Files
FabledSteward/plugins/snmp/routes.py
T
bvandeusenandClaude Opus 5.5 b8f73270e7
CI / lint (push) Successful in 3s
CI / integration (push) Failing after 1m14s
CI / unit (push) Successful in 1m33s
CI / publish (push) Skipped
perf(metrics): a latest-value table for "what is it now"; dashboard cells say loading, failed and as-of (#5208)
The dashboard's host widgets took 18-60 s. Every "latest reading" query
(hosts overview, host-agent fleet, host page, vitals, SNMP, MCP get_host)
searched plugin_metrics for the newest row per metric. Postgres has no skip
scan, so each one read every raw sample in the 7-day window.

- plugin_metric_latest: one row per (source, resource, metric).
  record_metrics upserts it in the same transaction, moving forward only and
  in sorted key order. Migration 0030 seeds it by stepping the existing index.
- Retention drops a latest row once its sample leaves the raw window, so a
  resource that stopped reporting disappears when its history does, as before.
  Renames carry it along.
- A quiet host keeps its last values, marked stale. A time-bounded query
  would have shown it as missing.
- Vitals sparklines span the 6 h they claim, averaged in SQL to ~120 points,
  instead of fetching 6 h raw and drawing the last 120 samples.
- Dashboard and share-view cells: "Loading…" until the first answer; a 20 s
  deadline per fetch; "Couldn't load (why)" with Retry now and an automatic
  retry for cells that don't poll; "as of HH:MM" in the header, and
  "couldn't refresh · as of" when a refresh fails over shown data.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 23:06:34 -04:00

