Files
FabledSteward/tests/integration/test_docker.py
T
bvandeusen 7b80552a7d
CI / lint (push) Successful in 3s
CI / integration (push) Successful in 2m16s
CI / unit (push) Successful in 4m28s
CI / publish (push) Successful in 1m4s
feat(docker): per-host collection via the host agent; drop central scrape
Docker collection moves off the central single-socket scrape onto the host
agent, giving Docker a real per-host dimension. The Steward host now reports
its own containers like any other host, and same-named containers on different
hosts no longer collide.

- agent: stdlib UDS Docker client (AF_UNIX HTTP/1.1, Connection: close,
  chunked-aware), collect_docker() ports the cpu%/mem math; sample["docker"]
  added best-effort (silent-skip on absent/unreadable socket). AGENT_VERSION
  1.2.0 → 1.3.0; optional docker_socket config key.
- ingest: host_agent ingest hands per-host container snapshots to the docker
  plugin via a new "docker.persist_host_samples" capability (no hard import,
  no-op when docker disabled), inside a SAVEPOINT so a docker failure never
  sinks the host metrics. Resource names are host-scoped ("<host>/<name>").
- schema: docker_containers re-keyed (host_id, name); docker_metrics gains
  host_id; docker_002 migration DROP+recreates (dev-only, rule 122).
- ui: Docker page + widgets grouped by host with host links; new per-host
  Docker panel embedded on the Hosts hub (gated on docker enabled via a new
  enabled_plugins template context). Replaces the SQLite-only strftime
  bucketing with DB-agnostic Python bucketing.
- provisioning: install/provision playbooks add steward-agent to the docker
  group (best-effort) so the agent can read the socket.
- removed central scrape: docker scheduler.py + scraper.py deleted; plugin.yaml
  socket_path/scrape_interval_seconds/include_stopped dropped (plugin 2.0.0).
- tests: agent docker collector units (math, chunked decode, silent-skip,
  sample shape, config) + integration (host-scoped schema + persistence).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016Jg27rgypiW2efULXJDtMC
2026-06-18 17:54:36 -04:00

110 lines
4.4 KiB
Python

"""Integration: per-host Docker schema + host-scoped persistence.
Validates the docker_002 migration (host_id columns + composite key) applied and
that persist_host_docker scopes containers/metrics by host so same-named
containers on different hosts no longer collide. Requires STEWARD_DATABASE_URL.
"""
from __future__ import annotations
import asyncio
import os
import uuid
from datetime import datetime, timezone
import pytest
pytestmark = pytest.mark.integration
_NEEDS_DB = pytest.mark.skipif(
not os.environ.get("STEWARD_DATABASE_URL"),
reason="integration test needs a live Postgres (STEWARD_DATABASE_URL)",
)
@pytest.fixture
def app():
if not os.environ.get("STEWARD_DATABASE_URL"):
pytest.skip("needs Postgres")
from steward.app import create_app
return create_app(testing=False)
@_NEEDS_DB
def test_docker_tables_are_host_scoped(app):
from sqlalchemy import text
async def _go():
async with app.db_sessionmaker() as s:
# Both tables carry a host_id column after docker_002.
for tbl in ("docker_containers", "docker_metrics"):
cols = {r[0] for r in (await s.execute(text(
"SELECT column_name FROM information_schema.columns "
"WHERE table_name = :t"), {"t": tbl})).all()}
assert "host_id" in cols, f"{tbl} missing host_id"
# docker_containers is keyed by (host_id, name), not name alone.
pk_cols = {r[0] for r in (await s.execute(text(
"SELECT a.attname FROM pg_index i "
"JOIN pg_attribute a ON a.attrelid = i.indrelid "
" AND a.attnum = ANY(i.indkey) "
"WHERE i.indrelid = 'docker_containers'::regclass AND i.indisprimary"
))).all()}
assert pk_cols == {"host_id", "name"}
asyncio.run(_go())
def _persist_fn(app):
"""Resolve persist_host_docker via the registered capability if the docker
plugin is loaded, else import it directly (the import is safe only when the
plugin is NOT loaded — otherwise its models are already mapped)."""
from steward.core.capabilities import has_capability, get_capability
if has_capability("docker.persist_host_samples"):
return get_capability("docker.persist_host_samples").fn
from plugins.docker.ingest import persist_host_docker
return persist_host_docker
@_NEEDS_DB
def test_persist_scopes_containers_by_host(app):
from sqlalchemy import text
from steward.models.hosts import Host
persist = _persist_fn(app)
now = datetime.now(timezone.utc)
snapshot = [(now, [{
"name": "web", "container_id": "abc123", "image": "nginx",
"status": "running", "cpu_pct": 12.5, "mem_pct": 30.0,
"mem_usage_bytes": 100, "mem_limit_bytes": 200, "ports": [], "started_at": None,
}])]
async def _go():
async with app.db_sessionmaker() as s:
async with s.begin():
await s.execute(text("DELETE FROM docker_metrics"))
await s.execute(text("DELETE FROM docker_containers"))
await s.execute(text(
"DELETE FROM plugin_metrics WHERE source_module = 'docker'"))
h1 = Host(id=str(uuid.uuid4()), name="alpha", address="10.0.0.1")
h2 = Host(id=str(uuid.uuid4()), name="beta", address="10.0.0.2")
s.add_all([h1, h2])
await s.flush()
# Same container name on two hosts — must not collide now.
await persist(s, h1, snapshot)
await persist(s, h2, snapshot)
web_rows = (await s.execute(text(
"SELECT COUNT(*) FROM docker_containers WHERE name = 'web'"))).scalar()
metric_hosts = (await s.execute(text(
"SELECT COUNT(DISTINCT host_id) FROM docker_metrics "
"WHERE container_name = 'web'"))).scalar()
# Alert pipeline received host-scoped resource names.
resources = {r[0] for r in (await s.execute(text(
"SELECT DISTINCT resource_name FROM plugin_metrics "
"WHERE source_module = 'docker'"))).all()}
return web_rows, metric_hosts, resources
web_rows, metric_hosts, resources = asyncio.run(_go())
assert web_rows == 2 # one 'web' per host, keyed by (host_id, name)
assert metric_hosts == 2 # time-series rows scoped per host
assert resources == {"alpha/web", "beta/web"}