GRM-123: fix: cast disk threshold to string in template-content verify assertion

This commit is contained in:
emil
2026-06-30 23:28:54 +00:00
parent 8fbe2d3f51
commit 63ef5cdbcf
16 changed files with 598 additions and 0 deletions
+10
View File
@@ -18,6 +18,16 @@
when: systemd_available.stat.exists
changed_when: true
- name: Stop and disable healthcheck timer
ansible.builtin.command: systemctl --user stop --disable runner-healthcheck.timer
become: true
become_user: "{{ gitea_runner_service_user | default('grm-' ~ runner_name) }}"
environment:
XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid | default('') }}"
when: systemd_available.stat.exists
changed_when: true
failed_when: false
- name: Include deregistration
ansible.builtin.include_role:
name: gitea-runner
+28
View File
@@ -79,6 +79,16 @@
tasks_from: deregister.yml
when: not skip_runner_registration | default(false)
- name: Stop and disable healthcheck timer
ansible.builtin.command: systemctl --user stop --disable runner-healthcheck.timer
become: true
become_user: "{{ gitea_runner_service_user | default('grm-' ~ runner_name) }}"
environment:
XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid | default('') }}"
when: systemd_available.stat.exists
changed_when: true
failed_when: false
- name: Remove docker-prune user service file
ansible.builtin.file:
path: "{{ gitea_runner_home | default('/home/grm-' ~ runner_name) }}/.config/systemd/user/docker-prune.service"
@@ -91,6 +101,24 @@
state: absent
failed_when: false
- name: Remove healthcheck user service file
ansible.builtin.file:
path: "{{ gitea_runner_home | default('/home/grm-' ~ runner_name) }}/.config/systemd/user/runner-healthcheck.service"
state: absent
failed_when: false
- name: Remove healthcheck user timer file
ansible.builtin.file:
path: "{{ gitea_runner_home | default('/home/grm-' ~ runner_name) }}/.config/systemd/user/runner-healthcheck.timer"
state: absent
failed_when: false
- name: Remove healthcheck script
ansible.builtin.file:
path: "{{ gitea_runner_config_dir | default('/etc/gitea-runner/' ~ runner_name) }}/healthcheck.sh"
state: absent
failed_when: false
- name: Remove systemd user unit file
ansible.builtin.file:
path: "{{ gitea_runner_home | default('/home/grm-' ~ runner_name) }}/.config/systemd/user/gitea-runner.service"
@@ -24,6 +24,12 @@ gitea_runner_prune_label: "gitea-runner=true"
# Service configuration
gitea_runner_service_restart_sec: "5"
# Health check configuration
gitea_runner_healthcheck_interval: "5min"
gitea_runner_healthcheck_boot_delay: "2min"
gitea_runner_healthcheck_disk_threshold: 85
gitea_runner_healthcheck_script_path: "{{ gitea_runner_config_dir }}/healthcheck.sh"
