Skip to content

Spark 4.0: Display write metrics on SQL UI #13253

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
manuzhang wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Spark 4.0: Display write metrics on SQL UI #13253

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion core/src/main/java/org/apache/iceberg/BaseTable.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import org.apache.iceberg.io.LocationProvider;
import org.apache.iceberg.metrics.LoggingMetricsReporter;
import org.apache.iceberg.metrics.MetricsReporter;
import org.apache.iceberg.metrics.MetricsReporters;
import org.apache.iceberg.relocated.com.google.common.base.Preconditions;

/**
Expand All @@ -41,7 +42,7 @@
public class BaseTable implements Table, HasTableOperations, Serializable {
private final TableOperations ops;
private final String name;
private final MetricsReporter reporter;
private MetricsReporter reporter;

public BaseTable(TableOperations ops, String name) {
this(ops, name, LoggingMetricsReporter.instance());
Expand All @@ -58,6 +59,10 @@ public MetricsReporter reporter() {
return reporter;
}

public void combineMetricsReporter(MetricsReporter metricsReporter) {
this.reporter = MetricsReporters.combine(this.reporter, metricsReporter);
}

@Override
public TableOperations operations() {
return ops;
Expand Down
10 changes: 10 additions & 0 deletions core/src/main/java/org/apache/iceberg/metrics/InMemoryMetricsReporter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
*/
package org.apache.iceberg.metrics;

import javax.annotation.Nullable;
import org.apache.iceberg.relocated.com.google.common.base.Preconditions;

public class InMemoryMetricsReporter implements MetricsReporter {
Expand All @@ -35,4 +36,13 @@ public ScanReport scanReport() {
"Metrics report is not a scan report");
return (ScanReport) metricsReport;
}

@Nullable
public CommitReport commitReport() {
if (metricsReport instanceof CommitReport) {
return (CommitReport) metricsReport;
} else {
return null;
}
}
}
Copy link

@nbdevos25 nbdevos25 Nov 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: should this be

if (!metricsReport instanceof CommitReport) {
     return null
 }
 return (CommitReport) metricsReport;

Copy link
Member Author

@manuzhang manuzhang Nov 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why do you think this is better?

Copy link

@nbdevos25 nbdevos25 Nov 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

more readable (it is a style thing); hence tagged with nit

Copy link
Member Author

@manuzhang manuzhang Nov 17, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I got it it's a style thing but not sure why what you suggests is better.

Copy link

@nbdevos25 nbdevos25 Nov 17, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more. 

if (!metricsReport instanceof CommitReport) {
     return null
 }
 return (CommitReport) metricsReport;

looks less verbose to me

127 changes: 127 additions & 0 deletions spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/SparkWriteUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,10 +23,38 @@
import static org.apache.spark.sql.connector.write.RowLevelOperation.Command.UPDATE;

import java.util.Arrays;
import java.util.List;
import org.apache.iceberg.DistributionMode;
import org.apache.iceberg.MetadataColumns;
import org.apache.iceberg.Table;
import org.apache.iceberg.metrics.CommitMetricsResult;
import org.apache.iceberg.metrics.CommitReport;
import org.apache.iceberg.metrics.CounterResult;
import org.apache.iceberg.metrics.InMemoryMetricsReporter;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.relocated.com.google.common.collect.ObjectArrays;
import org.apache.iceberg.spark.source.metrics.AddedDataFiles;
import org.apache.iceberg.spark.source.metrics.AddedDeleteFiles;
import org.apache.iceberg.spark.source.metrics.AddedEqualityDeleteFiles;
import org.apache.iceberg.spark.source.metrics.AddedEqualityDeletes;
import org.apache.iceberg.spark.source.metrics.AddedFileSizeInBytes;
import org.apache.iceberg.spark.source.metrics.AddedPositionalDeleteFiles;
import org.apache.iceberg.spark.source.metrics.AddedPositionalDeletes;
import org.apache.iceberg.spark.source.metrics.AddedRecords;
import org.apache.iceberg.spark.source.metrics.RemovedDataFiles;
import org.apache.iceberg.spark.source.metrics.RemovedDeleteFiles;
import org.apache.iceberg.spark.source.metrics.RemovedEqualityDeleteFiles;
import org.apache.iceberg.spark.source.metrics.RemovedEqualityDeletes;
import org.apache.iceberg.spark.source.metrics.RemovedFileSizeInBytes;
import org.apache.iceberg.spark.source.metrics.RemovedPositionalDeleteFiles;
import org.apache.iceberg.spark.source.metrics.RemovedPositionalDeletes;
import org.apache.iceberg.spark.source.metrics.RemovedRecords;
import org.apache.iceberg.spark.source.metrics.TotalDataFiles;
import org.apache.iceberg.spark.source.metrics.TotalDeleteFiles;
import org.apache.iceberg.spark.source.metrics.TotalEqualityDeletes;
import org.apache.iceberg.spark.source.metrics.TotalFileSizeInBytes;
import org.apache.iceberg.spark.source.metrics.TotalPositionalDeletes;
import org.apache.iceberg.spark.source.metrics.TotalRecords;
import org.apache.iceberg.types.Types;
import org.apache.iceberg.util.SortOrderUtil;
import org.apache.spark.sql.connector.distributions.Distribution;
Expand All @@ -36,6 +64,8 @@
import org.apache.spark.sql.connector.expressions.NamedReference;
import org.apache.spark.sql.connector.expressions.SortDirection;
import org.apache.spark.sql.connector.expressions.SortOrder;
import org.apache.spark.sql.connector.metric.CustomMetric;
import org.apache.spark.sql.connector.metric.CustomTaskMetric;
import org.apache.spark.sql.connector.write.RowLevelOperation.Command;

