[Azure-RDMA] cluster configuration preparation for az-rdma (#2004)

examples/cluster-configuration/services-configuration.yaml

@@ -24,9 +24,13 @@
 #    # HDFS, zookeeper data path on your cluster machine.
 #    data-path: "/datastorage"
 #
-#    #Enable QoS feature or not. Default value is "true"
+#    # Enable QoS feature or not. Default value is "true"
 #    qos-switch: "true"
 #
+#    # If your cluster is created by Azure and the machine is rdma enabled.
+#    # Set this configuration as  "true", the rdma environment will be set into your container.
+#    az-rdma: "false"
+#
 #
 #  # the docker registry to store docker images that contain system services like frameworklauncher, hadoop, etc.
 #  docker-registry:

src/cluster/config/cluster.md

@@ -31,6 +31,7 @@ cluster:
       cluster-id: pai
       data-path: "/datastorage"
       qos-switch: "true"
+      az-rdma: "false"
     docker-registry:
       namespace: openpai
       domain: docker.io
@@ -73,6 +74,12 @@ cluster:
     <td>cluster_cfg["cluster"]["common"]["qos-switch"]</td>
     <td>string</td>
 </tr>
+<tr>
+    <td>cluster.common.az-rdma</td>
+    <td>com["cluster"]["common"]["az-rdma"]</td>
+    <td>cluster_cfg["cluster"]["common"]["az-rdma"]</td>
+    <td>string, "true" or "false"</td>
+</tr>
 <tr>
     <td>cluster.docker-registry.namespace</td>
     <td>com["cluster"]["docker-registry"]["namespace"]</td>

src/cluster/config/cluster.py

@@ -52,6 +52,10 @@ def validation_common(self, common_configuration):
             return False, "cluster-id is miss in service-configuration.yaml -> cluster -> common -> cluster-id"
         if "data-path" not in common_configuration:
             return False, "data-path is miss in service-configuration.yaml -> cluster -> common -> data-path"
+        if "qos-switch" not in common_configuration:
+            return False, "qos-switch is miss in service-configuration.yaml -> cluster -> common -> qos-switch"
+        if "az-rdma" not in common_configuration:
+            return False, "az-rdma is miss in service-configuration.yaml -> cluster -> common -> az-rdma"
         return True, None
 
 

src/cluster/config/cluster.yaml

@@ -24,6 +24,9 @@ common:
 
   qos-switch: "true"
 
+  az-rdma: "false"
+
+
 
 # the docker registry to store docker images that contain system services like frameworklauncher, hadoop, etc.
 docker-registry: