[e2e] Add container-based agent-network e2e harness (Pillar 1)

Introduce a self-contained, OIDC-free e2e harness that stands up NetBird
in containers, so suites no longer depend on the hand-maintained Tilt
stack or a real IdP.

- harness brings up the combined server (management + signal + relay +
  STUN + embedded IdP) in a single container built from
  combined/Dockerfile.multistage, and mints an admin PAT through the
  unauthenticated /api/setup bootstrap (NB_SETUP_PAT_ENABLED). API access
  goes through the existing shared/management/client/rest typed client.
- the image is built via the docker CLI (BuildKit) so the Dockerfile's
  cache mounts are honored; testcontainers then runs the tagged image.
- everything is behind the `e2e` build tag so normal builds and unit
  tests never pull in testcontainers.

Adds BuildKit cache mounts to combined/Dockerfile.multistage so source
changes recompile incrementally rather than from scratch.

Pillar 1 proven by TestCombinedBootstrap: server builds, boots, mints a
PAT, and the PAT authenticates a real management API call.
This commit is contained in:
mlsmaycon
2026-06-28 18:39:20 +02:00
parent 6e458d2afe
commit 4a296c5338
9 changed files with 581 additions and 3 deletions
@@ -0,0 +1,259 @@
{
"annotations": {
"list": []
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"links": [],
"refresh": "",
"schemaVersion": 39,
"tags": [
"netbird",
"sync"
],
"templating": {
"list": [
{
"current": {
"text": "All",
"value": "$__all"
},
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"definition": "import \"influxdata/influxdb/schema\"\nschema.tagValues(bucket: \"metrics\", tag: \"version\")",
"includeAll": true,
"label": "version",
"multi": true,
"name": "version",
"query": "import \"influxdata/influxdb/schema\"\nschema.tagValues(bucket: \"metrics\", tag: \"version\")",
"refresh": 2,
"type": "query",
"allValue": ".*"
}
]
},
"time": {
"from": "now-2d",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "NetBird Sync Phases (where time goes)",
"uid": "netbird-sync-phases",
"version": 1,
"panels": [
{
"id": 1,
"title": "Time per phase over time (stacked, ms)",
"type": "timeseries",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"gridPos": {
"h": 10,
"w": 24,
"x": 0,
"y": 0
},
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"drawStyle": "bars",
"stacking": {
"mode": "normal",
"group": "A"
},
"fillOpacity": 80,
"lineWidth": 0
}
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "table",
"placement": "right",
"calcs": [
"max",
"mean"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"query": "from(bucket: \"metrics\")\n |> range(start: v.timeRangeStart, stop: v.timeRangeStop)\n |> filter(fn: (r) => r._measurement == \"netbird_sync_phase\" and r._field == \"duration_seconds\")\n |> filter(fn: (r) => r.version =~ /${version:regex}/)\n |> map(fn: (r) => ({ r with _value: r._value * 1000.0 }))\n |> keep(columns: [\"_time\", \"_value\", \"phase\"])\n |> group(columns: [\"phase\"])"
}
]
},
{
"id": 2,
"title": "p95 per phase (ms)",
"type": "bargauge",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"gridPos": {
"h": 11,
"w": 12,
"x": 0,
"y": 10
},
"fieldConfig": {
"defaults": {
"unit": "ms",
"color": {
"mode": "continuous-GrYlRd"
}
},
"overrides": []
},
"options": {
"displayMode": "gradient",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showUnfilled": true
