JkSelf commented on code in PR #6403:
URL: https://github.com/apache/incubator-gluten/pull/6403#discussion_r1683710529
##########
gluten-core/src/main/scala/org/apache/spark/sql/execution/GlutenColumnarWriteFilesExec.scala:
##########
@@ -17,150 +17,47 @@
package org.apache.spark.sql.execution
import org.apache.gluten.backendsapi.BackendsApiManager
-import org.apache.gluten.columnarbatch.ColumnarBatches
import org.apache.gluten.exception.GlutenException
import org.apache.gluten.extension.GlutenPlan
-import org.apache.gluten.memory.arrow.alloc.ArrowBufferAllocators
import org.apache.gluten.sql.shims.SparkShimLoader
import org.apache.spark.{Partition, SparkException, TaskContext,
TaskOutputFileAlreadyExistException}
import org.apache.spark.internal.io.{FileCommitProtocol,
SparkHadoopWriterUtils}
-import org.apache.spark.internal.io.FileCommitProtocol.TaskCommitMessage
import org.apache.spark.rdd.RDD
import org.apache.spark.shuffle.FetchFailedException
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.catalog.BucketSpec
import org.apache.spark.sql.catalyst.catalog.CatalogTypes.TablePartitionSpec
-import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeSet,
GenericInternalRow}
+import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeSet}
import org.apache.spark.sql.connector.write.WriterCommitMessage
import org.apache.spark.sql.execution.datasources._
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.vectorized.ColumnarBatch
import org.apache.spark.util.Utils
-import com.fasterxml.jackson.databind.ObjectMapper
-import com.fasterxml.jackson.module.scala.DefaultScalaModule
import org.apache.hadoop.fs.FileAlreadyExistsException
import java.util.Date
-import scala.collection.mutable
-
-// Velox write files metrics start
-//
-// Follows the code in velox `HiveDataSink::close()`
-// The json can be as following:
-// {
-// "inMemoryDataSizeInBytes":0,
-// "containsNumberedFileNames":true,
-// "onDiskDataSizeInBytes":307,
-// "fileWriteInfos":[
-// {
-// "fileSize":307,
-// "writeFileName":
-//
"Gluten_Stage_1_TID_2_0_2_d1db3b31-4f99-41cb-a4e7-3b8607506168.parquet",
-// "targetFileName":
-//
"Gluten_Stage_1_TID_2_0_2_d1db3b31-4f99-41cb-a4e7-3b8607506168.parquet"
-// }
-// ],
-//
"writePath":"file:/home/gluten/spark-warehouse/inserttable/part1=1/part2=1",
-// "rowCount":1,
-//
"targetPath":"file:/home/gluten/spark-warehouse/inserttable/part1=1/part2=1",
-// "updateMode":"NEW",
-// "name":"part1=1/part2=1"
-// }
-case class VeloxWriteFilesInfo(writeFileName: String, targetFileName: String,
fileSize: Long)
-
-case class VeloxWriteFilesMetrics(
- name: String,
- updateMode: String,
- writePath: String,
- targetPath: String,
- fileWriteInfos: Seq[VeloxWriteFilesInfo],
- rowCount: Long,
- inMemoryDataSizeInBytes: Long,
- onDiskDataSizeInBytes: Long,
- containsNumberedFileNames: Boolean)
-
-// Velox write files metrics end
+/**
+ * This trait is used in [[GlutenColumnarWriteFilesRDD]] to inject the staging
write path before
+ * initializing the native plan and collect native write files metrics for
each backend.
+ */
+trait BackendWrite {
+ def collectNativeWriteFilesMetrics(batch: ColumnarBatch):
Option[WriteTaskResult]
+}
/**
* This RDD is used to make sure we have injected staging write path before
initializing the native
* plan, and support Spark file commit protocol.
*/
-class VeloxColumnarWriteFilesRDD(
+class GlutenColumnarWriteFilesRDD(
Review Comment:
After moving VeloxColumnarWriteFilesExec from backend-velox to gluten-core,
can we update the class names by renaming GlutenColumnarWriteFilesExec to
ColumnarWriteFilesExec and GlutenColumnarWriteFilesRDD to
ColumnarWriteFilesRDD?
--
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]
