Compare commits
25 Commits
148bc87b9a
...
codex/s50-
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2c8968f5d0 | ||
|
|
0307ae16ae | ||
|
|
6c18f69cf2 | ||
|
|
47e2256556 | ||
|
|
9d77f8ba0e | ||
|
|
2f4be19c85 | ||
|
|
2a62c40990 | ||
|
|
7be98e5efc | ||
|
|
a65b356c9d | ||
|
|
08c17ef1b4 | ||
|
|
06f2f002b7 | ||
|
|
7ac4a8b4b7 | ||
|
|
90f2a86819 | ||
|
|
cbdefb2b23 | ||
|
|
1c36fe3a0a | ||
|
|
2b420ce8a4 | ||
|
|
5cbc1a06b1 | ||
|
|
9e7ee39b3a | ||
|
|
ae030a5f33 | ||
| bc8c35896f | |||
|
|
2cc91b6df0 | ||
| 0d2090fe81 | |||
|
|
bc3548e715 | ||
| 74333cc26b | |||
|
|
7310fb88c2 |
33
apps/fc-signalcontrol/README.md
Normal file
33
apps/fc-signalcontrol/README.md
Normal file
@@ -0,0 +1,33 @@
|
||||
# FlowerCore SignalControl platform notes
|
||||
|
||||
This app owns the cluster web manager at `signalcontrol.iamworkin.lan` and documents the physical Pi pilot at `signal-a.iamworkin.lan` / `pirelay`.
|
||||
|
||||
## mTLS enrollment pattern
|
||||
|
||||
Do not install or restart anything from this repo. The intended pirelay pattern is the Pi-signage step-ca-agent shape:
|
||||
|
||||
- stable node identity: `pirelay`
|
||||
- local private key and CSR generated on the node
|
||||
- CSR submitted through the approved DeviceManagement/step-ca enrollment path
|
||||
- client certificate and chain stored node-local under `/etc/flowercore/signalcontrol/mtls/`
|
||||
- daily renewal timer, renewing only when fewer than 30 days remain
|
||||
- certificate used for DM-agent to DM-web traffic and future SignalControl inter-service calls
|
||||
|
||||
Secrets, enrollment codes, private keys, p12 passphrases, and OIDC client secrets stay out of Git.
|
||||
|
||||
## Telemetry
|
||||
|
||||
Monitoring manifests add a dedicated Prometheus job:
|
||||
|
||||
- `signalcontrol-pi-app`
|
||||
- target `10.0.58.113:5200`
|
||||
- path `/metrics/prometheus`
|
||||
- labels `instance="pirelay"`, `host="signal-a.iamworkin.lan"`, `service="signalcontrol-pi"`
|
||||
|
||||
Host metrics continue through the `edge-nodes` node_exporter target at `10.0.58.113:9100`.
|
||||
|
||||
## Physical-control audit
|
||||
|
||||
The app ships with `FlowerCore:SignalControl:PhysicalAudit:Enabled=false` and `ForwardingEnabled=false`. Enabling local audit creates a SHA-256 hash chain for physical-control mutations. Forwarding to `https://audit.iamworkin.lan/api/v1/audit/signalcontrol` requires flipping the forwarding gate separately.
|
||||
|
||||
Telemetry reads and `/metrics` scrapes are not audited.
