refactor(k8s): Reorganize into 5-layer structure with production kustomizations
This commit is contained in:
Story Crater Bot
@@ -0,0 +1,6 @@
|
||||
apiVersion: v2
|
||||
name: ollama
|
||||
description: CPU-only Ollama LLM server with MinIO model registry
|
||||
type: application
|
||||
version: 0.1.0
|
||||
appVersion: "latest"
|
||||
@@ -0,0 +1,126 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: ollama
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
app.kubernetes.io/part-of: llm
|
||||
spec:
|
||||
replicas: {{ .Values.replicaCount }}
|
||||
strategy:
|
||||
type: Recreate
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: ollama
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
app.kubernetes.io/part-of: llm
|
||||
spec:
|
||||
affinity:
|
||||
nodeAffinity:
|
||||
requiredDuringSchedulingIgnoredDuringExecution:
|
||||
nodeSelectorTerms:
|
||||
- matchExpressions:
|
||||
- key: topology.kubernetes.io/zone
|
||||
operator: In
|
||||
values:
|
||||
- {{ .Values.nodeAffinity.zone }}
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Equal
|
||||
value: ""
|
||||
effect: NoSchedule
|
||||
|
||||
initContainers:
|
||||
- name: preload-model
|
||||
image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
|
||||
imagePullPolicy: {{ .Values.image.pullPolicy }}
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- |
|
||||
set -e
|
||||
echo "Starting Ollama server for model preload..."
|
||||
ollama serve &
|
||||
OLLAMA_PID=$!
|
||||
sleep 10
|
||||
{{- range .Values.preloadJob.hotModels }}
|
||||
echo "Preloading {{ . }}..."
|
||||
if ollama ls | grep -q "{{ . }}"; then
|
||||
echo "✓ {{ . }} already cached"
|
||||
else
|
||||
ollama pull {{ . }}
|
||||
fi
|
||||
{{- end }}
|
||||
echo "Model preload complete"
|
||||
kill $OLLAMA_PID || true
|
||||
wait $OLLAMA_PID 2>/dev/null || true
|
||||
volumeMounts:
|
||||
- name: models-cache
|
||||
mountPath: /root/.ollama/models
|
||||
env:
|
||||
- name: OLLAMA_HOST
|
||||
value: "127.0.0.1:11434"
|
||||
|
||||
containers:
|
||||
- name: ollama
|
||||
image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
|
||||
imagePullPolicy: {{ .Values.image.pullPolicy }}
|
||||
ports:
|
||||
- containerPort: 11434
|
||||
name: http
|
||||
env:
|
||||
{{- range $key, $value := .Values.env }}
|
||||
- name: {{ $key }}
|
||||
value: "{{ $value }}"
|
||||
{{- end }}
|
||||
- name: OLLAMA_MODELS_MINIO_ENDPOINT
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: ollama-minio
|
||||
key: endpoint
|
||||
- name: OLLAMA_MODELS_MINIO_BUCKET
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: ollama-minio
|
||||
key: bucket
|
||||
- name: OLLAMA_MODELS_MINIO_ACCESS_KEY
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: ollama-minio
|
||||
key: access_key
|
||||
- name: OLLAMA_MODELS_MINIO_SECRET_KEY
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: ollama-minio
|
||||
key: secret_key
|
||||
resources:
|
||||
requests:
|
||||
cpu: {{ .Values.resources.requests.cpu }}
|
||||
memory: {{ .Values.resources.requests.memory }}
|
||||
limits:
|
||||
cpu: {{ .Values.resources.limits.cpu }}
|
||||
memory: {{ .Values.resources.limits.memory }}
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /
|
||||
port: 11434
|
||||
initialDelaySeconds: 30
|
||||
periodSeconds: 10
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /
|
||||
port: 11434
|
||||
initialDelaySeconds: 10
|
||||
periodSeconds: 5
|
||||
volumeMounts:
|
||||
- name: models-cache
|
||||
mountPath: /root/.ollama/models
|
||||
|
||||
volumes:
|
||||
- name: models-cache
|
||||
persistentVolumeClaim:
|
||||
claimName: ollama-models-cache
|
||||
@@ -0,0 +1,28 @@
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: ollama-access
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: ollama
|
||||
policyTypes:
|
||||
- Ingress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: llm-worker
|
||||
ports:
|
||||
- protocol: TCP
|
||||
port: 11434
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/role: llm-debug
|
||||
ports:
|
||||
- protocol: TCP
|
||||
port: 11434
|
||||
@@ -0,0 +1,92 @@
|
||||
{{- if .Values.preloadJob.enabled }}
|
||||
apiVersion: batch/v1
|
||||
kind: Job
|
||||
metadata:
|
||||
name: ollama-preload
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama-preload
|
||||
spec:
|
||||
backoffLimit: 3
|
||||
template:
|
||||
spec:
|
||||
serviceAccountName: default
|
||||
restartPolicy: Never
|
||||
affinity:
|
||||
nodeAffinity:
|
||||
requiredDuringSchedulingIgnoredDuringExecution:
|
||||
nodeSelectorTerms:
|
||||
- matchExpressions:
|
||||
- key: topology.kubernetes.io/zone
|
||||
operator: In
|
||||
values:
|
||||
- az-a
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Equal
|
||||
effect: NoSchedule
|
||||
initContainers:
|
||||
- name: model-cache-init
|
||||
image: ollama/ollama:latest
|
||||
imagePullPolicy: IfNotPresent
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- |
|
||||
set -e
|
||||
echo "Starting Ollama server to cache models..."
