Files
FabledSteward/plugins/traefik/models.py
T
bvandeusenandClaude Opus 5.5 7ce61a2099
CI / lint (push) Failing after 2s
CI / integration (push) Successful in 54s
CI / unit (push) Successful in 1m24s
CI / publish (push) Skipped
fix(traefik): grade routers on their last 15 minutes; the Config tile reads Traefik's reload time (#5355)
The operator: problem cards "can disappear so quickly". Each router was
graded on its latest scrape, so a 4xx share near the 1% cutoff crossed it
on one scrape and fell back on the next. recent_window reads every
router's last 15 minutes in one query, the error shares weighted by
traffic; grade_routers uses it on the page and the dashboard widget, and
the why says "over the last 15 min".

traefik_config_last_reload_success is the Unix time of the last good
reload, not a 0/1 flag, so the tile said "Reload failed" on every scrape.
traefik_005 stores it as config_last_reload_at, and the tile reads
"Config reloaded 3m ago". The router index also carries the 4xx share.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 08:26:10 -04:00

70 lines
3.6 KiB
Python

# plugins/traefik/models.py
from __future__ import annotations
from datetime import datetime, timezone
from sqlalchemy import DateTime, Float, Integer, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from steward.models.base import Base
from steward.core.ids import time_ordered_id
class TraefikMetric(Base):
__tablename__ = "traefik_metrics"
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=time_ordered_id)
router_name: Mapped[str] = mapped_column(String(255), nullable=False)
scraped_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc)
)
request_rate: Mapped[float] = mapped_column(Float, nullable=False)
error_rate_4xx_pct: Mapped[float] = mapped_column(Float, nullable=False)
error_rate_5xx_pct: Mapped[float] = mapped_column(Float, nullable=False)
latency_p50_ms: Mapped[float] = mapped_column(Float, nullable=False)
latency_p95_ms: Mapped[float] = mapped_column(Float, nullable=False)
latency_p99_ms: Mapped[float] = mapped_column(Float, nullable=False)
response_bytes_rate: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
class TraefikCert(Base):
"""TLS certificate expiry tracking — upserted by serial each scrape."""
__tablename__ = "traefik_certs"
serial: Mapped[str] = mapped_column(String(255), primary_key=True)
cn: Mapped[str | None] = mapped_column(String(512), nullable=True)
sans: Mapped[str | None] = mapped_column(Text, nullable=True)
not_after: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
scraped_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc)
)
class TraefikAccessSummary(Base):
"""Aggregated traffic-origin summary — one row per scheduler tick."""
__tablename__ = "traefik_access_summaries"
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=time_ordered_id)
period_start: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
period_end: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
total_requests: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
internal_requests: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
external_requests: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
total_bytes: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
top_ips_json: Mapped[str] = mapped_column(Text, nullable=False, default="[]")
top_countries_json: Mapped[str] = mapped_column(Text, nullable=False, default="[]")
top_routers_json: Mapped[str] = mapped_column(Text, nullable=False, default="[]")
class TraefikGlobalStat(Base):
"""One row per scrape — process-level and config stats."""
__tablename__ = "traefik_global_stats"
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=time_ordered_id)
scraped_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc)
)
open_conns_total: Mapped[float | None] = mapped_column(Float, nullable=True)
config_reloads_total: Mapped[float | None] = mapped_column(Float, nullable=True)
# When Traefik last loaded its configuration successfully: its
# traefik_config_last_reload_success gauge is that moment, not a 0/1 flag.
config_last_reload_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
process_memory_bytes: Mapped[float | None] = mapped_column(Float, nullable=True)