|
||||
@@ -46,7 +46,7 @@ spec:
|
||||
spec:
|
||||
containers:
|
||||
- name: signalcontrol-web
|
||||
image: localhost/fc-signalcontrol-web:latest
|
||||
image: localhost/fc-signalcontrol-web:s50cx12-20260602-1d26c58
|
||||
imagePullPolicy: Never
|
||||
ports:
|
||||
- containerPort: 5000
|
||||
@@ -65,6 +65,48 @@ spec:
|
||||
secretKeyRef:
|
||||
name: signalcontrol-auth
|
||||
key: Auth__ApiKey
|
||||
- name: Auth__AdminApiKey
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: signalcontrol-auth
|
||||
key: Auth__AdminApiKey
|
||||
optional: true
|
||||
- name: Auth__Enabled
|
||||
value: "false"
|
||||
- name: FlowerCore__Auth__Enabled
|
||||
value: "false"
|
||||
- name: FlowerCore__Auth__Oidc__Enabled
|
||||
value: "true"
|
||||
- name: FlowerCore__Auth__Oidc__Authority
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: signalcontrol-oidc-client
|
||||
key: issuer_url
|
||||
optional: true
|
||||
- name: FlowerCore__Auth__Oidc__ClientId
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: signalcontrol-oidc-client
|
||||
key: client_id
|
||||
optional: true
|
||||
- name: FlowerCore__Auth__Oidc__ClientSecret
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: signalcontrol-oidc-client
|
||||
key: client_secret
|
||||
optional: true
|
||||
- name: TrafficSignal__RelayBridge__Enabled
|
||||
value: "true"
|
||||
- name: TrafficSignal__RelayBridge__BaseUrl
|
||||
value: https://pirelay.iamworkin.lan
|
||||
- name: TrafficSignal__RelayBridge__ApiKey
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: signalcontrol-pirelay
|
||||
key: ApiKey
|
||||
optional: true
|
||||
- name: LiveStatus__TrafficSignal__BaseAddress
|
||||
value: https://signalcontrol.iamworkin.lan
|
||||
volumeMounts:
|
||||
- name: data
|
||||
mountPath: /data
|
||||
|
||||
@@ -532,7 +532,7 @@ spec:
|
||||
fsGroupChangePolicy: OnRootMismatch
|
||||
containers:
|
||||
- name: web
|
||||
image: localhost/fc-ttsreader-web:v20260518-sprint36-demo-finish-b132cbf
|
||||
image: localhost/fc-ttsreader-web:v20260531-tts-corrections-r2
|
||||
imagePullPolicy: Never
|
||||
ports:
|
||||
- containerPort: 5217
|
||||
@@ -554,6 +554,8 @@ spec:
|
||||
value: "/data/chapter-context.db"
|
||||
- name: TtsReader__Jobs__Root
|
||||
value: "/data/jobs"
|
||||
- name: TtsReader__Export__LocalCasRoot
|
||||
value: "/data/bundles/cas"
|
||||
- name: TtsReader__Piper__Host
|
||||
value: "10.0.57.17"
|
||||
- name: TtsReader__Piper__Port
|
||||
|
||||
@@ -58,7 +58,7 @@ spec:
|
||||
nodeName: rke2-server
|
||||
containers:
|
||||
- name: web
|
||||
image: localhost/fc-updater-web:v20260509-4162dca-authgate
|
||||
image: localhost/fc-updater-web:v202605310029-7974fc4
|
||||
imagePullPolicy: Never
|
||||
ports:
|
||||
- containerPort: 8080
|
||||
@@ -88,6 +88,8 @@ spec:
|
||||
value: Faith AI Mike Edition
|
||||
- name: FlowerCore__Updater__PublicShares__Links__0__Description
|
||||
value: Private release link for Mike's Faith AI bundle.
|
||||
- name: FlowerCore__Audit__Sinks__Loki__Enabled
|
||||
value: "false"
|
||||
- name: FlowerCore__Updater__Auth__Bootstrap__Enabled
|
||||
value: "true"
|
||||
- name: FlowerCore__Updater__Auth__Bootstrap__Username
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -46,7 +46,7 @@ spec:
|
||||
spec:
|
||||
containers:
|
||||
- name: intranet-web
|
||||
image: localhost/fc-intranet-web:v20260508-brochure-w1
|
||||
image: localhost/fc-intranet-web:v20260531-ttsreader-bridge
|
||||
imagePullPolicy: Never
|
||||
ports:
|
||||
- containerPort: 5300
|
||||
|
||||
@@ -25,7 +25,7 @@ metadata:
|
||||
role: github-actions-runner
|
||||
flowercore.io/managed-by: bluejay-infra
|
||||
spec:
|
||||
runStrategy: Always
|
||||
runStrategy: Halted
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
|
||||
@@ -207,20 +207,13 @@ spec:
|
||||
- port: 993
|
||||
targetPort: 993
|
||||
name: imaps
|
||||
---
|
||||
# TLS Certificate via cert-manager
|
||||
apiVersion: cert-manager.io/v1
|
||||
kind: Certificate
|
||||
metadata:
|
||||
name: mail-tls
|
||||
namespace: mail
|
||||
spec:
|
||||
secretName: mail-tls
|
||||
issuerRef:
|
||||
name: step-ca-acme
|
||||
kind: ClusterIssuer
|
||||
dnsNames:
