From a54a25ebb7efb94e958952f372fa0ef7f9faa15e Mon Sep 17 00:00:00 2001 From: karpenok Date: Thu, 12 Nov 2026 13:00:15 +0700 Subject: [PATCH] =?UTF-8?q?fix(monitoring):=20Prometheus=20=D1=87=D0=B8?= =?UTF-8?q?=D1=82=D0=B0=D0=B5=D1=82=20=D0=BD=D0=BE=D0=B2=D1=8B=D0=B9=20?= =?UTF-8?q?=D0=BA=D0=BE=D0=BD=D1=84=D0=B8=D0=B3,=20=D0=B0=20=D0=BD=D0=B5?= =?UTF-8?q?=20=D1=81=D1=82=D0=B0=D1=80=D1=8B=D0=B9=20inode?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Файл в bind-mount не обновлялся после записи Ansible, поэтому ger-nod-02 не попадал в цели. Co-authored-by: Cursor --- .../core-mon/monitoring/handlers/main.yml | 26 ------------------- .../roles/core-mon/monitoring/tasks/main.yml | 11 +++++--- .../monitoring/templates/compose.yaml.j2 | 7 +++-- 3 files changed, 11 insertions(+), 33 deletions(-) delete mode 100644 ansible/roles/core-mon/monitoring/handlers/main.yml diff --git a/ansible/roles/core-mon/monitoring/handlers/main.yml b/ansible/roles/core-mon/monitoring/handlers/main.yml deleted file mode 100644 index e70227d..0000000 --- a/ansible/roles/core-mon/monitoring/handlers/main.yml +++ /dev/null @@ -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 }}" diff --git a/ansible/roles/core-mon/monitoring/tasks/main.yml b/ansible/roles/core-mon/monitoring/tasks/main.yml index cd19b6d..eab771f 100644 --- a/ansible/roles/core-mon/monitoring/tasks/main.yml +++ b/ansible/roles/core-mon/monitoring/tasks/main.yml @@ -55,7 +55,7 @@ owner: root group: root mode: "0644" - notify: Reload Prometheus configuration + register: prometheus_config - name: Установить правила алертов Prometheus ansible.builtin.copy: @@ -64,7 +64,7 @@ owner: root group: root mode: "0644" - notify: Reload Prometheus configuration + register: prometheus_alerts - name: Установить конфигурацию Alertmanager ansible.builtin.template: @@ -105,7 +105,6 @@ owner: root group: root mode: "0644" - notify: Restart Grafana - name: Установить compose.yaml для стека мониторинга ansible.builtin.template: @@ -114,12 +113,18 @@ owner: root group: root mode: "0644" + register: monitoring_compose - name: Запустить стек мониторинга через Docker Compose ansible.builtin.command: docker compose -f {{ monitoring_dir }}/compose.yaml up -d --remove-orphans 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" +- 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 ansible.builtin.uri: url: "http://127.0.0.1:80/v1/health" diff --git a/ansible/roles/core-mon/monitoring/templates/compose.yaml.j2 b/ansible/roles/core-mon/monitoring/templates/compose.yaml.j2 index a1559ad..c64af36 100644 --- a/ansible/roles/core-mon/monitoring/templates/compose.yaml.j2 +++ b/ansible/roles/core-mon/monitoring/templates/compose.yaml.j2 @@ -11,8 +11,7 @@ services: - "--storage.tsdb.retention.time={{ prometheus_retention }}" - "--web.enable-lifecycle" volumes: - - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro - - ./prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro + - ./prometheus:/etc/prometheus:ro - ./prometheus_data:/prometheus ports: - "9090:9090" @@ -27,7 +26,7 @@ services: - "--config.file=/etc/alertmanager/alertmanager.yml" - "--storage.path=/alertmanager" volumes: - - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro + - ./alertmanager:/etc/alertmanager:ro - ./alertmanager_data:/alertmanager ports: - "9093:9093" @@ -58,7 +57,7 @@ services: command: - "--configs=/etc/alertmanager-ntfy/config.yml" volumes: - - ./alertmanager-ntfy/config.yml:/etc/alertmanager-ntfy/config.yml:ro + - ./alertmanager-ntfy:/etc/alertmanager-ntfy:ro depends_on: - ntfy