/**
Expand Down Expand Up @@ -256,4 +286,101 @@ private static SortOrder[] orderBy(Expression... exprs) {
private static SortOrder sort(Expression expr) {
return Expressions.sort(expr, SortDirection.ASCENDING);
}

public static CustomMetric[] supportedCustomMetrics() {
return new CustomMetric[] {
new AddedDataFiles(),
new AddedDeleteFiles(),
new AddedEqualityDeletes(),
new AddedEqualityDeleteFiles(),
new AddedFileSizeInBytes(),
new AddedPositionalDeletes(),
new AddedPositionalDeleteFiles(),
new AddedRecords(),
new RemovedDataFiles(),
new RemovedDeleteFiles(),
new RemovedRecords(),
new RemovedEqualityDeleteFiles(),
new RemovedEqualityDeletes(),
new RemovedFileSizeInBytes(),
new RemovedPositionalDeleteFiles(),
new RemovedPositionalDeletes(),
new TotalDataFiles(),
new TotalDeleteFiles(),
new TotalEqualityDeletes(),
new TotalFileSizeInBytes(),
new TotalPositionalDeletes(),
new TotalRecords()
};
}

public static CustomTaskMetric[] customTaskMetrics(InMemoryMetricsReporter metricsReporter) {
List<CustomTaskMetric> taskMetrics = Lists.newArrayList();
if (metricsReporter != null) {
CommitReport commitReport = metricsReporter.commitReport();
if (commitReport != null) {
CommitMetricsResult metricsResult = commitReport.commitMetrics();
addMetricValue(new AddedDataFiles(), metricsResult.addedDataFiles(), taskMetrics);
addMetricValue(new AddedDeleteFiles(), metricsResult.addedDeleteFiles(), taskMetrics);
addMetricValue(
new AddedEqualityDeletes(), metricsResult.addedEqualityDeletes(), taskMetrics);
addMetricValue(
new AddedEqualityDeleteFiles(), metricsResult.addedEqualityDeleteFiles(), taskMetrics);
addMetricValue(
new AddedFileSizeInBytes(), metricsResult.addedFilesSizeInBytes(), taskMetrics);
addMetricValue(
new AddedPositionalDeletes(), metricsResult.addedPositionalDeletes(), taskMetrics);
addMetricValue(
new AddedPositionalDeleteFiles(),
metricsResult.addedPositionalDeleteFiles(),
taskMetrics);
addMetricValue(new AddedRecords(), metricsResult.addedRecords(), taskMetrics);
addMetricValue(new RemovedDataFiles(), metricsResult.removedDataFiles(), taskMetrics);
addMetricValue(new RemovedDeleteFiles(), metricsResult.removedDeleteFiles(), taskMetrics);
addMetricValue(new RemovedRecords(), metricsResult.removedRecords(), taskMetrics);
addMetricValue(
new RemovedEqualityDeleteFiles(),
metricsResult.removedEqualityDeleteFiles(),
taskMetrics);
addMetricValue(
new RemovedEqualityDeletes(), metricsResult.removedEqualityDeletes(), taskMetrics);
addMetricValue(
new RemovedFileSizeInBytes(), metricsResult.removedFilesSizeInBytes(), taskMetrics);
addMetricValue(
new RemovedPositionalDeleteFiles(),
metricsResult.removedPositionalDeleteFiles(),
taskMetrics);
addMetricValue(
new RemovedPositionalDeletes(), metricsResult.removedPositionalDeletes(), taskMetrics);
addMetricValue(new TotalDataFiles(), metricsResult.totalDataFiles(), taskMetrics);
addMetricValue(new TotalDeleteFiles(), metricsResult.totalDeleteFiles(), taskMetrics);
addMetricValue(
new TotalEqualityDeletes(), metricsResult.totalEqualityDeletes(), taskMetrics);
addMetricValue(
new TotalFileSizeInBytes(), metricsResult.totalFilesSizeInBytes(), taskMetrics);
addMetricValue(
new TotalPositionalDeletes(), metricsResult.totalPositionalDeletes(), taskMetrics);
addMetricValue(new TotalRecords(), metricsResult.totalRecords(), taskMetrics);
}
}
return taskMetrics.toArray(new CustomTaskMetric[0]);
}

