alexeykudinkin opened a new pull request, #6213: URL: https://github.com/apache/hudi/pull/6213
## *Tips* - *Thank you very much for contributing to Apache Hudi.* - *Please review https://hudi.apache.org/contribute/how-to-contribute before opening a pull request.* ## What is the purpose of the pull request In our internal benchmarks we've detected that there's a very clear performance gap b/w following sequences even though they are using essentially the same underlying infra: 1. Spark SQL: `INSERT INTO` statement 2. Writing via Spark DS The issue turned out to be inadvertent dereferencing of the incoming `Dataset` into `RDD[Row]`, entailing the penalty of deserialization of every row. After resolving both of this code-paths have comparable runtime. ## Brief change log - Cleaning up shaping up flow to avoid unnecessary conversions - Avoiding the conversion loop `Dataset` > `RDD[Row]` > `Dataset` - Tidying up ## Verify this pull request This pull request is already covered by existing tests, such as *(please describe tests)*. ## Committer checklist - [ ] Has a corresponding JIRA in PR title & commit - [ ] Commit message is descriptive of the change - [ ] CI is green - [ ] Necessary doc changes done or have another open PR - [ ] For large changes, please consider breaking it into sub-tasks under an umbrella JIRA. -- 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]
