andygrove opened a new pull request, #6869: URL: https://github.com/apache/datafusion-comet/pull/6869
## Which issue does this PR close? Closes #6304. Backport of #6403 to `branch-1.1`. ## Rationale for this change Spark can remove a task's execution-memory entry while a Comet shuffle allocation is waiting, causing the allocation to fail with `NoSuchElementException` instead of spilling. The fix should be available in the 1.1 release line. ## What changes are included in this PR? Cherry-picks #6403 with `-x`. The change retries the specific Spark allocation failure for both pages and pointer arrays, adds bounded-failure handling and logging, documents the behavior, and registers the regression suite in both PR workflows. No branch-specific adaptation was required. ## How are these changes tested? Ran: ```text ./mvnw test -Dtest=none -Dsuites='org.apache.spark.shuffle.comet.CometUnifiedShuffleMemoryAllocatorSuite' -Dscalastyle.skip=true ``` Result: 1 suite completed, 5 tests passed. -- 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]
