blumeops/argocd/manifests/grafana-config/dashboards/configmap-shower-apm.yaml
Erich Blume 6e37abda5d C1: deploy adelaide-baby-shower-app to ringtail k3s
Adds the Adelaide / Heidi / Addie baby shower app — a Django guest
splash, raffle picker, and prize-assignment console — on ringtail k3s.
Public landing at shower.eblu.me (via fly proxy), tailnet admin at
shower.ops.eblu.me. App source: forge.eblu.me/eblume/adelaide-baby-shower-app,
wheel-published to the Forgejo Packages PyPI index.

Manifests under argocd/manifests/shower/: NFS-backed PVC for /app/media,
local-path PVC for SQLite, ExternalSecret pulling DJANGO_SECRET_KEY from
1Password (item "Shower (blumeops)"), Tailscale ProxyGroup ingress.

Defense-in-depth for the public surface:
  - /admin/ blocked at the fly edge except /admin/login/ and /admin/logout/
  - shower_auth rate limit on the login path
  - new fail2ban filter+jail with a per-service shower-deny.conf
    (nginx-deny action generalized to accept nginx_deny_file)
  - django-axes (5 / 1h) keyed on (username, ip_address)

Plus: Caddy route on indri, Pulumi gandi CNAME, Grafana APM dashboard
mirroring docs-apm.json, runbook at how-to/operations/shower-app.md,
and a service-versions entry. X-Clacks-Overhead set on the new server
block — GNU Terry Pratchett.

Build: containers/shower/default.nix uses dockerTools to ship a
nixpkgs Python plus a startup wrapper that installs the wheel into
/app/data/.venv on first boot and execs gunicorn. Lets the wheel come
from forge PyPI without pinning hashes for every transitive dep.

Prerequisites tracked in the runbook (not yet executed):
  - NFS share sifaka:/volume1/shower (manual Synology step)
  - 1Password item "Shower (blumeops)" with secret-key field
  - container build via `mise run container-build-and-release shower`
  - Pulumi dns-up after merge
  - fly certs add shower.eblu.me

