zsxwing commented on a change in pull request #26225: [SPARK-29568][SS] Stop
existing running streams when a new stream is launched
URL: https://github.com/apache/spark/pull/26225#discussion_r342839057
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/streaming/StreamingQueryManager.scala
##########
@@ -355,11 +355,22 @@ class StreamingQueryManager private[sql] (sparkSession:
SparkSession) extends Lo
// Make sure no other query with same id is active across all sessions
val activeOption =
Option(sparkSession.sharedState.activeStreamingQueries.putIfAbsent(query.id,
this))
- if (activeOption.isDefined || activeQueries.values.exists(_.id ==
query.id)) {
+
+ val streamAlreadyActive =
+ activeOption.isDefined || activeQueries.values.exists(_.id == query.id)
+ val turnOffOldStream =
+
sparkSession.sessionState.conf.getConf(SQLConf.STOP_RUNNING_DUPLICATE_STREAM)
+ if (streamAlreadyActive && turnOffOldStream) {
+ val queryManager = activeOption.getOrElse(this)
+ logInfo(s"Stopping existing streaming query [id=${query.id}], as a new
run is being " +
+ "started.")
+ queryManager.get(query.id).stop()
+ } else if (streamAlreadyActive) {
throw new IllegalStateException(
- s"Cannot start query with id ${query.id} as another query with same
id is " +
- s"already active. Perhaps you are attempting to restart a query
from checkpoint " +
- s"that is already active.")
+ "Cannot start query with id ${query.id} as another query with same
id is " +
+ "already active. Perhaps you are attempting to restart a query
from checkpoint " +
+ "that is already active. You may stop the old query by setting the
SQL " +
+ s"""configuration:
spark.conf.set("${SQLConf.STOP_RUNNING_DUPLICATE_STREAM}", true).""")
Review comment:
`SQLConf.STOP_RUNNING_DUPLICATE_STREAM` =>
`SQLConf.STOP_RUNNING_DUPLICATE_STREAM.key`
And
```
You may stop the old query by setting the SQL ... and retry.
```
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
