Skip to content

[SPARK-53289][SQL] Invoke cancelJobsWithTag before start passing the SparkListenerSQLExecutionEnd event to prevent execution of canceled tasks. #52039

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
JkSelf wants to merge 5 commits into
base: master
Choose a base branch
from
Open

[SPARK-53289][SQL] Invoke cancelJobsWithTag before start passing the SparkListenerSQLExecutionEnd event to prevent execution of canceled tasks. #52039

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b3fb5ef
Invoke cancelJobGroup before start passing the ExecutionEnd event to …
JkSelf Aug 15, 2025
3b57ceb
Resolve comments
JkSelf Aug 18, 2025
3b27093
Resolve comments
JkSelf Aug 19, 2025
9794463
Resolve comments
JkSelf Aug 20, 2025
8c6344f
log
JkSelf Nov 12, 2025
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
36 changes: 36 additions & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/SQLExecution.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,6 +100,20 @@ object SQLExecution extends Logging {
if (sc.getLocalProperty(EXECUTION_ROOT_ID_KEY) == null) {
sc.setLocalProperty(EXECUTION_ROOT_ID_KEY, executionId.toString)
sc.addJobTag(executionIdJobTag(sparkSession, executionId))
logWarning("EXECUTION_ROOT_ID_KEY is null and addJobTag :" +
" " + executionIdJobTag(sparkSession, executionId) + " " +" " +
"the executionId is " + executionId + "" +
"and the rootExecutionId is " +
"" + sc.getLocalProperty(EXECUTION_ROOT_ID_KEY) +
" and the thread is " + Thread.currentThread().getId + "" +
" local property hash is " + sc.localProperties.hashCode())
} else {
logWarning("EXECUTION_ROOT_ID_KEY is not null and " +
"the executionId is " + executionId + "" +
"and the rootExecutionId is " +
"" + sc.getLocalProperty(EXECUTION_ROOT_ID_KEY) + " " +
" and the thread is " + Thread.currentThread().getId + "" +
" local property hash is " + sc.localProperties.hashCode())
}
val rootExecutionId = sc.getLocalProperty(EXECUTION_ROOT_ID_KEY).toLong
executionIdToQueryExecution.put(executionId, queryExecution)
Expand Down Expand Up @@ -211,6 +225,17 @@ object SQLExecution extends Logging {
}
}
}

// Cancel all spark jobs associated with this executionID, but only if it's the
// root execution.

// TODO: Consider enhancing this logic to cancel jobs earlier when nested
// query executions are completed.
if (executionId == rootExecutionId) {
sparkSession.sparkContext.cancelJobsWithTag(
executionIdJobTag(sparkSession, executionId))
}

val event = SparkListenerSQLExecutionEnd(
executionId,
System.currentTimeMillis(),
Expand Down Expand Up @@ -238,6 +263,17 @@ object SQLExecution extends Logging {
if (sc.getLocalProperty(EXECUTION_ROOT_ID_KEY) == executionId.toString) {
sc.setLocalProperty(EXECUTION_ROOT_ID_KEY, null)
sc.removeJobTag(executionIdJobTag(sparkSession, executionId))
logWarning("if branch removing the jobTag " +
"" + executionIdJobTag(sparkSession, executionId) + " thread is " +
"" + Thread.currentThread().getId + " executionId is " + executionId +
" rootExecutionId is " + sc.getLocalProperty(EXECUTION_ROOT_ID_KEY) + "" +
" local property hash is " + sc.localProperties.hashCode())
} else {
logWarning("not removing the jobTag " +
"" + executionIdJobTag(sparkSession, executionId) + " thread is " +
"" + Thread.currentThread().getId + " executionId is " + executionId +
" rootExecutionId is " + sc.getLocalProperty(EXECUTION_ROOT_ID_KEY) + "" +
" local property hash is " + sc.localProperties.hashCode())
}
sc.setLocalProperty(SPARK_JOB_INTERRUPT_ON_CANCEL, originalInterruptOnCancel)
}
Expand Down