# Admin token for runner deregistration via Gitea API.
# If not set, falls back to registration_token (which likely lacks admin scope).
# Set this to a token with admin scope to enable automatic runner cleanup on removal.
@@ -75,3 +75,42 @@
that:
- timer_stat.stat.exists
fail_msg: "Docker prune timer is missing"
- name: Check healthcheck script exists
ansible.builtin.stat:
path: "{{ gitea_runner_healthcheck_script_path }}"
register: healthcheck_script_stat
- name: Assert healthcheck script exists
ansible.builtin.assert:
that:
- healthcheck_script_stat.stat.exists
fail_msg: "Healthcheck script is missing"
- name: Assert healthcheck script is executable
ansible.builtin.assert:
that:
- healthcheck_script_stat.stat.mode == "0755"
fail_msg: "Healthcheck script is not executable"
- name: Check healthcheck service exists
ansible.builtin.stat:
path: "{{ gitea_runner_home }}/.config/systemd/user/runner-healthcheck.service"
register: healthcheck_service_stat
- name: Assert healthcheck service exists
ansible.builtin.assert:
that:
- healthcheck_service_stat.stat.exists
fail_msg: "Healthcheck systemd service is missing"
- name: Check healthcheck timer exists
ansible.builtin.stat:
path: "{{ gitea_runner_home }}/.config/systemd/user/runner-healthcheck.timer"
register: healthcheck_timer_stat
- name: Assert healthcheck timer exists
ansible.builtin.assert:
that:
- healthcheck_timer_stat.stat.exists
fail_msg: "Healthcheck systemd timer is missing"
@@ -89,6 +89,39 @@
- not prune_timer_stat.stat.exists
fail_msg: "docker-prune timer unit still exists after removal"
- name: Check healthcheck service unit is absent
ansible.builtin.stat:
path: "{{ gitea_runner_home }}/.config/systemd/user/runner-healthcheck.service"
register: healthcheck_service_stat
- name: Assert healthcheck service unit is absent
ansible.builtin.assert:
that:
- not healthcheck_service_stat.stat.exists
fail_msg: "runner-healthcheck service unit still exists after removal"
- name: Check healthcheck timer unit is absent
ansible.builtin.stat:
path: "{{ gitea_runner_home }}/.config/systemd/user/runner-healthcheck.timer"
register: healthcheck_timer_stat
- name: Assert healthcheck timer unit is absent
ansible.builtin.assert:
that:
- not healthcheck_timer_stat.stat.exists
fail_msg: "runner-healthcheck timer unit still exists after removal"
- name: Check healthcheck script is absent
ansible.builtin.stat:
path: "{{ gitea_runner_config_dir }}/healthcheck.sh"
register: healthcheck_script_stat
- name: Assert healthcheck script is absent
ansible.builtin.assert:
that:
- not healthcheck_script_stat.stat.exists
fail_msg: "healthcheck script still exists after removal"
- name: Check subuid entry is absent
ansible.builtin.command: "grep -c '^{{ gitea_runner_service_user }}:' /etc/subuid"
register: subuid_check
@@ -62,3 +62,45 @@
- "'OnCalendar={{ gitea_runner_prune_schedule }}' in prune_timer.content | b64decode"
- "'Persistent=true' in prune_timer.content | b64decode"
fail_msg: "Prune timer template is missing expected directives"
- name: Read rendered healthcheck service template
ansible.builtin.slurp:
src: "{{ gitea_runner_home }}/.config/systemd/user/runner-healthcheck.service"
register: healthcheck_service
- name: Assert healthcheck service contains expected directives
ansible.builtin.assert:
that:
- "'Type=oneshot' in healthcheck_service.content | b64decode"
- "'ExecStart={{ gitea_runner_healthcheck_script_path }}' in healthcheck_service.content | b64decode"
- "'DOCKER_HOST=unix:///run/user/' in healthcheck_service.content | b64decode"
- "'XDG_RUNTIME_DIR=/run/user/' in healthcheck_service.content | b64decode"
fail_msg: "Healthcheck service template is missing expected directives"
- name: Read rendered healthcheck timer template
ansible.builtin.slurp:
src: "{{ gitea_runner_home }}/.config/systemd/user/runner-healthcheck.timer"
register: healthcheck_timer
- name: Assert healthcheck timer contains expected directives
ansible.builtin.assert:
that:
- "'OnBootSec={{ gitea_runner_healthcheck_boot_delay }}' in healthcheck_timer.content | b64decode"
- "'OnUnitActiveSec={{ gitea_runner_healthcheck_interval }}' in healthcheck_timer.content | b64decode"
- "'Persistent=true' in healthcheck_timer.content | b64decode"
fail_msg: "Healthcheck timer template is missing expected directives"
- name: Read rendered healthcheck script
ansible.builtin.slurp:
src: "{{ gitea_runner_healthcheck_script_path }}"
register: healthcheck_script
- name: Assert healthcheck script contains expected content
ansible.builtin.assert:
that:
- "'docker info' in healthcheck_script.content | b64decode"
- "'systemctl --user restart docker.service' in healthcheck_script.content | b64decode"