|
||||
- mail.iamworkin.lan
|
||||
# --- mail-tls Certificate REMOVED 2026-06-01 ---
|
||||
# mail-tls is now managed OUTSIDE cert-manager: issued from step-ca's JWK 'admin'
|
||||
# provisioner and auto-renewed by a systemd timer on noc1 (step ca renew), which
|
||||
# writes the mail-tls secret directly. step-ca-acme only has an HTTP-01 (Traefik)
|
||||
# solver, but mail.iamworkin.lan must resolve to the dedicated MetalLB IP 10.0.56.202
|
||||
# (SMTP/IMAP), so HTTP-01 cannot validate. Do NOT re-add a cert-manager Certificate
|
||||
# here unless a DNS-01 solver is deployed for step-ca-acme.
|
||||
---
|
||||
# Traefik IngressRoute - Webmail placeholder
|
||||
apiVersion: traefik.io/v1alpha1
|
||||
|
||||
260
apps/monitoring/grafana-dashboard-signalcontrol.yaml
Normal file
260
apps/monitoring/grafana-dashboard-signalcontrol.yaml
Normal file
@@ -0,0 +1,260 @@
|
||||
# Grafana dashboard ConfigMap for FlowerCore.SignalControl on pirelay.
|
||||
#
|
||||
# The Grafana Deployment in noc-monitoring.yaml mounts this ConfigMap at
|
||||
# /var/lib/grafana/dashboards/signalcontrol. The paired Prometheus jobs are:
|
||||
# - signalcontrol-pi-app: 10.0.58.113:5200 /metrics/prometheus
|
||||
# - edge-nodes: 10.0.58.113:9100 with instance="pirelay"
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: grafana-dashboard-signalcontrol
|
||||
namespace: monitoring
|
||||
data:
|
||||
signalcontrol.json: |
|
||||
{
|
||||
"annotations": { "list": [] },
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 0,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "red", "value": null },
|
||||
{ "color": "green", "value": 1 }
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 5, "w": 6, "x": 0, "y": 0 },
|
||||
"id": 1,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{ "editorMode": "code", "expr": "up{job=\"signalcontrol-pi-app\",instance=\"pirelay\"}", "range": true, "refId": "A" }
|
||||
],
|
||||
"title": "SignalControl App Up",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "red", "value": null },
|
||||
{ "color": "green", "value": 1 }
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 5, "w": 6, "x": 6, "y": 0 },
|
||||
"id": 2,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{ "editorMode": "code", "expr": "up{job=\"edge-nodes\",instance=\"pirelay\"}", "range": true, "refId": "A" }
|
||||
],
|
||||
"title": "pirelay node_exporter Up",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "short" }, "overrides": [] },
|
||||
"gridPos": { "h": 5, "w": 6, "x": 12, "y": 0 },
|
||||
"id": 3,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false },
|
||||
"textMode": "name"
|
||||
},
|
||||
"targets": [
|
||||
{ "editorMode": "code", "expr": "signalcontrol_active_pattern{job=\"signalcontrol-pi-app\",instance=\"pirelay\"}", "legendFormat": "{{pattern}}", "range": true, "refId": "A" }
|
||||
],
|
||||
"title": "Active Pattern",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "short" }, "overrides": [] },
|
||||
"gridPos": { "h": 5, "w": 6, "x": 18, "y": 0 },
|
||||
"id": 4,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false },
|
||||
"textMode": "name"
|
||||
},
|
||||
"targets": [
|
||||
{ "editorMode": "code", "expr": "signalcontrol_phase{job=\"signalcontrol-pi-app\",instance=\"pirelay\"}", "legendFormat": "{{phase}}", "range": true, "refId": "A" }
|
||||
],
|
||||
"title": "Current Phase",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "ops" }, "overrides": [] },
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 5 },
|
||||
"id": 5,
|
||||
"options": { "legend": { "displayMode": "table", "placement": "bottom" }, "tooltip": { "mode": "single" } },
|
||||
"targets": [
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "sum by (channel, state) (rate(signal_relay_writes_total{job=\"signalcontrol-pi-app\",instance=\"pirelay\"}[$__rate_interval]))",
|
||||
"legendFormat": "channel {{channel}} {{state}}",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Relay Activations",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "ops" }, "overrides": [] },
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 5 },
|
||||
"id": 6,
|
||||
"options": { "legend": { "displayMode": "table", "placement": "bottom" }, "tooltip": { "mode": "single" } },
|
||||
"targets": [
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "sum by (source, to) (rate(signal_transitions_total{job=\"signalcontrol-pi-app\",instance=\"pirelay\"}[$__rate_interval]))",
|
||||
"legendFormat": "{{source}} -> {{to}}",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Phase Dwell / Transitions",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "short" }, "overrides": [] },
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 13 },
|
||||
"id": 7,
|
||||
"options": { "legend": { "displayMode": "table", "placement": "bottom" }, "tooltip": { "mode": "single" } },
|
||||
"targets": [
