bvandeusenandClaude Opus 5.5
98a0ced5eb
#5755 "Traefik latency was a percentile of every response since Traefik started, over unsummed label sets". _percentile_ms read the duration histogram as it stood, which counts from Traefik's start, so p50/p95/p99 were lifetime figures that barely moved. It also walked every code/method label set's buckets as one unsummed list, so equal counts from two sets returned an edge exactly: nextcloud's flat 100.0 ms p95. service_buckets() now takes each bucket's rise since the previous scrape, summed per le over every label set. A scrape with no responses, and the first scrape, record no latency: traefik_007_latency_nullable lets the columns be NULL, the batch skips the figure, and the page shows "—". Found while preparing #5741 "Traefik routers are graded against their own normal", which grades p95 against a learned normal. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
85 lines
4.4 KiB
Python
85 lines
4.4 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)
|
|
# None for a scrape with no responses: an idle router has no latency (#5741).
|
|
latency_p50_ms: Mapped[float | None] = mapped_column(Float, nullable=True)
|
|
latency_p95_ms: Mapped[float | None] = mapped_column(Float, nullable=True)
|
|
latency_p99_ms: Mapped[float | None] = mapped_column(Float, nullable=True)
|
|
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)
|
|
|
|
|
|
class TraefikStatusCode(Base):
|
|
"""How many responses a router answered with one 4xx or 5xx code in one
|
|
scrape interval (#5711): what lets a problem say whether it is scanners
|
|
probing (404), a login wall (401/403) or the app down (502/503/504).
|
|
Only codes that occurred are stored."""
|
|
__tablename__ = "traefik_status_codes"
|
|
|
|
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)
|
|
code: Mapped[str] = mapped_column(String(8), nullable=False)
|
|
count: Mapped[int] = mapped_column(Integer, nullable=False)
|