bvandeusen
af60ca446d
The fabledscryer->steward rename had only ever reached host_agent. The other five bundled plugins (http, snmp, traefik, unifi, docker) still imported `from fabledscryer.*` (package no longer exists) and read FABLEDSCRYER_* env vars — so every one of them was broken at import since the original rebrand. CI stayed green only because none are enabled by default and migrations don't import plugin modules. Now that they version in-tree, complete the rename: - fabledscryer.* -> steward.* imports across all five plugins - FABLEDSCRYER_* -> STEWARD_* in plugin migration env.py files - author/repository/homepage + user-facing 'Fabled Scryer' strings -> Steward - snmp/scheduler.py: also drop dead `now`/datetime; record_metric from steward Adds tests/test_no_legacy_names.py — fails if 'scryer'/'roundtable' ever reappear in shipped code (the drift bit twice; this stops a third time). Also clears pre-existing ruff lint debt (unused imports, semicolon statements, mid-file import) surfaced by the new lint lane. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
94 lines
3.3 KiB
Python
94 lines
3.3 KiB
Python
# plugins/docker/scheduler.py
|
|
from __future__ import annotations
|
|
import json
|
|
import logging
|
|
from datetime import datetime, timezone
|
|
|
|
from steward.core.scheduler import ScheduledTask
|
|
from steward.core.alerts import record_metric
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def make_task(app) -> ScheduledTask:
|
|
interval = int(
|
|
app.config["PLUGINS"]["docker"].get("scrape_interval_seconds", 60)
|
|
)
|
|
|
|
async def scrape():
|
|
await _do_scrape(app)
|
|
|
|
return ScheduledTask(
|
|
name="docker_scrape",
|
|
coro_factory=scrape,
|
|
interval_seconds=interval,
|
|
run_on_startup=True,
|
|
)
|
|
|
|
|
|
async def _do_scrape(app) -> None:
|
|
from .scraper import scrape_docker
|
|
from .models import DockerContainer, DockerMetric
|
|
|
|
cfg = app.config["PLUGINS"]["docker"]
|
|
socket_path = cfg.get("socket_path", "/var/run/docker.sock")
|
|
include_stopped = bool(cfg.get("include_stopped", False))
|
|
|
|
try:
|
|
containers = await scrape_docker(socket_path, include_stopped)
|
|
except ConnectionError as exc:
|
|
logger.error("Docker scrape failed: %s", exc)
|
|
return
|
|
except Exception:
|
|
logger.exception("Docker scrape error")
|
|
return
|
|
|
|
now = datetime.now(timezone.utc)
|
|
|
|
async with app.db_sessionmaker() as session:
|
|
async with session.begin():
|
|
for c in containers:
|
|
# Upsert container state
|
|
existing = await session.get(DockerContainer, c["name"])
|
|
if existing is None:
|
|
existing = DockerContainer(name=c["name"])
|
|
session.add(existing)
|
|
existing.container_id = c["container_id"]
|
|
existing.image = c["image"]
|
|
existing.status = c["status"]
|
|
existing.cpu_pct = c["cpu_pct"]
|
|
existing.mem_usage_bytes = c["mem_usage_bytes"]
|
|
existing.mem_limit_bytes = c["mem_limit_bytes"]
|
|
existing.mem_pct = c["mem_pct"]
|
|
existing.restart_count = c["restart_count"]
|
|
existing.ports_json = json.dumps(c["ports"])
|
|
existing.started_at = c["started_at"]
|
|
existing.scraped_at = now
|
|
|
|
# Time-series metric (running containers only)
|
|
if c["status"] == "running" and c["cpu_pct"] is not None:
|
|
session.add(DockerMetric(
|
|
container_name=c["name"],
|
|
scraped_at=now,
|
|
cpu_pct=c["cpu_pct"],
|
|
mem_pct=c["mem_pct"] or 0.0,
|
|
mem_usage_bytes=c["mem_usage_bytes"] or 0,
|
|
))
|
|
|
|
# Feed alert pipeline
|
|
await record_metric(
|
|
session=session,
|
|
source_module="docker",
|
|
resource_name=c["name"],
|
|
metric_name="cpu_pct",
|
|
value=c["cpu_pct"],
|
|
)
|
|
if c["mem_pct"] is not None:
|
|
await record_metric(
|
|
session=session,
|
|
source_module="docker",
|
|
resource_name=c["name"],
|
|
metric_name="mem_pct",
|
|
value=c["mem_pct"],
|
|
)
|