Apache Prometheus Alert Rules4 Prometheus alerting rules for Apache.Exported via Lusitaniae/apache_exporter.These rules cover critical and warning conditions — copy and paste the YAML into your Prometheus configuration.
Alert thresholds depend on the nature of your applications. Some queries may have arbitrary tolerance thresholds. Building an efficient monitoring platform takes time. 😉
groups:
- name: LusitaniaeApacheExporter
rules:
- alert: ApacheDown
expr: 'apache_up == 0'
for: 0m
labels:
severity: critical
annotations:
summary: Apache down (instance {{ $labels.instance }})
description: "Apache down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ApacheWorkersLoad
expr: '(sum by (instance) (apache_workers{state="busy"}) / sum by (instance) (apache_scoreboard) ) * 100 > 80 and sum by (instance) (apache_scoreboard) > 0'
for: 2m
labels:
severity: warning
annotations:
summary: Apache workers load (instance {{ $labels.instance }})
description: "Apache workers in busy state approach the max workers count 80% workers busy on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# 5000ms threshold is a rough default; acceptable response time varies by route and your SLO — adjust based on your baseline.
- alert: ApacheResponseTimeTooHigh
expr: 'increase(apache_duration_ms_total[5m]) / increase(apache_accesses_total[5m]) > 5000 and increase(apache_accesses_total[5m]) > 0'
for: 2m
labels:
severity: warning
annotations:
summary: Apache response time too high (instance {{ $labels.instance }})
description: "Apache average response time on {{ $labels.instance }} is {{ $value }}ms over the last 5 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ApacheRestart
expr: 'apache_uptime_seconds_total / 60 < 1'
for: 0m
labels:
severity: info
annotations:
summary: Apache restart (instance {{ $labels.instance }})
description: "Apache has just been restarted.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"Lusitaniae/apache_exporter(4 rules)wget https://raw.githubusercontent.com/samber/awesome-prometheus-alerts/refs/heads/master/dist/rules/apache/lusitaniae-apache-exporter.yml
Apache down
- alert: ApacheDown
expr: 'apache_up == 0'
for: 0m
labels:
severity: critical
annotations:
summary: Apache down (instance {{ $labels.instance }})
description: "Apache down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"Apache workers in busy state approach the max workers count 80% workers busy on {{ $labels.instance }}
- alert: ApacheWorkersLoad
expr: '(sum by (instance) (apache_workers{state="busy"}) / sum by (instance) (apache_scoreboard) ) * 100 > 80 and sum by (instance) (apache_scoreboard) > 0'
for: 2m
labels:
severity: warning
annotations:
summary: Apache workers load (instance {{ $labels.instance }})
description: "Apache workers in busy state approach the max workers count 80% workers busy on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"Apache average response time on {{ $labels.instance }} is {{ $value }}ms over the last 5 minutes.
# 5000ms threshold is a rough default; acceptable response time varies by route and your SLO — adjust based on your baseline.
- alert: ApacheResponseTimeTooHigh
expr: 'increase(apache_duration_ms_total[5m]) / increase(apache_accesses_total[5m]) > 5000 and increase(apache_accesses_total[5m]) > 0'
for: 2m
labels:
severity: warning
annotations:
summary: Apache response time too high (instance {{ $labels.instance }})
description: "Apache average response time on {{ $labels.instance }} is {{ $value }}ms over the last 5 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"Apache has just been restarted.
- alert: ApacheRestart
expr: 'apache_uptime_seconds_total / 60 < 1'
for: 0m
labels:
severity: info
annotations:
summary: Apache restart (instance {{ $labels.instance }})
description: "Apache has just been restarted.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"