ding-young opened a new pull request, #17363: URL: https://github.com/apache/datafusion/pull/17363
## 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. --> - Related to #17340 ## Rationale for this change Currently, when writing spill files, we construct the `IPCStreamWriter` with a fixed alignment of 8 bytes. However, depending on the schema, some array types such as `StringViewArray` require larger (16 byte in this case) alignment. If the actual buffer layout after IPC read does not satisfy the alignment requirement, Arrow ArrayBuilder will copy the buffer into a newly allocated, properly aligned buffer. (See https://github.com/apache/arrow-rs/blob/3dcd23ffa3cbc0d9496e1660c6f68ce563a336b4/arrow-data/src/data.rs#L717-L738 and https://github.com/apache/arrow-rs/blob/3dcd23ffa3cbc0d9496e1660c6f68ce563a336b4/arrow-data/src/data.rs#L2050-L2052) This copying may lead to memory blowup during IPC read due to duplicated buffers. To avoid this, we compute the maximum required alignment based on the schema and configure the `IPCStreamWriter` accordingly. While increasing the alignment value may slightly increase the size of the written file due to padding, this overhead is minimal compared to the memory overhead caused by unnecessary buffer copies. <!-- 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. --> ## What changes are included in this PR? This PR sets alignment based on max_alignment required for all the fields of given schema. <!-- 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. --> ## Are these changes tested? Yes. <!-- We typically require tests for all PRs in order to: 1. Prevent the code from being accidentally broken by subsequent changes 2. Serve as another way to document the expected behavior of the code If tests are not included in your PR, please explain why (for example, are they covered by existing tests)? --> ## Are there any user-facing changes? <!-- If there are user-facing changes then we may require documentation to be updated before approving the PR. --> <!-- 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]
