andygrove opened a new issue, #4625: URL: https://github.com/apache/datafusion-comet/issues/4625
Triage pass for issues labeled `requires-triage`. - **Date:** 2026-06-11 - **Issues processed:** 20 (15 triaged, 5 skipped, 0 failed) - **Priority counts applied:** `priority:medium` 9, `priority:low` 6 - **Guide:** [docs/source/contributor-guide/bug_triage.md](https://github.com/apache/datafusion-comet/blob/main/docs/source/contributor-guide/bug_triage.md) Labels have already been applied and `requires-triage` removed from the triaged issues. Please spot-check the calls below and close this issue when satisfied. Correct any label directly on the affected issue. ## Triaged ### priority:medium - Performance regression when a stage of WholeStageCodegen-fusible operators runs as separate native Comet operators ([#4614](https://github.com/apache/datafusion-comet/issues/4614)) - Area labels: none - Rationale: `priority:medium` was set by the reporter and preserved; performance regression with config workaround per decision-tree step 3. - Route array/map higher-order (lambda) functions through the codegen dispatcher ([#4617](https://github.com/apache/datafusion-comet/issues/4617)) - Area labels: `area:expressions` - Rationale: enables HOFs to stay native instead of falling back; missing-feature gap with a Spark fallback workaround. - Deliberately opt eligible Incompatible expressions into codegen dispatch with test coverage ([#4596](https://github.com/apache/datafusion-comet/issues/4596)) - Area labels: `area:expressions` - Rationale: feature work to wire currently-falling-back expressions through codegen dispatch; functional gap with workaround. - Rebalance deep associative binary expression chains (Add, Multiply, bitwise) to avoid protobuf recursion limit ([#4577](https://github.com/apache/datafusion-comet/issues/4577)) - Area labels: `area:expressions` (already present) - Rationale: query fails with a clean error on chains >100 deep; functional bug, uncommon trigger, simple workaround. - Investigate adopting DataFusion's allocator-level memory accounting to replace manual memory tuning ([#4576](https://github.com/apache/datafusion-comet/issues/4576)) - Area labels: none - Rationale: addresses real OOM pain documented in the tuning guide; current workaround is manual `memoryPool.fraction` tuning. - Support StringSplitSQL to enable split_part ([#4561](https://github.com/apache/datafusion-comet/issues/4561)) - Area labels: `area:expressions` - Rationale: missing expression support, falls back to Spark today. - try_to_date / try_to_timestamp fall back to Spark even though to_date / to_timestamp are accelerated ([#4556](https://github.com/apache/datafusion-comet/issues/4556)) - Area labels: `area:expressions` - Rationale: missing expression support / unnecessary fallback. - Natively support time-window grouping expressions: window, session_window, window_time ([#4553](https://github.com/apache/datafusion-comet/issues/4553)) - Area labels: `area:expressions` - Rationale: missing expression support, falls back to Spark today. - Natively support regr_sxx, regr_syy, regr_sxy, regr_slope, regr_intercept, regr_r2 aggregates ([#4552](https://github.com/apache/datafusion-comet/issues/4552)) - Area labels: `area:aggregation` (already present) - Rationale: missing aggregate expression support, falls back to Spark today. ### priority:low - docs: update CometBatchIterator references ([#4624](https://github.com/apache/datafusion-comet/issues/4624)) - Area labels: none - Rationale: documentation update to reflect the new Arrow stream reader; per the guide's "tooling, cosmetic" bucket. - Test dual-impl (native + codegen-dispatch) expressions consistently across the full routing matrix ([#4616](https://github.com/apache/datafusion-comet/issues/4616)) - Area labels: `area:expressions` - Rationale: test convention / consistency work for the dispatch routing matrix; test-only per the guide. - ci: Remove ORC testing from Iceberg Java tests ([#4586](https://github.com/apache/datafusion-comet/issues/4586)) - Area labels: `area:ci` - Rationale: CI/tooling change to skip a format Comet does not accelerate; CI bucket per the guide. - CometFromUnixTime reports unsupported format patterns as Incompatible instead of Unsupported ([#4575](https://github.com/apache/datafusion-comet/issues/4575)) - Area labels: `area:expressions` - Rationale: classification / generated-docs accuracy issue; the issue itself notes runtime behavior is already safe. - String expression (collation) audit followup ([#4573](https://github.com/apache/datafusion-comet/issues/4573)) - Area labels: `area:expressions` - Rationale: audit checklist; per the body, items are currently unreachable because the scan-level guard forces full fallback for collated columns. - Comet 0.17.0 Release ([#4564](https://github.com/apache/datafusion-comet/issues/4564)) - Area labels: none - Rationale: release coordination / planning tracker, not a defect; "everything else" bucket. ## Skipped — needs more info - Bug triage results: 2026-06-01 ([#4548](https://github.com/apache/datafusion-comet/issues/4548)) - Prior triage summary issue (auto-labeled `requires-triage`); meta, awaiting human review and closure, not a bug. - [EPIC] Support Spark interval types (CalendarInterval / YearMonthInterval / DayTimeInterval) and interval expressions ([#4540](https://github.com/apache/datafusion-comet/issues/4540)) - Open-ended EPIC umbrella; a single priority is a roadmap decision rather than a mechanical triage call. - [EPIC] Provide JVM/codegen-dispatch implementations for Incompatible expressions so they never fall back by default ([#4506](https://github.com/apache/datafusion-comet/issues/4506)) - Open-ended EPIC umbrella; a single priority is a roadmap decision rather than a mechanical triage call. - Discussion: Should Comet add geospatial (ST_*) function support? ([#4455](https://github.com/apache/datafusion-comet/issues/4455)) - Discussion / scope question needing community and maintainer input, not a triageable defect. - Bug triage results: 2026-05-26 ([#4441](https://github.com/apache/datafusion-comet/issues/4441)) - Prior triage summary issue (auto-labeled `requires-triage`); meta, awaiting human review and closure, not a bug. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
