deep_scrub_choked

2026-04-06 07:08:17 +03:00
commit 9149dc1d7f
840 changed files with 52471 additions and 0 deletions
@@ -0,0 +1,58 @@
+# This file is managed by ansible, don't make changes here - they will be
+# overwritten.
+[Unit]
+Description=alertmanager
+{% if container_binary == 'docker' %}
+After=docker.service network-online.target local-fs.target time-sync.target
+Requires=docker.service
+{% else %}
+After=network-online.target local-fs.target time-sync.target
+{% endif %}
+Wants=network-online.target local-fs.target time-sync.target
+
+[Service]
+WorkingDirectory={{ alertmanager_data_dir }}
+EnvironmentFile=-/etc/environment
+{% if container_binary == 'podman' %}
+ExecStartPre=-/usr/bin/rm -f /%t/%n-pid /%t/%n-cid
+ExecStartPre=-/usr/bin/{{ container_binary }} rm --storage alertmanager
+{% endif %}
+ExecStartPre=-/usr/bin/{{ container_binary }} rm -f alertmanager
+ExecStart=/usr/bin/{{ container_binary }} run --rm --name=alertmanager \
+{% if container_binary == 'podman' %}
+  -d --log-driver journald --conmon-pidfile /%t/%n-pid --cidfile /%t/%n-cid \
+{% endif %}
+  --pids-limit={{ 0 if container_binary == 'podman' else -1 }} \
+  -v "{{ alertmanager_conf_dir }}:/etc/alertmanager:Z" \
+  -v "{{ alertmanager_data_dir }}:/alertmanager:Z" \
+  --net=host \
+  --cpu-period={{ alertmanager_container_cpu_period }} \
+  --cpu-quota={{ alertmanager_container_cpu_period * alertmanager_container_cpu_cores }} \
+  --memory={{ alertmanager_container_memory }}GB \
+  --memory-swap={{ alertmanager_container_memory * 2 }}GB \
+  {{ alertmanager_container_image }} \
+  --config.file=/etc/alertmanager/alertmanager.yml \
+  --cluster.listen-address={{ grafana_server_addr }}:{{ alertmanager_cluster_port }} \
+{% for peer in grafana_server_addrs|difference(grafana_server_addr) %}
+  --cluster.peer={{ peer }}:{{ alertmanager_cluster_port }} \
+{% endfor %}
+  --storage.path=/alertmanager \
+  --web.external-url=http://{{ ansible_facts['fqdn'] }}:{{ alertmanager_port }}/ \
+  --web.listen-address={{ grafana_server_addr }}:{{ alertmanager_port }}
+{% if container_binary == 'podman' %}
+ExecStop=/usr/bin/sh -c "/usr/bin/{{ container_binary }} rm -f `cat /%t/%n-cid`"
+{% else %}
+ExecStop=/usr/bin/{{ container_binary }} stop alertmanager
+{% endif %}
+KillMode=none
+Restart=always
+RestartSec=10s
+TimeoutStartSec=120
+TimeoutStopSec=15
+{% if container_binary == 'podman' %}
+Type=forking
+PIDFile=/%t/%n-pid
+{% endif %}
+
+[Install]
+WantedBy=multi-user.target
@@ -0,0 +1,20 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  group_by: ['alertname']
+  group_wait: 10s
+  group_interval: 10s
+  repeat_interval: 1h
+  receiver: 'ceph-dashboard'
+receivers:
+- name: 'ceph-dashboard'
+  webhook_configs:
+{% for host in groups['mgrs'] | default(groups['mons']) %}
+  - url: '{{ dashboard_protocol }}://{{ hostvars[host]['ansible_facts']['fqdn'] }}:{{ dashboard_port }}/api/prometheus_receiver'
+{% if dashboard_protocol == 'https' and alertmanager_dashboard_api_no_ssl_verify | bool %}
+    http_config:
+      tls_config:
+        insecure_skip_verify: true
+{% endif %}
+{% endfor %}
@@ -0,0 +1,57 @@
+# This file is managed by ansible, don't make changes here - they will be
+# overwritten.
