DEV-578 investigation for hetzner api rate limits

roles/prometheus/tasks/main.yml

@@ -3,6 +3,8 @@
 ### tags:
 ###   update_config
 ###   update_deployment
+###   update-digitalocean-metrics
+###   update-hetzner-metrics
 
 - name: "Create/Resize LVM for datadir"
   include_role:
@@ -133,39 +135,70 @@
      }
   when: grafana_stats.json.users == 1
 
-- name: "Create DO-metrics script from template" 
+- name: "Create digitalocean api metric script from template"
   template:
-    src: do_too_many_req_metrics.sh.j2
+    src: digitalocean_api.sh.j2
-    dest: /root/do_too_many_req_metrics.sh
+    dest: /root/digitalocean_api.sh
     mode: 0700
     owner: root
-    group: root 
+    group: root
   tags:
-    - update-do-metrics
+    - update-digitalocean-metrics
 
-- name: "Create cronjob to exec DO-metrics script"
+- name: "Create cronjob to exec digitalocean api metric script"
   ansible.builtin.cron:
     name: "update replication table"
     minute: "*"
-    job: /root/do_too_many_req_metrics.sh 
+    job: /root/digitalocean_api.sh
   tags:
-    - update-do-metrics
+    - update-digitalocean-metrics
 
-- name: "Create hetzner-metrics script from template" 
+- name: "Create cronjob to exec digitalocean api metric script"
+  ansible.builtin.cron:
+    name: "update digitalocean metrics"
+    minute: "*"
+    job: /root/digitalocean_api.sh
+  tags:
+    - update-digitalocean-metrics
+
+- name: "Create hetzner api metric script from template"
   template:
-    src: hetzner_unattached_volumes.py.j2
+    src: hetzner_api.py.j2
-    dest: /root/hetzner_unattached_volumes.py
+    dest: /root/hetzner_api.py
     mode: 0700
     owner: root
-    group: root 
+    group: root
   tags:
     - update-hetzner-metrics
 
-- name: "Create cronjob to exec hetzner-metrics script"
+- name: "Create cronjob to exec hetzner api metric script"
   ansible.builtin.cron:
     name: "update hetzner metrics"
-    minute: "*/5"
+    minute: "*"
-    job: /root/hetzner_unattached_volumes.py
+    job: /root/hetzner_api.py
   tags:
     - update-hetzner-metrics
 
+# remove after 31.12.2022
+- name: "Remove old cronjob to exec digitalocean api metric script"
+  ansible.builtin.cron:
+    name: "update replication table"
+    state: "absent"
+  tags:
+    - update-digitalocean-metrics
+
+# remove after 31.12.2022
+- name: "Remove old digitalocean api metric script"
+  ansible.builtin.file:
+    path: /root/do_too_many_req_metrics.sh
+    state: absent
+  tags:
+    - update-digitalocean-metrics
+
+# remove after 31.12.2022
+- name: "Remove old hetzner api metric script"
+  ansible.builtin.file:
+    path: /root/hetzner_unattached_volumes.py
+    state: absent
+  tags:
+    - update-hetzner-metrics

templates/prometheus/config/prometheus/alert.rules.j2

@@ -367,7 +367,7 @@ groups:
     annotations:
       summary: "awx job failed with status failed"
       description: "Alert awx jobs failed"
-      
+
   - alert: postgres backup zombies
     expr: 100 - ((node_filesystem_avail_bytes{instance=~"{{ stage }}-postgres-01.smardigo.digital",job=~"node-exporter",device='/dev/mapper/vg.postgres_backup-lv.postgres_backup'} * 100) / node_filesystem_size_bytes{instance=~"{{ stage }}-postgres-01.smardigo.digital",job=~"node-exporter",device='/dev/mapper/vg.postgres_backup-lv.postgres_backup'}) > 10
     for: 2h
@@ -378,17 +378,6 @@ groups:
       summary: "postgres backup zombies, have not been deleted"
       description: "postgres backup zombies, have not been deleted"
 
-  - alert: hetzner unattached volumes
-    expr: hetzner_api_unattached_volumes > 0 or absent(hetzner_api_unattached_volumes)
-    for: 2h
-    labels:
-      severity: critical
-    annotations:
-      identifier: '{{ '{{' }} $labels.instance {{ '}}' }}'
-      summary: "unattached volumes in hetzner"
-      description: "unattached volumes in hetzner"
-
-
   - alert: hetzner ratelimit_remaining low
     expr: (hetzner_api_ratelimit_remaining * 100)/ hetzner_api_ratelimit_limit < 50 or absent(hetzner_api_ratelimit_remaining)
     for: 10m
@@ -399,6 +388,16 @@ groups:
       summary: "hetzner ratelimit_remaining below 50%"
       description: "hetzner ratelimit_remaining below 50%"
 
+  - alert: hetzner unattached volumes
+    expr: hetzner_api_unattached_volumes > 0 or absent(hetzner_api_unattached_volumes)
+    for: 2h
+    labels:
+      severity: critical
+    annotations:
+      identifier: '{{ '{{' }} $labels.instance {{ '}}' }}'
+      summary: "unattached volumes in hetzner"
+      description: "unattached volumes in hetzner"
+
   - alert: hetzner locked server exists
     expr: hetzner_api_locked_servers > 0 or absent(hetzner_api_locked_servers)
     for: 1h
@@ -408,5 +407,3 @@ groups:
       identifier: '{{ '{{' }} $labels.instance {{ '}}' }}'
       summary: "hetzner locked server exists"
       description: "hetzner locked server exists"
-
-