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "sum by (action, outcome) (increase(signal_schedule_fires_total{job=\"signalcontrol-pi-app\",instance=\"pirelay\"}[24h]))",
|
||||
"legendFormat": "{{action}} {{outcome}}",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "sum by (from_pattern, to_pattern) (increase(flowercore_signalcontrol_pattern_switches_total{job=\"signalcontrol-pi-app\",instance=\"pirelay\"}[24h]))",
|
||||
"legendFormat": "{{from_pattern}} -> {{to_pattern}}",
|
||||
"range": true,
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "Schedule Fires and Pattern Switches",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percentunit" }, "overrides": [] },
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 13 },
|
||||
"id": 8,
|
||||
"options": { "legend": { "displayMode": "table", "placement": "bottom" }, "tooltip": { "mode": "single" } },
|
||||
"targets": [
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "1 - avg by (instance) (rate(node_cpu_seconds_total{job=\"edge-nodes\",instance=\"pirelay\",mode=\"idle\"}[$__rate_interval]))",
|
||||
"legendFormat": "CPU",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "1 - (node_memory_MemAvailable_bytes{job=\"edge-nodes\",instance=\"pirelay\"} / node_memory_MemTotal_bytes{job=\"edge-nodes\",instance=\"pirelay\"})",
|
||||
"legendFormat": "Memory",
|
||||
"range": true,
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "pirelay Host Utilization",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "short" }, "overrides": [] },
|
||||
"gridPos": { "h": 6, "w": 12, "x": 0, "y": 21 },
|
||||
"id": 9,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{ "editorMode": "code", "expr": "signalcontrol_screen_saver_enabled{job=\"signalcontrol-pi-app\",instance=\"pirelay\"}", "range": true, "refId": "A" }
|
||||
],
|
||||
"title": "Screen-saver Enabled",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "short" }, "overrides": [] },
|
||||
"gridPos": { "h": 6, "w": 12, "x": 12, "y": 21 },
|
||||
"id": 10,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false },
|
||||
"textMode": "name"
|
||||
},
|
||||
"targets": [
|
||||
{ "editorMode": "code", "expr": "signalcontrol_animation_active{job=\"signalcontrol-pi-app\",instance=\"pirelay\"}", "legendFormat": "{{planner}}", "range": true, "refId": "A" }
|
||||
],
|
||||
"title": "Screen-saver / Animation Engaged",
|
||||
"type": "stat"
|
||||
}
|
||||
],
|
||||
"refresh": "30s",
|
||||
"schemaVersion": 39,
|
||||
"style": "dark",
|
||||
"tags": [ "flowercore", "signalcontrol", "pirelay" ],
|
||||
"templating": { "list": [] },
|
||||
"time": { "from": "now-24h", "to": "now" },
|
||||
"timezone": "browser",
|
||||
"title": "FlowerCore SignalControl",
|
||||
"uid": "flowercore-signalcontrol",
|
||||
"version": 1
|
||||
}
|
||||
@@ -230,6 +230,19 @@ data:
|
||||
vlan: "home"
|
||||
device: "pi3-ks0212"
|
||||
|
||||
# SignalControl Pi-edition app metrics (pirelay / signal-a)
|
||||
- job_name: "signalcontrol-pi-app"
|
||||
scrape_interval: 15s
|
||||
metrics_path: /metrics/prometheus
|
||||
static_configs:
|
||||
- targets: ["10.0.58.113:5200"]
|
||||
labels:
|
||||
instance: "pirelay"
|
||||
host: "signal-a.iamworkin.lan"
|
||||
service: "signalcontrol-pi"
|
||||
vlan: "home"
|
||||
device: "pi3-ks0212"
|
||||
|
||||
# Epson ET-3750 EcoTank Printer SNMP
|
||||
- job_name: "snmp-printer"
|
||||
scrape_interval: 5m
|
||||
@@ -479,11 +492,11 @@ data:
|
||||
- "https://gitea.iamworkin.lan/"
|
||||
- "https://argocd.iamworkin.lan/"
|
||||
- "https://intranet.iamworkin.lan/"
|
||||
- "https://signage.iamworkin.lan/"
|
||||
- "https://signage.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
|
||||
- "https://kiosk.iamworkin.lan/"
|
||||
- "https://media.iamworkin.lan/"
|
||||
- "https://mysql.iamworkin.lan/"
|
||||
- "https://php.iamworkin.lan/"
|
||||
- "https://mysql.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
|
||||
- "https://php.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
|
||||
- "https://zabbix.iamworkin.lan/"
|
||||
- "https://desktop.iamworkin.lan/"
|
||||
- "https://print.iamworkin.lan/"
|
||||
@@ -4051,6 +4064,9 @@ spec:
|
||||
- name: dashboards-remotedesktop
|
||||
mountPath: /var/lib/grafana/dashboards/remotedesktop
|
||||
readOnly: true
|
||||
- name: dashboards-signalcontrol
|
||||
mountPath: /var/lib/grafana/dashboards/signalcontrol
|
||||
readOnly: true
|
||||
- name: datasource-provisioning
|
||||
mountPath: /etc/grafana/provisioning/datasources
|
||||
readOnly: true
|
||||
@@ -4104,6 +4120,9 @@ spec:
|
||||
- name: dashboards-remotedesktop
|
||||
configMap:
|
||||
name: grafana-dashboard-remotedesktop
|
||||
- name: dashboards-signalcontrol
|
||||
configMap:
|
||||
name: grafana-dashboard-signalcontrol
|
||||
- name: datasource-provisioning
|
||||
configMap:
|
||||
name: grafana-datasource-provisioning
|
||||
|
||||
@@ -132,13 +132,18 @@ spec:
