hvanhovell commented on code in PR #47434:
URL: https://github.com/apache/spark/pull/47434#discussion_r1733414379
##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/SparkSession.scala:
##########
@@ -859,6 +865,49 @@ object SparkSession extends Logging {
}
}
+ /**
+ * Create a new Spark Connect server to connect locally.
+ */
+ private[sql] def withLocalConnectServer[T](f: => T): T = {
+ synchronized {
+ val remoteString = initOptions
+ .get("spark.remote")
+ .orElse(Option(System.getProperty("spark.remote"))) // Set from Spark
Submit
+ .orElse(sys.env.get(SparkConnectClient.SPARK_REMOTE))
+
+ if (server.isEmpty && remoteString.exists(_.startsWith("local"))) {
+ val sparkHome = System.getenv("SPARK_HOME")
+ server = Some {
+ val args = Seq(
+ Paths.get(sparkHome, "sbin", "start-connect-server.sh").toString,
+ "--master",
+ remoteString.get) ++ initOptions
+ .filter(p => !p._1.startsWith("spark.remote"))
+ .flatMap { case (k, v) => Seq("--conf", s"$k=$v") }
+ val pb = new ProcessBuilder(args: _*)
+ // So don't exclude spark-sql jar in classpath
+ pb.environment().remove(SparkConnectClient.SPARK_REMOTE)
+ pb.start()
+ }
+
+ // Let the server start. We will directly request to set the
configurations
+ // and this sleep makes less noisy with retries.
+ Thread.sleep(2000L)
Review Comment:
I'd argue that retries here are fine. We can tweak the retry policy a bit if
this is problematic.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
