CCCHH/ansible-infra
CCCHH/ansible-infra
4
2
Fork 0
Code Issues3 Pull requests Wiki Activity Actions

grafana: account for long backup jobs in Prom. hyperv. disk rw rate al.

Browse source
This commit is contained in:
June 2025-02-06 19:17:21 +01:00
parent c4e35c1adf
commit 40cddb67b4
Signed by: june
SSH key fingerprint: SHA256:o9EAq4Y9N9K0pBQeBTqhSDrND5E7oB+60ZNx0U1yPe0
1 changed files with 2 additions and 2 deletions

4
resources/chaosknoten/grafana/docker_compose/prometheus_alerts.rules.yaml
View file

@ -166,7 +166,7 @@ groups:
# Longer intervals to account for disk intensive hypervisor tasks (backups, moving VMs, etc.). # Longer intervals to account for disk intensive hypervisor tasks (backups, moving VMs, etc.).
- alert: HypervisorHostUnusualDiskReadRate - alert: HypervisorHostUnusualDiskReadRate
expr: (sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename="chaosknoten"} expr: (sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename="chaosknoten"}
for: 30m for: 60m
labels: labels:
severity: warning severity: warning
annotations: annotations:
@ -174,7 +174,7 @@ groups:
description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}" description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}"
- alert: HypervisorHostUnusualDiskWriteRate - alert: HypervisorHostUnusualDiskWriteRate
expr: (sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename="chaosknoten"} expr: (sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename="chaosknoten"}
for: 20m for: 60m
labels: labels:
severity: warning severity: warning
annotations: annotations: