Michael Schiemer
36ef2a1e2c
Some checks failed
🚀 Build & Deploy Image / Determine Build Necessity (push) Failing after 10m14s
🚀 Build & Deploy Image / Build Runtime Base Image (push) Has been skipped
🚀 Build & Deploy Image / Build Docker Image (push) Has been skipped
🚀 Build & Deploy Image / Run Tests & Quality Checks (push) Has been skipped
🚀 Build & Deploy Image / Auto-deploy to Staging (push) Has been skipped
🚀 Build & Deploy Image / Auto-deploy to Production (push) Has been skipped
Security Vulnerability Scan / Check for Dependency Changes (push) Failing after 11m25s
Security Vulnerability Scan / Composer Security Audit (push) Has been cancelled
- Remove middleware reference from Gitea Traefik labels (caused routing issues) - Optimize Gitea connection pool settings (MAX_IDLE_CONNS=30, authentication_timeout=180s) - Add explicit service reference in Traefik labels - Fix intermittent 504 timeouts by improving PostgreSQL connection handling Fixes Gitea unreachability via git.michaelschiemer.de
247 lines
11 KiB
YAML
247 lines
11 KiB
YAML
---
|
||
# Find Ansible Automation Source
|
||
# Findet die Quelle der externen Ansible-Automatisierung, die Traefik regelmäßig neu startet
|
||
- name: Find Ansible Automation Source
|
||
hosts: production
|
||
gather_facts: yes
|
||
become: yes
|
||
|
||
tasks:
|
||
- name: Check for running Ansible processes
|
||
ansible.builtin.shell: |
|
||
ps aux | grep -E "ansible|ansible-playbook|ansible-pull" | grep -v grep || echo "No Ansible processes found"
|
||
register: ansible_processes
|
||
changed_when: false
|
||
|
||
- name: Check for ansible-pull processes
|
||
ansible.builtin.shell: |
|
||
ps aux | grep ansible-pull | grep -v grep || echo "No ansible-pull processes found"
|
||
register: ansible_pull_processes
|
||
changed_when: false
|
||
|
||
- name: Check systemd timers for ansible-pull
|
||
ansible.builtin.shell: |
|
||
systemctl list-timers --all --no-pager | grep -i ansible || echo "No ansible timers found"
|
||
register: ansible_timers
|
||
changed_when: false
|
||
|
||
- name: Check for ansible-pull cronjobs
|
||
ansible.builtin.shell: |
|
||
for user in $(cut -f1 -d: /etc/passwd); do
|
||
crontab -u "$user" -l 2>/dev/null | grep -q "ansible-pull\|ansible.*playbook" && echo "=== User: $user ===" && crontab -u "$user" -l 2>/dev/null | grep -E "ansible-pull|ansible.*playbook" || true
|
||
done || echo "No ansible-pull cronjobs found"
|
||
register: ansible_cronjobs
|
||
changed_when: false
|
||
|
||
- name: Check system-wide cron for ansible
|
||
ansible.builtin.shell: |
|
||
for dir in /etc/cron.d /etc/cron.daily /etc/cron.hourly /etc/cron.weekly /etc/cron.monthly; do
|
||
if [ -d "$dir" ]; then
|
||
grep -rE "ansible-pull|ansible.*playbook" "$dir" 2>/dev/null && echo "=== Found in $dir ===" || true
|
||
fi
|
||
done || echo "No ansible in system cron"
|
||
register: ansible_system_cron
|
||
changed_when: false
|
||
|
||
- name: Check journalctl for ansible-ansible processes
|
||
ansible.builtin.shell: |
|
||
journalctl --since "24 hours ago" --no-pager | grep -iE "ansible-ansible|ansible-playbook|ansible-pull" | tail -50 || echo "No ansible processes in journalctl"
|
||
register: ansible_journal
|
||
changed_when: false
|
||
|
||
- name: Check for ansible-pull configuration files
|
||
ansible.builtin.shell: |
|
||
find /home -name "*ansible-pull*" -o -name "*ansible*.yml" -path "*/ansible-pull/*" 2>/dev/null | head -20 || echo "No ansible-pull config files found"
|
||
register: ansible_pull_configs
|
||
changed_when: false
|
||
|
||
- name: Check for running docker compose commands related to Traefik
|
||
ansible.builtin.shell: |
|
||
ps aux | grep -E "docker.*compose.*traefik|docker.*restart.*traefik" | grep -v grep || echo "No docker compose traefik commands running"
|
||
