Skip to content
Open
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
18 changes: 18 additions & 0 deletions helm/templates/pdb.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
{{- if .Values.pdb.enabled }}
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
name: {{ include "app.fullname" . }}
namespace: {{ .Values.namespace | default .Release.Namespace }}
labels:
{{- include "app.labels" . | nindent 4 }}
spec:
{{- if .Values.pdb.maxUnavailable }}
maxUnavailable: {{ .Values.pdb.maxUnavailable }}
{{- else }}
minAvailable: {{ .Values.pdb.minAvailable | default 1 }}
{{- end }}
selector:
matchLabels:
{{- include "app.selectorLabels" . | nindent 6 }}
{{- end }}
18 changes: 18 additions & 0 deletions helm/templates/scaling-object.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
{{- if .Values.keda.enabled }}
apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
name: {{ include "app.fullname" . }}
namespace: {{ .Values.namespace | default .Release.Namespace }}
labels:
{{- include "app.labels" . | nindent 4 }}
spec:
scaleTargetRef:
name: {{ include "app.fullname" . }}
minReplicaCount: {{ .Values.keda.minReplicaCount }}
maxReplicaCount: {{ .Values.keda.maxReplicaCount }}
pollingInterval: {{ .Values.keda.pollingInterval }}
cooldownPeriod: {{ .Values.keda.cooldownPeriod }}
triggers:
{{- toYaml .Values.keda.triggers | nindent 4 }}
{{- end }}
18 changes: 18 additions & 0 deletions helm/values-production.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Production-specific value overrides.

pdb:
enabled: true
minAvailable: 1

keda:
enabled: true
# LLM hub proxy — CPU under-reads long inference calls
minReplicaCount: 2
maxReplicaCount: 10
pollingInterval: 15
cooldownPeriod: 600
triggers:
- type: cpu
metricType: Utilization
metadata:
value: "70"
14 changes: 14 additions & 0 deletions helm/values-staging.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
# Staging-specific value overrides.

keda:
enabled: true
# LLM hub proxy — CPU under-reads long inference calls
minReplicaCount: 1
maxReplicaCount: 4
pollingInterval: 30
cooldownPeriod: 300
triggers:
- type: cpu
metricType: Utilization
metadata:
value: "70"
10 changes: 10 additions & 0 deletions helm/values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,16 @@ tolerations: []

affinity: {}

# KEDA autoscaling (ScaledObject). Disabled by default; enable and configure
# per-environment via values-<environment>.yaml.
keda:
enabled: false

# PodDisruptionBudget. Disabled by default; enable per-environment in values-*.yaml.
pdb:
enabled: false
minAvailable: 1

# Environment variables to pass to the hub container
env: []
# - name: DEBUG
Expand Down
Loading