+[Unit]
+Description=prometheus
+{% if container_binary == 'docker' %}
+After=docker.service network-online.target local-fs.target time-sync.target
+Requires=docker.service
+{% else %}
+After=network-online.target local-fs.target time-sync.target
+{% endif %}
+Wants=network-online.target local-fs.target time-sync.target
+
+[Service]
+EnvironmentFile=-/etc/environment
+{% if container_binary == 'podman' %}
+ExecStartPre=-/usr/bin/rm -f /%t/%n-pid /%t/%n-cid
+ExecStartPre=-/usr/bin/{{ container_binary }} rm --storage prometheus
+{% endif %}
+ExecStartPre=-/usr/bin/{{ container_binary }} rm -f prometheus
+ExecStart=/usr/bin/{{ container_binary }} run --rm --name=prometheus \
+{% if container_binary == 'podman' %}
+  -d --log-driver journald --conmon-pidfile /%t/%n-pid --cidfile /%t/%n-cid \
+{% endif %}
+  --pids-limit={{ 0 if container_binary == 'podman' else -1 }} \
+  -v "{{ prometheus_conf_dir }}:/etc/prometheus:Z" \
+  -v "{{ prometheus_data_dir }}:/prometheus:Z" \
+  --net=host \
+  --user={{ prometheus_user_id }} \
+  --cpu-period={{ prometheus_container_cpu_period }} \
+  --cpu-quota={{ prometheus_container_cpu_period * prometheus_container_cpu_cores }} \
+  --memory={{ prometheus_container_memory }}GB \
+  --memory-swap={{ prometheus_container_memory * 2 }}GB \
+  {{ prometheus_container_image }} \
+  --config.file=/etc/prometheus/prometheus.yml \
+  --storage.tsdb.path=/prometheus \
+{% if prometheus_storage_tsdb_retention_time is defined %}
+  --storage.tsdb.retention.time={{ prometheus_storage_tsdb_retention_time }} \
+{% endif %}
+  --web.external-url=http://{{ ansible_facts['fqdn'] }}:{{ prometheus_port }}/ \
+  --web.listen-address={{ grafana_server_addr }}:{{ prometheus_port }}
+{% if container_binary == 'podman' %}
+ExecStop=/usr/bin/sh -c "/usr/bin/{{ container_binary }} rm -f `cat /%t/%n-cid`"
+{% else %}
+ExecStop=/usr/bin/{{ container_binary }} stop prometheus
+{% endif %}
+KillMode=none
+Restart=always
+RestartSec=10s
+TimeoutStartSec=120
+TimeoutStopSec=15
+{% if container_binary == 'podman' %}
+Type=forking
+PIDFile=/%t/%n-pid
+{% endif %}
+
+[Install]
+WantedBy=multi-user.target
@@ -0,0 +1,38 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+rule_files:
+  - '/etc/prometheus/alerting/*'
+
+scrape_configs:
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['{{ grafana_server_addr }}:{{ prometheus_port }}']
+  - job_name: 'ceph'
+    honor_labels: true
+    static_configs:
+{% for host in groups[mgr_group_name] | default(groups[mon_group_name]) %}
+      - targets: ['{{ host }}:9283']
+        labels:
+          instance: 'ceph_cluster'
+{% endfor %}
+  - job_name: 'node'
+    static_configs:
+{% for host in (groups['all'] | difference(groups[monitoring_group_name] | union(groups.get(client_group_name, []))) | union(groups.get(osd_group_name, []))) %}
+      - targets: ['{{ host }}:{{ node_exporter_port }}']
+        labels:
+          instance: "{{ hostvars[host]['ansible_facts']['nodename'] }}"
+{% endfor %}
+  - job_name: 'grafana'
+    static_configs:
+{% for host in groups[monitoring_group_name] %}
+      - targets: ['{{ host }}:{{ node_exporter_port }}']
+        labels:
+          instance: "{{ hostvars[host]['ansible_facts']['nodename'] }}"
+{% endfor %}
+alerting:
+  alertmanagers:
+  - scheme: http
+    static_configs:
+    - targets: ['{{ grafana_server_addr }}:{{ alertmanager_port }}']