bvandeusenandClaude Opus 5.5
8ceb983183
The agent (1.9.0) said nothing when Docker could not be asked and nothing when Docker had no containers, so Steward could tell neither apart from the other, and kept a host's last containers on screen as running either way. - Agent: collect_docker returns (status, detail, containers). "ok" sends docker: [] when there are none; "unavailable" (no socket, nothing listening) and "error" (permission, timeout, bad answer) say why. collect_swarm says whether /info answered, and a node that is not a manager sends swarm_manager: false. A failed /info says nothing. - Ingest: an empty docker list is a snapshot; the newest sample's status goes to the Docker plugin with the rest. - docker_host_status (docker_011): per host, status, detail, since and last report. A host that never had Docker gets no row. - An "ok" empty snapshot reaps the host's containers; an error keeps them. swarm_manager: false drops the host's swarm services and nodes. - Docker page: a "Docker not answering" card names each such host, why, and since when; its containers read as stale. Duplicate header comment in rows.html removed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
106 lines
6.1 KiB
Python
106 lines
6.1 KiB
Python
"""The Docker page leads with what needs attention, ranked the way the MCP
|
|
tools rank it, and marks a container whose report is old as stale (#5123)."""
|
|
import re
|
|
from datetime import datetime, timedelta, timezone
|
|
from types import SimpleNamespace as NS
|
|
|
|
|
|
from plugins.docker import service as svc
|
|
from plugins.docker.routes import _is_stale
|
|
from tests._templates import render_plugin_template
|
|
from tests.test_style_tokens import hex_colours
|
|
|
|
NOW = datetime.now(timezone.utc)
|
|
|
|
|
|
def _c(name, **kw):
|
|
base = dict(name=name, host_id="h1", image="nginx:1", status="running", health=None, exit_code=None,
|
|
oom_killed=False, restart_count=0, cpu_pct=5.0, mem_pct=10.0, compose_project=None,
|
|
service_name=None, ports_json=None, started_at=NOW - timedelta(hours=2),
|
|
scraped_at=NOW - timedelta(seconds=20))
|
|
base.update(kw)
|
|
return NS(**base)
|
|
|
|
|
|
def test_needs_attention_ranks_the_worst_problem_first():
|
|
ranked = [{"container": _c(n), "problems": p, "since": None, "replaced": False} for n, p in [
|
|
("fine", []), ("oom", ["oom_killed"]), ("sick", ["unhealthy"]),
|
|
("loop", ["crash_looping"]), ("exit", ["exited_nonzero"]), ("bounce", ["restarting", "crash_looping"])]]
|
|
assert [r["container"].name for r in svc.needs_attention(ranked)] == ["bounce", "loop", "sick", "oom", "exit"]
|
|
|
|
|
|
def test_stale_is_older_than_the_agents_window():
|
|
assert not _is_stale(_c("a"), NOW, 180)
|
|
assert _is_stale(_c("a", scraped_at=NOW - timedelta(minutes=10)), NOW, 180)
|
|
assert _is_stale(_c("a", scraped_at=None), NOW, 180)
