bvandeusenandClaude Opus 5.5
f3433fe3ce
Host CPU, memory and load per core, container CPU and memory, and every monitor's response time learn a normal per hour (milestone 513, System 182). A reading past its fixed cutoff but within its normal reads healthy and says what is usual at this hour; one well out of it keeps its grade and is a metric anomaly. Disk, a monitor down and an agent offline keep their cutoffs. - Each normal's floor, the smallest departure that counts, is a setting: Settings -> Thresholds -> Normals (norms.floor.*). Defaults: host CPU 10 points, host memory 5, load per core 10, container CPU 10 points of one core, container memory 5, monitor response 100 ms; Traefik's 2-point 4xx and 50 ms p95 floors move there from constants. learn_normal takes a floor function (floor_setting) read at each pass. - learn_normal(parts=False): a host learns, its cores don't. - Ingest records load_pct (load_1m / cores x 100), the figure pages grade. - Shared grading: anomalies.against / graded, worst_reading(normals=), hosts' host_grades, docker usage(thresholds=, norms=), monitors' latency_grade. Applied to host vitals, the Hosts widget, MCP overview, Docker usage, and the monitor list, widget and page. - The monitor and container pages list their anomalies. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
86 lines
3.4 KiB
Python
86 lines
3.4 KiB
Python
# plugins/docker/__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 DockerContainer # noqa: F401 — register with Base
|
|
|
|
# Publish the per-host persist hook so the host agent can hand off the
|
|
# `docker` array from each sample without importing our models (opportunistic
|
|
# synergy — host_agent gates on has_capability and no-ops if we're disabled).
|
|
# required_role=viewer: this is a trusted server-side data-plane write driven
|
|
# by the authenticated agent ingest, not a user-facing privileged action.
|
|
from steward.core.capabilities import register_capability
|
|
from steward.models.users import UserRole
|
|
from .ingest import persist_host_docker
|
|
from .retention import prune_docker_logs, run_docker_retention
|
|
register_capability(
|
|
"docker.persist_host_samples", persist_host_docker,
|
|
label="Persist host Docker samples",
|
|
description="Store per-host container state + metrics pushed by the host agent.",
|
|
required_role=UserRole.viewer,
|
|
)
|
|
# Prune lifecycle events, driven by the core cleanup task without it
|
|
# importing our models. Same trusted server-side data-plane role as above.
|
|
# Container CPU and memory live in the one metric store and its retention.
|
|
register_capability(
|
|
"docker.run_retention", run_docker_retention,
|
|
label="Run Docker retention",
|
|
description="Prune Docker lifecycle events past their window.",
|
|
required_role=UserRole.viewer,
|
|
)
|
|
register_capability(
|
|
"docker.prune_logs", prune_docker_logs,
|
|
label="Prune Docker logs",
|
|
description="Keep each container's logs within the age window and byte cap.",
|
|
required_role=UserRole.viewer,
|
|
)
|
|
# Each container's CPU (100% is one core) and memory share learn their
|
|
# normal (#5742), each with its floor from Settings → Thresholds.
|
|
from steward.core.norms import floor_setting, learn_normal
|
|
learn_normal("docker", "cpu_pct", floor_setting(app, "container_cpu_pct"))
|
|
learn_normal("docker", "mem_pct", floor_setting(app, "container_mem_pct"))
|
|
|
|
|
|
def get_scheduled_tasks() -> list:
|
|
# Collection is now agent-driven (pushed to the host_agent ingest); the
|
|
# central socket scrape was removed. No periodic task to register.
|
|
return []
|
|
|
|
|
|
def get_blueprint():
|
|
from .routes import docker_bp
|
|
return docker_bp
|
|
|
|
|
|
def register_mcp_tools(register) -> None:
|
|
from .mcp_tools import register_tools
|
|
register_tools(register)
|
|
|
|
|
|
async def mcp_overview(db) -> list[dict]:
|
|
from .mcp_tools import mcp_overview as findings
|
|
return await findings(db)
|
|
|
|
|
|
def get_nav() -> list[dict]:
|
|
# Surfaces in the sidebar's Infrastructure group (fleet-wide container view).
|
|
return [{"label": "Docker", "href": "/plugins/docker/"}]
|
|
|
|
|
|
def get_alert_metrics() -> dict[str, list[str]]:
|
|
"""What ingest.py records per container (resource "<host>/<container>"):
|
|
restart_count is cumulative (alert on crash-looping); is_healthy is 1.0 /
|
|
0.0 from the container's HEALTHCHECK, only for containers that define one.
|
|
Per host (resource "<host>"), what Docker keeps on its disk (#5304)."""
|
|
from .disk_view import DISK_METRICS
|
|
return {"docker": ["cpu_pct", "mem_pct", "restart_count", "is_healthy", *DISK_METRICS]}
|