From 92ce8d4849a0341c4636e70821b7be57ad3055b1 Mon Sep 17 00:00:00 2001
From: Gurvinder Singh <gurvinder.singh@uninett.no>
Date: Thu, 8 Sep 2016 17:20:20 -0700
Subject: [SPARK-15487][WEB UI] Spark Master UI to reverse proxy Application
 and Workers UI

## What changes were proposed in this pull request?

This pull request adds the functionality to enable accessing worker and application UI through master UI itself. Thus helps in accessing SparkUI when running spark cluster in closed networks e.g. Kubernetes. Cluster admin needs to expose only spark master UI and rest of the UIs can be in the private network, master UI will reverse proxy the connection request to corresponding resource. It adds the path for workers/application UIs as

WorkerUI: <http/https>://master-publicIP:<port>/target/workerID/
ApplicationUI: <http/https>://master-publicIP:<port>/target/appID/

This makes it easy for users to easily protect the Spark master cluster access by putting some reverse proxy e.g. https://github.com/bitly/oauth2_proxy

## How was this patch tested?

The functionality has been tested manually and there is a unit test too for testing access to worker UI with reverse proxy address.

pwendell bomeng BryanCutler can you please review it, thanks.

Author: Gurvinder Singh <gurvinder.singh@uninett.no>

Closes #13950 from gurvindersingh/rproxy.
---
 .../src/main/scala/org/apache/spark/repl/SparkILoop.scala   | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'repl/scala-2.11')

diff --git a/repl/scala-2.11/src/main/scala/org/apache/spark/repl/SparkILoop.scala b/repl/scala-2.11/src/main/scala/org/apache/spark/repl/SparkILoop.scala
index 2707b0847a..76a66c1bea 100644
--- a/repl/scala-2.11/src/main/scala/org/apache/spark/repl/SparkILoop.scala
+++ b/repl/scala-2.11/src/main/scala/org/apache/spark/repl/SparkILoop.scala
@@ -43,7 +43,18 @@ class SparkILoop(in0: Option[BufferedReader], out: JPrintWriter)
           }
         @transient val sc = {
           val _sc = spark.sparkContext
-          _sc.uiWebUrl.foreach(webUrl => println(s"Spark context Web UI available at ${webUrl}"))
+          if (_sc.getConf.getBoolean("spark.ui.reverseProxy", false)) {
+            val proxyUrl = _sc.getConf.get("spark.ui.reverseProxyUrl", null)
+            if (proxyUrl != null) {
+              println(s"Spark Context Web UI is available at ${proxyUrl}/proxy/${_sc.applicationId}")
+            } else {
+              println(s"Spark Context Web UI is available at Spark Master Public URL")
+            }
+          } else {
+            _sc.uiWebUrl.foreach {
+              webUrl => println(s"Spark context Web UI available at ${webUrl}")
+            }
+          }
           println("Spark context available as 'sc' " +
             s"(master = ${_sc.master}, app id = ${_sc.applicationId}).")
           println("Spark session available as 'spark'.")
-- 
cgit v1.2.3