|
||||
initialDelaySeconds: 10
|
||||
periodSeconds: 5
|
||||
timeoutSeconds: 5
|
||||
# Hub baseline working set ~766Mi on 2026-05-25 (75% of prior 1Gi
|
||||
# limit). Bump to 1.5Gi / 1Gi to keep ~50% headroom; matches the
|
||||
# stampede-buffer pattern documented for multus
|
||||
# (feedback_k8s_cni_multus_sizing). CPU left alone — observed 54m
|
||||
# against a 500m limit, no contention.
|
||||
resources:
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 1Gi
|
||||
memory: 1536Mi
|
||||
requests:
|
||||
cpu: 250m
|
||||
memory: 512Mi
|
||||
memory: 1Gi
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
@@ -198,13 +203,18 @@ spec:
|
||||
port: 5555
|
||||
initialDelaySeconds: 15
|
||||
periodSeconds: 5
|
||||
# Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
|
||||
# -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
|
||||
# original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
|
||||
# was running 684Mi idle on the same cap. Matches the Firefox node's
|
||||
# tested-stable 2Gi limit. CPU unchanged.
|
||||
resources:
|
||||
limits:
|
||||
cpu: '1'
|
||||
memory: 1Gi
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: 500m
|
||||
memory: 512Mi
|
||||
memory: 1Gi
|
||||
volumeMounts:
|
||||
- mountPath: /dev/shm
|
||||
name: dshm
|
||||
@@ -378,13 +388,18 @@ spec:
|
||||
port: 5555
|
||||
initialDelaySeconds: 15
|
||||
periodSeconds: 5
|
||||
# Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
|
||||
# -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
|
||||
# original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
|
||||
# was running 684Mi idle on the same cap. Matches the Firefox node's
|
||||
# tested-stable 2Gi limit. CPU unchanged.
|
||||
resources:
|
||||
limits:
|
||||
cpu: '1'
|
||||
memory: 1Gi
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: 500m
|
||||
memory: 512Mi
|
||||
memory: 1Gi
|
||||
volumeMounts:
|
||||
- mountPath: /dev/shm
|
||||
name: dshm
|
||||
|
||||
@@ -67,6 +67,7 @@ public sealed class FleetManifestLintTests
|
||||
["github-runner-chat"] = "https://github.com/astoltz/FlowerCore.Chat",
|
||||
["github-runner-mysql"] = "https://github.com/astoltz/FlowerCore.MySQL",
|
||||
["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux",
|
||||
["github-runner-updater"] = "https://github.com/astoltz/FlowerCore.Updater",
|
||||
};
|
||||
|
||||
private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
|
||||
@@ -80,6 +81,7 @@ public sealed class FleetManifestLintTests
|
||||
"github-runner-chat",
|
||||
"github-runner-mysql",
|
||||
"github-runner-kiosk-linux",
|
||||
"github-runner-updater",
|
||||
};
|
||||
|
||||
private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
|
||||
@@ -225,6 +227,50 @@ public sealed class FleetManifestLintTests
|
||||
violations.Should().BeEmpty();
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void SignalControlDeployment_MustKeepAuthOffAndStageOidcSecret()
|
||||
{
|
||||
var deployment = Inventory.Documents.Single(document =>
|
||||
document.Kind == "Deployment"
|
||||
&& document.Namespace == "fc-signalcontrol"
|
||||
&& document.Name == "signalcontrol-web"
|
||||
&& document.RelativePath == "fc-signalcontrol/fc-signalcontrol.yaml");
|
||||
var container = deployment.MainContainerMappings().Single(container =>
|
||||
ManifestNodeExtensions.Scalar(container, "name") == "signalcontrol-web");
|
||||
|
||||
EnvValue(container, "Auth__Enabled").Should().Be("false");
|
||||
EnvValue(container, "FlowerCore__Auth__Enabled").Should().Be("false");
|
||||
EnvValue(container, "FlowerCore__Auth__Oidc__Enabled").Should().Be("true");
|
||||
