bvandeusenandClaude Opus 5.5
61b22056d5
#5209 "Docker views: readable names, CPU/memory in cores and bytes, failures listed with since-time" (milestone 477 "UI problems first"). - A swarm task reads as its service and slot ("codex_db · 1", or the node for a global service), with the raw name in the title: Docker page, host panel, busiest widget, container detail. - CPU reads in cores (Docker's 100% = one core), toned by its share of the host's CPUs from the agent's per-core series. Memory reads in bytes, against a limit only when one is really set (Docker reports host RAM otherwise). - Exit 137/143 without an OOM kill is a stop, not a failure: no exited_nonzero, no crash-loop death, no "failed (24h)", dim exit code. - "Failed (24h)" is a list (Docker page #failures, linked from the widget and the tile): plain containers by their deaths, swarm services by Swarm's failed tasks; a second manager's copy of a task death counts once. - Failing swarm services lead Needs attention; services sort problems first with since-times on the page, the widget and the Swarm page; nodes that are down or drained sort first. - Busiest widget orders by a 5-minute CPU average so the list holds still. - Host panel: a table, problems first with what is wrong and since when; replaced swarm tasks hidden and counted. - Container detail: node hostname, I/O labelled "since start", Restarts hidden for swarm tasks with a note on where task failures are. - Widget names: "Docker — Services & failures", "Docker — Busiest containers". Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
111 lines
5.8 KiB
Python
111 lines
5.8 KiB
Python
"""Unit tests for the docker plugin's shared query helpers (no DB)."""
|
|
from datetime import datetime, timedelta, timezone
|
|
from types import SimpleNamespace as NS
|
|
|
|
from plugins.docker import service as svc
|
|
from plugins.docker import swarm_view as sv
|
|
|
|
NOW = datetime(2026, 10, 6, 12, 0, tzinfo=timezone.utc)
|
|
|
|
|
|
def test_escape_like_makes_wildcards_literal():
|
|
# A log search for "100%" or "user_id" must match those characters, not
|
|
# treat them as LIKE wildcards.
|
|
assert svc.escape_like("100%") == "100\\%"
|
|
assert svc.escape_like("user_id") == "user\\_id"
|
|
assert svc.escape_like("C:\\temp") == "C:\\\\temp"
|
|
assert svc.escape_like("plain text") == "plain text"
|
|
|
|
|
|
def test_bucket_keeps_short_series_and_averages_long_ones():
|
|
assert svc.bucket([1.0, 2.0, 3.0]) == [1.0, 2.0, 3.0]
|
|
out = svc.bucket([float(i) for i in range(400)], target=40)
|
|
assert len(out) == 40
|
|
assert out[0] == sum(range(10)) / 10
|
|
|
|
|
|
def test_prune_extra_vars_mapping():
|
|
"""The prune buttons drive one playbook via prune_target; only 'images'
|
|
widens to ALL unused images (docker image prune -a), system stays -f."""
|
|
assert svc.prune_extra_vars("containers") == {"prune_target": "containers"}
|
|
assert svc.prune_extra_vars("images") == {
|
|
"prune_target": "images", "prune_all_images": True,
|
|
}
|
|
# System prune stays conservative — no prune_all_images key.
|
|
assert svc.prune_extra_vars("system") == {"prune_target": "system"}
|
|
|
|
|
|
def test_a_stop_is_not_a_failure():
