hsiang-c commented on code in PR #4128:
URL: https://github.com/apache/datafusion-comet/pull/4128#discussion_r3156173373
##########
spark/src/test/scala/org/apache/comet/CometIcebergNativeSuite.scala:
##########
@@ -548,6 +551,69 @@ class CometIcebergNativeSuite extends CometTestBase with
RESTCatalogHelper {
}
}
+ test("bytes_scanned includes delete file I/O") {
+ 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.delete_bytes_test (
+ id INT,
+ value DOUBLE
+ ) USING iceberg
+ TBLPROPERTIES (
+ 'write.delete.mode' = 'merge-on-read',
+ 'write.merge.mode' = 'merge-on-read'
+ )
+ """)
+
+ spark
+ .range(1000)
+ .selectExpr("CAST(id AS INT)", "CAST(id * 1.5 AS DOUBLE) as value")
+ .coalesce(1)
+ .write
+ .format("iceberg")
+ .mode("append")
+ .saveAsTable("test_cat.db.delete_bytes_test")
+
+ // Scan before deletes: data files only
+ val dfBefore = spark.sql("SELECT * FROM test_cat.db.delete_bytes_test")
+ val scanBefore = dfBefore.queryExecution.executedPlan
+ .collectLeaves()
+ .collect { case s: CometIcebergNativeScanExec => s }
+ .head
+ dfBefore.collect()
+ val bytesBefore = scanBefore.metrics("bytes_scanned").value
+ assert(bytesBefore > 0, s"bytes_scanned before deletes should be > 0,
got $bytesBefore")
+
+ // Create position delete files
+ spark.sql("DELETE FROM test_cat.db.delete_bytes_test WHERE id < 100")
Review Comment:
👍
--
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]
