vanzin commented on a change in pull request #23546: [SPARK-23153][K8s] Support 
client dependencies with a Hadoop Compatible File System
URL: https://github.com/apache/spark/pull/23546#discussion_r260919508
 
 

 ##########
 File path: core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala
 ##########
 @@ -374,6 +408,53 @@ private[spark] class SparkSubmit extends Logging {
       localPyFiles = Option(args.pyFiles).map {
         downloadFileList(_, targetDir, sparkConf, hadoopConf, secMgr)
       }.orNull
+
+      if (isKubernetesClient &&
+        sparkConf.getBoolean("spark.kubernetes.submitInDriver", false)) {
+        // Replace with the downloaded local jar path to avoid propagating 
hadoop compatible uris.
+        // Executors will get the jars from the Spark file server.
+        if (args.jars != null && localJars != null) {
+          args.jars = Utils.stringToSeq(args.jars).map {
+            jar => val jarUri = new URI(jar)
+              val path1 = {
+                val p1 = jarUri.getPath
+                p1.substring(p1.lastIndexOf('/') + 1)
+              }
+              Utils.stringToSeq(localJars).find { localUri =>
+                val path2 = {
+                  val p2 = new URI(localUri).getPath
+                  p2.substring(p2.lastIndexOf('/') + 1)
+                }
+                path1 == path2
+              }.getOrElse(jar)
+          }.mkString(",")
+        }
+
+        val notSecureUrl = (url: String) => !url.startsWith("https") &&
+          !url.startsWith("https") && !url.startsWith("https")
+
+        val localFiles = Option(args.files).filter(notSecureUrl).map {
+          downloadFileList(_, targetDir, sparkConf, hadoopConf, secMgr)
+        }.orNull
+
+        if (args.files != null && localFiles != null) {
 
 Review comment:
   This looks very similar to the previous code, which tells me it can be 
refactored.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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]

Reply via email to