Skip to content

Spark 4.1: Separate compaction and main operations #15301

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

Merged
aokolnychyi merged 4 commits into from
Feb 17, 2026
Merged

Spark 4.1: Separate compaction and main operations #15301

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d2c7cd5
Spark 4.1: Separate compaction and main operations
aokolnychyi Feb 11, 2026
f73b71c
Rework checks for table cache
aokolnychyi Feb 12, 2026
d5991fe
Remove unnecessary change
aokolnychyi Feb 16, 2026
11639f5
Remove no longer used local vars
aokolnychyi Feb 16, 2026
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
10 changes: 5 additions & 5 deletions .../test/java/org/apache/iceberg/spark/extensions/TestMetaColumnProjectionWithStageScan.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@
import org.apache.iceberg.spark.Spark3Util;
import org.apache.iceberg.spark.SparkCatalogConfig;
import org.apache.iceberg.spark.SparkReadOptions;
import org.apache.iceberg.spark.SparkTableCache;
import org.apache.iceberg.spark.source.SimpleRecord;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
Expand Down Expand Up @@ -88,32 +89,31 @@ public void testReadStageTableMeta() throws Exception {

Table table = Spark3Util.loadIcebergTable(spark, tableName);
table.refresh();
String tableLocation = table.location();

try (CloseableIterable<ScanTask> tasks = table.newBatchScan().planFiles()) {
String fileSetID = UUID.randomUUID().toString();
SparkTableCache.get().add(fileSetID, table);
stageTask(table, fileSetID, tasks);
Dataset<Row> scanDF2 =
spark
.read()
.format("iceberg")
.option(SparkReadOptions.FILE_OPEN_COST, "0")
.option(SparkReadOptions.SCAN_TASK_SET_ID, fileSetID)
.load(tableLocation);
.load(fileSetID);

assertThat(scanDF2.columns()).hasSize(2);
}

try (CloseableIterable<ScanTask> tasks = table.newBatchScan().planFiles()) {
String fileSetID = UUID.randomUUID().toString();
SparkTableCache.get().add(fileSetID, table);
stageTask(table, fileSetID, tasks);
Dataset<Row> scanDF =
spark
.read()
.format("iceberg")
.option(SparkReadOptions.FILE_OPEN_COST, "0")
.option(SparkReadOptions.SCAN_TASK_SET_ID, fileSetID)
.load(tableLocation)
.load(fileSetID)
.select("*", "_pos");

List<Row> rows = scanDF.collectAsList();
Expand Down
15 changes: 12 additions & 3 deletions ...ions/src/test/java/org/apache/iceberg/spark/extensions/TestRewriteDataFilesProcedure.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -830,7 +830,10 @@ public void testBinPackTableWithSpecialChars() {
List<Object[]> actualRecords = currentData(tableName(QUOTED_SPECIAL_CHARS_TABLE_NAME));
assertEquals("Data after compaction should not change", expectedRecords, actualRecords);

assertThat(SparkTableCache.get().size()).as("Table cache must be empty").isZero();
Table table = validationCatalog.loadTable(identifier);
assertThat(SparkTableCache.get().tables())
.as("Table cache must not contain the test table")
.noneMatch(cachedTable -> cachedTable.uuid().equals(table.uuid()));
}

@TestTemplate
Expand Down Expand Up @@ -870,7 +873,10 @@ public void testSortTableWithSpecialChars() {
List<Object[]> actualRecords = currentData(tableName(QUOTED_SPECIAL_CHARS_TABLE_NAME));
assertEquals("Data after compaction should not change", expectedRecords, actualRecords);

assertThat(SparkTableCache.get().size()).as("Table cache must be empty").isZero();
Table table = validationCatalog.loadTable(identifier);
assertThat(SparkTableCache.get().tables())
.as("Table cache must not contain the test table")
.noneMatch(cachedTable -> cachedTable.uuid().equals(table.uuid()));
}

@TestTemplate
Expand Down Expand Up @@ -910,7 +916,10 @@ public void testZOrderTableWithSpecialChars() {
List<Object[]> actualRecords = currentData(tableName(QUOTED_SPECIAL_CHARS_TABLE_NAME));
assertEquals("Data after compaction should not change", expectedRecords, actualRecords);

assertThat(SparkTableCache.get().size()).as("Table cache must be empty").isZero();
Table table = validationCatalog.loadTable(identifier);
assertThat(SparkTableCache.get().tables())
.as("Table cache must not contain the test table")
.noneMatch(cachedTable -> cachedTable.uuid().equals(table.uuid()));
}

@TestTemplate
Expand Down
257 changes: 0 additions & 257 deletions spark/v4.1/spark/src/main/java/org/apache/iceberg/spark/SparkCachedTableCatalog.java
View file
Open in desktop

This file was deleted.

4 changes: 0 additions & 4 deletions spark/v4.1/spark/src/main/java/org/apache/iceberg/spark/SparkReadConf.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,10 +131,6 @@ public String tag() {
return confParser.stringConf().option(SparkReadOptions.TAG).parseOptional();
}

public String scanTaskSetId() {
return confParser.stringConf().option(SparkReadOptions.SCAN_TASK_SET_ID).parseOptional();
}

public boolean streamingSkipDeleteSnapshots() {
return confParser
.booleanConf()
Expand Down
3 changes: 0 additions & 3 deletions spark/v4.1/spark/src/main/java/org/apache/iceberg/spark/SparkReadOptions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,9 +62,6 @@ private SparkReadOptions() {}
// Overrides the table's read.parquet.vectorization.batch-size
public static final String VECTORIZATION_BATCH_SIZE = "batch-size";

// Set ID that is used to fetch scan tasks
public static final String SCAN_TASK_SET_ID = "scan-task-set-id";

// skip snapshots of type delete while reading stream out of iceberg table
public static final String STREAMING_SKIP_DELETE_SNAPSHOTS = "streaming-skip-delete-snapshots";
public static final boolean STREAMING_SKIP_DELETE_SNAPSHOTS_DEFAULT = false;
Expand Down
Loading