Files
computer-playbook/tests/unit/python/plugins/lookup/test_native_metrics_target.py
T
kevinveenbirkenbachandClaude Opus 5 50b9f60c43 fix(prometheus): resolve the native-metrics scrape target per deployment mode
`native_metrics_target` was a Jinja filter, so it could not read
DEPLOYMENT_MODE: filters see no Ansible variables. It returned
`<services.<key>.name>:<port>` unconditionally, which is `matrix-synapse:9000`
for matrix. Compose serves that name; swarm does not, because `docker stack
deploy` ignores `container_name` and the alias never exists. This repository
says as much itself, through `lookup('compose_only', 'container_name', ...)`.
The target was therefore scraped and refused, and `playwright.spec.js:274`
reported `web-app-matrix: 1 matching target(s) reporting up != 1`, meaning one
matching target whose `up` value is not 1.

It becomes a lookup that delegates host resolution to `scrape_target`, which
was already mode-aware, so exactly one plugin knows the difference between the
two modes. The port has to be handed over explicitly: matrix exposes metrics on
9000 while `services.synapse.ports.internal.http` is 8008, so the existing
internal-port lookup cannot serve this case on its own.

`scrape_target` now refuses `port` together with an explicit `port_kind`.
Before, `port` won silently and the error text still named the
`ports.internal.<port_kind>` path that the call had never consulted.

`native_metrics_apps` drops an app that pins itself to compose through
`compose_mode_force` while the cluster runs swarm, because the scrape target
would then name the wrong object. Only the literal case: matrix declares that
override as a Jinja expression over its flavour, which this lookup cannot
resolve from the scraping role's variable scope, so variant 0 on swarm stays a
latent mismatch.

The two comment lines claiming `container_name:port` went with the change;
after it they state the opposite of what the code does.

Verified by mutation: with the swarm branch of `scrape_target` disabled, the
new test emits `matrix-synapse:9000`, the exact string CI reported.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-10-08 08:57:13 +02:00

120 lines
4.0 KiB
Python

"""Tests for the native_metrics_target lookup.
The lookup delegates host resolution to scrape_target, so these run the real
scrape_target rather than a stub: the regression being guarded is that swarm
must not receive a compose container name, and only the delegation proves it.
"""
from __future__ import annotations
import unittest
from typing import Any
from unittest.mock import MagicMock, patch
from ansible.errors import AnsibleError
from plugins.lookup.native_metrics_target import LookupModule
from plugins.lookup.scrape_target import LookupModule as ScrapeTargetLookup
ENTITIES = {"web-app-matrix": "matrix", "web-app-gitea": "gitea"}
class _Templar:
def __init__(self, vars_=None):
self.available_variables = vars_ or {}
def template(self, value, **_):
return value
def _apps(native_metrics: dict[str, Any]) -> dict[str, Any]:
return {
"web-app-matrix": {
"services": {
"prometheus": {"native_metrics": native_metrics},
"synapse": {
"name": "matrix-synapse",
"ports": {"internal": {"http": 8008}},
},
},
},
}
def _run(terms, *, mode, apps):
variables = {"DEPLOYMENT_MODE": mode}
lookup = LookupModule()
lookup._templar = _Templar(variables)
lookup._loader = MagicMock()
def _dispatch(name, **_kwargs):
if name == "applications":
return MagicMock(run=lambda *_a, **_k: [apps])
scrape = ScrapeTargetLookup()
scrape._templar = _Templar(variables)
scrape._loader = MagicMock()
return scrape
with (
patch(
"plugins.lookup.native_metrics_target.lookup_loader"
) as native_loader_mock,
patch("plugins.lookup.scrape_target.lookup_loader") as scrape_loader_mock,
patch(
"plugins.lookup.native_metrics_target.get_entity_name",
side_effect=lambda app_id: ENTITIES.get(app_id, ""),
),
patch(
"plugins.lookup.scrape_target.get_entity_name",
side_effect=lambda app_id: ENTITIES.get(app_id, ""),
),
):
native_loader_mock.get.side_effect = _dispatch
scrape_loader_mock.get.return_value = MagicMock(run=lambda *_a, **_k: [apps])
return lookup.run(terms, variables=variables)
class TestNativeMetricsTargetLookup(unittest.TestCase):
def test_swarm_uses_per_task_dns_not_the_container_name(self):
apps = _apps({"port": 9000, "service_key": "synapse"})
result = _run(["web-app-matrix"], mode="swarm", apps=apps)
self.assertEqual(result, ["tasks.matrix_synapse:9000"])
def test_compose_uses_the_container_name(self):
apps = _apps({"port": 9000, "service_key": "synapse"})
result = _run(["web-app-matrix"], mode="compose", apps=apps)
self.assertEqual(result, ["matrix-synapse:9000"])
def test_service_key_defaults_to_the_entity_name(self):
apps = {
"web-app-gitea": {
"services": {
"prometheus": {"native_metrics": {"port": 3000}},
"gitea": {
"name": "gitea",
"ports": {"internal": {"http": 3000}},
},
},
},
}
result = _run(["web-app-gitea"], mode="swarm", apps=apps)
self.assertEqual(result, ["tasks.gitea_gitea:3000"])
def test_native_metrics_port_takes_precedence_over_the_internal_port(self):
apps = _apps({"port": 9000, "service_key": "synapse"})
result = _run(["web-app-matrix"], mode="compose", apps=apps)
self.assertNotIn("8008", result[0])
def test_missing_port_raises(self):
apps = _apps({"service_key": "synapse"})
with self.assertRaises(AnsibleError):
_run(["web-app-matrix"], mode="compose", apps=apps)
def test_missing_application_id_raises(self):
with self.assertRaises(AnsibleError):
_run([], mode="compose", apps=_apps({"port": 9000}))
if __name__ == "__main__":
unittest.main()