fix(monitoring): Prometheus читает новый конфиг, а не старый inode
ansible-core-mon / deploy (push) Successful in 13s
ansible-core-mon / deploy (push) Successful in 13s
Файл в bind-mount не обновлялся после записи Ansible, поэтому ger-nod-02 не попадал в цели. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
1 parent
408dfd09c3
commit
a54a25ebb7
3 files changed
+11
-33
No files matched your search
@@ -1,26 +0,0 @@
|
|||||||
---
|
|
||||||
- name: Reload Prometheus configuration
|
|
||||||
ansible.builtin.uri:
|
|
||||||
url: http://127.0.0.1:9090/-/reload
|
|
||||||
method: POST
|
|
||||||
status_code: 200
|
|
||||||
register: prometheus_reload
|
|
||||||
until: prometheus_reload.status == 200
|
|
||||||
retries: 10
|
|
||||||
delay: 3
|
|
||||||
when: prometheus_config_reload | default(true) | bool
|
|
||||||
ignore_errors: true
|
|
||||||
|
|
||||||
- name: Restart Prometheus after failed reload
|
|
||||||
ansible.builtin.command: docker compose -f {{ monitoring_dir }}/compose.yaml restart prometheus
|
|
||||||
args:
|
|
||||||
chdir: "{{ monitoring_dir }}"
|
|
||||||
when:
|
|
||||||
- prometheus_config_reload | default(true) | bool
|
|
||||||
- prometheus_reload is defined
|
|
||||||
- prometheus_reload is failed or (prometheus_reload.status | default(0) != 200)
|
|
||||||
|
|
||||||
- name: Restart Grafana
|
|
||||||
ansible.builtin.command: docker compose -f {{ monitoring_dir }}/compose.yaml restart grafana
|
|
||||||
args:
|
|
||||||
chdir: "{{ monitoring_dir }}"
|
|
||||||
@@ -55,7 +55,7 @@
|
|||||||
owner: root
|
owner: root
|
||||||
group: root
|
group: root
|
||||||
mode: "0644"
|
mode: "0644"
|
||||||
notify: Reload Prometheus configuration
|
register: prometheus_config
|
||||||
|
|
||||||
- name: Установить правила алертов Prometheus
|
- name: Установить правила алертов Prometheus
|
||||||
ansible.builtin.copy:
|
ansible.builtin.copy:
|
||||||
@@ -64,7 +64,7 @@
|
|||||||
owner: root
|
owner: root
|
||||||
group: root
|
group: root
|
||||||
mode: "0644"
|
mode: "0644"
|
||||||
notify: Reload Prometheus configuration
|
register: prometheus_alerts
|
||||||
|
|
||||||
- name: Установить конфигурацию Alertmanager
|
- name: Установить конфигурацию Alertmanager
|
||||||
ansible.builtin.template:
|
ansible.builtin.template:
|
||||||
@@ -105,7 +105,6 @@
|
|||||||
owner: root
|
owner: root
|
||||||
group: root
|
group: root
|
||||||
mode: "0644"
|
mode: "0644"
|
||||||
notify: Restart Grafana
|
|
||||||
|
|
||||||
- name: Установить compose.yaml для стека мониторинга
|
- name: Установить compose.yaml для стека мониторинга
|
||||||
ansible.builtin.template:
|
ansible.builtin.template:
|
||||||
@@ -114,12 +113,18 @@
|
|||||||
owner: root
|
owner: root
|
||||||
group: root
|
group: root
|
||||||
mode: "0644"
|
mode: "0644"
|
||||||
|
register: monitoring_compose
|
||||||
|
|
||||||
- name: Запустить стек мониторинга через Docker Compose
|
- name: Запустить стек мониторинга через Docker Compose
|
||||||
ansible.builtin.command: docker compose -f {{ monitoring_dir }}/compose.yaml up -d --remove-orphans
|
ansible.builtin.command: docker compose -f {{ monitoring_dir }}/compose.yaml up -d --remove-orphans
|
||||||
register: compose_up
|
register: compose_up
|
||||||
changed_when: "'Started' in compose_up.stderr or 'Created' in compose_up.stderr or 'Recreated' in compose_up.stderr or 'Pulled' in compose_up.stderr"
|
changed_when: "'Started' in compose_up.stderr or 'Created' in compose_up.stderr or 'Recreated' in compose_up.stderr or 'Pulled' in compose_up.stderr"
|
||||||
|
|
||||||
|
- name: Пересоздать Prometheus, чтобы подхватить конфиг
|
||||||
|
ansible.builtin.command: docker compose -f {{ monitoring_dir }}/compose.yaml up -d --force-recreate --no-deps prometheus
|
||||||
|
when: prometheus_config is changed or prometheus_alerts is changed or monitoring_compose is changed
|
||||||
|
changed_when: true
|
||||||
|
|
||||||
- name: Дождаться готовности Ntfy
|
- name: Дождаться готовности Ntfy
|
||||||
ansible.builtin.uri:
|
ansible.builtin.uri:
|
||||||
url: "http://127.0.0.1:80/v1/health"
|
url: "http://127.0.0.1:80/v1/health"
|
||||||
|
|||||||
@@ -11,8 +11,7 @@ services:
|
|||||||
- "--storage.tsdb.retention.time={{ prometheus_retention }}"
|
- "--storage.tsdb.retention.time={{ prometheus_retention }}"
|
||||||
- "--web.enable-lifecycle"
|
- "--web.enable-lifecycle"
|
||||||
volumes:
|
volumes:
|
||||||
- ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
- ./prometheus:/etc/prometheus:ro
|
||||||
- ./prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro
|
|
||||||
- ./prometheus_data:/prometheus
|
- ./prometheus_data:/prometheus
|
||||||
ports:
|
ports:
|
||||||
- "9090:9090"
|
- "9090:9090"
|
||||||
@@ -27,7 +26,7 @@ services:
|
|||||||
- "--config.file=/etc/alertmanager/alertmanager.yml"
|
- "--config.file=/etc/alertmanager/alertmanager.yml"
|
||||||
- "--storage.path=/alertmanager"
|
- "--storage.path=/alertmanager"
|
||||||
volumes:
|
volumes:
|
||||||
- ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
|
- ./alertmanager:/etc/alertmanager:ro
|
||||||
- ./alertmanager_data:/alertmanager
|
- ./alertmanager_data:/alertmanager
|
||||||
ports:
|
ports:
|
||||||
- "9093:9093"
|
- "9093:9093"
|
||||||
@@ -58,7 +57,7 @@ services:
|
|||||||
command:
|
command:
|
||||||
- "--configs=/etc/alertmanager-ntfy/config.yml"
|
- "--configs=/etc/alertmanager-ntfy/config.yml"
|
||||||
volumes:
|
volumes:
|
||||||
- ./alertmanager-ntfy/config.yml:/etc/alertmanager-ntfy/config.yml:ro
|
- ./alertmanager-ntfy:/etc/alertmanager-ntfy:ro
|
||||||
depends_on:
|
depends_on:
|
||||||
- ntfy
|
- ntfy
|
||||||
|
|
||||||
|
|||||||
Reference in new issue
Block a user