rock
e4f6f03a8c
## Problem ComfyUI pod restarting 273+ times over 45h. Startup probe failed every time. ## Root Cause ai-dock image runs ComfyUI on port 18188 (adds 10000 to configured port), not 8188. Caddy does NOT proxy 8188->18188. ## Fix - deployment: containerPort, probes -> 18188 - service: targetPort -> 18188 - ingress: TLS at comfyui.riotpiao.com, WebSocket headers - CoreDNS: rewrite comfyui.riotpiao.com ## Post-merge CoreDNS rewrite needs terraform apply + make apply-cp. Cloudflare DNS: add CNAME comfyui.riotpiao.com -> tunnel.Reviewed-on: #44 Co-authored-by: rock <[email protected]>
83 lines
2.0 KiB
YAML
83 lines
2.0 KiB
YAML
# ComfyUI — GPU-accelerated image generation on worker-1.
|
|
# Uses 1x V100 32GB (sm70). Freed by scaling ornith 2→1.
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: comfyui
|
|
namespace: comfyui
|
|
labels:
|
|
app: comfyui
|
|
spec:
|
|
replicas: 1
|
|
strategy:
|
|
type: Recreate
|
|
selector:
|
|
matchLabels:
|
|
app: comfyui
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: comfyui
|
|
spec:
|
|
nodeSelector:
|
|
kubernetes.io/hostname: worker-1
|
|
runtimeClassName: nvidia
|
|
containers:
|
|
- name: comfyui
|
|
image: ghcr.io/ai-dock/comfyui:v2-cuda-12.1.1-base-22.04
|
|
ports:
|
|
- containerPort: 18188
|
|
protocol: TCP
|
|
env:
|
|
- name: NVIDIA_VISIBLE_DEVICES
|
|
value: "all"
|
|
# ai-dock adds 10000 to port: ComfyUI listens on 18188 (localhost)
|
|
# caddy is NOT configured to proxy 8188->18188 in this image
|
|
- name: COMFYUI_PORT_HOST
|
|
value: "18188"
|
|
resources:
|
|
requests:
|
|
cpu: "4"
|
|
memory: 8Gi
|
|
nvidia.com/gpu: "1"
|
|
limits:
|
|
cpu: "8"
|
|
memory: 16Gi
|
|
nvidia.com/gpu: "1"
|
|
volumeMounts:
|
|
- mountPath: /workspace/ComfyUI/models
|
|
name: models
|
|
- mountPath: /workspace/ComfyUI/output
|
|
name: output
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /
|
|
port: 18188
|
|
periodSeconds: 10
|
|
initialDelaySeconds: 30
|
|
startupProbe:
|
|
httpGet:
|
|
path: /
|
|
port: 18188
|
|
failureThreshold: 60
|
|
periodSeconds: 10
|
|
volumes:
|
|
- name: models
|
|
persistentVolumeClaim:
|
|
claimName: comfyui-models
|
|
- name: output
|
|
emptyDir: {}
|
|
---
|
|
apiVersion: v1
|
|
kind: PersistentVolumeClaim
|
|
metadata:
|
|
name: comfyui-models
|
|
namespace: comfyui
|
|
spec:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
storageClassName: longhorn
|
|
resources:
|
|
requests:
|
|
storage: 50Gi
|