bvandeusenandClaude Opus 5.5
9f14620271
#5741 "Traefik routers are graded against their own normal", milestone 513. - A router's 4xx share and p95 learn their normal (learn_normal in the plugin's setup). Once a router has 5 days of history, a reading over the fixed cutoff but inside its normal is healthy, and the healthy table says it is usual for that router. One out of its normal is a warning that says what is usual, and a metric anomaly. - The 5xx share is a failure: fixed cutoff always, whatever the history or traffic (System 182's ruling). - A 4xx share over fewer requests than Settings -> Thresholds' new "Fewest requests to judge 4xx" (30 per 15 minutes) isn't graded on the page, and isn't judged for anomalies. - Core: learn_normal(gate=(metric, least)) judges a key only while its resource's gate metric averages at least `least`; `least` may be a function, so it follows a setting. learn_normal(since=...) learns only from history after a moment: Traefik latency learns from #5755's per-scrape figures only. - The Traefik page lists the routers' metric anomalies of the last 30 days (_anomaly_card.html). The dashboard widget keeps its why to problems. - Thresholds and docs say when the cutoffs give way to a normal. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
65 lines
2.6 KiB
Python
65 lines
2.6 KiB
Python
# plugins/traefik/__init__.py
|
|
from __future__ import annotations
|
|
from typing import TYPE_CHECKING
|
|
|
|
if TYPE_CHECKING:
|
|
from quart import Quart
|
|
|
|
_app: "Quart | None" = None
|
|
|
|
|
|
def setup(app: "Quart") -> None:
|
|
global _app
|
|
_app = app
|
|
from .models import ( # noqa: F401
|
|
TraefikAccessSummary, TraefikCert, TraefikGlobalStat, TraefikMetric, TraefikStatusCode,
|
|
)
|
|
from steward.core.cleanup import prune_by_age
|
|
# Samples older than data.retention_days are pruned by the cleanup (#5155).
|
|
prune_by_age(TraefikMetric.scraped_at)
|
|
prune_by_age(TraefikStatusCode.scraped_at)
|
|
prune_by_age(TraefikGlobalStat.scraped_at)
|
|
prune_by_age(TraefikAccessSummary.period_end)
|
|
# Each router's 4xx share and p95 learn their normal (#5741), judged only
|
|
# while the router answers the Thresholds minimum of requests a window
|
|
# (read at each pass, so a saved change applies at once). Latency is
|
|
# learned from the scrape-by-scrape figures only: before #5755 it was a
|
|
# percentile of every response since Traefik started.
|
|
from datetime import datetime, timezone
|
|
from steward.core.norms import learn_normal
|
|
from .routes import FLOOR_4XX, FLOOR_P95, STATE_WINDOW, min_requests
|
|
gate = ("request_rate",
|
|
lambda: min_requests(app.config.get("THRESHOLDS", {})) / STATE_WINDOW.total_seconds())
|
|
learn_normal("traefik", "error_rate_4xx_pct", FLOOR_4XX, gate=gate)
|
|
learn_normal("traefik", "latency_p95_ms", FLOOR_P95, gate=gate,
|
|
since=datetime(2026, 10, 14, 18, 47, tzinfo=timezone.utc))
|
|
|
|
|
|
def get_scheduled_tasks() -> list:
|
|
from .scheduler import make_scrape_task, make_access_log_task
|
|
tasks = [make_scrape_task(_app)]
|
|
access_log_cfg = _app.config["PLUGINS"]["traefik"].get("access_log", {})
|
|
if not isinstance(access_log_cfg, dict):
|
|
access_log_cfg = {}
|
|
if access_log_cfg.get("enabled", False):
|
|
tasks.append(make_access_log_task(_app))
|
|
return tasks
|
|
|
|
|
|
def get_blueprint():
|
|
from .routes import traefik_bp
|
|
return traefik_bp
|
|
|
|
|
|
def get_nav() -> list[dict]:
|
|
# Surfaces in the sidebar's Infrastructure group (Traefik services view).
|
|
return [{"label": "Traefik", "href": "/plugins/traefik/"}]
|
|
|
|
|
|
def get_alert_metrics() -> dict[str, list[str]]:
|
|
"""What scheduler.py records for alert rules: per router (resource = the
|
|
router name) and cert_expiry_days per certificate (resource = its CN)."""
|
|
return {"traefik": ["request_rate", "error_rate_4xx_pct", "error_rate_5xx_pct",
|
|
"latency_p50_ms", "latency_p95_ms", "latency_p99_ms",
|
|
"response_bytes_rate", "cert_expiry_days"]}
|