akshaychitneni opened a new pull request, #2212: URL: https://github.com/apache/datafusion-ballista/pull/2212
When every executor dies mid-query, the scheduler reset the affected tasks but had nothing to schedule them onto, leaving the job Running forever and hanging the client. On ExecutorLost, if no live executors remain, wait a bounded, configurable grace period (no_executors_grace_period_seconds, default 30s) for an executor to (re)register, then fail any still-running job with a clear error. The check is scoped to the ExecutorLost path, so jobs merely queued waiting for their first executor (autoscaling cold start) are unaffected. Adds unit tests for both total loss (job fails) and partial loss (job survives while an executor remains). # Which issue does this PR close? <!-- We generally require a GitHub issue to be filed for all bug fixes and enhancements and this helps us generate change logs for our releases. You can link an issue to this PR using the GitHub syntax. For example `Closes #123` indicates that this PR will close issue #123. --> Closes #. https://github.com/apache/datafusion-ballista/issues/2029 # Rationale for this change <!-- Why are you proposing this change? If this is already explained clearly in the issue then this section is not needed. Explaining clearly why changes are proposed helps reviewers understand your changes and offer better suggestions for fixes. --> When all executors die mid-query, the scheduler leaves the job `Running` forever and the client hangs. # What changes are included in this PR? <!-- There is no need to duplicate the description in the issue here but it is sometimes worth providing a summary of the individual changes in this PR. --> On `ExecutorLost` with no live executors left, wait a bounded, configurable grace period (`no_executors_grace_period_seconds`, default 30s) for an executor to re-register, then fail any still-running job. # Are there any user-facing changes? <!-- If there are user-facing changes then we may require documentation to be updated before approving the PR. --> New scheduler config `no_executors_grace_period_seconds` (default 30s); a total executor loss now fails jobs with a clear error instead of hanging. <!-- If there are any breaking changes to public APIs, please add the `api change` label. --> -- 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]
