[SkyServe] Support mixture of spot and on-demand

examples/serve/spot_policy/base_on_demand_fallback_replicas.yaml

@@ -0,0 +1,21 @@
+# SkyServe YAML to launch a service with mixed spot and on-demand instances.
+# The policy will maintain `base_ondemand_fallback_replicas` number of on-demand instances, in addition to spot instances.
+# On-demand instances are counted in autoscaling decisions (i.e., between `min_replicas` and `max_replicas`).
+
+service:
+  readiness_probe: /health
+  replica_policy:
+    min_replicas: 2
+    max_replicas: 3
+    target_qps_per_replica: 1
+    base_ondemand_fallback_replicas: 1
+
+resources:
+  ports: 8081
+  cpus: 2+
+  # use_spot is needed for ondemand fallback
+  use_spot: true
+
+workdir: examples/serve/http_server
+
+run: python3 server.py

examples/serve/spot_policy/dynamic_on_demand_fallback.yaml

@@ -0,0 +1,23 @@
+# SkyServe YAML to launch a service with mixed spot and on-demand instances.
+# The policy will dynamically fallback to on-demand instances when spot instances are not available. 
+
+service:
+  readiness_probe: /health
+  replica_policy:
+    min_replicas: 2
+    max_replicas: 3
+    target_qps_per_replica: 1
+    dynamic_ondemand_fallback: true
+
+resources:
+  any_of:
+  - zone: us-central1-a
+  - region: us-east1
+  ports: 8081
+  cpus: 2+
+  # use_spot is needed for ondemand fallback
+  use_spot: true
+
+workdir: examples/serve/http_server
+
+run: python3 server.py

examples/serve/spot_policy/multi_accelerators.yaml

@@ -0,0 +1,23 @@
+# SkyServe YAML to launch a service with mixed spot and on-demand instances and an ordered preference for accelerators.
+# The policy will maintain `base_ondemand_fallback_replicas` number of on-demand instances, in addition to spot instances.
+
+service:
+  readiness_probe: /health
+  replica_policy:
+    min_replicas: 2
+    max_replicas: 3
+    target_qps_per_replica: 1
+    base_ondemand_fallback_replicas: 1
+
+resources:
+  ordered:
+  - accelerators: V100
+  - accelerators: T4
+  ports: 8081
+  cpus: 2+
+  # use_spot is needed for ondemand fallback
+  use_spot: true
+
+workdir: examples/serve/http_server
+
+run: python3 server.py

sky/execution.py

@@ -274,8 +274,11 @@ def _execute(
                                               task)
 
     if not cluster_exists:
+        # If spot is launched by skyserve controller or managed spot controller,
+        # We don't need to print out the logger info.
         if (Stage.PROVISION in stages and task.use_spot and
-                not _is_launched_by_spot_controller):
+                not _is_launched_by_spot_controller and
+                not _is_launched_by_sky_serve_controller):
             yellow = colorama.Fore.YELLOW
             bold = colorama.Style.BRIGHT
             reset = colorama.Style.RESET_ALL