feat(helm) add PDB per deployment (#851)

* feat(helm) add pdb and expose various options in the values. Add tests

Signed-off-by: enneitex <etienne.divet@gmail.com>

* feat(helm) update README and json schema with new fields

Signed-off-by: enneitex <etienne.divet@gmail.com>

---------

Signed-off-by: enneitex <etienne.divet@gmail.com>
Co-authored-by: Rui Zhang <51696593+ruizhang0101@users.noreply.github.com>

Author: enneitex

.github/values-01-2pods-minimal-example.yaml

@@ -9,7 +9,13 @@ servingEngineSpec:
     modelURL: "facebook/opt-125m"
 
     replicaCount: 2
-
+    pdb:
+      enabled: true
+      minAvailable: 1
+      labels:
+        model: "opt125m"
+      annotations:
+        model: "opt125m"
     requestCPU: 6
     requestMemory: "16Gi"
     requestGPU: 0.5

.github/values-06-session-routing.yaml

@@ -8,6 +8,9 @@ servingEngineSpec:
       tag: "v0.3.9post2"
       modelURL: "facebook/opt-125m"
       replicaCount: 2
+      pdb:
+        enabled: true
+        minAvailable: 1
       requestCPU: 6
       requestMemory: "30Gi"
       requestGPU: 1

helm/README.md

@@ -87,6 +87,11 @@ This table documents all available configuration values for the Production Stack
 | `servingEngineSpec.modelSpec[].modelURL` | string | `""` | The URL of the model, e.g., "facebook/opt-125m" |
 | `servingEngineSpec.modelSpec[].chatTemplate` | string | `null` | (Optional) Chat template (Jinja2) specifying tokenizer configuration |
 | `servingEngineSpec.modelSpec[].replicaCount` | integer | `1` | The number of replicas for the model |
+| `servingEngineSpec.modelSpec[].pdb.enabled`| boolean |  `false` | Whether to create a PodDisruptionBudget for the model |
+| `servingEngineSpec.modelSpec[].pdb.labels`| map | `{}` | Labels to add to the PodDisruptionBudget |
+| `servingEngineSpec.modelSpec[].pdb.annotations`| map | `{}` | Annotations to add to the PodDisruptionBudget |
+| `servingEngineSpec.modelSpec[].pdb.minAvailable`| string | `""` | Number of pods that are available after eviction as number or percentage (eg.: 50%) |
+| `servingEngineSpec.modelSpec[].pdb.maxUnavailable`| string | `""` | Number of pods that are unavailable after eviction as number or percentage (eg.: 50%). |
 | `servingEngineSpec.modelSpec[].resources` | object | `{}` | Standard Kubernetes resources block (requests/limits). If specified, this takes priority over and ignores simplified resource fields (requestCPU, requestMemory, requestGPU, etc.) |
 | `servingEngineSpec.modelSpec[].requestCPU` | integer | `0` | The number of CPUs requested for the model |
 | `servingEngineSpec.modelSpec[].requestMemory` | string | `""` | The amount of memory requested for the model, e.g., "16Gi" |
@@ -196,12 +201,17 @@ This table documents all available configuration values for the Production Stack
 
 | Field | Type | Default | Description |
 |-------|------|---------|-------------|
+| `routerSpec.enableRouter` | boolean | `true` | Whether to enable the router service |
 | `routerSpec.repository` | string | `"lmcache/lmstack-router"` | Docker image repository for the router |
 | `routerSpec.tag` | string | `"latest"` | Docker image tag for the router |
 | `routerSpec.imagePullPolicy` | string | `"Always"` | Image pull policy for the router |
 | `routerSpec.imagePullSecrets` | list | `[]` | Image pull secrets for private container registries |
-| `routerSpec.enableRouter` | boolean | `true` | Whether to enable the router service |
 | `routerSpec.replicaCount` | integer | `1` | Number of replicas for the router pod |
+| `routerSpec.pdb.enabled`| boolean |  `false` | Whether to create a PodDisruptionBudget for the model |
+| `routerSpec.pdb.labels`| map | `{}` | Labels to add to the PodDisruptionBudget |
+| `routerSpec.pdb.annotations`| map | `{}` | Annotations to add to the PodDisruptionBudget |
+| `routerSpec.pdb.minAvailable`| string | `""` | Number of pods that are available after eviction as number or percentage (eg.: 50%) |
+| `routerSpec.pdb.maxUnavailable`| string | `""` | Number of pods that are unavailable after eviction as number or percentage (eg.: 50%). |
 | `routerSpec.priorityClassName` | string | `""` | Priority class for router |
 | `routerSpec.containerPort` | integer | `8000` | Port the router container is listening on |
 | `routerSpec.serviceType` | string | `"ClusterIP"` | Kubernetes service type for the router |
@@ -325,7 +335,10 @@ This table documents all available configuration values for the Production Stack
 | `loraController.image.tag` | string | `"latest"` | Docker image tag |
 | `loraController.image.pullPolicy` | string | `"IfNotPresent"` | Image pull policy |
 | `loraController.imagePullSecrets` | list | `[]` | Image pull secrets |
+| `loraController.annotations` | map | `{}` | Deployment annotations |
+| `loraController.labels` | map | `{}` | Deployment labels |
 | `loraController.podAnnotations` | map | `{}` | Pod annotations |
+| `loraController.podLabels` | map | `{}` | Pod labels |
 | `loraController.podSecurityContext.runAsNonRoot` | boolean | `true` | Run as non-root user |
 | `loraController.podSecurityContext.seccompProfile.type` | string | `RuntimeDefault` | Seccomp profile type |
 | `loraController.containerSecurityContext.allowPrivilegeEscalation` | boolean | `false` | Allow privilege escalation |
@@ -336,6 +349,12 @@ This table documents all available configuration values for the Production Stack
 | `loraController.tolerations` | list | `[]` | Tolerations configuration |
 | `loraController.env` | list | `[]` | Environment variables |
 | `loraController.extraArgs` | list | `[]` | Extra arguments for the controller |
+| `loraController.metrics.enabled` | boolean | `true` | Whether to expose lora controller metrics |
+| `loraController.pdb.enabled`| boolean |  `false` | Whether to create a PodDisruptionBudget for the loraController |
+| `loraController.pdb.labels`| map | `{}` | Labels to add to the PodDisruptionBudget |
+| `loraController.pdb.annotations`| map | `{}` | Annotations to add to the PodDisruptionBudget |
+| `loraController.pdb.minAvailable`| string | `""` | Number of pods that are available after eviction as number or percentage (eg.: 50%) |
+| `loraController.pdb.maxUnavailable`| string | `""` | Number of pods that are unavailable after eviction as number or percentage (eg.: 50%). |
 
