[Azure] SkyPilot provisioner for Azure (#3704)

* Use SkyPilot for status query * format * Avoid reconfig * Add todo * Add termination and stopping * add stop and termination into __init__ * get rid of azure special handling in backend * format * Fix filtering for autodown clusters * Move NSG waiting * wip * wip * working? * Fix and format * remove node providers * Add manifest and fix formating * Fix waiting for deletion * remove azure provider format * Skip termination for resource group does not exist * Add retry for fetching subscription ID * Fix provisioning state * Fix restarting instances by adding wait for pendings * fixs * fix * Add azure handler * adopt changes from node provider * format * fix merge conflict * format * Add detailed reason * fix import * Fix backward compat * fix head node fetching * format * fix existing instances * backward compat test for multi-node * backward compat for cached cluster info * fix back compat for provisioner update * minor * fix restarting * revert accidental changes * fix logging controller utils * add path * activate python env for sky jobs logs * fix quote * format * Longer timeout for docker initialization * fix * make cloud init more readable * fix * fix docker * fix tests * add region argument for eu-south-1 region * Add --region argument for storage aws s3 * Fix tests * longer * wip * wip * address comments * revert storage * revert changes
skypilot-org · Jul 15, 2024 · 465d36c · 465d36c
1 parent bce117d
commit 465d36c
Show file tree

Hide file tree

Showing 37 changed files with 1,142 additions and 1,272 deletions.
diff --git a/.github/workflows/format.yml b/.github/workflows/format.yml
@@ -35,18 +35,15 @@ jobs:
     - name: Running yapf
       run: |
         yapf --diff --recursive ./ --exclude 'sky/skylet/ray_patches/**' \
-            --exclude 'sky/skylet/providers/azure/**' \
             --exclude 'sky/skylet/providers/ibm/**'
     - name: Running black
       run: |
-        black --diff --check sky/skylet/providers/azure/ \
-            sky/skylet/providers/ibm/
+        black --diff --check sky/skylet/providers/ibm/
     - name: Running isort for black formatted files
       run: |
         isort --diff --check --profile black -l 88 -m 3 \
             sky/skylet/providers/ibm/
     - name: Running isort for yapf formatted files
       run: |
         isort --diff --check ./ --sg 'sky/skylet/ray_patches/**' \
-            --sg 'sky/skylet/providers/azure/**' \
             --sg 'sky/skylet/providers/ibm/**'
diff --git a/format.sh b/format.sh
@@ -48,18 +48,15 @@ YAPF_FLAGS=(
 
 YAPF_EXCLUDES=(
     '--exclude' 'build/**'
-    '--exclude' 'sky/skylet/providers/azure/**'
     '--exclude' 'sky/skylet/providers/ibm/**'
 )
 
 ISORT_YAPF_EXCLUDES=(
     '--sg' 'build/**'
-    '--sg' 'sky/skylet/providers/azure/**'
     '--sg' 'sky/skylet/providers/ibm/**'
 )
 
 BLACK_INCLUDES=(
-    'sky/skylet/providers/azure'
     'sky/skylet/providers/ibm'
 )
 

diff --git a/sky/adaptors/azure.py b/sky/adaptors/azure.py
@@ -82,3 +82,10 @@ def get_client(name: str, subscription_id: str):
 def create_security_rule(**kwargs):
     from azure.mgmt.network.models import SecurityRule
     return SecurityRule(**kwargs)
+
+
+@common.load_lazy_modules(modules=_LAZY_MODULES)
+def deployment_mode():
+    """Azure deployment mode."""
+    from azure.mgmt.resource.resources.models import DeploymentMode
+    return DeploymentMode
diff --git a/sky/authentication.py b/sky/authentication.py
@@ -19,7 +19,6 @@
 is an exception, due to the limitation of the cloud provider. See the
 comments in setup_lambda_authentication)
 """
-import base64
 import copy
 import functools
 import os
@@ -270,36 +269,6 @@ def setup_gcp_authentication(config: Dict[str, Any]) -> Dict[str, Any]:
     return configure_ssh_info(config)
 
 
-# In Azure, cloud-init script must be encoded in base64. See
-# https://learn.microsoft.com/en-us/azure/virtual-machines/custom-data
-# for more information. Here we decode it and replace the ssh user
-# and public key content, then encode it back.
-def setup_azure_authentication(config: Dict[str, Any]) -> Dict[str, Any]:
-    _, public_key_path = get_or_generate_keys()
-    with open(public_key_path, 'r', encoding='utf-8') as f:
-        public_key = f.read().strip()
-    for node_type in config['available_node_types']:
-        node_config = config['available_node_types'][node_type]['node_config']
-        cloud_init = (
-            node_config['azure_arm_parameters']['cloudInitSetupCommands'])
-        cloud_init = base64.b64decode(cloud_init).decode('utf-8')
-        cloud_init = cloud_init.replace('skypilot:ssh_user',
-                                        config['auth']['ssh_user'])
-        cloud_init = cloud_init.replace('skypilot:ssh_public_key_content',
-                                        public_key)
-        cloud_init = base64.b64encode(
-            cloud_init.encode('utf-8')).decode('utf-8')
-        node_config['azure_arm_parameters']['cloudInitSetupCommands'] = (
-            cloud_init)
-    config_str = common_utils.dump_yaml_str(config)
-    config_str = config_str.replace('skypilot:ssh_user',
-                                    config['auth']['ssh_user'])
-    config_str = config_str.replace('skypilot:ssh_public_key_content',
-                                    public_key)
-    config = yaml.safe_load(config_str)
-    return config
-
-
 def setup_lambda_authentication(config: Dict[str, Any]) -> Dict[str, Any]:
 
     get_or_generate_keys()

diff --git a/sky/backends/backend_utils.py b/sky/backends/backend_utils.py
@@ -158,7 +158,8 @@
     ('available_node_types', 'ray.head.default', 'node_config',
      'IamInstanceProfile'),
     ('available_node_types', 'ray.head.default', 'node_config', 'UserData'),
-    ('available_node_types', 'ray.worker.default', 'node_config', 'UserData'),
+    ('available_node_types', 'ray.head.default', 'node_config',
+     'azure_arm_parameters', 'cloudInitSetupCommands'),
 ]
 
 
@@ -1019,13 +1020,18 @@ def _add_auth_to_cluster_config(cloud: clouds.Cloud, cluster_config_file: str):
     """
     config = common_utils.read_yaml(cluster_config_file)
     # Check the availability of the cloud type.
-    if isinstance(cloud, (clouds.AWS, clouds.OCI, clouds.SCP, clouds.Vsphere,
-                          clouds.Cudo, clouds.Paperspace)):
+    if isinstance(cloud, (
+            clouds.AWS,
+            clouds.OCI,
+            clouds.SCP,
+            clouds.Vsphere,
+            clouds.Cudo,
+            clouds.Paperspace,
+            clouds.Azure,
+    )):
         config = auth.configure_ssh_info(config)
     elif isinstance(cloud, clouds.GCP):
         config = auth.setup_gcp_authentication(config)
-    elif isinstance(cloud, clouds.Azure):
-        config = auth.setup_azure_authentication(config)
     elif isinstance(cloud, clouds.Lambda):
         config = auth.setup_lambda_authentication(config)
     elif isinstance(cloud, clouds.Kubernetes):