register: docker_traefik_commands
|
||
changed_when: false
|
||
|
||
- name: Check Docker events for Traefik kill events (last hour)
|
||
ansible.builtin.shell: |
|
||
docker events --since 1h --until now --filter container=traefik --filter event=die --format "{{ '{{' }}.Time{{ '}}' }} {{ '{{' }}.Action{{ '}}' }} {{ '{{' }}.Actor.Attributes.signal{{ '}}' }}" 2>/dev/null | tail -20 || echo "No Traefik die events in last hour"
|
||
register: traefik_kill_events
|
||
changed_when: false
|
||
failed_when: false
|
||
|
||
- name: Check journalctl for docker compose traefik commands
|
||
ansible.builtin.shell: |
|
||
journalctl --since "24 hours ago" --no-pager | grep -iE "docker.*compose.*traefik|docker.*restart.*traefik" | tail -30 || echo "No docker compose traefik commands in journalctl"
|
||
register: docker_traefik_journal
|
||
changed_when: false
|
||
|
||
- name: Check for CI/CD scripts that might run Ansible
|
||
ansible.builtin.shell: |
|
||
find /home/deploy -type f \( -name "*.sh" -o -name "*.yml" -o -name "*.yaml" \) -exec grep -lE "ansible.*playbook.*traefik|docker.*compose.*traefik.*restart" {} \; 2>/dev/null | head -20 || echo "No CI/CD scripts found"
|
||
register: cicd_scripts
|
||
changed_when: false
|
||
|
||
- name: Check for Gitea Workflows that run Ansible
|
||
ansible.builtin.shell: |
|
||
find /home/deploy -type f -path "*/.gitea/workflows/*.yml" -o -path "*/.github/workflows/*.yml" 2>/dev/null | xargs grep -lE "ansible.*playbook.*traefik|docker.*compose.*traefik" 2>/dev/null | head -10 || echo "No Gitea workflows found"
|
||
register: gitea_workflows
|
||
changed_when: false
|
||
|
||
- name: Check for monitoring/healthcheck scripts
|
||
ansible.builtin.shell: |
|
||
find /home/deploy -type f -name "*monitor*" -o -name "*health*" 2>/dev/null | xargs grep -lE "traefik.*restart|docker.*compose.*traefik" 2>/dev/null | head -10 || echo "No monitoring scripts found"
|
||
register: monitoring_scripts
|
||
changed_when: false
|
||
|
||
- name: Summary
|
||
ansible.builtin.debug:
|
||
msg: |
|
||
================================================================================
|
||
ANSIBLE AUTOMATION SOURCE DIAGNOSE:
|
||
================================================================================
|
||
|
||
Laufende Ansible-Prozesse:
|
||
{{ ansible_processes.stdout }}
|
||
|
||
Ansible-Pull Prozesse:
|
||
{{ ansible_pull_processes.stdout }}
|
||
|
||
Systemd Timers für Ansible:
|
||
{{ ansible_timers.stdout }}
|
||
|
||
Cronjobs für Ansible:
|
||
{{ ansible_cronjobs.stdout }}
|
||
|
||
System-Cron für Ansible:
|
||
{{ ansible_system_cron.stdout }}
|
||
|
||
Ansible-Prozesse in Journalctl (letzte 24h):
|
||
{{ ansible_journal.stdout }}
|
||
|
||
Ansible-Pull Konfigurationsdateien:
|
||
{{ ansible_pull_configs.stdout }}
|
||
|
||
Laufende Docker Compose Traefik-Befehle:
|
||
{{ docker_traefik_commands.stdout }}
|
||
|
||
Traefik Kill-Events (letzte Stunde):
|
||
{{ traefik_kill_events.stdout }}
|
||
|
||
Docker Compose Traefik-Befehle in Journalctl:
|
||
{{ docker_traefik_journal.stdout }}
|
||
|
||
CI/CD Scripts die Traefik restarten:
|
||
{{ cicd_scripts.stdout }}
|
||
|
||
Gitea Workflows die Traefik restarten:
|
||
{{ gitea_workflows.stdout }}
|
||
|
||
Monitoring-Scripts die Traefik restarten:
|
||
{{ monitoring_scripts.stdout }}
|
||
|
||
================================================================================
|
||
ANALYSE:
|
||
================================================================================
|
||
|
||
{% if 'No Ansible processes found' not in ansible_processes.stdout %}
|
||
⚠️ AKTIVE ANSIBLE-PROZESSE GEFUNDEN:
|
||
{{ ansible_processes.stdout }}
|
||
|
||
→ Diese Prozesse könnten Traefik regelmäßig neu starten
|
||
→ Prüfe die Kommandozeile dieser Prozesse um das Playbook zu identifizieren
