygrove Member Loading…
fix: let explicit Hadoop Azure auth outrank ambient AZURE_* environment variables area:scan Parquet scan / data reading bug Something isn't working
#6059 opened Sep 20, 2026 by dwsmith1983 Contributor Loading…
docs: add a scan contributor guide and a scan PR review skill documentation Improvements or additions to documentation
#6052 opened Sep 19, 2026 by andygrove Member Loading…
fix: let decimal SUM recover from an intermediate overflow like Spark area:aggregation Hash aggregates, aggregate expressions bug Something isn't working
#6041 opened Sep 19, 2026 by dwsmith1983 Contributor Loading…
chore: add a native Iceberg write benchmark area:Iceberg enhancement New feature or request
#6038 opened Sep 19, 2026 by 0lai0 Contributor Loading…
perf: reuse prepared broadcast builds across executor tasks area:joins Join operators and dynamic filter pushdown area:memory Memory pools, reservations, OOM handling area:scan Parquet scan / data reading enhancement New feature or request performance run-spark-4.1-tests Run the Spark 4.1 SQL tests on this pull request instead of waiting for the merge queue
#6037 opened Sep 19, 2026 by sunchao Member Draft
feat: admit string maps in Spark-to-Comet conversion area:ffi Arrow FFI / JNI boundary enhancement New feature or request run-spark-4.1-tests Run the Spark 4.1 SQL tests on this pull request instead of waiting for the merge queue
#6036 opened Sep 19, 2026 by sunchao Member Loading…
fix: defer throwing literal casts to Spark at runtime area:expressions Expression evaluation bug Something isn't working run-spark-4.1-tests Run the Spark 4.1 SQL tests on this pull request instead of waiting for the merge queue
#6035 opened Sep 19, 2026 by sunchao Member Loading…
feat: scope-aware object_store cache for the S3 credential SPI area:ffi Arrow FFI / JNI boundary area:scan Parquet scan / data reading enhancement New feature or request
#6031 opened Sep 18, 2026 by snmvaughan Contributor Loading…
docs: document the 24-hour review window for non-trivial pull requests documentation Improvements or additions to documentation
#6030 opened Sep 18, 2026 by andygrove Member Loading…
fix: Native S3 scan on EKS/IRSA turns a transient STS throttle into a had 403 storm area:Iceberg area:scan Parquet scan / data reading bug Something isn't working
#6025 opened Sep 18, 2026 by parthchandra Contributor Loading…
feat: built-in S3 credential provider adapters for the native Parquet scan area:scan Parquet scan / data reading enhancement New feature or request
#6023 opened Sep 18, 2026 by parthchandra Contributor Loading…
docs: add local-diff mode to review-comet-pr skill and ask about it in the PR template documentation Improvements or additions to documentation
#6017 opened Sep 18, 2026 by andygrove Member Draft
1 of 2 tasks
docs: add pr-triage skill for PR hygiene and duplicate detection documentation Improvements or additions to documentation
#6016 opened Sep 18, 2026 by andygrove Member Draft
fix: use Spark-compatible shuffle for wide decimal hash keys area:aggregation Hash aggregates, aggregate expressions area:expressions Expression evaluation area:shuffle Shuffle (JVM and native) bug Something isn't working correctness run-all-spark-profiles Run the Comet test suites against every Spark profile on this pull request, ahead of the merge queue
#6005 opened Sep 17, 2026 by sunchao Member Draft
feat: report JVM Arrow allocations to Spark's memory manager area:expressions Expression evaluation area:ffi Arrow FFI / JNI boundary area:udf enhancement New feature or request
#5998 opened Sep 17, 2026 by andygrove Member Draft
fix: count each memory pool once in analyze_trace area:expressions Expression evaluation area:memory Memory pools, reservations, OOM handling bug Something isn't working run-spark-4.1-tests Run the Spark 4.1 SQL tests on this pull request instead of waiting for the merge queue
#5991 opened Sep 16, 2026 by andygrove Member Loading…
fix: reverse ordering and range in NegativeExpr::get_properties area:expressions Expression evaluation bug Something isn't working
#5982 opened Sep 16, 2026 by Smallfu666 Contributor Loading…
ci: reuse Linux native libraries across workflow runs area:ci CI/CD, GitHub Actions, build tooling area:Iceberg build Build environment enhancement New feature or request
#5976 opened Sep 16, 2026 by sunchao Member Loading…
fix: preserve Spark evaluation for next_day and levenshtein area:expressions Expression evaluation bug Something isn't working
#5972 opened Sep 15, 2026 by sunchao Member Loading…
test: cover matching nested nulls in collect aggregates enhancement New feature or request test Testing related
#5970 opened Sep 15, 2026 by sunchao Member Loading…
fix: preserve Spark Parquet schema conversion errors (WIP) area:ffi Arrow FFI / JNI boundary area:scan Parquet scan / data reading bug Something isn't working
#5958 opened Sep 15, 2026 by Abhishek-Mohan Draft
3 tasks
ProTip! Follow long discussions with comments:>50.