EnvSecretName(container, "FlowerCore__Auth__Oidc__Authority").Should().Be("signalcontrol-oidc-client");
|
||||
EnvSecretKey(container, "FlowerCore__Auth__Oidc__Authority").Should().Be("issuer_url");
|
||||
EnvSecretName(container, "FlowerCore__Auth__Oidc__ClientId").Should().Be("signalcontrol-oidc-client");
|
||||
EnvSecretKey(container, "FlowerCore__Auth__Oidc__ClientId").Should().Be("client_id");
|
||||
EnvSecretName(container, "FlowerCore__Auth__Oidc__ClientSecret").Should().Be("signalcontrol-oidc-client");
|
||||
EnvSecretKey(container, "FlowerCore__Auth__Oidc__ClientSecret").Should().Be("client_secret");
|
||||
EnvSecretOptional(container, "FlowerCore__Auth__Oidc__Authority").Should().BeTrue();
|
||||
EnvSecretOptional(container, "FlowerCore__Auth__Oidc__ClientId").Should().BeTrue();
|
||||
EnvSecretOptional(container, "FlowerCore__Auth__Oidc__ClientSecret").Should().BeTrue();
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void SignalControlDeployment_MustWirePirelayRelayBridgeSecret()
|
||||
{
|
||||
var deployment = Inventory.Documents.Single(document =>
|
||||
document.Kind == "Deployment"
|
||||
&& document.Namespace == "fc-signalcontrol"
|
||||
&& document.Name == "signalcontrol-web"
|
||||
&& document.RelativePath == "fc-signalcontrol/fc-signalcontrol.yaml");
|
||||
var container = deployment.MainContainerMappings().Single(container =>
|
||||
ManifestNodeExtensions.Scalar(container, "name") == "signalcontrol-web");
|
||||
|
||||
EnvValue(container, "TrafficSignal__RelayBridge__Enabled").Should().Be("true");
|
||||
EnvValue(container, "TrafficSignal__RelayBridge__BaseUrl").Should().Be("https://pirelay.iamworkin.lan");
|
||||
EnvSecretName(container, "TrafficSignal__RelayBridge__ApiKey").Should().Be("signalcontrol-pirelay");
|
||||
EnvSecretKey(container, "TrafficSignal__RelayBridge__ApiKey").Should().Be("ApiKey");
|
||||
EnvSecretOptional(container, "TrafficSignal__RelayBridge__ApiKey").Should().BeTrue();
|
||||
EnvValue(container, "LiveStatus__TrafficSignal__BaseAddress").Should().Be("https://signalcontrol.iamworkin.lan");
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void GitHubRunnerFleet_MustRegisterRequiredReposAsRepoScopedDeployments()
|
||||
{
|
||||
@@ -234,7 +280,7 @@ public sealed class FleetManifestLintTests
|
||||
{
|
||||
deployments.Should().ContainKey(expectedRunner.Key);
|
||||
|
||||
var container = deployments[expectedRunner.Key].ContainerMappings().Should().ContainSingle().Subject;
|
||||
var container = deployments[expectedRunner.Key].MainContainerMappings().Should().ContainSingle().Subject;
|
||||
EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
|
||||
EnvValue(container, "EPHEMERAL").Should().Be("true");
|
||||
EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
|
||||
@@ -250,7 +296,7 @@ public sealed class FleetManifestLintTests
|
||||
{
|
||||
foreach (var deployment in GitHubRunnerDeployments().Values)
|
||||
{
|
||||
var container = deployment.ContainerMappings().Should().ContainSingle().Subject;
|
||||
var container = deployment.MainContainerMappings().Should().ContainSingle().Subject;
|
||||
|
||||
foreach (var expectedEnv in WritableRunnerEnv)
|
||||
{
|
||||
@@ -277,7 +323,10 @@ public sealed class FleetManifestLintTests
|
||||
foreach (var deploymentName in ScaledLinuxRunnerDeployments)
|
||||
{
|
||||
var deployment = deployments[deploymentName];
|
||||
ReplicaCount(deployment).Should().Be(2);
|
||||
// Scaled runners must have >= 2 replicas (avoid single-pod bottleneck).
|
||||
// Individual deployments may be tuned upward per CI activity — see
|
||||
// "runners: right-size replica counts per 14d CI activity (#24)".
