Skip to content

Core, Spark: Fix incorrect partial commit failure count in rewrite data files #16970

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
john801205 wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Core, Spark: Fix incorrect partial commit failure count in rewrite data files #16970

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
69d1156
Core, Spark: Fix incorrect partial commit failure count in rewrite da…
john801205 Jun 26, 2026
c4c6538
add integration tests
john801205 Jun 26, 2026
f3805c2
Update comment for clarity
john801205 Jun 30, 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
7 changes: 4 additions & 3 deletions core/src/main/java/org/apache/iceberg/actions/BaseCommitService.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import java.util.concurrent.Executors;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.atomic.AtomicBoolean;
import java.util.concurrent.atomic.AtomicInteger;
import org.apache.iceberg.Table;
import org.apache.iceberg.relocated.com.google.common.annotations.VisibleForTesting;
import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
Expand Down Expand Up @@ -60,7 +61,7 @@ abstract class BaseCommitService<T> implements Closeable {
private final int rewritesPerCommit;
private final AtomicBoolean running = new AtomicBoolean(false);
private final long timeoutInMS;
private int succeededCommits = 0;
private final AtomicInteger succeededCommits = new AtomicInteger(0);

/**
* Constructs a {@link BaseCommitService}
Expand Down Expand Up @@ -228,7 +229,7 @@ private void commitReadyCommitGroups() {
try {
commitOrClean(batch);
committedRewrites.addAll(batch);
succeededCommits++;
succeededCommits.incrementAndGet();
} catch (Exception e) {
LOG.error("Failure during rewrite commit process, partial progress enabled. Ignoring", e);
}
Expand All @@ -237,7 +238,7 @@ private void commitReadyCommitGroups() {
}

public int succeededCommits() {
return succeededCommits;
return succeededCommits.get();
}

@VisibleForTesting
Expand Down
3 changes: 2 additions & 1 deletion ...3.5/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteDataFilesSparkAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,8 @@ private Builder doExecuteWithPartialProgress(
// stop commit service
commitService.close();

int totalCommits = Math.min(plan.totalGroupCount(), maxCommits);
int totalCommits =
IntMath.divide(plan.totalGroupCount(), groupsPerCommit, RoundingMode.CEILING);
int failedCommits = totalCommits - commitService.succeededCommits();
if (failedCommits > 0 && failedCommits <= maxFailedCommits) {
LOG.warn(
Expand Down
34 changes: 34 additions & 0 deletions ...v3.5/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteDataFilesAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1441,6 +1441,40 @@ public void testParallelPartialProgressWithMaxCommitsLargerThanTotalGroupCount()
shouldHaveACleanCache(table);
}

@TestTemplate
public void testParallelPartialProgressWithTotalCommitsLessThanMaxCommits() {
Table table = createTable(20);
int fileSize = averageFileSize(table);

table.updateProperties().set(COMMIT_NUM_RETRIES, "10").commit();

List<Object[]> originalData = currentData();

RewriteDataFilesSparkAction rewrite =
basicRewrite(table)
.option(
RewriteDataFiles.MAX_FILE_GROUP_SIZE_BYTES, Integer.toString(fileSize * 2 + 1000))
.option(RewriteDataFiles.MAX_CONCURRENT_FILE_GROUP_REWRITES, "2")
.option(RewriteDataFiles.PARTIAL_PROGRESS_ENABLED, "true")
// Since we can have at most one commit per 2 file groups and there
// are only 10 file groups, actual number of commits is 5.
.option(RewriteDataFiles.PARTIAL_PROGRESS_MAX_COMMITS, "7")
.option(RewriteDataFiles.PARTIAL_PROGRESS_MAX_FAILED_COMMITS, "0");

RewriteDataFiles.Result result = rewrite.execute();
assertThat(result.rewriteResults()).hasSize(10);
assertThat(result.rewriteFailures()).hasSize(0);

List<Object[]> postRewriteData = currentData();
assertEquals("We shouldn't have changed the data", originalData, postRewriteData);

// With 10 original groups and max commits of 7, we have 2 groups per commit.
// That produces 5 rewrite commits plus the initial snapshot (6 snapshots total).
shouldHaveSnapshots(table, 6);
shouldHaveNoOrphans(table);
shouldHaveACleanCache(table);
}