190 lines
7.2 KiB
Python

# plugins/snmp/routes.py
from __future__ import annotations
from datetime import datetime, timedelta, timezone
from quart import Blueprint, current_app, render_template, request
from sqlalchemy import select
from steward.auth.middleware import require_role
from steward.models.users import UserRole
from steward.core.metric_series import latest_by_resource
from steward.models.metrics import PluginMetric
snmp_bp = Blueprint("snmp", __name__, template_folder="templates")
async def _latest_readings(db, device_names: list[str]) -> dict[str, dict[str, float]]:
"""Return {device_name: {label: latest_value}} for all configured devices."""
latest = await latest_by_resource(db, "snmp", device_names)
return {name: {m: r.value for m, r in metrics.items()} for name, metrics in latest.items()}
async def _history(db, device_name: str, hours: int = 24) -> dict[str, list]:
"""Return {label: [(recorded_at, value), ...]} for a single device."""
since = datetime.now(timezone.utc) - timedelta(hours=hours)
result = await db.execute(
select(PluginMetric)
.where(
PluginMetric.source_module == "snmp",
PluginMetric.resource_name == device_name,
PluginMetric.recorded_at >= since,
)
.order_by(PluginMetric.recorded_at)
)
rows = result.scalars().all()
out: dict[str, list] = {}
for row in rows:
out.setdefault(row.metric_name, []).append(
(row.recorded_at.isoformat(), row.value)
)
return out
@snmp_bp.get("/")
@require_role(UserRole.viewer)
async def index():
devices_cfg: list[dict] = current_app.config["PLUGINS"]["snmp"].get("devices", [])
device_names = [d.get("name") or d.get("host", "?") for d in devices_cfg]
async with current_app.db_sessionmaker() as db:
latest = await _latest_readings(db, device_names)
# Merge config + latest readings for the template
devices = []
for cfg in devices_cfg:
name = cfg.get("name") or cfg.get("host", "?")
devices.append({
"name": name,
"host": cfg.get("host", ""),
"oids": cfg.get("oids", []),
"readings": latest.get(name, {}),
})
poll_interval = current_app.config.get("MONITORS_POLL_INTERVAL", 60)
return await render_template("snmp/index.html",
devices=devices,
poll_interval=poll_interval)
def _device_binds_to_host(d: dict, keys: set[str], host_id: str) -> bool:
"""Does config device `d` belong on the host identified by `keys`
(lowercased {address, name}) / `host_id`?
A device may declare an **explicit** binding that decouples "which Steward
host this belongs to" from "where to poll" (the `host` field):
• `host_id` — the Steward Host UUID (exact match), the explicit link.
• `steward_host` — a friendly bind by Host name or address (case-insensitive).
An explicit binding is **exclusive**: a device bound to host A must not also
match host B by a coincidental poll-target string. Only when no explicit
binding is present do we fall back to the implicit `host`-string match
(backward compatible with configs that only set `host`).
"""
explicit_id = str(d.get("host_id", "")).strip()
explicit_name = str(d.get("steward_host", "")).strip().lower()
if explicit_id or explicit_name:
if explicit_id and host_id and explicit_id == host_id:
return True
return bool(explicit_name and explicit_name in keys)
return str(d.get("host", "")).strip().lower() in keys
def _devices_for_host(devices_cfg: list, address: str | None, name: str | None,
host_id: str | None = None) -> list[dict]:
"""SNMP devices that map onto a Steward host's page. Prefers an explicit
per-device binding (`host_id` / `steward_host`); otherwise falls back to
matching the device's `host` (poll target) against the host's address or
name (case-insensitive). See `_device_binds_to_host` for the precedence."""
keys = {(address or "").strip().lower(), (name or "").strip().lower()}
keys.discard("")
hid = (host_id or "").strip()
return [
d for d in devices_cfg
if isinstance(d, dict) and _device_binds_to_host(d, keys, hid)
]
@snmp_bp.get("/host/<host_id>")
@require_role(UserRole.viewer)
async def host_panel(host_id: str):
"""Per-host SNMP fragment for the Hosts hub. Surfaces any configured SNMP
device that maps to this host (by address or name) with its latest readings.
Renders nothing when no device maps, so hosts without SNMP carry no empty card.
"""
from steward.models.hosts import Host
devices_cfg: list[dict] = current_app.config["PLUGINS"]["snmp"].get("devices", [])
async with current_app.db_sessionmaker() as db:
host = (await db.execute(
select(Host).where(Host.id == host_id))).scalar_one_or_none()
if host is None:
return ""
matched = _devices_for_host(devices_cfg, host.address, host.name, host.id)
if not matched:
return ""
names = [d.get("name") or d.get("host", "?") for d in matched]
latest = await _latest_readings(db, names)
devices = [{
"name": d.get("name") or d.get("host", "?"),
"host": d.get("host", ""),
"oids": d.get("oids", []),
"readings": latest.get(d.get("name") or d.get("host", "?"), {}),
"bound": bool(str(d.get("host_id", "")).strip()
or str(d.get("steward_host", "")).strip()),
} for d in matched]
return await render_template("snmp/host_panel.html", devices=devices)
@snmp_bp.get("/widget")
@require_role(UserRole.viewer)
async def widget():
devices_cfg: list[dict] = current_app.config["PLUGINS"]["snmp"].get("devices", [])
device_names = [d.get("name") or d.get("host", "?") for d in devices_cfg]
async with current_app.db_sessionmaker() as db:
latest = await _latest_readings(db, device_names[:10])
devices = []
for cfg in devices_cfg[:10]:
name = cfg.get("name") or cfg.get("host", "?")
devices.append({
"name": name,
"oids": cfg.get("oids", []),
"readings": latest.get(name, {}),
})
return await render_template("snmp/widget.html",
devices=devices,
total=len(devices_cfg))
@snmp_bp.get("/device/<device_name>")
@require_role(UserRole.viewer)
async def device_detail(device_name: str):
devices_cfg: list[dict] = current_app.config["PLUGINS"]["snmp"].get("devices", [])
device_cfg = next(
(d for d in devices_cfg if (d.get("name") or d.get("host")) == device_name),
None,
)
if device_cfg is None:
from quart import abort
abort(404)
hours = int(request.args.get("hours", 24))
async with current_app.db_sessionmaker() as db:
hist = await _history(db, device_name, hours=hours)
import json
history_json = json.dumps(hist)
oid_labels = [o.get("label") or o.get("oid") for o in device_cfg.get("oids", [])]
return await render_template(
"snmp/device.html",
device=device_cfg,
device_name=device_name,
oid_labels=oid_labels,
history_json=history_json,
hours=hours,
)