[Spot] Make the controller resources configurable

docs/source/examples/spot-jobs.rst

@@ -242,17 +242,16 @@ you can still tear it down manually with
 .. note::
   Tearing down the spot controller will lose all logs and status information for the spot jobs and can cause resource leakage when there are still in-progress spot jobs.
 
-Customize spot controller resources
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Customizing spot controller resources
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Although the default setting works for most of people, you may want to customize the resources of the spot controller for the following reasons:
+You may customize the resources of the spot controller for the following reasons:
 
 1. Enforcing the spot controller to run on a specific location. (Default: cheapest location)
 2. Changing the maximum number of spot jobs that can be run concurrently. (Default: 16)
 3. Changing the disk_size of the spot controller to store more logs. (Default: 50GB)
-4. Using a specific instance type for the spot controller. (Default: choose automatically)
 
-To achieve the above goals, you can specify the configs in the :code:`~/.sky/skypilot_config.yaml` with the following fields (the :code:`resources` field has the same spec as a normal SkyPilot job, see `here <https://skypilot.readthedocs.io/en/latest/reference/yaml-spec.html>`_):
+To achieve the above, you can specify custom configs in :code:`~/.sky/config.yaml` with the following fields (the :code:`resources` field has the same spec as a normal SkyPilot job; see `here <https://skypilot.readthedocs.io/en/latest/reference/yaml-spec.html>`_):
 
 .. code-block:: yaml
 
@@ -267,8 +266,6 @@ To achieve the above goals, you can specify the configs in the :code:`~/.sky/sky
           cpus: 4+ # number of vCPUs, max # spot jobs = 2 * cpus
           # 3. Specify the disk_size of the spot controller.
           disk_size: 100
-          # 4. Specify the instance type of the spot controller.
-          instance_type: n1-standard-4
 
 
 

sky/execution.py

@@ -673,11 +673,13 @@ def spot_launch(
             controller_resources = sky.Resources.from_yaml_config(
                 controller_resources_config)
         except ValueError as e:
-            raise ValueError(
-                'Spot controller resources is not valid, please check '
-                '~/.sky/skypilot_config.yaml file. Details:\n'
-                f'  {common_utils.format_exception(e, use_bracket=True)}'
-            ) from e
+            with ux_utils.print_exception_no_traceback():
+                raise ValueError(
+                    'Spot controller resources is not valid, please check '
+                    '~/.sky/config.yaml file and make sure it\'s a '
+                    'valid resources spec. Details:\n'
+                    f'  {common_utils.format_exception(e, use_bracket=True)}'
+                ) from e
 
         yaml_path = os.path.join(spot.SPOT_CONTROLLER_YAML_PREFIX,
                                  f'{name}-{task_uuid}.yaml')
@@ -686,10 +688,11 @@ def spot_launch(
                                     output_path=yaml_path)
         controller_task = task_lib.Task.from_yaml(yaml_path)
         assert len(controller_task.resources) == 1, controller_task
-        # Backward compatibility: if the user changed the spot-controller.yaml.j2
-        # to customize the controller resources, we should use it.
+        # Backward compatibility: if the user changed the
+        # spot-controller.yaml.j2 to customize the controller resources,
+        # we should use it.
         controller_task_resources = list(controller_task.resources)[0]
-        if not controller_task_resources.is_same_resources(sky.Resources()):
+        if not controller_task_resources.is_empty():
             controller_resources = controller_task_resources
         controller_task.set_resources(controller_resources)
 

sky/resources.py

@@ -799,9 +799,6 @@ def less_demanding_than(self,
         # self <= other
         return True
 
-    def is_same_resources(self, other: 'Resources') -> bool:
-        return self.to_yaml_config() == other.to_yaml_config()
-
     def should_be_blocked_by(self, blocked: 'Resources') -> bool:
         """Whether this Resources matches the blocked Resources.
 
@@ -834,6 +831,8 @@ def is_empty(self) -> bool:
             self.accelerators is None,
             self.accelerator_args is None,
             not self._use_spot_specified,
+            self.disk_size == _DEFAULT_DISK_SIZE_GB,
+            self._image_id is None,
         ])
 
     def copy(self, **override) -> 'Resources':

sky/spot/constants.py

@@ -13,4 +13,8 @@
 SPOT_FM_LOCAL_TMP_DIR = 'skypilot-filemounts-files-{id}'
 SPOT_FM_REMOTE_TMP_DIR = '/tmp/sky-spot-filemounts-files'
 
+# It is now using default CPU instance type for spot controller, i.e.
+# m6i.2xlarge (8vCPUs, 32 GB) for AWS, Standard_D8s_v4 (8vCPUs, 32 GB)
+# for Azure, and n1-standard-8 (8 vCPUs, 32 GB) for GCP.
+# We use 50 GB disk size to reduce the cost.
 CONTROLLER_RESOURCES = {'disk_size': 50}