bvandeusenandClaude Opus 5.5
81995051dc
The scraper folded traefik_service_requests_total{code} into two shares and
dropped the code, so a problem couldn't say whether it was scanners (404), a
login wall (401/403) or the app down (502/503/504). Each scrape now stores the
responses per router and code that occurred (traefik_status_codes, migration
traefik_006), pruned with the router metrics and left out of backups (System
180 ruling: Traefik history is not backed up). A problem card lists its codes
over the last 15 minutes, most first, or says none occurred, or that codes
aren't recorded yet.
A counter series new since the previous scrape now counts from 0 instead of
being skipped: Traefik creates a router's 502 series at its first 502, so a
first burst of 5xx read as 0% until it happened again.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
52 lines
1.7 KiB
Python
52 lines
1.7 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)
|
|
|
|
|
|
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"]}
|