viirya commented on a change in pull request #33239:
URL: https://github.com/apache/spark/pull/33239#discussion_r672584143
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListenerSuite.scala
##########
@@ -852,6 +857,33 @@ class SQLAppStatusListenerSuite extends SharedSparkSession
with JsonTestUtils
assert(metrics.contains(expectedMetric.id))
assert(metrics(expectedMetric.id) === expectedValue)
}
+
+ test("SPARK-36030: Report metrics from Datasource v2 write") {
+ withTempDir { dir =>
+ val statusStore = spark.sharedState.statusStore
+ val oldCount = statusStore.executionsList().size
+
+ val cls = classOf[CustomMetricsDataSource].getName
+ spark.range(10).select('id as 'i, -'id as 'j).write.format(cls)
+ .option("path", dir.getCanonicalPath).mode("append").save()
+
+ // Wait until the new execution is started and being tracked.
+ while (statusStore.executionsCount() < oldCount) {
Review comment:
Switched to `eventually`. Thanks.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatDataWriter.scala
##########
@@ -41,7 +42,8 @@ import org.apache.spark.util.SerializableConfiguration
abstract class FileFormatDataWriter(
description: WriteJobDescription,
taskAttemptContext: TaskAttemptContext,
- committer: FileCommitProtocol) extends DataWriter[InternalRow] {
+ committer: FileCommitProtocol,
+ customMetrics: Map[String, SQLMetric]) extends DataWriter[InternalRow] {
Review comment:
Let me try to add one.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatDataWriter.scala
##########
@@ -41,7 +42,8 @@ import org.apache.spark.util.SerializableConfiguration
abstract class FileFormatDataWriter(
description: WriteJobDescription,
taskAttemptContext: TaskAttemptContext,
- committer: FileCommitProtocol) extends DataWriter[InternalRow] {
+ committer: FileCommitProtocol,
+ customMetrics: Map[String, SQLMetric]) extends DataWriter[InternalRow] {
Review comment:
I added custom metric for writing to InMemory table for test purpose.
The tests are in `FileFormatDataWriterMetricSuite`.
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileFormatDataWriterMetricSuite.scala
##########
@@ -0,0 +1,96 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.spark.sql.execution.datasources
+
+import java.util.Collections
+
+import org.scalatest.BeforeAndAfter
+import org.scalatest.time.SpanSugar._
+
+import org.apache.spark.sql.QueryTest
+import org.apache.spark.sql.connector.catalog.{Identifier,
InMemoryTableCatalog}
+import org.apache.spark.sql.functions.lit
+import org.apache.spark.sql.test.SharedSparkSession
+import org.apache.spark.sql.types.StructType
+
+class FileFormatDataWriterMetricSuite
Review comment:
Yea, I think so.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/metric/CustomMetrics.scala
##########
@@ -51,7 +51,7 @@ object CustomMetrics {
currentMetricsValues: Seq[CustomTaskMetric],
customMetrics: Map[String, SQLMetric]): Unit = {
currentMetricsValues.foreach { metric =>
- customMetrics(metric.name()).set(metric.value())
+ customMetrics.get(metric.name()).map(_.set(metric.value()))
Review comment:
Ok.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/metric/CustomMetrics.scala
##########
@@ -51,7 +51,7 @@ object CustomMetrics {
currentMetricsValues: Seq[CustomTaskMetric],
customMetrics: Map[String, SQLMetric]): Unit = {
currentMetricsValues.foreach { metric =>
- customMetrics(metric.name()).set(metric.value())
+ customMetrics.get(metric.name()).map(_.set(metric.value()))
Review comment:
Added test and updated the method doc. Thanks.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatDataWriter.scala
##########
@@ -79,9 +81,15 @@ abstract class FileFormatDataWriter(
/** Write an iterator of records. */
def writeWithIterator(iterator: Iterator[InternalRow]): Unit = {
+ var count = 0L
Review comment:
sounds good. let me update.
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileFormatDataWriterMetricSuite.scala
##########
@@ -0,0 +1,96 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.spark.sql.execution.datasources
+
+import java.util.Collections
+
+import org.scalatest.BeforeAndAfter
+import org.scalatest.time.SpanSugar._
+
+import org.apache.spark.sql.QueryTest
+import org.apache.spark.sql.connector.catalog.{Identifier,
InMemoryTableCatalog}
+import org.apache.spark.sql.functions.lit
+import org.apache.spark.sql.test.SharedSparkSession
+import org.apache.spark.sql.types.StructType
+
+class FileFormatDataWriterMetricSuite
Review comment:
Ah, right, I was writing tests for custom `FileTable` which uses custom
metrics but may copying some duplicated codes for `FileWrite`, etc. So in the
end I turned to `InMemoryTable` but forgot that `InMemoryTable` doesn't use
`FileWriterFactory`...
I will rename this test suite to `InMemoryTableMetricSuite`.
Let me do a follow up adding tests for `FileTable`. Thanks.
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
