diff options
Diffstat (limited to 'roles/monitoring/prometheus')
-rw-r--r-- | roles/monitoring/prometheus/server/defaults/main/rules_node.yml | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml index 6d4f763f..8a02e67b 100644 --- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml +++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml @@ -209,6 +209,15 @@ prometheus_server_rules_node: summary: Host conntrack limit (instance {{ '{{' }} $labels.instance {{ '}}' }}) description: "The number of conntrack is approching limit\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" + - alert: HostNetworkBondDegraded + expr: (node_bonding_active - node_bonding_slaves) != 0 + for: 1m + labels: + severity: warning + annotations: + title: Bond is degraded on (instance {{ '{{' }} $labels.instance {{ '}}' }}) + description: "Bond \"{{ '{{' }} $labels.master {{ '}}' }}\" on \"{{ '{{' }} $labels.instance {{ '}}' }}\" is degraded\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" + - alert: HostClockSkew expr: (node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0) for: 2m |