- "'systemctl --user restart gitea-runner.service' in healthcheck_script.content | b64decode"
- "'docker system prune' in healthcheck_script.content | b64decode"
- "gitea_runner_healthcheck_disk_threshold | string in healthcheck_script.content | b64decode"
fail_msg: "Healthcheck script template is missing expected content"
@@ -0,0 +1,46 @@
---
- name: Create healthcheck script
ansible.builtin.template:
src: runner-healthcheck.sh.j2
dest: "{{ gitea_runner_healthcheck_script_path }}"
owner: "{{ gitea_runner_service_user }}"
group: "{{ gitea_runner_service_user }}"
mode: "0755"
- name: Create healthcheck user service file
ansible.builtin.template:
src: runner-healthcheck.service.j2
dest: "{{ gitea_runner_home }}/.config/systemd/user/runner-healthcheck.service"
owner: "{{ gitea_runner_service_user }}"
group: "{{ gitea_runner_service_user }}"
mode: "0644"
- name: Create healthcheck user timer file
ansible.builtin.template:
src: runner-healthcheck.timer.j2
dest: "{{ gitea_runner_home }}/.config/systemd/user/runner-healthcheck.timer"
owner: "{{ gitea_runner_service_user }}"
group: "{{ gitea_runner_service_user }}"
mode: "0644"
- name: Reload systemd user daemon for healthcheck timer
ansible.builtin.command: systemctl --user daemon-reload
become: true
become_user: "{{ gitea_runner_service_user }}"
environment:
XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
changed_when: true
when:
- systemd_available.stat.exists
- docker_rootless_setup
- name: Enable and start healthcheck user timer
ansible.builtin.command: systemctl --user enable --now runner-healthcheck.timer
become: true
become_user: "{{ gitea_runner_service_user }}"
environment:
XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
changed_when: true
when:
- systemd_available.stat.exists
- docker_rootless_setup
@@ -14,6 +14,9 @@
- name: Include prune setup
ansible.builtin.include_tasks: prune.yml
- name: Include healthcheck setup
ansible.builtin.include_tasks: healthcheck.yml
- name: Include integration test
ansible.builtin.include_tasks: integration_test.yml
when: not skip_runner_registration
@@ -0,0 +1,9 @@
[Unit]
Description=Gitea Runner health check (Docker + service + disk)
After=docker.service gitea-runner.service
[Service]
Type=oneshot
Environment=DOCKER_HOST=unix:///run/user/{{ gitea_runner_uid }}/docker.sock
Environment=XDG_RUNTIME_DIR=/run/user/{{ gitea_runner_uid }}
ExecStart={{ gitea_runner_healthcheck_script_path }}
@@ -0,0 +1,49 @@
#!/bin/bash
# Health check for gitea-runner: verifies Docker daemon and runner service.
# Exits 0 if healthy, 1 if Docker is down (triggers restart), 2 if runner is down.
set -euo pipefail
DOCKER_HOST="unix:///run/user/{{ gitea_runner_uid }}/docker.sock"
XDG_RUNTIME_DIR="/run/user/{{ gitea_runner_uid }}"
export DOCKER_HOST XDG_RUNTIME_DIR
# 1. Check Docker daemon responsiveness
if ! docker info >/dev/null 2>&1; then
echo "ERROR: Docker daemon not responding at ${DOCKER_HOST}"
systemctl --user restart docker.service
sleep 3
if ! docker info >/dev/null 2>&1; then
echo "CRITICAL: Docker daemon still down after restart"
exit 1
fi
echo "RECOVERED: Docker daemon restarted successfully"
fi
# 2. Check gitea-runner service is active
runner_state=$(systemctl --user is-active gitea-runner.service 2>/dev/null || true)
if [[ "$runner_state" != "active" ]]; then
echo "ERROR: gitea-runner service is ${runner_state}, restarting"
systemctl --user restart gitea-runner.service
sleep 2
runner_state=$(systemctl --user is-active gitea-runner.service 2>/dev/null || true)
if [[ "$runner_state" != "active" ]]; then
echo "CRITICAL: gitea-runner service still down after restart"
exit 2
fi
echo "RECOVERED: gitea-runner service restarted successfully"
fi
# 3. Check disk space — prune aggressively if below threshold
disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
if [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_threshold }} ]]; then
echo "WARN: Disk usage at ${disk_pct}%, pruning all runner resources"
docker system prune -af --filter "label={{ gitea_runner_prune_label }}" --filter "until=1h" || true
docker volume prune -af --filter "label={{ gitea_runner_prune_label }}" || true
# Also prune dangling images (no label)
docker image prune -af || true
disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
echo "INFO: Disk usage after prune: ${disk_pct}%"
fi
echo "OK: runner healthy, disk at ${disk_pct}%"
exit 0
@@ -0,0 +1,10 @@
[Unit]
Description=Periodic Gitea Runner health check
[Timer]
OnBootSec={{ gitea_runner_healthcheck_boot_delay }}
OnUnitActiveSec={{ gitea_runner_healthcheck_interval }}
Persistent=true
[Install]
WantedBy=timers.target