@TestTemplate
public void testInvalidOptions() {
Table table = createTable(20);
Expand Down
3 changes: 2 additions & 1 deletion ...4.0/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteDataFilesSparkAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,8 @@ private Builder doExecuteWithPartialProgress(
// stop commit service
commitService.close();

int totalCommits = Math.min(plan.totalGroupCount(), maxCommits);
int totalCommits =
IntMath.divide(plan.totalGroupCount(), groupsPerCommit, RoundingMode.CEILING);
int failedCommits = totalCommits - commitService.succeededCommits();
if (failedCommits > 0 && failedCommits <= maxFailedCommits) {
LOG.warn(
Expand Down
34 changes: 34 additions & 0 deletions ...v4.0/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteDataFilesAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1442,6 +1442,40 @@ public void testParallelPartialProgressWithMaxCommitsLargerThanTotalGroupCount()
shouldHaveACleanCache(table);
}

@TestTemplate
public void testParallelPartialProgressWithTotalCommitsLessThanMaxCommits() {
Table table = createTable(20);
int fileSize = averageFileSize(table);

table.updateProperties().set(COMMIT_NUM_RETRIES, "10").commit();

List<Object[]> originalData = currentData();

RewriteDataFilesSparkAction rewrite =
basicRewrite(table)
.option(
RewriteDataFiles.MAX_FILE_GROUP_SIZE_BYTES, Integer.toString(fileSize * 2 + 1000))
.option(RewriteDataFiles.MAX_CONCURRENT_FILE_GROUP_REWRITES, "2")
.option(RewriteDataFiles.PARTIAL_PROGRESS_ENABLED, "true")
// Since we can have at most one commit per 2 file groups and there
// are only 10 file groups, actual number of commits is 5.
.option(RewriteDataFiles.PARTIAL_PROGRESS_MAX_COMMITS, "7")
.option(RewriteDataFiles.PARTIAL_PROGRESS_MAX_FAILED_COMMITS, "0");

RewriteDataFiles.Result result = rewrite.execute();
assertThat(result.rewriteResults()).hasSize(10);
assertThat(result.rewriteFailures()).hasSize(0);

List<Object[]> postRewriteData = currentData();
assertEquals("We shouldn't have changed the data", originalData, postRewriteData);

// With 10 original groups and max commits of 7, we have 2 groups per commit.
// That produces 5 rewrite commits plus the initial snapshot (6 snapshots total).
shouldHaveSnapshots(table, 6);
shouldHaveNoOrphans(table);
shouldHaveACleanCache(table);
}

@TestTemplate
public void testInvalidOptions() {
Table table = createTable(20);
Expand Down
3 changes: 2 additions & 1 deletion ...4.1/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteDataFilesSparkAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,8 @@ private Builder doExecuteWithPartialProgress(
// stop commit service
commitService.close();

int totalCommits = Math.min(plan.totalGroupCount(), maxCommits);
int totalCommits =
IntMath.divide(plan.totalGroupCount(), groupsPerCommit, RoundingMode.CEILING);
int failedCommits = totalCommits - commitService.succeededCommits();
if (failedCommits > 0 && failedCommits <= maxFailedCommits) {
LOG.warn(
Expand Down
34 changes: 34 additions & 0 deletions ...v4.1/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteDataFilesAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1442,6 +1442,40 @@ public void testParallelPartialProgressWithMaxCommitsLargerThanTotalGroupCount()
shouldHaveACleanCache(table);
}

@TestTemplate
public void testParallelPartialProgressWithTotalCommitsLessThanMaxCommits() {
Table table = createTable(20);
int fileSize = averageFileSize(table);

table.updateProperties().set(COMMIT_NUM_RETRIES, "10").commit();

List<Object[]> originalData = currentData();

RewriteDataFilesSparkAction rewrite =
basicRewrite(table)
.option(
RewriteDataFiles.MAX_FILE_GROUP_SIZE_BYTES, Integer.toString(fileSize * 2 + 1000))
.option(RewriteDataFiles.MAX_CONCURRENT_FILE_GROUP_REWRITES, "2")
.option(RewriteDataFiles.PARTIAL_PROGRESS_ENABLED, "true")
// Since we can have at most one commit per 2 file groups and there
// are only 10 file groups, actual number of commits is 5.
.option(RewriteDataFiles.PARTIAL_PROGRESS_MAX_COMMITS, "7")
.option(RewriteDataFiles.PARTIAL_PROGRESS_MAX_FAILED_COMMITS, "0");

RewriteDataFiles.Result result = rewrite.execute();
assertThat(result.rewriteResults()).hasSize(10);
assertThat(result.rewriteFailures()).hasSize(0);

List<Object[]> postRewriteData = currentData();
assertEquals("We shouldn't have changed the data", originalData, postRewriteData);

// With 10 original groups and max commits of 7, we have 2 groups per commit.
// That produces 5 rewrite commits plus the initial snapshot (6 snapshots total).
shouldHaveSnapshots(table, 6);
shouldHaveNoOrphans(table);
shouldHaveACleanCache(table);
}

@TestTemplate
public void testInvalidOptions() {
Table table = createTable(20);
Expand Down