Stéphane Tailland
3937b4f366
Deploys the whole stack into the observability namespace of the local cluster with Kustomize alone — no helm install, no dashboard created by hand in the UI. The Makefile carries every command: deploy, dashboards, diagnostics, PVC flush, teardown. Dashboards are files, never UI objects. Each carries a stable uid, which is what keeps URLs, cross-links and alerts alive across redeployments, and references datasources by stable uid rather than by name. The dashboard ConfigMap is generated without a name-suffix hash so applying it updates it in place and Grafana reloads without a restart, while the provisioning ConfigMaps keep their hash precisely so that a change there does force one. Prometheus scrapes the kubelet /metrics/resource endpoint rather than /metrics/cadvisor: on this cluster cadvisor exposes machine_* series only and no container_* at all, which would leave every CPU and memory panel empty. Alloy ships every pod's logs to Loki through the Kubernetes API, so no /var/log mount is needed. Tempo's metrics_generator feeds span metrics and the service graph back into Prometheus, and the datasources are wired so a log line's trace_id opens the matching trace. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
74 lines
2.0 KiB
YAML
74 lines
2.0 KiB
YAML
apiVersion: apps/v1
|
|
kind: DaemonSet
|
|
metadata:
|
|
name: alloy
|
|
namespace: observability
|
|
labels:
|
|
app.kubernetes.io/name: alloy
|
|
app.kubernetes.io/component: collector
|
|
app.kubernetes.io/part-of: observability
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
app: alloy
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: alloy
|
|
app.kubernetes.io/name: alloy
|
|
app.kubernetes.io/component: collector
|
|
app.kubernetes.io/part-of: observability
|
|
annotations:
|
|
prometheus.io/scrape: "true"
|
|
prometheus.io/port: "12345"
|
|
spec:
|
|
serviceAccountName: alloy
|
|
tolerations:
|
|
- operator: Exists
|
|
containers:
|
|
- name: alloy
|
|
image: grafana/alloy:v1.19.0
|
|
args:
|
|
- run
|
|
- /etc/alloy/config.alloy
|
|
- --storage.path=/var/lib/alloy/data
|
|
- --server.http.listen-addr=0.0.0.0:12345
|
|
- --disable-reporting
|
|
env:
|
|
# Used by config.alloy to tail only the pods on the current node.
|
|
- name: HOSTNAME_NODE
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: spec.nodeName
|
|
ports:
|
|
- name: http
|
|
containerPort: 12345
|
|
resources:
|
|
requests:
|
|
cpu: 50m
|
|
memory: 128Mi
|
|
limits:
|
|
cpu: "1"
|
|
memory: 512Mi
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /-/ready
|
|
port: http
|
|
initialDelaySeconds: 10
|
|
periodSeconds: 10
|
|
volumeMounts:
|
|
- name: config
|
|
mountPath: /etc/alloy
|
|
- name: storage
|
|
mountPath: /var/lib/alloy
|
|
volumes:
|
|
- name: config
|
|
configMap:
|
|
name: alloy-config
|
|
- name: storage
|
|
# Read positions persisted on the node: no full log re-ingestion
|
|
# when the pod restarts.
|
|
hostPath:
|
|
path: /var/lib/alloy
|
|
type: DirectoryOrCreate
|