juliuszsompolski commented on a change in pull request #28544:
URL: https://github.com/apache/spark/pull/28544#discussion_r427196726
##########
File path:
sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/HiveThriftServer2Listener.scala
##########
@@ -131,60 +132,81 @@ private[thriftserver] class HiveThriftServer2Listener(
updateLiveStore(session)
}
- private def onSessionClosed(e: SparkListenerThriftServerSessionClosed): Unit
= {
- val session = sessionList.get(e.sessionId)
- session.finishTimestamp = e.finishTime
- updateStoreWithTriggerEnabled(session)
- sessionList.remove(e.sessionId)
- }
+ private def onSessionClosed(e: SparkListenerThriftServerSessionClosed): Unit
=
+ Option(sessionList.get(e.sessionId)) match {
+ case None => logWarning(s"onSessionClosed called with unknown session
id: ${e.sessionId}")
+ case Some(sessionData) =>
+ val session = sessionData
+ session.finishTimestamp = e.finishTime
+ updateStoreWithTriggerEnabled(session)
+ sessionList.remove(e.sessionId)
+ }
- private def onOperationStart(e: SparkListenerThriftServerOperationStart):
Unit = {
- val info = getOrCreateExecution(
- e.id,
- e.statement,
- e.sessionId,
- e.startTime,
- e.userName)
-
- info.state = ExecutionState.STARTED
- executionList.put(e.id, info)
- sessionList.get(e.sessionId).totalExecution += 1
- executionList.get(e.id).groupId = e.groupId
- updateLiveStore(executionList.get(e.id))
- updateLiveStore(sessionList.get(e.sessionId))
- }
+ private def onOperationStart(e: SparkListenerThriftServerOperationStart):
Unit =
+ Option(sessionList.get(e.sessionId)) match {
+ case None => logWarning(s"onOperationStart called with unknown session
id: ${e.sessionId}")
Review comment:
@maropu the server does get to a normal state. This is used only for
displaying SparkUI, so wouldn't affect the server functioning.
Before this change, a NullPointerException would be thrown on
`sessionList.get(e.sessionId).totalExecution += 1`, so I think a WARN message
is strictly better than a NPE in the logs.
But good catch that it could be further improved - don't fail on missing
session, just log the query with that sessionId, and just don't do
`sessionList.get(e.sessionId).totalExecution += 1`
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
