bvandeusen
a8de3570fe
Ingest side of container logs. The host_agent ingest route extracts sample["docker_logs"] as time-series batches (append every line, each carrying its own Docker ts with recorded_at as fallback) and hands them to the docker capability alongside the existing container/swarm/disk data — still under the begin_nested SAVEPOINT so a logs failure can't sink host metrics. - ingest.py: _persist_logs + pure _log_rows(batches, host_id) that shapes/filters records (drops the _steward truncation marker, malformed + lineless records, normalises unknown stream → stdout); persist_host_docker gains a logs= param - routes.py: accumulate docker_log_batches, add to the guard + capability call - unit test for _log_rows shaping/filtering; integration push→store→query test Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CAGR73DUowdVFVvYzLXC5C
100 lines
4.4 KiB
Python
100 lines
4.4 KiB
Python
"""Unit tests for the docker plugin's lifecycle-event derivation.
|
|
|
|
_derive_events is a pure function (no DB), and ingest.py imports its models
|
|
lazily inside functions, so importing it here doesn't register ORM tables —
|
|
safe for the no-DB unit lane.
|
|
"""
|
|
from plugins.docker.ingest import _derive_events
|
|
|
|
|
|
def _c(name, status, **kw):
|
|
return {"name": name, "status": status, **kw}
|
|
|
|
|
|
def test_start_on_running_after_stopped():
|
|
old = {"web": {"status": "exited", "health": None, "oom_killed": False, "exit_code": 0}}
|
|
events = _derive_events(old, [_c("web", "running", image="nginx")])
|
|
assert events == [("web", "start", "nginx")]
|
|
|
|
|
|
def test_start_for_new_container_when_state_exists():
|
|
# old_state is non-empty (host already seen), a fresh container appears running.
|
|
old = {"other": {"status": "running", "health": None, "oom_killed": False, "exit_code": None}}
|
|
events = _derive_events(old, [
|
|
_c("other", "running"),
|
|
_c("new", "running", image="redis"),
|
|
])
|
|
assert ("new", "start", "redis") in events
|
|
# the unchanged 'other' produces nothing
|
|
assert all(e[0] != "other" for e in events)
|
|
|
|
|
|
def test_stop_on_clean_exit():
|
|
old = {"job": {"status": "running", "health": None, "oom_killed": False, "exit_code": None}}
|
|
events = _derive_events(old, [_c("job", "exited", exit_code=0)])
|
|
assert events == [("job", "stop", None)]
|
|
|
|
|
|
def test_die_on_nonzero_exit():
|
|
old = {"job": {"status": "running", "health": None, "oom_killed": False, "exit_code": None}}
|
|
events = _derive_events(old, [_c("job", "exited", exit_code=137)])
|
|
assert events == [("job", "die", "exit 137")]
|
|
|
|
|
|
def test_oom_on_flip_to_true():
|
|
old = {"hog": {"status": "running", "health": None, "oom_killed": False, "exit_code": None}}
|
|
# OOM-killed → also no longer running with a non-zero exit, so die + oom both fire.
|
|
events = _derive_events(old, [_c("hog", "exited", exit_code=137, oom_killed=True)])
|
|
assert ("hog", "oom", None) in events
|
|
assert ("hog", "die", "exit 137") in events
|
|
|
|
|
|
def test_health_change_emitted():
|
|
old = {"svc": {"status": "running", "health": "healthy", "oom_killed": False, "exit_code": None}}
|
|
events = _derive_events(old, [_c("svc", "running", health="unhealthy")])
|
|
assert events == [("svc", "health_change", "healthy→unhealthy")]
|
|
|
|
|
|
def test_removed_running_container_stops():
|
|
old = {"gone": {"status": "running", "health": None, "oom_killed": False, "exit_code": None}}
|
|
events = _derive_events(old, []) # vanished from the listing entirely
|
|
assert events == [("gone", "stop", "removed")]
|
|
|
|
|
|
def test_no_event_when_unchanged():
|
|
old = {"web": {"status": "running", "health": "healthy", "oom_killed": False, "exit_code": None}}
|
|
events = _derive_events(old, [_c("web", "running", health="healthy")])
|
|
assert events == []
|
|
|
|
|
|
# ── container-log row shaping (m79, pure) ─────────────────────────────────────
|
|
|
|
def test_log_rows_shapes_and_filters():
|
|
from datetime import datetime, timezone
|
|
from plugins.docker.ingest import _log_rows
|
|
|
|
rec_at = datetime(2026, 1, 1, tzinfo=timezone.utc)
|
|
batches = [(rec_at, [
|
|
{"container": "web", "stream": "stdout",
|
|
"ts": "2026-01-01T00:00:01+00:00", "line": "hello"},
|
|
{"container": "web", "stream": "stderr", "ts": None, "line": "no-ts"},
|
|
{"container": "_steward", "stream": "stderr",
|
|
"ts": None, "line": "truncated"}, # advisory marker → dropped
|
|
{"container": "web", "stream": "weird", "ts": None, "line": "bad-stream"},
|
|
{"container": "", "line": "x"}, # no name → dropped
|
|
{"container": "web", "ts": None, "line": None}, # no line → dropped
|
|
"not-a-dict", # malformed → dropped
|
|
])]
|
|
rows = list(_log_rows(batches, "host-1"))
|
|
assert [r["line"] for r in rows] == ["hello", "no-ts", "bad-stream"]
|
|
assert rows[0]["host_id"] == "host-1" and rows[0]["container_name"] == "web"
|
|
assert rows[1]["ts"] == rec_at # None ts → recorded_at fallback
|
|
assert rows[2]["stream"] == "stdout" # unknown stream normalised
|
|
|
|
|
|
def test_log_rows_skips_non_list_records():
|
|
from datetime import datetime, timezone
|
|
from plugins.docker.ingest import _log_rows
|
|
rec_at = datetime(2026, 1, 1, tzinfo=timezone.utc)
|
|
assert list(_log_rows([(rec_at, None)], "h")) == []
|