Skip to content

[fix](cloud) fix routine load job progress cache incorrect in cloud mode #39313

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
dataroaring merged 1 commit into from
Aug 14, 2024
Merged

[fix](cloud) fix routine load job progress cache incorrect in cloud mode #39313

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
23 changes: 21 additions & 2 deletions fe/fe-core/src/main/java/org/apache/doris/load/routineload/KafkaProgress.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@

package org.apache.doris.load.routineload;

import org.apache.doris.common.Config;
import org.apache.doris.common.DdlException;
import org.apache.doris.common.Pair;
import org.apache.doris.common.util.DebugUtil;
Expand All @@ -36,6 +37,7 @@
import java.util.Map;
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.ConcurrentMap;
import java.util.concurrent.locks.ReentrantLock;

/**
* this is description of kafka routine load progress
Expand All @@ -58,6 +60,8 @@ public class KafkaProgress extends RoutineLoadProgress {
@SerializedName(value = "pito")
private ConcurrentMap<Integer, Long> partitionIdToOffset = Maps.newConcurrentMap();

private ReentrantLock lock = new ReentrantLock(true);

public KafkaProgress() {
super(LoadDataSourceType.KAFKA);
}
Expand Down Expand Up @@ -208,9 +212,24 @@ public String toJsonString() {
@Override
public void update(RLTaskTxnCommitAttachment attachment) {
KafkaProgress newProgress = (KafkaProgress) attachment.getProgress();

// + 1 to point to the next msg offset to be consumed
newProgress.partitionIdToOffset.entrySet().stream()
.forEach(entity -> this.partitionIdToOffset.put(entity.getKey(), entity.getValue() + 1));
if (Config.isCloudMode()) {
lock.lock();
try {
newProgress.partitionIdToOffset.forEach((partitionId, newOffset) -> {
this.partitionIdToOffset.compute(partitionId, (key, oldOffset) -> {
return (oldOffset == null || newOffset + 1 > oldOffset) ? newOffset + 1 : oldOffset;
});
});
} finally {
lock.unlock();
}
} else {
newProgress.partitionIdToOffset.entrySet().stream()
.forEach(entity -> this.partitionIdToOffset.put(entity.getKey(), entity.getValue() + 1));
}

if (LOG.isDebugEnabled()) {
LOG.debug("update kafka progress: {}, task: {}, job: {}",
newProgress.toJsonString(), DebugUtil.printId(attachment.getTaskId()), attachment.getJobId());
Expand Down