bvandeusen
82c3d2cf36
First slice of milestone 77 (Docker monitoring depth). Surfaces real per-container
stats beyond basic state, all read-only on the existing push model.
- agent (→1.4.0): collect_docker now inspects each container (health, restart
count, exit code, OOM) and reads net + block I/O from the stats payload; pulls
compose project + swarm service/task/node from container labels. Per-container
inspect+stats calls run over a small bounded ThreadPool so the ~1s-per-stats
blocking doesn't stretch the sample on a busy host.
- schema (docker_003): additive columns on docker_containers — health, exit_code,
oom_killed, compose_project, service_name, task_id, node_id, and BigInteger
net/blk byte counters.
- ingest: persists the enrichment + restart_count (.get keeps older agents working).
- ui: Docker page rows now show health badge, uptime ("up 3d 4h"), restart count,
exit code (+OOM) for stopped containers, and compose/service grouping label.
- tests: agent helpers (grouping, inspect fields, net/IO sum) + collect_docker
assembly incl. inspect; integration asserts enrichment round-trips.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016Jg27rgypiW2efULXJDtMC
88 lines
4.6 KiB
Python
88 lines
4.6 KiB
Python
# plugins/docker/models.py
|
|
from __future__ import annotations
|
|
import uuid
|
|
from datetime import datetime, timezone
|
|
from sqlalchemy import (
|
|
BigInteger, Boolean, DateTime, Float, ForeignKey, Index, Integer, String, Text,
|
|
)
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
from steward.models.base import Base
|
|
|
|
|
|
class DockerContainer(Base):
|
|
"""Latest known state per container, scoped to the host that reported it.
|
|
|
|
Collection is per-host via the host agent, so container names are only
|
|
unique within a host — the natural key is (host_id, name). host_id is NOT
|
|
NULL: every container arrives through a host_agent ingest that resolves a
|
|
Host first. Deleting a host cascades its containers away.
|
|
"""
|
|
__tablename__ = "docker_containers"
|
|
|
|
host_id: Mapped[str] = mapped_column(
|
|
String(36), ForeignKey("hosts.id", ondelete="CASCADE"), primary_key=True
|
|
)
|
|
name: Mapped[str] = mapped_column(String(255), primary_key=True)
|
|
container_id: Mapped[str] = mapped_column(String(64), nullable=False, default="")
|
|
image: Mapped[str] = mapped_column(String(512), nullable=False, default="")
|
|
status: Mapped[str] = mapped_column(String(32), nullable=False, default="unknown")
|
|
# running | stopped | paused | exited | dead
|
|
cpu_pct: Mapped[float | None] = mapped_column(Float, nullable=True)
|
|
mem_usage_bytes: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
|
mem_limit_bytes: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
|
mem_pct: Mapped[float | None] = mapped_column(Float, nullable=True)
|
|
restart_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
|
|
ports_json: Mapped[str] = mapped_column(Text, nullable=False, default="[]")
|
|
# JSON: [{"host_port": 8080, "container_port": 80, "protocol": "tcp"}]
|
|
started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
|
|
scraped_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), nullable=False,
|
|
default=lambda: datetime.now(timezone.utc),
|
|
)
|
|
|
|
# ── Enrichment (agent ≥ 1.4.0) ────────────────────────────────────────────
|
|
# Health/exit/restart come from `docker inspect` (not the list endpoint);
|
|
# exit_code is only meaningful for stopped containers.
|
|
health: Mapped[str | None] = mapped_column(String(16), nullable=True) # healthy|unhealthy|starting
|
|
exit_code: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
|
oom_killed: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
|
|
# Grouping: compose project + swarm placement, read off container labels.
|
|
compose_project: Mapped[str | None] = mapped_column(String(255), nullable=True)
|
|
service_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
|
|
task_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
|
|
node_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
|
|
# Cumulative-since-start I/O counters (BigInteger — they exceed 2^31 quickly).
|
|
net_rx_bytes: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
|
|
net_tx_bytes: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
|
|
blk_read_bytes: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
|
|
blk_write_bytes: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
|
|
|
|
|
|
class DockerMetric(Base):
|
|
"""Time-series CPU/memory per container — one row per sample per running
|
|
container, scoped to the reporting host."""
|
|
__tablename__ = "docker_metrics"
|
|
|
|
id: Mapped[str] = mapped_column(
|
|
String(36), primary_key=True, default=lambda: str(uuid.uuid4())
|
|
)
|
|
host_id: Mapped[str] = mapped_column(
|
|
String(36), ForeignKey("hosts.id", ondelete="CASCADE"), nullable=False, index=True
|
|
)
|
|
container_name: Mapped[str] = mapped_column(String(255), nullable=False, index=True)
|
|
scraped_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), nullable=False,
|
|
default=lambda: datetime.now(timezone.utc),
|
|
index=True,
|
|
)
|
|
cpu_pct: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
|
|
mem_pct: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
|
|
mem_usage_bytes: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
|
|
|
|
# Per-container history lookups filter on (host_id, container_name) then sort
|
|
# by time — a composite index keeps the rows() sparkline queries cheap.
|
|
__table_args__ = (
|
|
Index("ix_docker_metrics_host_container_time",
|
|
"host_id", "container_name", "scraped_at"),
|
|
)
|