aokolnychyi commented on code in PR #7447:
URL: https://github.com/apache/iceberg/pull/7447#discussion_r1263182514
##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/SparkScan.java:
##########
@@ -170,8 +189,35 @@ public String description() {
table(), branch(), Spark3Util.describe(filterExpressions),
groupingKeyFieldNamesAsString);
}
+ @Override
+ public CustomTaskMetric[] reportDriverMetrics() {
+ ScanReport scanReport = scanReportSupplier != null ?
scanReportSupplier.get() : null;
+ if (scanReport == null) {
Review Comment:
Optional: What about an empty line before `if` to separate this block?
##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/metrics/TaskTotalPlanningDuration.java:
##########
@@ -0,0 +1,48 @@
+/*
+ * 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.iceberg.spark.source.metrics;
+
+import org.apache.iceberg.metrics.ScanReport;
+import org.apache.iceberg.metrics.TimerResult;
+import org.apache.spark.sql.connector.metric.CustomTaskMetric;
+
+public class TaskTotalPlanningDuration implements CustomTaskMetric {
+
+ private final long value;
+
+ private TaskTotalPlanningDuration(long value) {
+ this.value = value;
+ }
+
+ @Override
+ public String name() {
+ return TotalPlanningDuration.NAME;
+ }
+
+ @Override
+ public long value() {
+ return value;
+ }
+
+ public static TaskTotalPlanningDuration from(ScanReport scanReport) {
+ TimerResult timerResult = scanReport.scanMetrics().totalPlanningDuration();
+ long value = timerResult != null ? timerResult.count() : -1;
Review Comment:
Shouldn't this be `totalDuration().toMillis()`? Shall we also use 0 as the
default value?
##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/metrics/TotalFileSize.java:
##########
@@ -0,0 +1,36 @@
+/*
+ * 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.iceberg.spark.source.metrics;
+
+import org.apache.spark.sql.connector.metric.CustomSumMetric;
+
+public class TotalFileSize extends CustomSumMetric {
+
+ static final String NAME = "totalFileSize";
+
+ @Override
+ public String name() {
+ return NAME;
+ }
+
+ @Override
+ public String description() {
+ return "total file size";
Review Comment:
What about `total file size (bytes)`?
##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/metrics/TotalPlanningDuration.java:
##########
@@ -0,0 +1,36 @@
+/*
+ * 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.iceberg.spark.source.metrics;
+
+import org.apache.spark.sql.connector.metric.CustomSumMetric;
+
+public class TotalPlanningDuration extends CustomSumMetric {
+
+ static final String NAME = "totalPlanningDuration";
+
+ @Override
+ public String name() {
+ return NAME;
+ }
+
+ @Override
+ public String description() {
+ return "total planning duration";
Review Comment:
What about adding info on what values we show?
```
total planning duration (ms)
```
##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/metrics/ScannedDataManifests.java:
##########
@@ -0,0 +1,45 @@
+/*
+ * 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.iceberg.spark.source.metrics;
+
+import org.apache.spark.sql.connector.metric.CustomSumMetric;
+
+public class ScannedDataManifests extends CustomSumMetric {
+
+ static final String NAME = "scannedDataManifests";
+
+ @Override
+ public String name() {
+ return NAME;
+ }
+
+ @Override
+ public String description() {
+ return "number of scanned data manifests";
+ }
+
+ @Override
+ public String aggregateTaskMetrics(long[] taskMetrics) {
Review Comment:
This seems redundant as we extend `CustomSumMetric`?
##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/SparkPartitioningAwareScan.java:
##########
@@ -74,9 +76,10 @@ abstract class SparkPartitioningAwareScan<T extends
PartitionScanTask> extends S
Scan<?, ? extends ScanTask, ? extends ScanTaskGroup<?>> scan,
SparkReadConf readConf,
Schema expectedSchema,
- List<Expression> filters) {
+ List<Expression> filters,
+ Supplier<ScanReport> scanReportSupplier) {
Review Comment:
Same comment about the empty line here.
##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/SparkCopyOnWriteScan.java:
##########
@@ -68,9 +71,10 @@ class SparkCopyOnWriteScan extends
SparkPartitioningAwareScan<FileScanTask>
Snapshot snapshot,
SparkReadConf readConf,
Schema expectedSchema,
- List<Expression> filters) {
+ List<Expression> filters,
+ Supplier<ScanReport> scanReportSupplier) {
- super(spark, table, scan, readConf, expectedSchema, filters);
Review Comment:
I see that you removed an empty line before super in `SparkBatchQueryScan`
above. I think that makes sense, could you apply it to this class too for
consistency?
##########
spark/v3.4/spark/src/test/java/org/apache/iceberg/spark/source/TestSparkReadMetrics.java:
##########
@@ -0,0 +1,84 @@
+/*
+ * 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.iceberg.spark.source;
+
+import static scala.collection.JavaConverters.seqAsJavaListConverter;
+
+import java.util.List;
+import java.util.Map;
+import org.apache.iceberg.spark.SparkTestBaseWithCatalog;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.catalyst.analysis.NoSuchTableException;
+import org.apache.spark.sql.execution.SparkPlan;
+import org.apache.spark.sql.execution.metric.SQLMetric;
+import org.assertj.core.api.Assertions;
+import org.junit.After;
+import org.junit.Test;
+import scala.collection.JavaConverters;
+
+public class TestSparkReadMetrics extends SparkTestBaseWithCatalog {
+
+ @After
+ public void removeTables() {
+ sql("DROP TABLE IF EXISTS %s", tableName);
+ }
+
+ @Test
+ public void testReadMetricsForV1Table() throws NoSuchTableException {
+ sql(
+ "CREATE TABLE %s (id BIGINT) USING iceberg TBLPROPERTIES
('format-version'='2')",
+ tableName);
+
+ spark.range(10000).coalesce(1).writeTo(tableName).append();
+ spark.range(10001, 20000).coalesce(1).writeTo(tableName).append();
+
+ Dataset<Row> df = spark.sql(String.format("select * from %s where id <
10000", tableName));
+ df.collect();
+
+ List<SparkPlan> sparkPlans =
+
seqAsJavaListConverter(df.queryExecution().executedPlan().collectLeaves()).asJava();
+ Map<String, SQLMetric> metricsMap =
+
JavaConverters.mapAsJavaMapConverter(sparkPlans.get(0).metrics()).asJava();
+
Assertions.assertThat(metricsMap.get("skippedDataFiles").value()).isEqualTo(1);
+
Assertions.assertThat(metricsMap.get("scannedDataManifests").value()).isEqualTo(2);
+
Assertions.assertThat(metricsMap.get("resultDataFiles").value()).isEqualTo(1);
Review Comment:
I guess some of these were renamed.
##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/metrics/scannedDataFiles.java:
##########
@@ -0,0 +1,36 @@
+/*
+ * 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.iceberg.spark.source.metrics;
+
+import org.apache.spark.sql.connector.metric.CustomSumMetric;
+
+public class scannedDataFiles extends CustomSumMetric {
Review Comment:
Seems like a typo? Should start with a capital letter?
--
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]