|
|
# docker stop ends a container with 143 (SIGTERM) or 137 (SIGKILL).
|
|
assert not svc.exit_is_failure(None) and not svc.exit_is_failure(0)
|
|
assert not svc.exit_is_failure(137) and not svc.exit_is_failure(143)
|
|
assert svc.exit_is_failure(1) and svc.exit_is_failure(2)
|
|
assert svc.exit_is_failure(137, oom_killed=True)
|
|
|
|
|
|
def _ev(name, event, detail="", mins=5, host="h1"):
|
|
return NS(container_name=name, host_id=host, event=event, detail=detail, at=NOW - timedelta(minutes=mins))
|
|
|
|
|
|
def test_event_is_failure_reads_the_exit_from_the_die_detail():
|
|
assert svc.event_is_failure(_ev("a", "die", "exit 1"))
|
|
assert not svc.event_is_failure(_ev("a", "die", "exit 143"))
|
|
assert not svc.event_is_failure(_ev("a", "die", "exit 0"))
|
|
assert svc.event_is_failure(_ev("a", "oom"))
|
|
assert not svc.event_is_failure(_ev("a", "start"))
|
|
|
|
|
|
def _service(name, *, known=True, failures=0, error=None):
|
|
return {"name": name, "tasks_known": known, "failures_24h": failures if known else None,
|
|
"last_error": error}
|
|
|
|
|
|
def test_failures_24h_counts_services_once_and_skips_stops():
|
|
events = [_ev("backup", "die", "exit 2", mins=30), _ev("backup", "die", "exit 2", mins=90),
|
|
_ev("web", "die", "exit 143", mins=10), # someone stopped it
|
|
_ev("app.1.abc", "die", "exit 1", mins=3), # Swarm counts its tasks
|
|
_ev("old.1.x", "die", "exit 1", mins=4), _ev("old.2.y", "die", "exit 1", mins=40),
|
|
_ev("old.1.x", "die", "exit 1", mins=4, host="h2")] # a second manager's copy
|
|
services = [_service("app", failures=3, error={"state": "failed", "error": "boom", "node": "nas",
|
|
"at": (NOW - timedelta(minutes=1)).isoformat()}),
|
|
_service("old", known=False)] # agent before 1.8.0
|
|
rows = svc.failures_24h(events, services, {"h1": "nas"})
|
|
got = {(r["kind"], r["name"]): r for r in rows}
|
|
assert set(got) == {("container", "backup"), ("service", "app"), ("service", "old")}
|
|
assert got[("container", "backup")]["count"] == 2 and got[("container", "backup")]["host"] == "nas"
|
|
assert got[("service", "app")]["count"] == 3 and got[("service", "app")]["detail"] == "boom"
|
|
assert got[("service", "old")]["count"] == 2 # its tasks' deaths
|
|
assert [r["name"] for r in rows] == ["app", "old", "backup"] # newest first
|
|
|
|
|
|
def test_task_label_names_the_service_and_slot():
|
|
assert svc.task_label(NS(name="nginx", service_name=None)) == "nginx"
|
|
assert svc.task_label(NS(name="codex_db.1.37ma", service_name="codex_db")) == "codex_db · 1"
|
|
agent = NS(name="agent.n0d3id.t4sk", service_name="agent", node_id="n0d3id")
|
|
assert svc.task_label(agent, {"n0d3id": "node-3"}) == "agent · node-3"
|
|
assert svc.task_label(agent) == "agent"
|
|
|
|
|
|
def test_usage_reads_cpu_in_cores_and_memory_against_a_real_limit():
|
|
gib = 1024 ** 3
|
|
c = NS(cpu_pct=150.0, mem_usage_bytes=gib, mem_limit_bytes=16 * gib, mem_pct=6.25)
|
|
u = svc.usage(c, 4, 16 * gib)
|
|
assert u["cores"] == 1.5 and u["cpu_share"] == 37.5
|
|
# A limit of the host's whole memory is Docker saying "no limit".
|
|
assert u["mem_limit"] is None and u["mem_of"] == "the host's memory"
|
|
limited = svc.usage(NS(cpu_pct=None, mem_usage_bytes=gib, mem_limit_bytes=2 * gib, mem_pct=50.0), 4, 16 * gib)
|
|
assert limited["cores"] is None and limited["mem_limit"] == 2 * gib and limited["mem_of"] == "its limit"
|
|
# Unknown host size: cores still read, no share to grade against.
|
|
assert svc.usage(c, None, None)["cpu_share"] is None
|
|
assert svc.usage(c, 4, 16 * gib, cpu_pct=50.0)["cores"] == 0.5 # an average in place
|
|
|
|
|
|
def test_services_in_trouble_come_first_worst_first():
|
|
def s(name, state, loop=False, f24=0):
|
|
return {"name": name, "state": state, "crash_looping": loop, "failures_24h": f24}
|
|
services = [s("alpha", "healthy"), s("beta", "healthy", f24=2), s("gamma", "degraded"),
|
|
s("delta", "down"), s("eps", "down", loop=True)]
|
|
assert [x["name"] for x in sv.services_problems_first(services)] == ["eps", "delta", "gamma", "beta", "alpha"]
|
|
# A recovered service's failed tasks are history: not in Needs attention.
|
|
assert [x["name"] for x in sv.failing_services(services)] == ["eps", "delta", "gamma"]
|