[Core] Faster optimizer table by disabling reservation check (#3280)

* Support h100

* Fix H100 from sku

* Fix H100

* Disable reservation check for GCP by default

* Update docs/source/reference/config.rst

Co-authored-by: Zongheng Yang <zongheng.y@gmail.com>

* Update docs/source/reference/config.rst

Co-authored-by: Zongheng Yang <zongheng.y@gmail.com>

* rename config

* fix

---------

Co-authored-by: Zongheng Yang <zongheng.y@gmail.com>

docs/source/reference/config.rst

@@ -190,10 +190,29 @@ Available fields and semantics:
 
 
     # Reserved capacity (optional).
+    # 
+    # Whether to prioritize reserved instance types/locations (considered as 0
+    # cost) in the optimizer.
+    # 
+    # If you have "automatically consumed" reservations in your GCP project:
+    # Setting this to true guarantees the optimizer will pick any matching
+    # reservation and GCP will auto consume your reservation, and setting to
+    # false means optimizer uses regular, non-zero pricing in optimization (if
+    # by chance any matching reservation is selected, GCP still auto consumes
+    # the reservation).
+    # 
+    # If you have "specifically targeted" reservations (set by the
+    # `specific_reservations` field below): This field will automatically be set
+    # to true.
+    # 
+    # Default: false.
+    prioritize_reservations: false
+    #
+    # The "specifically targeted" reservations to be considered when provisioning
+    # clusters on GCP. SkyPilot will automatically prioritize this reserved
+    # capacity (considered as zero cost) if the requested resources matches the
+    # reservation.
     #
-    # The specific reservation to be considered when provisioning clusters on GCP.
-    # SkyPilot will automatically prioritize this reserved capacity (considered as
-    # zero cost) if the requested resources matches the reservation.
     # Ref: https://cloud.google.com/compute/docs/instances/reservations-overview#consumption-type
     specific_reservations:
       - projects/my-project/reservations/my-reservation1

sky/clouds/utils/gcp_utils.py

@@ -139,6 +139,12 @@ def _list_reservations_for_instance_type(
     For example, if we have a specific reservation with n1-highmem-8
     in us-central1-c. `sky launch --gpus V100` will fail.
     """
+    prioritize_reservations = skypilot_config.get_nested(
+        ('gcp', 'prioritize_reservations'), False)
+    specific_reservations = skypilot_config.get_nested(
+        ('gcp', 'specific_reservations'), [])
+    if not prioritize_reservations and not specific_reservations:
+        return []
     logger.debug(f'Querying GCP reservations for instance {instance_type!r}')
     list_reservations_cmd = (
         'gcloud compute reservations list '

sky/utils/schemas.py

@@ -579,6 +579,9 @@ def get_config_schema():
             'required': [],
             'additionalProperties': False,
             'properties': {
+                'prioritize_reservations': {
+                    'type': 'boolean',
+                },
                 'specific_reservations': {
                     'type': 'array',
                     'items': {

sky/utils/subprocess_utils.py

@@ -167,6 +167,8 @@ def run_with_retries(
         if retry_cnt < max_retry:
             if (retry_returncode is not None and
                     returncode in retry_returncode):
+                logger.debug(
+                    f'Retrying command due to returncode {returncode}: {cmd}')
                 retry_cnt += 1
                 time.sleep(random.uniform(0, 1) * 2)
                 continue