Skip to content
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

Jump to bottom

Spark 3.5: Adapt DeleteFileIndexBenchmark for DVs #11529

Merged
merged 1 commit into from
Nov 15, 2024
Merged

Spark 3.5: Adapt DeleteFileIndexBenchmark for DVs #11529

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
29 changes: 24 additions & 5 deletions spark/v3.5/spark-extensions/src/jmh/java/org/apache/iceberg/DeleteFileIndexBenchmark.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,8 +81,8 @@ public class DeleteFileIndexBenchmark {

private List<DataFile> dataFiles;

@Param({"true", "false"})
private boolean oneToOneMapping;
@Param({"partition", "file", "dv"})
private String type;

@Setup
public void setupBenchmark() throws NoSuchTableException, ParseException {
Expand All @@ -93,10 +93,12 @@ public void setupBenchmark() throws NoSuchTableException, ParseException {
}

private void initDataAndDeletes() {
if (oneToOneMapping) {
if (type.equals("partition")) {
initDataAndPartitionScopedDeletes();
} else if (type.equals("file")) {
initDataAndFileScopedDeletes();
} else {
initDataAndPartitionScopedDeletes();
initDataAndDVs();
}
}

Expand Down Expand Up @@ -183,6 +185,23 @@ private void initDataAndFileScopedDeletes() {
}
}

private void initDataAndDVs() {
for (int partitionOrdinal = 0; partitionOrdinal < NUM_PARTITIONS; partitionOrdinal++) {
StructLike partition = TestHelpers.Row.of(partitionOrdinal);

RowDelta rowDelta = table.newRowDelta();

for (int fileOrdinal = 0; fileOrdinal < NUM_DATA_FILES_PER_PARTITION; fileOrdinal++) {
DataFile dataFile = FileGenerationUtil.generateDataFile(table, partition);
DeleteFile dv = FileGenerationUtil.generateDV(table, dataFile);
rowDelta.addRows(dataFile);
rowDelta.addDeletes(dv);
}

rowDelta.commit();
}
}

private void setupSpark() {
this.spark =
SparkSession.builder()
Expand Down Expand Up @@ -240,7 +259,7 @@ private void initTable() throws NoSuchTableException, ParseException {
TableProperties.DELETE_MODE,
RowLevelOperationMode.MERGE_ON_READ.modeName(),
TableProperties.FORMAT_VERSION,
2);
type.equals("dv") ? 3 : 2);

this.table = Spark3Util.loadIcebergTable(spark, TABLE_NAME);
}
Expand Down