feat(docker): per-host collection via the host agent; drop central scrape
Docker collection moves off the central single-socket scrape onto the host
agent, giving Docker a real per-host dimension. The Steward host now reports
its own containers like any other host, and same-named containers on different
hosts no longer collide.
- agent: stdlib UDS Docker client (AF_UNIX HTTP/1.1, Connection: close,
chunked-aware), collect_docker() ports the cpu%/mem math; sample["docker"]
added best-effort (silent-skip on absent/unreadable socket). AGENT_VERSION
1.2.0 → 1.3.0; optional docker_socket config key.
- ingest: host_agent ingest hands per-host container snapshots to the docker
plugin via a new "docker.persist_host_samples" capability (no hard import,
no-op when docker disabled), inside a SAVEPOINT so a docker failure never
sinks the host metrics. Resource names are host-scoped ("<host>/<name>").
- schema: docker_containers re-keyed (host_id, name); docker_metrics gains
host_id; docker_002 migration DROP+recreates (dev-only, rule 122).
- ui: Docker page + widgets grouped by host with host links; new per-host
Docker panel embedded on the Hosts hub (gated on docker enabled via a new
enabled_plugins template context). Replaces the SQLite-only strftime
bucketing with DB-agnostic Python bucketing.
- provisioning: install/provision playbooks add steward-agent to the docker
group (best-effort) so the agent can read the socket.
- removed central scrape: docker scheduler.py + scraper.py deleted; plugin.yaml
socket_path/scrape_interval_seconds/include_stopped dropped (plugin 2.0.0).
- tests: agent docker collector units (math, chunked decode, silent-skip,
sample shape, config) + integration (host-scoped schema + persistence).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016Jg27rgypiW2efULXJDtMC
This commit is contained in:
@@ -0,0 +1,94 @@
|
||||
"""Docker collection goes per-host: add host_id, re-key by (host_id, name)
|
||||
|
||||
Collection moved from the central single-socket scrape to the host agent, so
|
||||
containers are now scoped to the host that reported them. docker_containers is
|
||||
re-keyed (host_id, name) and docker_metrics gains host_id.
|
||||
|
||||
Dev-only posture (rule 122): the old tables only ever held the Steward box's
|
||||
own containers (a single global namespace), which are disposable — so this
|
||||
DROP+recreates rather than backfilling a host_id onto orphan rows.
|
||||
|
||||
Revision ID: docker_002_host_scoped
|
||||
Revises: docker_001_initial
|
||||
Create Date: 2026-06-18
|
||||
"""
|
||||
from typing import Sequence, Union
|
||||
from alembic import op
|
||||
import sqlalchemy as sa
|
||||
|
||||
revision: str = "docker_002_host_scoped"
|
||||
down_revision: Union[str, None] = "docker_001_initial"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
# FK targets hosts.id (created in 0002_core_monitors) — make the edge explicit.
|
||||
depends_on: Union[str, Sequence[str], None] = ("0002_core_monitors",)
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
op.drop_table("docker_metrics")
|
||||
op.drop_table("docker_containers")
|
||||
|
||||
op.create_table(
|
||||
"docker_containers",
|
||||
sa.Column("host_id", sa.String(36),
|
||||
sa.ForeignKey("hosts.id", ondelete="CASCADE"), primary_key=True),
|
||||
sa.Column("name", sa.String(255), primary_key=True),
|
||||
sa.Column("container_id", sa.String(64), nullable=False, server_default=""),
|
||||
sa.Column("image", sa.String(512), nullable=False, server_default=""),
|
||||
sa.Column("status", sa.String(32), nullable=False, server_default="unknown"),
|
||||
sa.Column("cpu_pct", sa.Float, nullable=True),
|
||||
sa.Column("mem_usage_bytes", sa.Integer, nullable=True),
|
||||
sa.Column("mem_limit_bytes", sa.Integer, nullable=True),
|
||||
sa.Column("mem_pct", sa.Float, nullable=True),
|
||||
sa.Column("restart_count", sa.Integer, nullable=False, server_default="0"),
|
||||
sa.Column("ports_json", sa.Text, nullable=False, server_default="[]"),
|
||||
sa.Column("started_at", sa.DateTime(timezone=True), nullable=True),
|
||||
sa.Column("scraped_at", sa.DateTime(timezone=True), nullable=False),
|
||||
)
|
||||
|
||||
op.create_table(
|
||||
"docker_metrics",
|
||||
sa.Column("id", sa.String(36), primary_key=True),
|
||||
sa.Column("host_id", sa.String(36),
|
||||
sa.ForeignKey("hosts.id", ondelete="CASCADE"), nullable=False),
|
||||
sa.Column("container_name", sa.String(255), nullable=False),
|
||||
sa.Column("scraped_at", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("cpu_pct", sa.Float, nullable=False, server_default="0"),
|
||||
sa.Column("mem_pct", sa.Float, nullable=False, server_default="0"),
|
||||
sa.Column("mem_usage_bytes", sa.Integer, nullable=False, server_default="0"),
|
||||
)
|
||||
op.create_index("ix_docker_metrics_host_id", "docker_metrics", ["host_id"])
|
||||
op.create_index("ix_docker_metrics_container_name", "docker_metrics",
|
||||
["container_name"])
|
||||
op.create_index("ix_docker_metrics_scraped_at", "docker_metrics", ["scraped_at"])
|
||||
op.create_index("ix_docker_metrics_host_container_time", "docker_metrics",
|
||||
["host_id", "container_name", "scraped_at"])
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
op.drop_table("docker_metrics")
|
||||
op.drop_table("docker_containers")
|
||||
|
||||
op.create_table(
|
||||
"docker_containers",
|
||||
sa.Column("name", sa.String(255), primary_key=True),
|
||||
sa.Column("container_id", sa.String(64), nullable=False, server_default=""),
|
||||
sa.Column("image", sa.String(512), nullable=False, server_default=""),
|
||||
sa.Column("status", sa.String(32), nullable=False, server_default="unknown"),
|
||||
sa.Column("cpu_pct", sa.Float, nullable=True),
|
||||
sa.Column("mem_usage_bytes", sa.Integer, nullable=True),
|
||||
sa.Column("mem_limit_bytes", sa.Integer, nullable=True),
|
||||
sa.Column("mem_pct", sa.Float, nullable=True),
|
||||
sa.Column("restart_count", sa.Integer, nullable=False, server_default="0"),
|
||||
sa.Column("ports_json", sa.Text, nullable=False, server_default="[]"),
|
||||
sa.Column("started_at", sa.DateTime(timezone=True), nullable=True),
|
||||
sa.Column("scraped_at", sa.DateTime(timezone=True), nullable=False),
|
||||
)
|
||||
op.create_table(
|
||||
"docker_metrics",
|
||||
sa.Column("id", sa.String(36), primary_key=True),
|
||||
sa.Column("container_name", sa.String(255), nullable=False, index=True),
|
||||
sa.Column("scraped_at", sa.DateTime(timezone=True), nullable=False, index=True),
|
||||
sa.Column("cpu_pct", sa.Float, nullable=False, server_default="0"),
|
||||
sa.Column("mem_pct", sa.Float, nullable=False, server_default="0"),
|
||||
sa.Column("mem_usage_bytes", sa.Integer, nullable=False, server_default="0"),
|
||||
)
|
||||
Reference in New Issue
Block a user