[TEZ-3984] Shuffle: Out of Band DME event sending causes errors

• Type: Bug
• Status: Resolved
• Priority: Critical
• Resolution: Fixed
• Affects Version/s: 0.8.4, 0.9.1, 0.10.0
• Fix Version/s: 0.10.1
• Labels: correctness
• Assignee: Jaume M
• Reporter: Gopal Vijayaraghavan
• Created: 27/Aug/18 22:33
• Updated: 25/Jun/21 10:00
• Resolved: 25/Jun/21 10:00

Description

In case of a task Input throwing an exception, the outputs are also closed in the LogicalIOProcessorRuntimeTask.cleanup().

Cleanup ignore all the events returned by output close, however if any output tries to send an event out of band by directly calling outputContext.sendEvents(events), then those events can reach the AM before the task failure is reported.

This can cause correctness issues with shuffle since zero sized events can be sent out due to an input failure and downstream tasks may never reattempt a fetch from the valid attempt.

Issue Links

• depends upon: TEZ-3985 Correctness: Throw a clear exception for DMEs sent during cleanup
• relates to: TEZ-3974 Tez: Correctness regression of TEZ-955 in TEZ-2937