suneet-s opened a new pull request, #14396: URL: https://github.com/apache/druid/pull/14396
This change is still WIP. It's only been tested in local clusters. And it hasn't been tested with the lag based auto-scaler. ### Description Currently, the number of slots needed for for a streaming supervisor to handover quickly is 2 * number of tasks needed for reading from the stream. This is because when the taskDuration expires, the previously reading tasks need to publish the segments, and if this takes time, and there are no available slots on the cluster, Druid will not be reading from the stream until a slot is available. This change makes it so that during regular operations, tasks are rolled over one at a time, so that an operator can plan to have a capacity of number of tasks need to read from the stream + 1. It seems like different clusters might have different preferences for whether one task at a time is sufficiently fast enough, so I think making this part of the ioConfig seems like a better approach than a hardcoded option. #### Release note <!-- Give your best effort to summarize your changes in a couple of sentences aimed toward Druid users. If your change doesn't have end user impact, you can skip this section. For tips about how to write a good release note, see [Release notes](https://github.com/apache/druid/blob/master/CONTRIBUTING.md#release-notes). --> This PR has: - [ ] been self-reviewed. - [ ] using the [concurrency checklist](https://github.com/apache/druid/blob/master/dev/code-review/concurrency.md) (Remove this item if the PR doesn't have any relation to concurrency.) - [ ] added documentation for new or modified features or behaviors. - [ ] a release note entry in the PR description. - [ ] added Javadocs for most classes and all non-trivial methods. Linked related entities via Javadoc links. - [ ] added or updated version, license, or notice information in [licenses.yaml](https://github.com/apache/druid/blob/master/dev/license.md) - [ ] added comments explaining the "why" and the intent of the code wherever would not be obvious for an unfamiliar reader. - [ ] added unit tests or modified existing tests to cover new code paths, ensuring the threshold for [code coverage](https://github.com/apache/druid/blob/master/dev/code-review/code-coverage.md) is met. - [ ] added integration tests. - [ ] been tested in a test Druid cluster. -- 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]
