Drill-only --synthetic-until/--accelerate and evo-world-clone compare (compare_region_histories) prove a candidate build runs the same world on clones of one cut before any barrier. upgrade-check.sh rehearses a failed migration under load and the version barrier with real hosts; upgrade-barrier.sh retires an old build in dev/stage only once the new digest is Ready. Nodes: aevolution.io/stores pins every objects-volume pod, aevolution.io/compute is preference-only (Alertmanager first), checked by policy and scheduling-check.sh. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
100 lines
3.0 KiB
YAML
100 lines
3.0 KiB
YAML
# M8.5 Alertmanager (ADR-0072), pinned by digest. Every alert routes to the null
|
|
# receiver until the maintainer chooses a destination (docs/BACKLOG.md); alerts are
|
|
# still visible in its API and UI. Silences live in memory (emptyDir).
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: alertmanager
|
|
labels:
|
|
app.kubernetes.io/name: alertmanager
|
|
spec:
|
|
replicas: 1
|
|
strategy:
|
|
type: Recreate
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: alertmanager
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: alertmanager
|
|
app.kubernetes.io/part-of: aevolution
|
|
spec:
|
|
serviceAccountName: aevolution-alertmanager
|
|
automountServiceAccountToken: false
|
|
# Stateless: prefers nodes labelled for AEvolution compute (ADR-0076), and
|
|
# schedules anywhere while none is labelled (the single-node plan).
|
|
affinity:
|
|
nodeAffinity:
|
|
preferredDuringSchedulingIgnoredDuringExecution:
|
|
- weight: 100
|
|
preference:
|
|
matchExpressions:
|
|
- {key: aevolution.io/compute, operator: In, values: ["true"]}
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
runAsUser: 65534
|
|
runAsGroup: 65534
|
|
fsGroup: 65534
|
|
seccompProfile: {type: RuntimeDefault}
|
|
containers:
|
|
- name: alertmanager
|
|
image: quay.io/prometheus/alertmanager:v0.34.1@sha256:e9733bafb1bdef9b00e25a21f8f99dc26a22224bf16641ad754d1649f4c3357a
|
|
args:
|
|
- --config.file=/etc/alertmanager/alertmanager.yml
|
|
- --storage.path=/alertmanager
|
|
- --web.listen-address=:9093
|
|
- --cluster.listen-address= # Single instance: no gossip port.
|
|
ports:
|
|
- {name: web, containerPort: 9093}
|
|
readinessProbe:
|
|
httpGet: {path: /-/ready, port: web}
|
|
periodSeconds: 10
|
|
livenessProbe:
|
|
httpGet: {path: /-/healthy, port: web}
|
|
periodSeconds: 20
|
|
resources:
|
|
requests: {cpu: 50m, memory: 64Mi}
|
|
limits: {memory: 128Mi}
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: true
|
|
capabilities: {drop: [ALL]}
|
|
volumeMounts:
|
|
- {name: config, mountPath: /etc/alertmanager, readOnly: true}
|
|
- {name: data, mountPath: /alertmanager}
|
|
volumes:
|
|
- name: config
|
|
configMap:
|
|
name: alertmanager-config
|
|
- name: data
|
|
emptyDir: {sizeLimit: 64Mi}
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: alertmanager
|
|
spec:
|
|
type: ClusterIP
|
|
selector:
|
|
app.kubernetes.io/name: alertmanager
|
|
ports:
|
|
- {name: web, port: 9093, targetPort: web}
|
|
---
|
|
apiVersion: networking.k8s.io/v1
|
|
kind: NetworkPolicy
|
|
metadata:
|
|
name: alertmanager
|
|
spec:
|
|
podSelector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: alertmanager
|
|
policyTypes: [Ingress]
|
|
ingress:
|
|
- from:
|
|
- podSelector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: prometheus
|
|
ports:
|
|
- {protocol: TCP, port: 9093}
|