Skip to content

[fix](cloud) fix routine load job stuck if commit transaction failed #40539

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
Sep 11, 2024
Merged

[fix](cloud) fix routine load job stuck if commit transaction failed #40539

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
18 changes: 17 additions & 1 deletion fe/fe-core/src/main/java/org/apache/doris/cloud/transaction/CloudGlobalTransactionMgr.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -505,7 +505,17 @@ private void commitTransaction(long dbId, List<Table> tableList, long transactio
}

final CommitTxnRequest commitTxnRequest = builder.build();
commitTxn(commitTxnRequest, transactionId, is2PC, dbId, tableList);
try {
commitTxn(commitTxnRequest, transactionId, is2PC, dbId, tableList);
} catch (UserException e) {
// For routine load, it is necessary to release the write lock when commit transaction fails,
// otherwise it will cause the lock added in beforeCommitted to not be released.
if (txnCommitAttachment != null && txnCommitAttachment instanceof RLTaskTxnCommitAttachment) {
RLTaskTxnCommitAttachment rlTaskTxnCommitAttachment = (RLTaskTxnCommitAttachment) txnCommitAttachment;
Env.getCurrentEnv().getRoutineLoadManager().getJob(rlTaskTxnCommitAttachment.getJobId()).writeUnlock();
}
throw e;
}
}

private void commitTxn(CommitTxnRequest commitTxnRequest, long transactionId, boolean is2PC, long dbId,
Expand Down Expand Up @@ -1021,6 +1031,12 @@ public void abortTransaction(Long dbId, Long transactionId, String reason,
Preconditions.checkNotNull(abortTxnResponse.getStatus());
} catch (RpcException e) {
LOG.warn("abortTxn failed, transactionId:{}, Exception", transactionId, e);
// For routine load, it is necessary to release the write lock when abort transaction fails,
// otherwise it will cause the lock added in beforeAborted to not be released.
if (txnCommitAttachment != null && txnCommitAttachment instanceof RLTaskTxnCommitAttachment) {
RLTaskTxnCommitAttachment rlTaskTxnCommitAttachment = (RLTaskTxnCommitAttachment) txnCommitAttachment;
Env.getCurrentEnv().getRoutineLoadManager().getJob(rlTaskTxnCommitAttachment.getJobId()).writeUnlock();
}
throw new UserException("abortTxn failed, errMsg:" + e.getMessage());
}

Expand Down
2 changes: 1 addition & 1 deletion fe/fe-core/src/main/java/org/apache/doris/load/routineload/RoutineLoadJob.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -485,7 +485,7 @@ protected void writeLock() {
lock.writeLock().lock();
}

protected void writeUnlock() {
public void writeUnlock() {
lock.writeLock().unlock();
}

Expand Down