CCCHH/ansible-infra
CCCHH/ansible-infra
18
0
Fork 0
Code Issues 5 Pull requests Wiki Activity

Reduce Host Memory is underutilized to 10%

Browse source
This commit is contained in:
christian 2024-10-18 21:15:20 +02:00
parent b660d937dc
commit 34dc6d9a84
Signed by: c6ristian
SSH key fingerprint: SHA256:B3m+yzpaxGXSEcDBpPHfvza/DNC0wuX+CKMeGq8wgak
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
playbooks/files/chaosknoten/configs/grafana/docker_compose/prometheus_alerts.rules.yaml
View file

@ -21,13 +21,13 @@ groups:
description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}" description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}"
# You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly # You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
- alert: HostMemoryIsUnderutilized - alert: HostMemoryIsUnderutilized
expr: (100 - (avg_over_time(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"} expr: (100 - (avg_over_time(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 1w for: 1w
labels: labels:
severity: info severity: info
annotations: annotations:
summary: Host Memory is underutilized (instance {{ $labels.instance }}) summary: Host Memory is underutilized (instance {{ $labels.instance }})
description: "Node memory is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})\n VALUE = {{ $value }}" description: "Node memory is < 10% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})\n VALUE = {{ $value }}"
- alert: HostUnusualNetworkThroughputIn - alert: HostUnusualNetworkThroughputIn
expr: (sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"} expr: (sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 5m for: 5m