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"query": "from(bucket: \"metrics\")\n |> range(start: v.timeRangeStart, stop: v.timeRangeStop)\n |> filter(fn: (r) => r._measurement == \"netbird_sync_phase\" and r._field == \"duration_seconds\")\n |> filter(fn: (r) => r.version =~ /${version:regex}/)\n |> map(fn: (r) => ({ r with _value: r._value * 1000.0 }))\n |> group(columns: [\"phase\"])\n |> quantile(q: 0.95)\n |> group()\n |> sort(columns: [\"_value\"], desc: true)"
}
]
},
{
"id": 3,
"title": "Per-phase stats (ms): mean / p95 / max",
"type": "table",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"gridPos": {
"h": 11,
"w": 12,
"x": 12,
"y": 10
},
"fieldConfig": {
"defaults": {
"unit": "ms"
},
"overrides": []
},
"options": {
"showHeader": true,
"sortBy": [
{
"displayName": "max",
"desc": true
}
]
},
"transformations": [
{
"id": "merge",
"options": {}
}
],
"targets": [
{
"refId": "mean",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"query": "from(bucket: \"metrics\")\n |> range(start: v.timeRangeStart, stop: v.timeRangeStop)\n |> filter(fn: (r) => r._measurement == \"netbird_sync_phase\" and r._field == \"duration_seconds\")\n |> filter(fn: (r) => r.version =~ /${version:regex}/)\n |> map(fn: (r) => ({ r with _value: r._value * 1000.0 }))\n |> group(columns: [\"phase\"])\n |> mean()\n |> group()\n |> keep(columns: [\"phase\", \"_value\"])\n |> rename(columns: {_value: \"mean\"})"
},
{
"refId": "p95",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"query": "from(bucket: \"metrics\")\n |> range(start: v.timeRangeStart, stop: v.timeRangeStop)\n |> filter(fn: (r) => r._measurement == \"netbird_sync_phase\" and r._field == \"duration_seconds\")\n |> filter(fn: (r) => r.version =~ /${version:regex}/)\n |> map(fn: (r) => ({ r with _value: r._value * 1000.0 }))\n |> group(columns: [\"phase\"])\n |> quantile(q: 0.95)\n |> group()\n |> keep(columns: [\"phase\", \"_value\"])\n |> rename(columns: {_value: \"p95\"})"
},
{
"refId": "max",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"query": "from(bucket: \"metrics\")\n |> range(start: v.timeRangeStart, stop: v.timeRangeStop)\n |> filter(fn: (r) => r._measurement == \"netbird_sync_phase\" and r._field == \"duration_seconds\")\n |> filter(fn: (r) => r.version =~ /${version:regex}/)\n |> map(fn: (r) => ({ r with _value: r._value * 1000.0 }))\n |> group(columns: [\"phase\"])\n |> max()\n |> group()\n |> keep(columns: [\"phase\", \"_value\"])\n |> rename(columns: {_value: \"max\"})"
}
]
},
{
"id": 4,
"title": "Total sync duration (netbird_sync, ms) \u2014 reference",
"type": "timeseries",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 21
},
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"drawStyle": "points",
"pointSize": 5
}
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "table",
"placement": "right",
"calcs": [
"max",
"mean"
]
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "influxdb",
"uid": "influxdb"
},
"query": "from(bucket: \"metrics\")\n |> range(start: v.timeRangeStart, stop: v.timeRangeStop)\n |> filter(fn: (r) => r._measurement == \"netbird_sync\" and r._field == \"duration_seconds\")\n |> filter(fn: (r) => r.version =~ /${version:regex}/)\n |> map(fn: (r) => ({ r with _value: r._value * 1000.0 }))\n |> keep(columns: [\"_time\", \"_value\", \"version\"])\n |> group(columns: [\"version\"])"
}
]
}
]
}
@@ -59,6 +59,19 @@ var allowedMeasurements = map[string]measurementSpec{
"peer_id": true,
},
},
"netbird_sync_phase": {
allowedFields: map[string]bool{
"duration_seconds": true,
},
allowedTags: map[string]bool{
"deployment_type": true,
"version": true,
"os": true,
"arch": true,
"peer_id": true,
"phase": true,
},
},
"netbird_login": {
allowedFields: map[string]bool{
"duration_seconds": true,