Zouxxyy commented on PR #10714: URL: https://github.com/apache/incubator-gluten/pull/10714#issuecomment-3293231903
> https://github.com/apache/incubator-gluten/blob/main/gluten-substrait/src/main/scala/org/apache/gluten/execution/ColumnarV2TableWriteExec.scala#L45-L51 should eliminate the format conversion, but seems it does not work in some condition, could you help take a look? Thanks! @zhztheplayer Yes, the `ColumnarV2TableWriteExec` is fine, but the inserted AQE node (by iceberg partitioned write which will produce a sort) is not a batch node, which causes c2r and r2c to be inserted around it. This PR just mark the AQE child of v2 columnar write as supportsColumnar = true. -- 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]
