bvandeusen
7b80552a7d
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
114 lines
3.6 KiB
YAML
114 lines
3.6 KiB
YAML
---
|
|
# description: Install or re-enroll the Steward host agent on an already-provisioned host.
|
|
# steward:category: host-agent
|
|
# Install (or update) the Steward host agent on a target. Mirrors the
|
|
# curl-based install.sh. Pass the per-host registration token as extra-vars:
|
|
# steward_url=https://steward.example steward_token=<token from Host Agents>
|
|
# Re-running updates agent.py in place and restarts the service.
|
|
- name: Install Steward host agent
|
|
hosts: all
|
|
become: true
|
|
gather_facts: false
|
|
# steward_token is a per-host inventory var — not declared here, or a play var
|
|
# would outrank and shadow it. steward_url arrives as an extra-var.
|
|
vars:
|
|
steward_url: ""
|
|
agent_interval: 30
|
|
tasks:
|
|
- name: Require steward_url and steward_token
|
|
ansible.builtin.assert:
|
|
that:
|
|
- steward_url | default('') | length > 0
|
|
- steward_token | default('') | length > 0
|
|
fail_msg: "Pass steward_url and steward_token (Steward injects these)."
|
|
|
|
- name: Create steward-agent system user
|
|
ansible.builtin.user:
|
|
name: steward-agent
|
|
system: true
|
|
shell: /usr/sbin/nologin
|
|
create_home: false
|
|
|
|
# Let the agent read the local Docker socket so it can report this host's
|
|
# containers (the per-host docker collection path). Best-effort: skipped on
|
|
# hosts without Docker. Restart picks up the new supplementary group.
|
|
- name: Detect docker group
|
|
ansible.builtin.command: getent group docker
|
|
register: _docker_grp
|
|
changed_when: false
|
|
failed_when: false
|
|
|
|
- name: Add steward-agent to the docker group
|
|
ansible.builtin.user:
|
|
name: steward-agent
|
|
groups: docker
|
|
append: true
|
|
when: _docker_grp.rc == 0
|
|
notify: restart steward-agent
|
|
|
|
- name: Create agent directory
|
|
ansible.builtin.file:
|
|
path: /usr/local/lib/steward-agent
|
|
state: directory
|
|
mode: "0755"
|
|
|
|
- name: Download agent.py
|
|
ansible.builtin.get_url:
|
|
url: "{{ steward_url }}/plugins/host_agent/agent.py"
|
|
dest: /usr/local/lib/steward-agent/agent.py
|
|
mode: "0755"
|
|
force: true
|
|
notify: restart steward-agent
|
|
|
|
- name: Write agent config
|
|
ansible.builtin.copy:
|
|
dest: /etc/steward-agent.conf
|
|
owner: root
|
|
group: steward-agent
|
|
mode: "0640"
|
|
content: |
|
|
url = {{ steward_url }}
|
|
token = {{ steward_token }}
|
|
interval_seconds = {{ agent_interval }}
|
|
notify: restart steward-agent
|
|
|
|
- name: Install systemd unit
|
|
ansible.builtin.copy:
|
|
dest: /etc/systemd/system/steward-agent.service
|
|
mode: "0644"
|
|
content: |
|
|
[Unit]
|
|
Description=Steward host agent
|
|
After=network-online.target
|
|
Wants=network-online.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
User=steward-agent
|
|
Environment=STEWARD_AGENT_CONFIG=/etc/steward-agent.conf
|
|
ExecStart=/usr/bin/env python3 /usr/local/lib/steward-agent/agent.py
|
|
Restart=on-failure
|
|
RestartSec=5
|
|
NoNewPrivileges=true
|
|
ProtectSystem=strict
|
|
ProtectHome=true
|
|
PrivateTmp=true
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|
|
notify: restart steward-agent
|
|
|
|
- name: Enable and start the agent
|
|
ansible.builtin.systemd:
|
|
name: steward-agent
|
|
enabled: true
|
|
state: started
|
|
daemon_reload: true
|
|
|
|
handlers:
|
|
- name: restart steward-agent
|
|
ansible.builtin.systemd:
|
|
name: steward-agent
|
|
state: restarted
|
|
daemon_reload: true
|