private static void addMetricValue(
CustomMetric metric, CounterResult result, List<CustomTaskMetric> taskMetrics) {
if (result != null) {
taskMetrics.add(
new CustomTaskMetric() {
@Override
public String name() {
return metric.name();
}

@Override
public long value() {
return result.value();
}
});
}
}
}
21 changes: 21 additions & 0 deletions spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/source/SparkPositionDeltaWrite.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
import java.util.Locale;
import java.util.Map;
import java.util.function.Function;
import org.apache.iceberg.BaseTable;
import org.apache.iceberg.ContentFile;
import org.apache.iceberg.DataFile;
import org.apache.iceberg.DeleteFile;
Expand Down Expand Up @@ -66,12 +67,14 @@
import org.apache.iceberg.io.PartitioningWriter;
import org.apache.iceberg.io.PositionDeltaWriter;
import org.apache.iceberg.io.WriteResult;
import org.apache.iceberg.metrics.InMemoryMetricsReporter;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.spark.CommitMetadata;
import org.apache.iceberg.spark.SparkSchemaUtil;
import org.apache.iceberg.spark.SparkWriteConf;
import org.apache.iceberg.spark.SparkWriteRequirements;
import org.apache.iceberg.spark.SparkWriteUtil;
import org.apache.iceberg.types.Types;
import org.apache.iceberg.util.CharSequenceSet;
import org.apache.iceberg.util.DeleteFileSet;
Expand All @@ -83,6 +86,8 @@
import org.apache.spark.sql.catalyst.expressions.JoinedRow;
import org.apache.spark.sql.connector.distributions.Distribution;
import org.apache.spark.sql.connector.expressions.SortOrder;
import org.apache.spark.sql.connector.metric.CustomMetric;
import org.apache.spark.sql.connector.metric.CustomTaskMetric;
import org.apache.spark.sql.connector.write.DeltaBatchWrite;
import org.apache.spark.sql.connector.write.DeltaWrite;
import org.apache.spark.sql.connector.write.DeltaWriter;
Expand Down Expand Up @@ -116,6 +121,7 @@ class SparkPositionDeltaWrite implements DeltaWrite, RequiresDistributionAndOrde
private final Map<String, String> writeProperties;

private boolean cleanupOnAbort = false;
private InMemoryMetricsReporter metricsReporter;

SparkPositionDeltaWrite(
SparkSession spark,
Expand All @@ -139,6 +145,11 @@ class SparkPositionDeltaWrite implements DeltaWrite, RequiresDistributionAndOrde
this.writeRequirements = writeConf.positionDeltaRequirements(command);
this.context = new Context(dataSchema, writeConf, info, writeRequirements);
this.writeProperties = writeConf.writeProperties();

if (this.table instanceof BaseTable) {
this.metricsReporter = new InMemoryMetricsReporter();
((BaseTable) this.table).combineMetricsReporter(metricsReporter);
}
}

@Override
Expand Down Expand Up @@ -172,6 +183,16 @@ public DeltaBatchWrite toBatch() {
return new PositionDeltaBatchWrite();
}

@Override
public CustomMetric[] supportedCustomMetrics() {
return SparkWriteUtil.supportedCustomMetrics();
}

