Upload k8s/base/pdbs/pdbs.yaml with huggingface_hub

k8s/base/pdbs/pdbs.yaml

@@ -0,0 +1,62 @@
+# =============================================================================
+# Pod Disruption Budgets — Availability Guarantees Per Workload
+# =============================================================================
+# PDBs prevent voluntary evictions (upgrades, drain) from taking down too many pods.
+# Without PDBs: kubectl drain or cluster-autoscaler can cause unplanned outages.
+# =============================================================================
+
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: frontend-pdb
+  namespace: frontend
+spec:
+  minAvailable: 2  # At least 2 pods always running (3 replicas total)
+  selector:
+    matchLabels:
+      app: frontend
+---
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: backend-pdb
+  namespace: backend
+spec:
+  minAvailable: 2
+  selector:
+    matchLabels:
+      app: backend
+---
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: ml-inference-pdb
+  namespace: ml-pipeline
+spec:
+  maxUnavailable: 1  # At most 1 pod disrupted at a time
+  selector:
+    matchLabels:
+      app: ml-inference
+---
+# Platform services — always keep 1 available
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: prometheus-pdb
+  namespace: monitoring
+spec:
+  minAvailable: 1
+  selector:
+    matchLabels:
+      app: kube-prometheus-stack-prometheus
+---
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: argocd-pdb
+  namespace: platform-system
+spec:
+  minAvailable: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: argocd