Loading deploy/rules/swarm_node.rules.prod.yml +22 −1 Original line number Diff line number Diff line Loading @@ -42,3 +42,24 @@ groups: description: Swarm node {{ $labels.node_name }} disk is going to fill up in 6h. summary: Disk fill alert for Swarm node '{{ $labels.node_name }}' - alert: node_ebs_disk_usage expr: ((node_filesystem_size_bytes{mountpoint=~".*/ebs/.*"} - node_filesystem_free_bytes{mountpoint=~".*/ebs/.*"}) * 100 / node_filesystem_size_bytes{mountpoint=~".*/ebs/.*"}) * ON(instance) GROUP_LEFT(node_name) node_meta > 85 for: 1m labels: severity: warning annotations: description: Swarm node {{ $labels.node_name }} EBS disk {{ $labels.mountpoint }} usage is at {{ humanize $value}}%. summary: EBS disk alert for Swarm node '{{ $labels.node_name }}' - alert: node_ebs_disk_fill_rate_6h expr: predict_linear(node_filesystem_free_bytes{mountpoint=~".*/ebs/.*"}[1h], 6 * 3600) * ON(instance) GROUP_LEFT(node_name) node_meta < 0 for: 1h labels: severity: critical annotations: description: Swarm node {{ $labels.node_name }} EBS disk {{ $labels.mountpoint }} is going to fill up in 6h. summary: EBS disk fill alert for Swarm node '{{ $labels.node_name }}' Loading
deploy/rules/swarm_node.rules.prod.yml +22 −1 Original line number Diff line number Diff line Loading @@ -42,3 +42,24 @@ groups: description: Swarm node {{ $labels.node_name }} disk is going to fill up in 6h. summary: Disk fill alert for Swarm node '{{ $labels.node_name }}' - alert: node_ebs_disk_usage expr: ((node_filesystem_size_bytes{mountpoint=~".*/ebs/.*"} - node_filesystem_free_bytes{mountpoint=~".*/ebs/.*"}) * 100 / node_filesystem_size_bytes{mountpoint=~".*/ebs/.*"}) * ON(instance) GROUP_LEFT(node_name) node_meta > 85 for: 1m labels: severity: warning annotations: description: Swarm node {{ $labels.node_name }} EBS disk {{ $labels.mountpoint }} usage is at {{ humanize $value}}%. summary: EBS disk alert for Swarm node '{{ $labels.node_name }}' - alert: node_ebs_disk_fill_rate_6h expr: predict_linear(node_filesystem_free_bytes{mountpoint=~".*/ebs/.*"}[1h], 6 * 3600) * ON(instance) GROUP_LEFT(node_name) node_meta < 0 for: 1h labels: severity: critical annotations: description: Swarm node {{ $labels.node_name }} EBS disk {{ $labels.mountpoint }} is going to fill up in 6h. summary: EBS disk fill alert for Swarm node '{{ $labels.node_name }}'