Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions charts/llm-d-modelservice/templates/_helpers.tpl
Original file line number Diff line number Diff line change
Expand Up @@ -255,6 +255,11 @@ resources:
{{- end -}}
{{- end }}

{{/* EPP labels */}}
{{- define "llm-d-modelservice.eppLabels" -}}
llm-d.ai/epp: {{ include "llm-d-modelservice.eppName" . }}
{{- end }}

{{/* default http route name */}}
{{- define "llm-d-modelservice.httpRouteName" -}}
{{ include "llm-d-modelservice.fullname" . }}
Expand Down
16 changes: 16 additions & 0 deletions charts/llm-d-modelservice/templates/epp-clusterrolebinding.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
{{- if .Values.routing.epp.monitoring.servicemonitor.enabled }}
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: {{ include "llm-d-modelservice.eppServiceAccountName" . }}
labels:
{{- include "llm-d-modelservice.labels" . | nindent 4 }}
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: {{ include "llm-d-modelservice.eppName" . }}-metrics
subjects:
- kind: ServiceAccount
name: {{ include "llm-d-modelservice.eppServiceAccountName" . }}
namespace: {{ .Release.Namespace }}
{{- end }}
7 changes: 4 additions & 3 deletions charts/llm-d-modelservice/templates/epp-deployment.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -4,17 +4,18 @@ kind: Deployment
metadata:
name: {{ include "llm-d-modelservice.eppName" . }}
labels:
llm-d.ai/epp: {{ include "llm-d-modelservice.eppName" . }}
{{- include "llm-d-modelservice.labels" . | nindent 4 }}
{{- include "llm-d-modelservice.eppLabels" . | nindent 4 }}
namespace: {{ .Release.Namespace }}
spec:
replicas: {{ default 1 .Values.routing.epp.replicas }}
selector:
matchLabels:
llm-d.ai/epp: {{ include "llm-d-modelservice.eppName" . }}
{{- include "llm-d-modelservice.eppLabels" . | nindent 6 }}
template:
metadata:
labels:
llm-d.ai/epp: {{ include "llm-d-modelservice.eppName" . }}
{{- include "llm-d-modelservice.eppLabels" . | nindent 8 }}
spec:
containers:
- name: epp
Expand Down
33 changes: 33 additions & 0 deletions charts/llm-d-modelservice/templates/epp-metrics-clusterrole.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
{{- if .Values.routing.epp.monitoring.servicemonitor.enabled }}
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: {{ include "llm-d-modelservice.eppName" . }}-metrics
labels:
{{- include "llm-d-modelservice.labels" . | nindent 4 }}
rules:
- apiGroups:
- ""
resources:
- pods
verbs:
- get
- watch
- list
- apiGroups:
- authentication.k8s.io
resources:
- tokenreviews
verbs:
- create
- apiGroups:
- authorization.k8s.io
resources:
- subjectaccessreviews
verbs:
- create
- nonResourceURLs:
- {{ .Values.routing.epp.monitoring.servicemonitor.path }}
verbs:
- get
{{- end }}
11 changes: 11 additions & 0 deletions charts/llm-d-modelservice/templates/epp-sa-token-secret.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
{{- if or .Values.routing.epp.create .Values.routing.epp.monitoring.servicemonitor.enabled }}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "llm-d-modelservice.eppServiceAccountName" . }}-token
labels:
{{- include "llm-d-modelservice.labels" . | nindent 4 }}
annotations:
kubernetes.io/service-account.name: {{ include "llm-d-modelservice.eppServiceAccountName" . }}
type: kubernetes.io/service-account-token
{{- end }}
2 changes: 1 addition & 1 deletion charts/llm-d-modelservice/templates/epp-sa.yaml
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
{{- if .Values.routing.epp.create -}}
{{- if or .Values.routing.epp.create .Values.routing.epp.monitoring.servicemonitor.enabled }}
apiVersion: v1
kind: ServiceAccount
metadata:
Expand Down
9 changes: 8 additions & 1 deletion charts/llm-d-modelservice/templates/epp-service.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ metadata:
name: {{ include "llm-d-modelservice.eppServiceName" . }}
labels:
{{- include "llm-d-modelservice.labels" . | nindent 4 }}
{{- include "llm-d-modelservice.eppLabels" . | nindent 4 }}
spec:
type: {{ .Values.routing.epp.service.type }}
ports:
Expand All @@ -13,9 +14,15 @@ spec:
targetPort: {{ .Values.routing.epp.service.targetPort }}
protocol: TCP
appProtocol: {{ .Values.routing.epp.service.appProtocol }}
{{- if .Values.routing.epp.monitoring.servicemonitor.enabled }}
- name: metrics
port: 9090
targetPort: 9090
protocol: TCP
{{- end }}
{{- with .Values.routing.epp.service.extraPorts }}
{{- toYaml . | nindent 4 }}
{{- end }}
selector:
llm-d.ai/epp: {{ include "llm-d-modelservice.eppName" . }}
{{- include "llm-d-modelservice.eppLabels" . | nindent 4 }}
{{- end }}
25 changes: 25 additions & 0 deletions charts/llm-d-modelservice/templates/epp-servicemonitor.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
{{- if .Values.routing.epp.monitoring.servicemonitor.enabled }}
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
name: {{ include "llm-d-modelservice.eppServiceAccountName" . }}-monitor
namespace: {{ .Release.Namespace }}
labels:
{{- include "llm-d-modelservice.labels" . | nindent 4 }}
spec:
endpoints:
- interval: {{ .Values.routing.epp.monitoring.servicemonitor.interval }}
port: "metrics"
path: "/metrics"
authorization:
credentials:
key: token
name: {{ include "llm-d-modelservice.eppServiceAccountName" . }}-token
jobLabel: {{ include "llm-d-modelservice.eppServiceAccountName" . }}
namespaceSelector:
matchNames:
- {{ .Release.Namespace }}
selector:
matchLabels:
{{- include "llm-d-modelservice.eppLabels" . | nindent 6 }}
{{- end }}
6 changes: 6 additions & 0 deletions charts/llm-d-modelservice/values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -218,6 +218,12 @@ routing:
# - name: ENABLE_KVCACHE_AWARE_SCORER
# value: "false"

# Monitoring configuration for EPP
monitoring:
# ServiceMonitor configuration for EPP metrics collection with Prometheus Operator
servicemonitor:
enabled: false
interval: "10s"

# @schema
# additionalProperties: true
Expand Down
Loading