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-11 08:14:12 -07:00

229 lines
9.4 KiB
YAML

apiVersion: v1
kind: ConfigMap
metadata:
name: grafana-dashboard-shower-apm
namespace: monitoring
labels:
grafana_dashboard: "1"
data:
shower-apm.json: |
{
"annotations": { "list": [] },
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"panels": [
{
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"color": { "mode": "palette-classic" },
"custom": {
"axisLabel": "req/s",
"drawStyle": "line",
"fillOpacity": 20,
"lineInterpolation": "linear",
"lineWidth": 1,
"showPoints": "never",
"spanNulls": false,
"stacking": { "group": "A", "mode": "normal" }
},
"mappings": [],
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
"unit": "reqps"
},
"overrides": []
},
"gridPos": { "h": 8, "w": 16, "x": 0, "y": 0 },
"id": 1,
"options": {
"legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true },
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "sum by (status) (rate(flyio_nginx_http_requests_total{host=\"shower.eblu.me\"}[5m]))", "legendFormat": "{{status}}", "refId": "A" }
],
"title": "Request Rate by Status",
"type": "timeseries"
},
{
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }, { "color": "yellow", "value": 0.01 }, { "color": "red", "value": 0.05 }] },
"unit": "percentunit"
},
"overrides": []
},
"gridPos": { "h": 4, "w": 8, "x": 16, "y": 0 },
"id": 2,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "center",
"orientation": "auto",
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"textMode": "auto"
},
"targets": [
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "sum(rate(flyio_nginx_http_requests_total{host=\"shower.eblu.me\",status=~\"5..\"}[5m])) / sum(rate(flyio_nginx_http_requests_total{host=\"shower.eblu.me\"}[5m]))", "refId": "A" }
],
"title": "Error Rate (5xx)",
"type": "stat"
},
{
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }, { "color": "yellow", "value": 1 }, { "color": "red", "value": 5 }] },
"unit": "short"
},
"overrides": []
},
"gridPos": { "h": 4, "w": 4, "x": 16, "y": 4 },
"id": 3,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "center",
"orientation": "auto",
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"textMode": "auto"
},
"targets": [
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "sum(increase(flyio_nginx_http_requests_total{host=\"shower.eblu.me\",request_uri=~\"/admin/login.*\",status=~\"4..\"}[$__range]))", "refId": "A" }
],
"title": "Failed admin logins (range)",
"type": "stat"
},
{
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
"unit": "reqps"
},
"overrides": []
},
"gridPos": { "h": 4, "w": 4, "x": 20, "y": 4 },
"id": 4,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "center",
"orientation": "auto",
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"textMode": "auto"
},
"targets": [
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "sum(rate(flyio_nginx_http_requests_total{host=\"shower.eblu.me\"}[5m]))", "refId": "A" }
],
"title": "Current RPS",
"type": "stat"
},
{
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"color": { "mode": "palette-classic" },
"custom": {
"axisLabel": "seconds",
"drawStyle": "line",
"fillOpacity": 10,
"lineInterpolation": "linear",
"lineWidth": 1,
"showPoints": "never",
"spanNulls": false,
"stacking": { "group": "A", "mode": "none" }
},
"mappings": [],
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
"unit": "s"
},
"overrides": []
},
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
"id": 5,
"options": {
"legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true },
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "histogram_quantile(0.50, sum by (le) (rate(flyio_nginx_http_request_duration_seconds_bucket{host=\"shower.eblu.me\"}[5m])))", "legendFormat": "p50", "refId": "A" },
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "histogram_quantile(0.90, sum by (le) (rate(flyio_nginx_http_request_duration_seconds_bucket{host=\"shower.eblu.me\"}[5m])))", "legendFormat": "p90", "refId": "B" },
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "histogram_quantile(0.99, sum by (le) (rate(flyio_nginx_http_request_duration_seconds_bucket{host=\"shower.eblu.me\"}[5m])))", "legendFormat": "p99", "refId": "C" }
],
"title": "Latency Percentiles",
"type": "timeseries"
},
{
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"color": { "mode": "palette-classic" },
"custom": {
"axisLabel": "",
"drawStyle": "line",
"fillOpacity": 20,
"lineInterpolation": "linear",
"lineWidth": 1,
"showPoints": "never",
"spanNulls": false,
"stacking": { "group": "A", "mode": "none" }
},
"mappings": [],
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
"unit": "Bps"
},
"overrides": []
},
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
"id": 6,
"options": {
"legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true },
"tooltip": { "mode": "single", "sort": "none" }
},
"targets": [
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "sum(rate(flyio_nginx_http_response_bytes_total{host=\"shower.eblu.me\"}[5m]))", "legendFormat": "Bandwidth", "refId": "A" }
],
"title": "Bandwidth",
"type": "timeseries"
},
{
"datasource": { "type": "loki", "uid": "loki" },
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 16 },
"id": 7,
"options": {
"dedupStrategy": "none",
"enableLogDetails": true,
"prettifyLogMessage": false,
"showCommonLabels": false,
"showLabels": false,
"showTime": true,
"sortOrder": "Descending",
"wrapLogMessage": false
},
"targets": [
{ "datasource": { "type": "loki", "uid": "loki" }, "expr": "{instance=\"flyio-proxy\", job=\"flyio-nginx\"} |= \"shower.eblu.me\" | json | line_format \"{{.client_ip}} {{.request_method}} {{.request_uri}} {{.status}} {{.request_time}}s\"", "refId": "A" }
],
"title": "Recent Access Logs",
"type": "logs"
}
],
"refresh": "30s",
"schemaVersion": 38,
"tags": ["shower", "flyio", "apm"],
"templating": { "list": [] },
"time": { "from": "now-6h", "to": "now" },
"timepicker": {},
"timezone": "",
"title": "Shower APM",
"uid": "shower-apm",
"version": 1,
"weekStart": ""
}