bvandeusen
4fc8c96c41
The SNMP plugin ships in the image but logged "pysnmp not installed — SNMP polling disabled" on every poll, so polling never worked. Two coupled defects: 1. The Dockerfile installed only `.[ansible]`, so the `snmp` extra (pysnmp) was never bundled even though the plugin is first-party and shipped. 2. poller.py used the synchronous pysnmp HLAPI (`next(getCmd(...))`), which pysnmp-lextudio 6.x removed — it's asyncio-only now — so even with the dep present, polling would have thrown and silently returned nothing. The 5.x line that still has the sync API isn't safe on the image's Python 3.13. Fix: - Dockerfile: install `.[ansible,snmp]`. - poller.py: `poll_device_sync` → `async def poll_device` on the asyncio HLAPI, with a dual-version import (pysnmp 7.x `pysnmp.hlapi.v3arch.asyncio`/`get_cmd` + async `UdpTransportTarget.create`; pysnmp-lextudio 6.2.x `pysnmp.hlapi.asyncio`/`getCmd` + direct `UdpTransportTarget`) so a dependency bump can't silently re-break it. - scheduler.py: await poll_device directly; drop the run_in_executor wrapper and the now-unused asyncio import. - Add tests/plugins/snmp/test_poller.py covering the version→mpModel mapping, that the poller is a coroutine, and the graceful no-pysnmp path. Note: CI confirms import/load and the no-pysnmp path, but has no SNMP target — live polling against real devices is verified after deploy. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016Jg27rgypiW2efULXJDtMC
70 lines
2.2 KiB
Python
70 lines
2.2 KiB
Python
# plugins/snmp/scheduler.py
|
|
from __future__ import annotations
|
|
import logging
|
|
from typing import TYPE_CHECKING
|
|
|
|
if TYPE_CHECKING:
|
|
from quart import Quart
|
|
|
|
from steward.core.scheduler import ScheduledTask
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def make_poll_task(app: "Quart") -> ScheduledTask:
|
|
interval = app.config["PLUGINS"]["snmp"].get("poll_interval_seconds", 60)
|
|
|
|
async def poll() -> None:
|
|
await _do_poll(app)
|
|
|
|
return ScheduledTask(
|
|
name="snmp_poll",
|
|
coro_factory=poll,
|
|
interval_seconds=int(interval),
|
|
run_on_startup=True,
|
|
)
|
|
|
|
|
|
async def _do_poll(app: "Quart") -> None:
|
|
from .poller import poll_device
|
|
from steward.core.alerts import record_metric
|
|
|
|
devices: list[dict] = app.config["PLUGINS"]["snmp"].get("devices", [])
|
|
if not devices:
|
|
return
|
|
|
|
async with app.db_sessionmaker() as session:
|
|
async with session.begin():
|
|
for device in devices:
|
|
if not isinstance(device, dict):
|
|
continue
|
|
name = device.get("name") or device.get("host", "unknown")
|
|
host = device.get("host", "")
|
|
port = int(device.get("port", 161))
|
|
community = device.get("community", "public")
|
|
version = str(device.get("version", "2c"))
|
|
oids = device.get("oids", [])
|
|
|
|
if not host or not oids:
|
|
continue
|
|
|
|
try:
|
|
readings = await poll_device(host, port, community, version, oids)
|
|
except Exception:
|
|
logger.exception("SNMP poll failed for device %s (%s)", name, host)
|
|
continue
|
|
|
|
for label, value in readings.items():
|
|
await record_metric(
|
|
session=session,
|
|
source_module="snmp",
|
|
resource_name=name,
|
|
metric_name=label,
|
|
value=value,
|
|
)
|
|
|
|
if readings:
|
|
logger.debug("SNMP polled %s (%s): %d OID(s)", name, host, len(readings))
|
|
else:
|
|
logger.debug("SNMP polled %s (%s): no readings", name, host)
|