Handle sudo and refactor ssh method

Signed-off-by: Partho Sarthi <[email protected]>
NVIDIA · Sep 19, 2023 · c445c6a · c445c6a
1 parent 97386ec
commit c445c6a
Show file tree

Hide file tree

Showing 6 changed files with 19 additions and 9 deletions.
diff --git a/user_tools/src/spark_rapids_pytools/cloud_api/databricks_aws.py b/user_tools/src/spark_rapids_pytools/cloud_api/databricks_aws.py
@@ -122,7 +122,7 @@ def pull_cluster_props_by_args(self, args: dict) -> str:
             return json.dumps(raw_prop_container.props)
         return cluster_described
 
-    def _build_ssh_cmd_prefix_for_node(self, node: ClusterNode) -> str:
+    def _build_cmd_ssh_prefix_for_node(self, node: ClusterNode) -> str:
         port = self.env_vars.get('sshPort')
         key_file = self.env_vars.get('sshKeyFile')
         prefix_args = ['ssh',

diff --git a/user_tools/src/spark_rapids_pytools/cloud_api/databricks_azure.py b/user_tools/src/spark_rapids_pytools/cloud_api/databricks_azure.py
@@ -125,7 +125,7 @@ def pull_cluster_props_by_args(self, args: dict) -> str:
             self.logger.error('Invalid arguments to pull the cluster properties')
         return self.run_sys_cmd(get_cluster_cmd)
 
-    def _build_ssh_cmd_prefix_for_node(self, node: ClusterNode) -> str:
+    def _build_cmd_ssh_prefix_for_node(self, node: ClusterNode) -> str:
         port = self.env_vars.get('sshPort')
         key_file = self.env_vars.get('sshKeyFile')
         prefix_args = ['ssh',

diff --git a/user_tools/src/spark_rapids_pytools/cloud_api/dataproc.py b/user_tools/src/spark_rapids_pytools/cloud_api/dataproc.py
@@ -213,7 +213,7 @@ def exec_platform_describe_accelerator(self,
                     self.get_env_var('zone')]
         return self.run_sys_cmd(cmd_args)
 
-    def _build_ssh_cmd_prefix_for_node(self, node: ClusterNode) -> str:
+    def _build_cmd_ssh_prefix_for_node(self, node: ClusterNode) -> str:
         pref_args = ['gcloud',
                      'compute', 'ssh',
                      node.name,

diff --git a/user_tools/src/spark_rapids_pytools/cloud_api/emr.py b/user_tools/src/spark_rapids_pytools/cloud_api/emr.py
@@ -158,7 +158,7 @@ def pull_cluster_props_by_args(self, args: dict) -> str:
             return EMRPlatform.process_raw_cluster_prop(raw_prop_container)
         return cluster_described
 
-    def _build_ssh_cmd_prefix_for_node(self, node: ClusterNode) -> str:
+    def _build_cmd_ssh_prefix_for_node(self, node: ClusterNode) -> str:
         # get the pem file
         pem_file_path = self.env_vars.get('keyPairPath')
         prefix_args = ['ssh',

diff --git a/user_tools/src/spark_rapids_pytools/cloud_api/sp_types.py b/user_tools/src/spark_rapids_pytools/cloud_api/sp_types.py
@@ -463,7 +463,7 @@ def append_to_cmd(original_cmd, extra_args: list) -> Any:
         sys_cmd = SysCmd().build(cmd_args)
         return sys_cmd.exec()
 
-    def _build_ssh_cmd_prefix_for_node(self, node: ClusterNode) -> str:
+    def _build_cmd_ssh_prefix_for_node(self, node: ClusterNode) -> str:
         del node  # Unused by super method.
         return ''
 
@@ -479,7 +479,7 @@ def _construct_ssh_cmd_with_prefix(self, prefix: str, remote_cmd: str) -> str:
         return f'{prefix} {remote_cmd}'
 
     def ssh_cmd_node(self, node: ClusterNode, ssh_cmd: str, cmd_input: str = None) -> str:
-        prefix_cmd = self._build_ssh_cmd_prefix_for_node(node=node)
+        prefix_cmd = self._build_cmd_ssh_prefix_for_node(node=node)
         full_ssh_cmd = self._construct_ssh_cmd_with_prefix(prefix=prefix_cmd, remote_cmd=ssh_cmd)
         return self.run_sys_cmd(full_ssh_cmd, cmd_input=cmd_input)
 

diff --git a/user_tools/src/spark_rapids_pytools/resources/collect.sh b/user_tools/src/spark_rapids_pytools/resources/collect.sh
@@ -61,10 +61,20 @@ if command -v lshw ; then
 else
     # Downgrade to 'lspci'
     if [[ "$PLATFORM_TYPE" == *"databricks"* ]]; then
-        sudo apt install -y pciutils
-        lspci | { grep 'Ethernet controller' || true; } >> $OUTPUT_NODE_INFO
+        if command -v sudo ; then
+            sudo apt install -y pciutils
+        fi
+        if command -v lspci ; then
+            lspci | { grep 'Ethernet controller' || true; } >> $OUTPUT_NODE_INFO
+        else
+             echo 'not found' >> $OUTPUT_NODE_INFO
+        fi
     elif [ "$PLATFORM_TYPE" == "emr" ]; then
-        /usr/sbin/lspci | { grep 'Ethernet controller' || true; } >> $OUTPUT_NODE_INFO
+        if command -v /usr/sbin/lspci ; then
+            /usr/sbin/lspci | { grep 'Ethernet controller' || true; } >> $OUTPUT_NODE_INFO
+        else
+             echo 'not found' >> $OUTPUT_NODE_INFO
+        fi
     fi
 fi