|
||||
ollama serve &
|
||||
OLLAMA_PID=$!
|
||||
sleep 10
|
||||
echo "Caching hot-tier models..."
|
||||
{{- range .Values.preloadJob.hotModels }}
|
||||
echo "Checking if {{ . }} is cached..."
|
||||
if ollama ls | grep -q "{{ . }}"; then
|
||||
echo "✓ {{ . }} already cached, skipping"
|
||||
else
|
||||
echo "Pulling {{ . }}..."
|
||||
ollama pull {{ . }}
|
||||
fi
|
||||
{{- end }}
|
||||
echo "Model cache initialization complete"
|
||||
kill $OLLAMA_PID || true
|
||||
wait $OLLAMA_PID 2>/dev/null || true
|
||||
volumeMounts:
|
||||
- name: models
|
||||
mountPath: /root/.ollama
|
||||
env:
|
||||
- name: OLLAMA_HOST
|
||||
value: "127.0.0.1:11434"
|
||||
|
||||
containers:
|
||||
- name: cache-populate
|
||||
image: curlimages/curl:latest
|
||||
imagePullPolicy: IfNotPresent
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- |
|
||||
set -e
|
||||
echo "Waiting for Ollama pod to be ready..."
|
||||
until curl -f http://ollama.llm.svc.cluster.local:11434/api/tags 2>/dev/null; do
|
||||
echo "Ollama not ready, waiting..."
|
||||
sleep 5
|
||||
done
|
||||
echo "Ollama is ready, populating local cache..."
|
||||
{{- range .Values.preloadJob.hotModels }}
|
||||
echo "Checking if {{ . }} is already cached..."
|
||||
if curl -s http://ollama.llm.svc.cluster.local:11434/api/tags | grep -q "{{ . }}"; then
|
||||
echo "✓ {{ . }} already cached, skipping"
|
||||
else
|
||||
echo "Caching {{ . }} locally..."
|
||||
curl -X POST http://ollama.llm.svc.cluster.local:11434/api/pull \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"name":"{{ . }}","stream":false}'
|
||||
fi
|
||||
{{- end }}
|
||||
echo "Local cache population complete"
|
||||
|
||||
volumes:
|
||||
- name: models
|
||||
emptyDir: {}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,14 @@
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: ollama-models-cache
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
spec:
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
storageClassName: {{ .Values.pvc.storageClassName }}
|
||||
resources:
|
||||
requests:
|
||||
storage: {{ .Values.pvc.size }}
|
||||
@@ -0,0 +1,16 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: ollama
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
spec:
|
||||
type: {{ .Values.service.type }}
|
||||
ports:
|
||||
- port: {{ .Values.service.port }}
|
||||
targetPort: http
|
||||
protocol: TCP
|
||||
name: http
|
||||
selector:
|
||||
app.kubernetes.io/name: ollama
|
||||
@@ -0,0 +1,12 @@
|
||||
apiVersion: storage.k8s.io/v1
|
||||
kind: StorageClass
|
||||
metadata:
|
||||
name: longhorn-llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
provisioner: driver.longhorn.io
|
||||
parameters:
|
||||
numberOfReplicas: "1"
|
||||
staleReplicaTimeout: "2880"
|
||||
reclaimPolicy: Retain
|
||||
allowVolumeExpansion: true
|
||||
@@ -0,0 +1,40 @@
|
||||
replicaCount: 1
|
||||
|
||||
image:
|
||||
repository: ollama/ollama
|
||||
pullPolicy: IfNotPresent
|
||||
tag: "latest"
|
||||
|
||||
service:
|
||||
type: ClusterIP
|
||||
port: 11434
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 8
|
||||
memory: 60Gi
|
||||
limits:
|
||||
cpu: 16
|
||||
memory: 100Gi
|
||||
|
||||
pvc:
|
||||
enabled: true
|
||||
size: 115Gi
|
||||
storageClassName: longhorn-llm
|
||||
|
||||
nodeAffinity:
|
||||
zone: az-a
|
||||
|
||||
env:
|
||||
OLLAMA_MODELS: /root/.ollama/models
|
||||
OLLAMA_MAX_LOADED_MODELS: "2"
|
||||
OLLAMA_NUM_PARALLEL: "2"
|
||||
OLLAMA_MAX_QUEUE: "64"
|
||||
OLLAMA_KEEP_ALIVE: "-1"
|
||||
OLLAMA_HOST: "0.0.0.0:11434"
|
||||
|
||||
preloadJob:
|
||||
enabled: false
|
||||
hotModels:
|
||||
- ornith:35b
|
||||
- deepseek-r1:70b
|
||||
Reference in New Issue
Block a user