Files
llmgw/deploy/helm/llmgw/templates/statefulset.yaml
T
Ilker ManapandClaude Opus 5.5 bae16426a2 Offline sites and Kubernetes: llmgw bundle create, import and trust, offline.mirror, server init --bundle; a Helm chart for the control plane
A bundle carries what a cluster would download — llmgw's release with its
signed checksums, every llama.cpp build per architecture with GitHub's
checksums, model files pinned and checked against Hugging Face's — into a
directory or a tar whose manifest sha256 is carried apart. Import checks
everything, the release against the signing key, before anything is put in
the mirror. With offline.mirror set, nodes install llama.cpp from the
mirror against checksums the control plane holds and sends over the agent
stream; releases default to the mirror for node add, ctl upgrade and agent
upgrades. server init and the setup form install from a bundle.

The Helm chart runs one control plane with SQLite on a claim or an external
PostgreSQL, Secrets for the agent certificate and admin token, Services,
Ingress and ServiceMonitor; deploy/container/Dockerfile builds its image.
GPU nodes stay outside Kubernetes, as docs/kubernetes.md explains.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-05 00:13:39 +02:00

182 lines
6.3 KiB
YAML

apiVersion: apps/v1
kind: StatefulSet
metadata:
name: {{ include "llmgw.fullname" . }}
labels:
{{- include "llmgw.labels" . | nindent 4 }}
spec:
# One control plane: Kubernetes replaces it within seconds when it goes,
# and the agents reconnect on their own. See replicas in values.yaml.
replicas: 1
serviceName: {{ include "llmgw.fullname" . }}-headless
selector:
matchLabels:
{{- include "llmgw.selectorLabels" . | nindent 6 }}
template:
metadata:
labels:
{{- include "llmgw.selectorLabels" . | nindent 8 }}
{{- with .Values.podLabels }}
{{- toYaml . | nindent 8 }}
{{- end }}
annotations:
# server.yaml is read at start: a changed one restarts the pod.
checksum/config: {{ include "llmgw.serverConfig" . | sha256sum }}
{{- with .Values.podAnnotations }}
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
# Agents reconnect within seconds of a control plane going; a long
# grace period only delays the one that replaces it.
terminationGracePeriodSeconds: 30
securityContext:
runAsNonRoot: true
runAsUser: 65532
runAsGroup: 65532
fsGroup: 65532
seccompProfile:
type: RuntimeDefault
containers:
- name: llmgw
image: {{ include "llmgw.image" . }}
imagePullPolicy: {{ .Values.image.pullPolicy }}
args: ["server", "--config", "/etc/llmgw/server.yaml"]
env:
# For `kubectl exec ... -- llmgw ctl`, which reads the token
# from here; the server reads admin_token_file.
- name: LLMGW_ADMIN_TOKEN
valueFrom:
secretKeyRef:
name: {{ include "llmgw.adminSecret" . }}
key: {{ if .Values.adminToken.existingSecret }}{{ .Values.adminToken.secretKey }}{{ else }}admin-token{{ end }}
ports:
- name: api
containerPort: 8080
- name: agents
containerPort: 7443
- name: metrics
containerPort: 9091
# Up is /health. Ready is /leader: a control plane holds the
# agents' connections and places models only once it leads — on
# PostgreSQL, once the lease of the one it replaced has run out. A
# cluster with no node yet is still ready: /ready would wait for a
# replica, and nodes could then never connect.
startupProbe:
httpGet: {path: /health, port: api}
periodSeconds: 5
failureThreshold: 60
livenessProbe:
httpGet: {path: /health, port: api}
periodSeconds: 10
failureThreshold: 6
readinessProbe:
httpGet: {path: /leader, port: api}
periodSeconds: 5
failureThreshold: 2
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop: ["ALL"]
resources:
{{- toYaml .Values.resources | nindent 12 }}
volumeMounts:
- name: config
mountPath: /etc/llmgw/server.yaml
subPath: server.yaml
readOnly: true
- name: agent-tls
mountPath: /etc/llmgw/tls
readOnly: true
- name: admin-token
mountPath: /etc/llmgw/admin
readOnly: true
{{- if eq .Values.store.type "postgres" }}
- name: store
mountPath: /etc/llmgw/store
readOnly: true
{{- end }}
{{- if .Values.offlineChecksums.configMap }}
- name: offline
mountPath: /etc/llmgw/offline
readOnly: true
{{- end }}
- name: data
mountPath: /var/lib/llmgw
- name: tmp
mountPath: /tmp
volumes:
- name: config
configMap:
name: {{ include "llmgw.fullname" . }}
- name: agent-tls
secret:
secretName: {{ .Values.agentTLS.existingSecret }}
defaultMode: 0440
items:
- {key: ca.pem, path: ca.pem}
- {key: server.pem, path: server.pem}
- {key: server-key.pem, path: server-key.pem}
- name: admin-token
secret:
secretName: {{ include "llmgw.adminSecret" . }}
defaultMode: 0440
items:
- key: {{ if .Values.adminToken.existingSecret }}{{ .Values.adminToken.secretKey }}{{ else }}admin-token{{ end }}
path: admin-token
{{- if eq .Values.store.type "postgres" }}
- name: store
secret:
secretName: {{ .Values.store.postgres.existingSecret }}
defaultMode: 0440
items:
- key: {{ .Values.store.postgres.secretKey }}
path: dsn
{{- end }}
{{- if .Values.offlineChecksums.configMap }}
- name: offline
configMap:
name: {{ .Values.offlineChecksums.configMap }}
items:
- key: {{ .Values.offlineChecksums.key }}
path: offline.sha256
{{- end }}
- name: tmp
emptyDir: {}
{{- if eq .Values.store.type "postgres" }}
# The store is PostgreSQL; nothing here outlives the pod.
- name: data
emptyDir: {}
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- if eq .Values.store.type "sqlite" }}
volumeClaimTemplates:
- metadata:
name: data
labels:
{{- include "llmgw.selectorLabels" . | nindent 10 }}
spec:
accessModes: ["ReadWriteOnce"]
{{- with .Values.store.sqlite.storageClass }}
storageClassName: {{ . }}
{{- end }}
resources:
requests:
storage: {{ .Values.store.sqlite.size }}
{{- end }}