|
||||
ReplicaCount(deployment).Should().BeGreaterOrEqualTo(2, $"{deploymentName} is in the scaled set and must run with at least 2 replicas");
|
||||
|
||||
var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
|
||||
var claimNames = volumes
|
||||
@@ -303,6 +352,108 @@ public sealed class FleetManifestLintTests
|
||||
.Be("github-runner-nuget-cache");
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void Runners_MustNotPinToOperatorWorkstationHosts()
|
||||
{
|
||||
// CRITICAL SAFETY (operator directive 2026-05-26): BLUEJAY-WS is the
|
||||
// operator's primary workstation — host of the 1Password Connect
|
||||
// bearer token, fcadmin SSH keys to noc1, signing CA private keys,
|
||||
// and source for every FC repo. A self-hosted GitHub Actions runner
|
||||
// there would execute arbitrary PR code with that local access.
|
||||
// Build-side analog of the Sprint 9 NEW safe-account exclusion gate
|
||||
// (Puppet GPO/AppLocker/WDAC/audit-forwarder modules refuse to apply
|
||||
// on BLUEJAY-WS). This lint asserts no GitHub-runner Deployment in
|
||||
// apps/github-runner/ pins to a forbidden operator-workstation host
|
||||
// via nodeName, nodeSelector, nodeAffinity, or tolerations.
|
||||
// Existing legacy `bluejay-ws-sandbox-1` GitHub-registered runner is
|
||||
// out of scope here (it's a runtime registration, not a K8s
|
||||
// Deployment) — see CLAUDE.md "Common Mistakes" entry and
|
||||
// feedback_bluejay_ws_never_public_runner.md.
|
||||
var forbiddenHostPatterns = new[]
|
||||
{
|
||||
"bluejay-ws",
|
||||
"BLUEJAY-WS",
|
||||
"bluejay-ws.iamworkin.lan",
|
||||
"iamworkin-ws",
|
||||
};
|
||||
|
||||
bool ContainsForbidden(string? value) =>
|
||||
!string.IsNullOrWhiteSpace(value)
|
||||
&& forbiddenHostPatterns.Any(pattern => value!.Contains(pattern, StringComparison.OrdinalIgnoreCase));
|
||||
|
||||
var violations = GitHubRunnerDeployments().Values.SelectMany(deployment =>
|
||||
{
|
||||
var local = new List<string>();
|
||||
var podSpec = ManifestNodeExtensions.Mapping(deployment.Root, "spec", "template", "spec");
|
||||
if (podSpec is null)
|
||||
{
|
||||
return local;
|
||||
}
|
||||
|
||||
// nodeName: pins the pod to a specific node by name.
|
||||
var nodeName = ManifestNodeExtensions.Scalar(podSpec, "nodeName");
|
||||
if (ContainsForbidden(nodeName))
|
||||
{
|
||||
local.Add($"{deployment.Name} sets nodeName='{nodeName}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
|
||||
// nodeSelector: dict of label → value pinning the pod to nodes
|
||||
// carrying matching labels. Examples that would trip this:
|
||||
// kubernetes.io/hostname: bluejay-ws
|
||||
// flowercore.io/host: bluejay-ws.iamworkin.lan
|
||||
var nodeSelector = ManifestNodeExtensions.Mapping(podSpec, "nodeSelector");
|
||||
if (nodeSelector is not null)
|
||||
{
|
||||
foreach (var entry in nodeSelector.Children)
|
||||
{
|
||||
var key = entry.Key is YamlScalarNode keyScalar ? keyScalar.Value : null;
|
||||
var value = entry.Value is YamlScalarNode valueScalar ? valueScalar.Value : null;
|
||||
if (ContainsForbidden(value))
|
||||
{
|
||||
local.Add($"{deployment.Name} has nodeSelector entry '{key}: {value}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// nodeAffinity: matchExpressions over node labels.
|
||||
foreach (var term in ManifestNodeExtensions.MappingSequence(podSpec, "affinity", "nodeAffinity", "requiredDuringSchedulingIgnoredDuringExecution", "nodeSelectorTerms"))
|
||||
{
|
||||
foreach (var expr in ManifestNodeExtensions.MappingSequence(term, "matchExpressions"))
|
||||
{
|
||||
var key = ManifestNodeExtensions.Scalar(expr, "key");
|
||||
foreach (var valueNode in ManifestNodeExtensions.ScalarSequence(expr, "values"))
|
||||
{
|
||||
if (ContainsForbidden(valueNode))
|
||||
{
|
||||
local.Add($"{deployment.Name} has nodeAffinity matchExpression '{key}' value '{valueNode}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// tolerations: scheduling onto a tainted operator-workstation
|
||||
// node would let the runner run there. Forbid any toleration
|
||||
// value that names the workstation.