@Override
public CustomTaskMetric[] reportDriverMetrics() {
return SparkWriteUtil.customTaskMetrics(metricsReporter);
}

private class PositionDeltaBatchWrite implements DeltaBatchWrite {

@Override
Expand Down
15 changes: 15 additions & 0 deletions spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/source/SparkWrite.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
import java.util.function.Function;
import java.util.stream.Collectors;
import org.apache.iceberg.AppendFiles;
import org.apache.iceberg.BaseTable;
import org.apache.iceberg.DataFile;
import org.apache.iceberg.FileFormat;
import org.apache.iceberg.FileScanTask;
Expand All @@ -53,12 +54,14 @@
import org.apache.iceberg.io.OutputFileFactory;
import org.apache.iceberg.io.PartitioningWriter;
import org.apache.iceberg.io.RollingDataWriter;
import org.apache.iceberg.metrics.InMemoryMetricsReporter;
import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.spark.CommitMetadata;
import org.apache.iceberg.spark.FileRewriteCoordinator;
import org.apache.iceberg.spark.SparkWriteConf;
import org.apache.iceberg.spark.SparkWriteRequirements;
import org.apache.iceberg.spark.SparkWriteUtil;
import org.apache.iceberg.util.ContentFileUtil;
import org.apache.iceberg.util.DataFileSet;
import org.apache.iceberg.util.DeleteFileSet;
Expand All @@ -72,6 +75,7 @@
import org.apache.spark.sql.catalyst.expressions.JoinedRow;
import org.apache.spark.sql.connector.distributions.Distribution;
import org.apache.spark.sql.connector.expressions.SortOrder;
import org.apache.spark.sql.connector.metric.CustomTaskMetric;
import org.apache.spark.sql.connector.write.BatchWrite;
import org.apache.spark.sql.connector.write.DataWriter;
import org.apache.spark.sql.connector.write.DataWriterFactory;
Expand Down Expand Up @@ -108,6 +112,7 @@ abstract class SparkWrite implements Write, RequiresDistributionAndOrdering {
private final Map<String, String> writeProperties;

private boolean cleanupOnAbort = false;
private InMemoryMetricsReporter metricsReporter;

SparkWrite(
SparkSession spark,
Expand Down Expand Up @@ -135,6 +140,11 @@ abstract class SparkWrite implements Write, RequiresDistributionAndOrdering {
this.writeRequirements = writeRequirements;
this.outputSpecId = writeConf.outputSpecId();
this.writeProperties = writeConf.writeProperties();

if (this.table instanceof BaseTable) {
this.metricsReporter = new InMemoryMetricsReporter();
((BaseTable) this.table).combineMetricsReporter(metricsReporter);
}
}

@Override
Expand Down Expand Up @@ -265,6 +275,11 @@ private DataFileSet files(WriterCommitMessage[] messages) {
return files;
}

@Override
public CustomTaskMetric[] reportDriverMetrics() {
return SparkWriteUtil.customTaskMetrics(metricsReporter);
}

@Override
public String toString() {
return String.format("IcebergWrite(table=%s, format=%s)", table, format);
Expand Down
7 changes: 7 additions & 0 deletions spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/source/SparkWriteBuilder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,8 +32,10 @@
import org.apache.iceberg.spark.SparkUtil;
import org.apache.iceberg.spark.SparkWriteConf;
import org.apache.iceberg.spark.SparkWriteRequirements;
import org.apache.iceberg.spark.SparkWriteUtil;
import org.apache.iceberg.types.TypeUtil;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.connector.metric.CustomMetric;
import org.apache.spark.sql.connector.read.Scan;
import org.apache.spark.sql.connector.write.BatchWrite;
import org.apache.spark.sql.connector.write.LogicalWriteInfo;
Expand Down Expand Up @@ -186,6 +188,11 @@ public StreamingWrite toStreaming() {
return asStreamingAppend();
}
}

@Override
public CustomMetric[] supportedCustomMetrics() {
return SparkWriteUtil.supportedCustomMetrics();
}
};
}

Expand Down
36 changes: 36 additions & 0 deletions spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/source/metrics/AddedDataFiles.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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 AddedDataFiles extends CustomSumMetric {

static final String NAME = "addedDataFiles";

@Override
public String name() {
return NAME;
}

@Override
public String description() {
return "number of added data files";
}
}
Loading