9dc4d2585f
Rewrite all 5 Grafana dashboards using only confirmed-existing Prometheus
metric names (1023 metrics inventoried). Dashboards now use hardcoded
datasource UIDs instead of unresolvable ${DS_*} template variables.
- Cockpit: 38 panels (service health, gRPC, Argo CI/CD, trading, metrics)
- Training: 33 panels (epochs, loss, Sharpe, Q-values, GPU, hyperopt)
- Trading: 5 rows (overview, latency, gRPC pipeline, data acq, backtesting)
- Infrastructure: 25 panels (cluster, nodes, workloads, storage, GPU, Prometheus)
- Observability: 22 panels (API gateway auth/security/routing, Loki, Tempo)
Fix kube-state-metrics: add part-of label for netpol, fix nodeSelector
(infra→platform), increase memory limit (128→256Mi for OOM), add K8s API
egress rules covering both 10.32.0.0/16 and 172.16.0.0/16 CIDR ranges.
Add training-pods pod-based scrape job for ephemeral Argo workflow pods
exposing metrics on port 9094.
Migrate all image references from localhost:30500 to internal DNS
(gitlab-registry.foxhunt.svc.cluster.local:5000) across 14 YAML files.
Fix import.sh ConfigMap name (grafana-dashboards-infra → infrastructure).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
197 lines
3.9 KiB
YAML
197 lines
3.9 KiB
YAML
# GitLab CE - Foxhunt deployment
|
|
# Runs on 'infra' node pool alongside platform services
|
|
# External Postgres + Redis on same pool
|
|
|
|
global:
|
|
edition: ce
|
|
kas:
|
|
enabled: false
|
|
hosts:
|
|
domain: fxhnt.ai
|
|
gitlab:
|
|
name: git.fxhnt.ai
|
|
https: true
|
|
registry:
|
|
name: git.fxhnt.ai
|
|
https: true
|
|
ingress:
|
|
enabled: false
|
|
configureCertmanager: false
|
|
shell:
|
|
port: 2222
|
|
psql:
|
|
host: postgres.foxhunt.svc.cluster.local
|
|
port: 5432
|
|
database: gitlab
|
|
username: gitlab
|
|
password:
|
|
secret: gitlab-secrets
|
|
key: db-password
|
|
redis:
|
|
host: redis.foxhunt.svc.cluster.local
|
|
port: 6379
|
|
auth:
|
|
enabled: false
|
|
minio:
|
|
enabled: false
|
|
registry:
|
|
bucket: foxhunt-gitlab-registry
|
|
appConfig:
|
|
lfs:
|
|
bucket: foxhunt-gitlab-artifacts
|
|
connection:
|
|
secret: gitlab-s3-credentials
|
|
key: connection
|
|
artifacts:
|
|
bucket: foxhunt-gitlab-artifacts
|
|
connection:
|
|
secret: gitlab-s3-credentials
|
|
key: connection
|
|
uploads:
|
|
bucket: foxhunt-gitlab-artifacts
|
|
connection:
|
|
secret: gitlab-s3-credentials
|
|
key: connection
|
|
packages:
|
|
bucket: foxhunt-gitlab-artifacts
|
|
connection:
|
|
secret: gitlab-s3-credentials
|
|
key: connection
|
|
gitlab_kas:
|
|
enabled: false
|
|
|
|
# Disable bundled databases — use external
|
|
postgresql:
|
|
install: false
|
|
redis:
|
|
install: false
|
|
|
|
# Disable components we don't need
|
|
installCertmanager: false
|
|
certmanager:
|
|
installCRDs: false
|
|
nginx-ingress:
|
|
enabled: false
|
|
prometheus:
|
|
install: true
|
|
rbac:
|
|
create: true
|
|
alertmanager:
|
|
enabled: false
|
|
server:
|
|
nodeSelector:
|
|
k8s.scaleway.com/pool-name: infra
|
|
persistentVolume:
|
|
enabled: false
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 512Mi
|
|
limits:
|
|
cpu: 500m
|
|
memory: 1Gi
|
|
gitlab-runner:
|
|
install: false
|
|
|
|
# Registry — S3-backed, NodePort for kubelet image pulls
|
|
# Token auth disabled (cluster-internal only, secured by network policies)
|
|
# Pods pull via gitlab-registry.foxhunt.svc.cluster.local:5000 (internal DNS)
|
|
registry:
|
|
replicaCount: 1
|
|
hpa:
|
|
minReplicas: 1
|
|
maxReplicas: 1
|
|
service:
|
|
type: NodePort
|
|
nodePort: 30500
|
|
storage:
|
|
secret: gitlab-s3-credentials
|
|
key: registry
|
|
redirect:
|
|
disable: true
|
|
nodeSelector:
|
|
k8s.scaleway.com/pool-name: infra
|
|
|
|
# GitLab core components — all on infra node pool
|
|
gitlab:
|
|
webservice:
|
|
replicaCount: 1
|
|
hpa:
|
|
minReplicas: 1
|
|
maxReplicas: 1
|
|
workerProcesses: 2
|
|
workhorse:
|
|
extraArgs: "-apiLimit 0 -apiQueueLimit 0"
|
|
nodeSelector:
|
|
k8s.scaleway.com/pool-name: infra
|
|
resources:
|
|
requests:
|
|
cpu: 500m
|
|
memory: 2Gi
|
|
limits:
|
|
cpu: 2000m
|
|
memory: 4Gi
|
|
extraEnv:
|
|
REDIS_URL: "redis://redis.foxhunt.svc.cluster.local:6379/8"
|
|
|
|
sidekiq:
|
|
replicas: 1
|
|
hpa:
|
|
minReplicas: 1
|
|
maxReplicas: 1
|
|
concurrency: 10
|
|
nodeSelector:
|
|
k8s.scaleway.com/pool-name: infra
|
|
resources:
|
|
requests:
|
|
cpu: 250m
|
|
memory: 1Gi
|
|
limits:
|
|
cpu: 1000m
|
|
memory: 2Gi
|
|
extraEnv:
|
|
REDIS_URL: "redis://redis.foxhunt.svc.cluster.local:6379/8"
|
|
|
|
gitaly:
|
|
persistence:
|
|
enabled: true
|
|
size: 50Gi
|
|
nodeSelector:
|
|
k8s.scaleway.com/pool-name: infra
|
|
resources:
|
|
requests:
|
|
cpu: 200m
|
|
memory: 512Mi
|
|
limits:
|
|
cpu: 1000m
|
|
memory: 2Gi
|
|
|
|
gitlab-shell:
|
|
replicaCount: 1
|
|
hpa:
|
|
minReplicas: 1
|
|
maxReplicas: 1
|
|
nodeSelector:
|
|
k8s.scaleway.com/pool-name: infra
|
|
service:
|
|
type: NodePort
|
|
nodePort: 32222
|
|
|
|
toolbox:
|
|
backups:
|
|
objectStorage:
|
|
config:
|
|
secret: gitlab-s3-credentials
|
|
key: connection
|
|
nodeSelector:
|
|
k8s.scaleway.com/pool-name: infra
|
|
|
|
kas:
|
|
enabled: false
|
|
hpa:
|
|
minReplicas: 0
|
|
maxReplicas: 0
|
|
|
|
gitlab-exporter:
|
|
enabled: false
|