|
||||
foreach (var toleration in ManifestNodeExtensions.MappingSequence(podSpec, "tolerations"))
|
||||
{
|
||||
var key = ManifestNodeExtensions.Scalar(toleration, "key");
|
||||
var value = ManifestNodeExtensions.Scalar(toleration, "value");
|
||||
if (ContainsForbidden(key))
|
||||
{
|
||||
local.Add($"{deployment.Name} has toleration key '{key}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
if (ContainsForbidden(value))
|
||||
{
|
||||
local.Add($"{deployment.Name} has toleration value '{value}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
}
|
||||
|
||||
return local;
|
||||
}).ToList();
|
||||
|
||||
violations.Should().BeEmpty("BLUEJAY-WS / iamworkin-ws must never host a fleet GitHub Actions runner; see CLAUDE.md 'Registering BLUEJAY-WS as a fleet GitHub Actions runner' and feedback_bluejay_ws_never_public_runner.md");
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable()
|
||||
{
|
||||
@@ -317,6 +468,36 @@ public sealed class FleetManifestLintTests
|
||||
monitoring.Should().Contain("alert_channel: irc");
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void Monitoring_MustScrapeSignalControlPiAppAndMountDashboard()
|
||||
{
|
||||
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
|
||||
|
||||
monitoring.Should().Contain("job_name: \"signalcontrol-pi-app\"");
|
||||
monitoring.Should().Contain("metrics_path: /metrics/prometheus");
|
||||
monitoring.Should().Contain("10.0.58.113:5200");
|
||||
monitoring.Should().Contain("host: \"signal-a.iamworkin.lan\"");
|
||||
monitoring.Should().Contain("mountPath: /var/lib/grafana/dashboards/signalcontrol");
|
||||
monitoring.Should().Contain("name: grafana-dashboard-signalcontrol");
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void SignalControlGrafanaDashboard_MustCoverAppNodeAndPhysicalControlMetrics()
|
||||
{
|
||||
var dashboard = File.ReadAllText(Path.Combine(
|
||||
Inventory.BluejayRoot,
|
||||
"apps",
|
||||
"monitoring",
|
||||
"grafana-dashboard-signalcontrol.yaml"));
|
||||
|
||||
dashboard.Should().Contain("uid\": \"flowercore-signalcontrol\"");
|
||||
dashboard.Should().Contain("up{job=\\\"signalcontrol-pi-app\\\",instance=\\\"pirelay\\\"}");
|
||||
dashboard.Should().Contain("up{job=\\\"edge-nodes\\\",instance=\\\"pirelay\\\"}");
|
||||
dashboard.Should().Contain("signal_relay_writes_total");
|
||||
dashboard.Should().Contain("signal_schedule_fires_total");
|
||||
dashboard.Should().Contain("signalcontrol_screen_saver_enabled");
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
|
||||
{
|
||||
@@ -655,6 +836,16 @@ public sealed class FleetManifestLintTests
|
||||
: null;
|
||||
}
|
||||
|
||||
private static bool EnvSecretOptional(YamlMappingNode container, string name)
|
||||
{
|
||||
return string.Equals(
|
||||
EnvMapping(container, name) is { } env
|
||||
? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "optional")
|
||||
: null,
|
||||
"true",
|
||||
StringComparison.Ordinal);
|
||||
}
|
||||
|
||||
private static YamlMappingNode? EnvMapping(YamlMappingNode container, string name)
|
||||
{
|
||||
return ManifestNodeExtensions.MappingSequence(container, "env")
|
||||
@@ -890,6 +1081,22 @@ internal sealed record ManifestDocument(
|
||||
.ToList();
|
||||
}
|
||||
|
||||
// MainContainerMappings excludes initContainers. Use this when asserting
|
||||
// properties of the primary container (env, image, volumeMounts) where an
|
||||
// initContainer would be a false-positive match — e.g. the GitHub runner
|
||||
// image's `setup-runner-home` initContainer should not count toward the
|
||||
// single-container assertions on the runner deployments.
|
||||
public IReadOnlyList<YamlMappingNode> MainContainerMappings()
|
||||
{
|
||||
var podSpec = PodSpec();
|
||||
if (podSpec is null)
|
||||
{
|
||||
return Array.Empty<YamlMappingNode>();
|
||||
}
|
||||
|
||||
return ManifestNodeExtensions.MappingSequence(podSpec, "containers").ToList();
|
||||
}
|
||||
|
||||
public IReadOnlyList<ContainerSpec> ContainerSpecs()
|
||||
{
|
||||
return ContainerMappings()
|
||||
|
||||
Reference in New Issue
Block a user