Compare commits

...

2 Commits

Author SHA1 Message Date
vfebvre a3472eaea5 ajout de règles supplémentaires pour les alertes 2021-10-21 16:09:53 +02:00
vfebvre 4ef331f6a1 ajout surveillance /var 2021-10-21 11:00:11 +02:00
3 changed files with 46 additions and 0 deletions

View File

@ -5,6 +5,7 @@
<file filelist='prometheus' name='/etc/prometheus/prometheus.yml' mkdir='True' rm='True'/> <file filelist='prometheus' name='/etc/prometheus/prometheus.yml' mkdir='True' rm='True'/>
<file filelist='prometheus-alertmanager' name='/etc/prometheus/alertmanager.yml' mkdir='True' rm='True'/> <file filelist='prometheus-alertmanager' name='/etc/prometheus/alertmanager.yml' mkdir='True' rm='True'/>
<file filelist='prometheus-alertmanager' name='/etc/prometheus/rules.d/alert-rules.yml' mkdir='True' rm='True'/> <file filelist='prometheus-alertmanager' name='/etc/prometheus/rules.d/alert-rules.yml' mkdir='True' rm='True'/>
<file filelist='prometheus-alertmanager' name='/etc/prometheus/rules.d/alert-rules-node-exporter.yml' mkdir='True' rm='True'/>
<file filelist='prometheus-alertmanager' name='/etc/prometheus/rules.d/predict-rules.yml' mkdir='True' rm='True'/> <file filelist='prometheus-alertmanager' name='/etc/prometheus/rules.d/predict-rules.yml' mkdir='True' rm='True'/>
<file filelist='grafana' name='/etc/grafana/grafana.ini' mkdir='True' rm='True'/> <file filelist='grafana' name='/etc/grafana/grafana.ini' mkdir='True' rm='True'/>
<file filelist='grafana' name='/etc/grafana/provisioning/dashboards/eole.yml' source='grafana-dashboards.yml' mkdir='True' rm='True'/> <file filelist='grafana' name='/etc/grafana/provisioning/dashboards/eole.yml' source='grafana-dashboards.yml' mkdir='True' rm='True'/>

View File

@ -0,0 +1,35 @@
#
# Alert Rules
#
groups:
- name: GeneralNodeExporterRules
rules:
# TooMuch Data IN
- alert: TooMuchNetworkThroughputIn
expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual network throughput in (instance {{ $labels.instance }})
description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: AlertInodes
expr: node_filesystem_files_free{mountpoint ="/"} / node_filesystem_files{mountpoint="/"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/"} == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host out of inodes (instance {{ $labels.instance }})
description: "Disk is almost running out of available inodes (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostSwapIsFillingUp
expr: (1 - (node_memory_SwapFree / node_memory_SwapTotal)) * 100 > 80
for: 2m
labels:
severity: warning
annotations:
summary: Host swap is filling up (instance {{ $labels.instance }})
description: "Swap is filling up (>80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"

View File

@ -34,6 +34,16 @@ groups:
- alert: filesystem_threshold_exceeded - alert: filesystem_threshold_exceeded
expr: node_filesystem_avail{job="%%{job_name_node}",mountpoint="/"} / node_filesystem_size{job="%%{job_name_node}"} expr: node_filesystem_avail{job="%%{job_name_node}",mountpoint="/"} / node_filesystem_size{job="%%{job_name_node}"}
* 100 < 20 * 100 < 20
for: 2m
annotations:
description: This device's filesystem usage has exceeded the threshold with
a value of {{ $value }}.
summary: Instance {{ $labels.instance }} filesystem usage is dangerously high
# Heavy "/var" use
- alert: var_filesystem_threshold_exceeded
expr: node_filesystem_avail{job="node",mountpoint="/var"} / node_filesystem_size{job="node"}
* 100 < 20
annotations: annotations:
description: This device's filesystem usage has exceeded the threshold with description: This device's filesystem usage has exceeded the threshold with
a value of {{ $value }}. a value of {{ $value }}.