Diferències

Ací es mostren les diferències entre la revisió seleccionada i la versió actual de la pàgina.

Enllaç a la visualització de la comparació

--- info:cursos:pue:devops:sesion7 [09/03/2019 00:24] – mate
+++ info:cursos:pue:devops:sesion7 [04/06/2019 08:36] (actual) – [prometheus] mate
@@ Línia 289: / Línia 289: @@
 </code>
+<code yaml; swarm_node.rules.yaml>
+groups:
+- name: /1/store/projects/vagrant/docker-swarm-vagrant/apps/swarmprom/prometheus/rules/swarm_node.rules.yml
+  rules:
+  - alert: node_cpu_usage
+    expr: 100 - (avg(irate(node_cpu_seconds_total{mode="idle"}[1m]) * ON(instance) GROUP_LEFT(node_name)
+      node_meta * 100) BY (node_name)) > 50
+    for: 1m
+    labels:
+      severity: warning
+    annotations:
+      description: Swarm node {{ $labels.node_name }} CPU usage is at {{ humanize
+        $value}}%.
+      summary: CPU alert for Swarm node '{{ $labels.node_name }}'
+  - alert: node_memory_usage
+    expr: sum(((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes)
+      * ON(instance) GROUP_LEFT(node_name) node_meta * 100) BY (node_name) > 80
+    for: 1m
+    labels:
+      severity: warning
+    annotations:
+      description: Swarm node {{ $labels.node_name }} memory usage is at {{ humanize
+        $value}}%.
+      summary: Memory alert for Swarm node '{{ $labels.node_name }}'
+  - alert: node_disk_usage
+    expr: ((node_filesystem_size_bytes{mountpoint="/rootfs"} - node_filesystem_free_bytes{mountpoint="/rootfs"})
+      * 100 / node_filesystem_size_bytes{mountpoint="/rootfs"}) * ON(instance) GROUP_LEFT(node_name)
+      node_meta > 85
+    for: 1m
+    labels:
+      severity: warning
+    annotations:
+      description: Swarm node {{ $labels.node_name }} disk usage is at {{ humanize
+        $value}}%.
+      summary: Disk alert for Swarm node '{{ $labels.node_name }}'
+  - alert: node_disk_fill_rate_6h
+    expr: predict_linear(node_filesystem_free_bytes{mountpoint="/rootfs"}[1h], 6 * 3600) * ON(instance)
+      GROUP_LEFT(node_name) node_meta < 0
+    for: 1h
+    labels:
+      severity: critical
+    annotations:
+      description: Swarm node {{ $labels.node_name }} disk is going to fill up in
+h.
+      summary: Disk fill alert for Swarm node '{{ $labels.node_name }}'
+</code>
+<code yaml; swarm_tasks.rules.yaml>
+groups:
+- name: /1/store/projects/vagrant/docker-swarm-vagrant/apps/swarmprom/prometheus/rules/swarm_task.rules.yml
+  rules:
+  - alert: task_high_cpu_usage_50
+    expr: sum(rate(container_cpu_usage_seconds_total{container_label_com_docker_swarm_task_name=~".+"}[1m]))
+      BY (container_label_com_docker_swarm_task_name, container_label_com_docker_swarm_node_id)
+      * 100 > 50
+    for: 1m
+    annotations:
+      description: '{{ $labels.container_label_com_docker_swarm_task_name }} on ''{{
+        $labels.container_label_com_docker_swarm_node_id }}'' CPU usage is at {{ humanize
+        $value}}%.'
+      summary: CPU alert for Swarm task '{{ $labels.container_label_com_docker_swarm_task_name
+        }}' on '{{ $labels.container_label_com_docker_swarm_node_id }}'
+  - alert: task_high_memory_usage_1g
+    expr: sum(container_memory_rss{container_label_com_docker_swarm_task_name=~".+"})
+      BY (container_label_com_docker_swarm_task_name, container_label_com_docker_swarm_node_id) > 1e+09
+    for: 1m
+    annotations:
+      description: '{{ $labels.container_label_com_docker_swarm_task_name }} on ''{{
+        $labels.container_label_com_docker_swarm_node_id }}'' memory usage is {{ humanize
+        $value}}.'
+      summary: Memory alert for Swarm task '{{ $labels.container_label_com_docker_swarm_task_name
+        }}' on '{{ $labels.container_label_com_docker_swarm_node_id }}'
+</code>
 == otros
   * [[http://fediafedia.com/neo/scp/]]