6df0be81c9
- Prometheus: change nodeSelector from hardware=high-memory (nonexistent label) to kubernetes.io/arch: amd64 Fixes OOMKilled cause - pod was being scheduled on wrong nodes. - litellm-deployment: add resource limits (2Gi/500m requests, 4Gi/2000m limits) + pin image to v1.34.0 Fixes OOMKilled cause - no resource limits were set. - gitea-runner: pin image to v0.12.0 from :latest + add resource limits (512Mi/250m requests, 1Gi/500m limits) Addresses extreme restart count (281) caused by unbounded memory usage and rolling image updates.
55 lines
1.5 KiB
YAML
55 lines
1.5 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: prometheus
|
|
namespace: monitoring
|
|
labels:
|
|
app: prometheus
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: prometheus
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: prometheus
|
|
spec:
|
|
# Target the nucbox (amd64, 24Gi RAM) which is the only node with enough memory for Prometheus.
|
|
nodeSelector:
|
|
kubernetes.io/os: linux
|
|
kubernetes.io/arch: amd64
|
|
serviceAccountName: prometheus
|
|
containers:
|
|
- name: prometheus
|
|
image: prom/prometheus:v2.48.1
|
|
args:
|
|
- '--config.file=/etc/prometheus/prometheus.yml'
|
|
- '--storage.tsdb.path=/prometheus'
|
|
- '--web.console.libraries=/etc/prometheus/console_libraries'
|
|
- '--web.console.templates=/etc/prometheus/consoles'
|
|
- '--storage.tsdb.retention.time=15d'
|
|
- '--web.enable-lifecycle'
|
|
ports:
|
|
- containerPort: 9090
|
|
name: web
|
|
volumeMounts:
|
|
- name: prometheus-config
|
|
mountPath: /etc/prometheus
|
|
- name: prometheus-storage
|
|
mountPath: /prometheus
|
|
resources:
|
|
requests:
|
|
memory: "512Mi"
|
|
cpu: "500m"
|
|
limits:
|
|
memory: "1Gi"
|
|
cpu: "1000m"
|
|
volumes:
|
|
- name: prometheus-config
|
|
configMap:
|
|
name: prometheus-config
|
|
- name: prometheus-storage
|
|
persistentVolumeClaim:
|
|
claimName: prometheus-storage
|