|
|
# A fresh row on a host whose Docker stopped answering is stale too (#5152).
|
|
assert _is_stale(_c("a"), NOW, 180, {"h1": object()})
|
|
assert not _is_stale(_c("a"), NOW, 180, {"h2": object()})
|
|
assert svc.stale_after_seconds({"PLUGINS": {"host_agent": {"stale_after_seconds": 60}}}) == 60
|
|
assert svc.stale_after_seconds({}) == 180
|
|
|
|
|
|
async def test_a_crash_loop_comes_first_and_a_stale_row_says_so(app):
|
|
loop = _c("api", status="restarting", exit_code=1, restart_count=7)
|
|
old = _c("cache", scraped_at=NOW - timedelta(minutes=30), cpu_pct=95.0)
|
|
attention = [{"container": loop, "problems": ["restarting", "crash_looping"], "replaced": False,
|
|
"since": datetime.now(timezone.utc) - timedelta(minutes=8), "stale": False}]
|
|
groups = [{"host": None, "host_id": "h1", "host_name": "nas", "running": 1, "stopped": 1, "grouped": False,
|
|
"subgroups": [{"label": None, "containers": [
|
|
{"container": loop, "ports": [], "uptime": None, "stale": False},
|
|
{"container": old, "ports": [], "uptime": "2h", "stale": True}]}]}]
|
|
async with app.test_request_context("/plugins/docker/rows"):
|
|
page = await render_plugin_template(
|
|
app, "docker", "docker/rows.html", attention=attention, says=svc.PROBLEM_SAYS, severity=svc.PROBLEM_SEVERITY,
|
|
unhealthy=0, restarting=1, stale=1, host_groups=groups, swarm_services=[],
|
|
running=1, stopped=1, total=2)
|
|
page = re.sub(r">\s+<", "><", " ".join(page.split()))
|
|
|
|
card = page[page.index("Needs attention"):page.index("</section>")]
|
|
assert '<span class="badge badge-crit">Restarting</span>' in card
|
|
assert 'href="/plugins/docker/container/h1/api">api</a>' in card
|
|
assert "is restarting and keeps dying · exit 1 · since <time" in card and ">8m ago</time>" in card
|
|
assert "cache" not in card
|
|
assert page.index("Needs attention") < page.index("<table")
|
|
|
|
assert '<span class="stat-tile-label">Restarting</span><span class="stat-tile-value">1</span>' in page
|
|
assert '<span class="stat-tile-label">Stale</span><span class="stat-tile-value">1</span>' in page
|
|
assert 'class="badge badge-warn" title="Last report' in page # the stale row
|
|
assert '<span class="tone-crit">95.0%</span>' in page # CPU through Settings → Thresholds
|
|
assert "history" not in page.lower() and "<svg" not in page # no sparklines on the overview
|
|
assert not hex_colours(page), hex_colours(page)
|
|
|
|
|
|
async def test_a_healthy_board_has_no_attention_card(app):
|
|
async with app.test_request_context("/plugins/docker/rows"):
|
|
page = await render_plugin_template(
|
|
app, "docker", "docker/rows.html", attention=[], says=svc.PROBLEM_SAYS, severity=svc.PROBLEM_SEVERITY,
|
|
unhealthy=0, restarting=0, stale=0, host_groups=[], swarm_services=[], running=0, stopped=0, total=0)
|
|
assert "Needs attention</h2>" not in page and "No containers reported yet" in page
|
|
|
|
|
|
async def test_a_host_whose_docker_stopped_answering_says_so(app):
|
|
down = [{"host_id": "h1", "host_name": "nas", "status": "unavailable",
|
|
"detail": "no Docker socket at /var/run/docker.sock", "since": NOW - timedelta(minutes=5)},
|
|
{"host_id": "h2", "host_name": "web-1", "status": "error",
|
|
"detail": "permission denied on /var/run/docker.sock", "since": NOW - timedelta(minutes=1)}]
|
|
async with app.test_request_context("/plugins/docker/rows"):
|
|
page = await render_plugin_template(
|
|
app, "docker", "docker/rows.html", docker_down=down, attention=[], says=svc.PROBLEM_SAYS,
|
|
severity=svc.PROBLEM_SEVERITY, unhealthy=0, restarting=0, stale=0, host_groups=[],
|
|
swarm_services=[], running=0, stopped=0, total=0)
|
|
page = re.sub(r">\s+<", "><", " ".join(page.split()))
|
|
card = page[page.index("Docker not answering"):page.index("</section>")]
|
|
assert '<span class="badge badge-warn">No Docker</span><a href="/hosts/h1">nas</a>' in card
|
|
assert "no Docker socket at /var/run/docker.sock · since <time" in card and ">5m ago</time>" in card
|
|
assert '<span class="badge badge-crit">Error</span><a href="/hosts/h2">web-1</a>' in card
|
|
|
|
|
|
async def test_no_card_while_every_docker_answers(app):
|
|
async with app.test_request_context("/plugins/docker/rows"):
|
|
page = await render_plugin_template(
|
|
app, "docker", "docker/rows.html", docker_down=[], attention=[], says=svc.PROBLEM_SAYS,
|
|
severity=svc.PROBLEM_SEVERITY, unhealthy=0, restarting=0, stale=0, host_groups=[],
|
|
swarm_services=[], running=0, stopped=0, total=0)
|
|
assert "Docker not answering" not in page
|