Merge pull request #2 from microsoft/master

merge from master

samples/features/azure-arc/deployment/kubeadm/ubuntu-single-node-vm/setup-controller-new.sh

@@ -1,26 +1,5 @@
 #!/bin/bash
 
-# Get controller username and password as input. It is used as default for the controller.
-#
-if [ -z "$AZDATA_USERNAME" ]
-then
-    read -p "Create Username for Azure Arc Data Controller: " username
-    echo
-    export AZDATA_USERNAME=$username
-fi
-if [ -z "$AZDATA_PASSWORD" ]
-then
-    while true; do
-        read -s -p "Create Password for Azure Arc Data Controller: " password
-        echo
-        read -s -p "Confirm your Password: " password2
-        echo
-        [ "$password" = "$password2" ] && break
-        echo "Password mismatch. Please try again."
-    done
-    export AZDATA_PASSWORD=$password
-fi
-
 # Prompt for private preview repository username and password provided by Microsoft
 #
 if [ -z "$DOCKER_USERNAME" ]
@@ -67,6 +46,27 @@ then
     export ARC_DC_REGION=$dc_region
 fi
 
+# Get controller username and password as input. It is used as default for the controller.
+#
+if [ -z "$AZDATA_USERNAME" ]
+then
+    read -p "Create Username for Azure Arc Data Controller: " username
+    echo
+    export AZDATA_USERNAME=$username
+fi
+if [ -z "$AZDATA_PASSWORD" ]
+then
+    while true; do
+        read -s -p "Create Password for Azure Arc Data Controller: " password
+        echo
+        read -s -p "Confirm your Password: " password2
+        echo
+        [ "$password" = "$password2" ] && break
+        echo "Password mismatch. Please try again."
+    done
+    export AZDATA_PASSWORD=$password
+fi
+
 set -Eeuo pipefail
 
 # This is a script to create single-node Kubernetes cluster and deploy Azure Arc Data Controller on it.

samples/features/sql-big-data-cluster/spark/config-install/installpackage_Spark.ipynb

@@ -106,9 +106,20 @@
                 "The following code can be used to install packages on each executor node at runtime. \\\n",
                 "**Note**: This functionality is not available on a non-root BDC deployment (including OpenShift). This installation is temporary, and must be performed each time a new Spark session is invoked.\n",
                 "\n",
+                "If you want to use this from CU5 upwards, you must add two settings pre-deployment.\n",
+                "\n",
+                "In contron.json, add (under security):\n",
+                "\n",
+                "_\"allowRunAsRoot\": true_\n",
+                "\n",
+                "In BDC.json, add (under spec.services.spark.settings): \n",
+                "\n",
+                "_\"yarn-site.yarn.nodemanager.container-executor.class\": \"org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor\"_\n",
+                "\n",
                 "``` Python\n",
                 "import subprocess\n",
-                "\n",
+                "import os\n",
+                "os.environ[\"XDG_CACHE_HOME\"]=\"/tmp\"\n",
                 "# Install TensorFlow\n",
                 "stdout = subprocess.check_output(\n",
                 "    \"pip3 install tensorflow\",\n",