5380bd9186
- Split single H100 GPU pool into two purpose-specific pools: - gpu-training: H100-1-80G (€2.73/hr) for 10-model ensemble training - gpu-inference: L4-1-24G (€0.75/hr) for cost-effective trading inference - Add GPU taint controller DaemonSet that auto-taints new GPU nodes with nvidia.com/gpu=true:NoSchedule to prevent non-GPU workloads - Fix service log directory permissions with emptyDir volumes (observability init fails creating /app/logs as non-root user) - Increase postgres max_connections from 25 to 100 (7 services each requesting connection pools exhausted the limit) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
96 lines
2.1 KiB
YAML
96 lines
2.1 KiB
YAML
apiVersion: v1
|
|
kind: PersistentVolumeClaim
|
|
metadata:
|
|
name: postgres-pvc
|
|
namespace: foxhunt
|
|
labels:
|
|
app.kubernetes.io/name: postgres
|
|
app.kubernetes.io/part-of: foxhunt
|
|
spec:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
resources:
|
|
requests:
|
|
storage: 10Gi
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: postgres
|
|
namespace: foxhunt
|
|
labels:
|
|
app.kubernetes.io/name: postgres
|
|
app.kubernetes.io/part-of: foxhunt
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: postgres
|
|
strategy:
|
|
type: Recreate
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: postgres
|
|
spec:
|
|
nodeSelector:
|
|
k8s.scaleway.com/pool-name: always-on
|
|
containers:
|
|
- name: postgres
|
|
image: timescale/timescaledb:latest-pg16
|
|
ports:
|
|
- containerPort: 5432
|
|
name: postgres
|
|
args:
|
|
- -c
|
|
- max_connections=100
|
|
env:
|
|
- name: POSTGRES_DB
|
|
value: foxhunt
|
|
- name: POSTGRES_USER
|
|
value: foxhunt
|
|
- name: POSTGRES_PASSWORD
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: foxhunt-secrets
|
|
key: db-password
|
|
volumeMounts:
|
|
- name: postgres-data
|
|
mountPath: /var/lib/postgresql/data
|
|
subPath: pgdata
|
|
readinessProbe:
|
|
exec:
|
|
command:
|
|
- pg_isready
|
|
- -U
|
|
- foxhunt
|
|
initialDelaySeconds: 10
|
|
periodSeconds: 10
|
|
resources:
|
|
requests:
|
|
cpu: 200m
|
|
memory: 512Mi
|
|
limits:
|
|
cpu: 500m
|
|
memory: 1Gi
|
|
volumes:
|
|
- name: postgres-data
|
|
persistentVolumeClaim:
|
|
claimName: postgres-pvc
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: postgres
|
|
namespace: foxhunt
|
|
labels:
|
|
app.kubernetes.io/name: postgres
|
|
app.kubernetes.io/part-of: foxhunt
|
|
spec:
|
|
selector:
|
|
app.kubernetes.io/name: postgres
|
|
ports:
|
|
- port: 5432
|
|
targetPort: 5432
|
|
name: postgres
|