comphead commented on code in PR #4128:
URL: https://github.com/apache/datafusion-comet/pull/4128#discussion_r3155702191
##########
spark/src/test/scala/org/apache/comet/CometIcebergNativeSuite.scala:
##########
@@ -2764,4 +2769,82 @@ class CometIcebergNativeSuite extends CometTestBase with
RESTCatalogHelper {
}
}
}
+
+ test("task-level inputMetrics.bytesRead is populated for Iceberg native
scan") {
+ assume(icebergAvailable, "Iceberg not available in classpath")
+
+ withTempIcebergDir { warehouseDir =>
+ withSQLConf(
+ "spark.sql.catalog.test_cat" ->
"org.apache.iceberg.spark.SparkCatalog",
+ "spark.sql.catalog.test_cat.type" -> "hadoop",
+ "spark.sql.catalog.test_cat.warehouse" -> warehouseDir.getAbsolutePath,
+ CometConf.COMET_ENABLED.key -> "true",
+ CometConf.COMET_EXEC_ENABLED.key -> "true",
+ CometConf.COMET_ICEBERG_NATIVE_ENABLED.key -> "true") {
+
+ spark.sql("""
+ CREATE TABLE test_cat.db.task_metrics_test (
+ id INT,
+ value DOUBLE
+ ) USING iceberg
+ """)
+
+ spark
+ .range(10000)
+ .selectExpr("CAST(id AS INT)", "CAST(id * 1.5 AS DOUBLE) as value")
+ .coalesce(1)
+ .write
+ .format("iceberg")
+ .mode("append")
+ .saveAsTable("test_cat.db.task_metrics_test")
+
+ val bytesReadValues = mutable.ArrayBuffer.empty[Long]
+ val recordsReadValues = mutable.ArrayBuffer.empty[Long]
+
+ val listener = new SparkListener {
+ override def onTaskEnd(taskEnd: SparkListenerTaskEnd): Unit = {
+ val im = taskEnd.taskMetrics.inputMetrics
+ if (im.bytesRead > 0) {
+ bytesReadValues.synchronized {
+ bytesReadValues += im.bytesRead
+ recordsReadValues += im.recordsRead
+ }
+ }
+ }
+ }
+ spark.sparkContext.addSparkListener(listener)
+
+ try {
+ val df = spark.sql("SELECT * FROM test_cat.db.task_metrics_test")
+
+ val scanNodes = df.queryExecution.executedPlan
+ .collectLeaves()
+ .collect { case s: CometIcebergNativeScanExec => s }
+ assert(scanNodes.nonEmpty, "Expected CometIcebergNativeScanExec in
plan")
+
+ df.collect()
+
+ // listenerBus.waitUntilEmpty() is package-private to
org.apache.spark
+ Thread.sleep(1000)
+
+ val totalBytes = bytesReadValues.sum
+ val totalRecords = recordsReadValues.sum
+
+ assert(totalBytes > 0, s"task inputMetrics.bytesRead should be > 0,
got $totalBytes")
+ assert(
+ totalRecords == 10000,
Review Comment:
we can prob test records and bytes against what Spark reports, similar to
```
native_datafusion scan reports task-level input metrics matching Spark
```
--
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]