 ### Shared Storage Configuration
 

helm/templates/deployment-lora-controller.yaml

@@ -8,7 +8,15 @@ metadata:
   labels:
     app.kubernetes.io/component: lora-controller
     helm-release-name: {{ .Release.Name }}
+  {{- with .Values.loraController.labels }}
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+  {{- with .Values.loraController.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
 spec:
+  replicas: {{ .Values.loraController.replicaCount }}
   selector:
     matchLabels:
       app.kubernetes.io/component: lora-controller
@@ -18,6 +26,9 @@ spec:
       labels:
         app.kubernetes.io/component: lora-controller
         helm-release-name: {{ .Release.Name }}
+      {{- with .Values.loraController.podLabels }}
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       {{- with .Values.loraController.podAnnotations }}
       annotations:
         {{- toYaml . | nindent 8 }}
@@ -91,8 +102,10 @@ spec:
               port: 8081
             initialDelaySeconds: 5
             periodSeconds: 10
+          {{- with .Values.loraController.resources }}
           resources:
-            {{- toYaml .Values.loraController.resources | nindent 12 }}
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
           securityContext:
             {{- toYaml .Values.loraController.containerSecurityContext | nindent 12 }}
           volumeMounts:

helm/templates/pdb-lora-controller.yaml

@@ -0,0 +1,25 @@
+{{- if and .Values.loraController.enableLoraController .Values.loraController.pdb.enabled }}
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: "{{ .Release.Name }}-pdb-lora-controller"
+  namespace: {{ .Release.Namespace }}
+  {{- with .Values.loraController.pdb.labels }}
+  labels:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+  {{- with .Values.loraController.pdb.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- with .Values.loraController.pdb.maxUnavailable }}
+  maxUnavailable: {{ . }}
+  {{- else }}
+  minAvailable: {{ .Values.loraController.pdb.minAvailable | default 0 }}
+  {{- end }}
+  selector:
+    matchLabels:
+      app.kubernetes.io/component: lora-controller
+      helm-release-name: {{ .Release.Name }}
+{{- end }}

helm/templates/pdb-router.yaml

@@ -0,0 +1,25 @@
+{{- if and .Values.routerSpec.enableRouter .Values.routerSpec.pdb.enabled }}
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: "{{ .Release.Name }}-pdb-router"
+  namespace: {{ .Release.Namespace }}
+  {{- with .Values.routerSpec.pdb.labels }}
+  labels:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+  {{- with .Values.routerSpec.pdb.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- with .Values.routerSpec.pdb.maxUnavailable }}
+  maxUnavailable: {{ . }}
+  {{- else }}
+  minAvailable: {{ .Values.routerSpec.pdb.minAvailable | default 0 }}
+  {{- end }}
+  selector:
+    matchLabels:
+    {{- include "chart.routerStandardLabels" (dict "releaseName" .Release.Name "chartName" .Chart.Name) | nindent 6 }}
+    {{- include "chart.routerLabels" . | nindent 6 }}
+{{- end }}

helm/templates/pdb-vllm-multi.yaml

@@ -0,0 +1,34 @@
+{{- if .Values.servingEngineSpec.enableEngine -}}
+{{- range $modelSpec := .Values.servingEngineSpec.modelSpec }}
+{{- if and $modelSpec.pdb $modelSpec.pdb.enabled }}
+{{- with $ }}
+---
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: "{{ .Release.Name }}-{{ $modelSpec.name }}-pdb-vllm"
+  namespace: {{ .Release.Namespace }}
+  {{- with $modelSpec.pdb.labels }}
+  labels:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+  {{- with $modelSpec.pdb.annotations }}
+  annotations:
+   {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- with $modelSpec.pdb.maxUnavailable }}
+  maxUnavailable: {{ . }}
+  {{- else }}
+  minAvailable: {{ $modelSpec.pdb.minAvailable | default 0 }}
+  {{- end }}
+  selector:
+    matchLabels:
+      model: {{ $modelSpec.name }}
+      helm-release-name: {{ .Release.Name }}
+    {{- include "chart.engineStandardLabels" (dict "releaseName" .Release.Name "modelName" $modelSpec.name "chartName" .Chart.Name) | nindent 6 }}
+    {{- include "chart.engineLabels" . | nindent 6 }}
+{{- end }}
+{{- end }}
+{{- end }}
+{{- end }}