XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-21 08:57:19 +08:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'master' into master

Browse source
This commit is contained in:
Samuel Berthe 2020-10-11 17:42:51 +02:00 committed by GitHub
commit 2e6e46da45
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
_data/rules.yml
View file

@ -157,11 +157,11 @@ groups:
severity: warning
- name: Host unusual disk read latency
description: Disk latency is growing (read operations > 100ms)
query: "rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 100"
query: "rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0"
severity: warning
- name: Host unusual disk write latency
description: Disk latency is growing (write operations > 100ms)
query: "rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 100"
query: "rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0"
severity: warning
- name: Host high CPU load
description: CPU load is > 80%
@ -197,7 +197,7 @@ groups:
severity: critical
- name: Host RAID disk failure
description: 'At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap'
query: 'node_md_disks{state="fail"} > 0'
query: 'node_md_disks{state="failed"} > 0'
severity: warning
- name: Host kernel version deviations
description: Different kernel versions are running
@ -239,8 +239,9 @@ groups:
severity: warning
- name: Container Memory usage
description: Container Memory usage is above 80%
query: "(sum(container_memory_usage_bytes) BY (instance, name) / sum(container_spec_memory_limit_bytes) BY (instance, name) * 100) > 80"
query: "(sum(container_memory_working_set_bytes) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) > 80"
severity: warning
comments: See https://medium.com/faun/how-much-is-too-much-the-linux-oomkiller-and-used-memory-d32186f29c9d
- name: Container Volume usage
description: Container Volume usage is above 80%
query: "(1 - (sum(container_fs_inodes_free) BY (instance) / sum(container_fs_inodes_total) BY (instance)) * 100) > 80"
@ -476,7 +477,7 @@ groups:
severity: critical
- name: SQL Server deadlock
description: SQL Server is having some deadlock.
query: irate(mssql_deadlocks[2m]) > 0
query: rate(mssql_deadlocks[1m]) > 0
severity: warning
- name: PGBouncer
@ -1004,11 +1005,11 @@ groups:
severity: critical
- name: Kubernetes HPA scaling ability
description: Pod is unable to scale
query: 'kube_hpa_status_condition{condition="false", status="AbleToScale"} == 1'
query: 'kube_hpa_status_condition{status="false", condition ="AbleToScale"} == 1'
severity: warning
- name: Kubernetes HPA metric availability
description: HPA is not able to colelct metrics
query: 'kube_hpa_status_condition{condition="false", status="ScalingActive"} == 1'
description: HPA is not able to collect metrics
query: 'kube_hpa_status_condition{status="false", condition="ScalingActive"} == 1'
severity: warning
- name: Kubernetes HPA scale capability
description: The maximum number of desired Pods has been hit