Will Anderson
93358505fc
Security: - Drop ALL capabilities, enforce non-root, RuntimeDefault seccomp on neuron-mcp, neuron-rest, neuron-marketing pods - Add startup probes (150s window for JVM) so liveness doesn't fire early - Replace docker-sock hostPath with BuildKit rootless TCP endpoint (moby/buildkit:v0.19.0-rootless) — removes node root access from CI - Document full ESO AppRole migration path in cluster-secret-store.yaml Autoscaling & availability: - HPAs on mcp (1–6), rest (1–4), marketing (2–8) at 65–70% CPU - PodDisruptionBudgets (minAvailable: 1) on all three services - NetworkPolicy: default-deny-all in neuron-prod, explicit allow rules for Traefik ingress, intra-namespace, and egress to DNS/platform/vault Observability: - ServiceMonitors for mcp, rest, marketing (cross-namespace enabled in kube-prometheus-stack with serviceMonitorSelectorNilUsesHelmValues:false) - PrometheusRules: high error rate, high latency, crash loops, replica shortage, Postgres down/connections, backup failure, backup staleness Chart version pinning: - kube-prometheus-stack, loki, tempo, redis, alloy, postgres — all pinned to major-version ranges to block silent breaking upgrades Backup hardening: - restic:latest → restic:0.17.3 (deterministic image) - Weekly backup-verify CronJob: restores latest snapshot and validates SQL dump structure (≥5 CREATE TABLE, pg_dump header check) ArgoCD: - neuron-prod AppProject: scopes deploys to neuron-prod + platform ns, blacklists ClusterRole/ClusterRoleBinding/Namespace creation, automated sync window 2–6am UTC, manual always allowed
83 lines
2.4 KiB
YAML
83 lines
2.4 KiB
YAML
apiVersion: argoproj.io/v1alpha1
|
|
kind: Application
|
|
metadata:
|
|
name: alloy
|
|
namespace: argocd
|
|
spec:
|
|
project: default
|
|
source:
|
|
repoURL: https://grafana.github.io/helm-charts
|
|
chart: alloy
|
|
targetRevision: ">=0.9.0, <1.0.0"
|
|
helm:
|
|
values: |
|
|
controller:
|
|
type: daemonset
|
|
alloy:
|
|
configMap:
|
|
content: |
|
|
discovery.kubernetes "pods" {
|
|
role = "pod"
|
|
}
|
|
|
|
discovery.relabel "pods" {
|
|
targets = discovery.kubernetes.pods.targets
|
|
rule {
|
|
source_labels = ["__meta_kubernetes_namespace"]
|
|
target_label = "namespace"
|
|
}
|
|
rule {
|
|
source_labels = ["__meta_kubernetes_pod_name"]
|
|
target_label = "pod"
|
|
}
|
|
rule {
|
|
source_labels = ["__meta_kubernetes_pod_container_name"]
|
|
target_label = "container"
|
|
}
|
|
rule {
|
|
source_labels = ["__meta_kubernetes_pod_label_app"]
|
|
target_label = "app"
|
|
}
|
|
}
|
|
|
|
loki.source.kubernetes "pods" {
|
|
targets = discovery.relabel.pods.output
|
|
forward_to = [loki.write.default.receiver]
|
|
}
|
|
|
|
loki.write "default" {
|
|
endpoint {
|
|
url = "http://loki-gateway.monitoring.svc.cluster.local/loki/api/v1/push"
|
|
tenant_id = "legion"
|
|
}
|
|
}
|
|
|
|
otelcol.receiver.otlp "default" {
|
|
grpc { endpoint = "0.0.0.0:4317" }
|
|
http { endpoint = "0.0.0.0:4318" }
|
|
output {
|
|
traces = [otelcol.exporter.otlp.tempo.input]
|
|
logs = [otelcol.exporter.loki.pantheon.input]
|
|
}
|
|
}
|
|
|
|
otelcol.exporter.otlp "tempo" {
|
|
client {
|
|
endpoint = "tempo.monitoring.svc.cluster.local:4317"
|
|
tls { insecure = true }
|
|
}
|
|
}
|
|
|
|
otelcol.exporter.loki "pantheon" {
|
|
forward_to = [loki.write.default.receiver]
|
|
}
|
|
destination:
|
|
server: https://kubernetes.default.svc
|
|
namespace: monitoring
|
|
syncPolicy:
|
|
automated:
|
|
prune: true
|
|
selfHeal: true
|
|
syncOptions:
|
|
- CreateNamespace=true
|