Files
FabledSteward/plugins/traefik/models.py
T
bvandeusenandClaude Opus 5.5 ad4f7d9232
CI / lint (push) Successful in 2s
CI / integration (push) Successful in 45s
CI / unit (push) Successful in 1m10s
CI / publish (push) Successful in 54s
fix(metrics): time-series rows get time-ordered ids, so an insert stops costing a disk read (#5149)
Measured on dev (385a579), agent posts cut to five samples still dropped:
flush=8.8s for 990 rows, 6.6s for 680, 8.4s for 1000 — about 110 rows/s,
~9 ms a row, with rules and evaluation near zero. One random read per
row fits a random uuid4 primary key whose index no longer fits in memory:
every new row lands on a random page of it. (Inferred from the rate; the
table and index sizes have not been read.)

- steward.core.ids.time_ordered_id: a UUIDv7-layout string (48-bit ms
  timestamp, then random), same 36-char shape as the stored uuid4 ids, so
  no migration. Python's uuid7() arrives in 3.14; the image runs 3.13.
- Used for plugin_metrics and its hourly rollup, monitor_results,
  audit_events, the docker metrics/hourly/events/logs tables, and the
  traefik and unifi time series.
- MAX_SAMPLES_PER_INGEST 5 → 2 (~400 rows) for now: it fits the agent's
  10 s even at the old rate, so hosts land data whichever way the new rate
  comes out. Raise it once the new rate is measured.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 18:58:41 -04:00

68 lines
3.5 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)
config_last_reload_success: Mapped[float | None] = mapped_column(Float, nullable=True)
process_memory_bytes: Mapped[float | None] = mapped_column(Float, nullable=True)