|
||
{% endif %}
|
||
|
||
{% if 'No ansible-pull processes found' not in ansible_pull_processes.stdout %}
|
||
❌ ANSIBLE-PULL LÄUFT:
|
||
{{ ansible_pull_processes.stdout }}
|
||
|
||
→ ansible-pull führt regelmäßig Playbooks aus
|
||
→ Dies ist wahrscheinlich die Quelle der Traefik-Restarts
|
||
{% endif %}
|
||
|
||
{% if 'No ansible timers found' not in ansible_timers.stdout %}
|
||
❌ ANSIBLE TIMER GEFUNDEN:
|
||
{{ ansible_timers.stdout }}
|
||
|
||
→ Ein Systemd-Timer führt regelmäßig Ansible aus
|
||
→ Deaktiviere mit: systemctl disable <timer-name>
|
||
{% endif %}
|
||
|
||
{% if 'No ansible-pull cronjobs found' not in ansible_cronjobs.stdout %}
|
||
❌ ANSIBLE CRONJOB GEFUNDEN:
|
||
{{ ansible_cronjobs.stdout }}
|
||
|
||
→ Ein Cronjob führt regelmäßig Ansible aus
|
||
→ Entferne oder kommentiere den Cronjob-Eintrag
|
||
{% endif %}
|
||
|
||
{% if cicd_scripts.stdout and 'No CI/CD scripts found' not in cicd_scripts.stdout %}
|
||
⚠️ CI/CD SCRIPTS GEFUNDEN:
|
||
{{ cicd_scripts.stdout }}
|
||
|
||
→ Diese Scripts könnten Traefik regelmäßig neu starten
|
||
→ Prüfe diese Dateien und entferne/kommentiere Traefik-Restart-Befehle
|
||
{% endif %}
|
||
|
||
{% if gitea_workflows.stdout and 'No Gitea workflows found' not in gitea_workflows.stdout %}
|
||
⚠️ GITEA WORKFLOWS GEFUNDEN:
|
||
{{ gitea_workflows.stdout }}
|
||
|
||
→ Diese Workflows könnten Traefik regelmäßig neu starten
|
||
→ Prüfe diese Workflows und entferne/kommentiere Traefik-Restart-Schritte
|
||
{% endif %}
|
||
|
||
{% if monitoring_scripts.stdout and 'No monitoring scripts found' not in monitoring_scripts.stdout %}
|
||
⚠️ MONITORING SCRIPTS GEFUNDEN:
|
||
{{ monitoring_scripts.stdout }}
|
||
|
||
→ Diese Scripts könnten Traefik regelmäßig neu starten
|
||
→ Prüfe diese Scripts und entferne/kommentiere Traefik-Restart-Befehle
|
||
{% endif %}
|
||
|
||
================================================================================
|
||
LÖSUNG:
|
||
================================================================================
|
||
|
||
{% if 'No Ansible processes found' in ansible_processes.stdout and 'No ansible-pull processes found' in ansible_pull_processes.stdout and 'No ansible timers found' in ansible_timers.stdout and 'No ansible-pull cronjobs found' in ansible_cronjobs.stdout %}
|
||
ℹ️ Keine aktiven Ansible-Automatisierungen gefunden
|
||
|
||
Mögliche Ursachen:
|
||
1. Ansible-Prozesse laufen nur zeitweise (intermittierend)
|
||
2. Externe CI/CD-Pipeline führt Ansible aus
|
||
3. Manuelle Ansible-Aufrufe von außen
|
||
|
||
Nächste Schritte:
|
||
1. Beobachte Docker Events in Echtzeit: docker events --filter container=traefik
|
||
2. Beobachte Ansible-Prozesse: watch -n 1 'ps aux | grep ansible'
|
||
3. Prüfe ob externe CI/CD-Pipelines Ansible ausführen
|
||
{% else %}
|
||
|
||
SOFORTMASSNAHME:
|
||
|
||
{% if 'No ansible-pull processes found' not in ansible_pull_processes.stdout %}
|
||
1. ❌ Stoppe ansible-pull:
|
||
pkill -f ansible-pull
|
||
{% endif %}
|
||
|
||
{% if 'No ansible timers found' not in ansible_timers.stdout %}
|
||
2. ❌ Deaktiviere Ansible-Timer:
|
||
systemctl stop <timer-name>
|
||
systemctl disable <timer-name>
|
||
{% endif %}
|
||
|
||
{% if 'No ansible-pull cronjobs found' not in ansible_cronjobs.stdout %}
|
||
3. ❌ Entferne Ansible-Cronjobs:
|
||
crontab -u <user> -e
|
||
(Kommentiere oder entferne die Ansible-Zeilen)
|
||
{% endif %}
|
||
|
||
LANGZEITLÖSUNG:
|
||
|
||
1. Prüfe gefundene Scripts/Workflows und entferne Traefik-Restart-Befehle
|
||
2. Falls Healthchecks nötig sind, setze größere Intervalle (z.B. 5 Minuten statt 30 Sekunden)
|
||
3. Restarte Traefik nur bei echten Fehlern, nicht präventiv
|
||
{% endif %}
|
||
|
||
================================================================================
|
||
|