XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-22 17:37:19 +08:00
Code Issues Projects Releases Packages Wiki Activity

rate is better than irate for alerting

Browse source
This commit is contained in:
Samuel Berthe 2020-11-07 17:46:18 +01:00
parent 59fd40b113
commit be20363602
No known key found for this signature in database
GPG key ID: 64863511FFBD0E3C
1 changed files with 12 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
_data/rules.yml
View file

@ -129,19 +129,19 @@ groups:
severity: warning
- name: Host unusual network throughput in
description: Host network interfaces are probably receiving too much data (> 100 MB/s)
query: "sum by (instance) (irate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100"
query: "sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100"
severity: warning
- name: Host unusual network throughput out
description: Host network interfaces are probably sending too much data (> 100 MB/s)
query: "sum by (instance) (irate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100"
query: "sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100"
severity: warning
- name: Host unusual disk read rate
description: Disk is probably reading too much data (> 50 MB/s)
query: "sum by (instance) (irate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50"
query: "sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50"
severity: warning
- name: Host unusual disk write rate
description: Disk is probably writing too much data (> 50 MB/s)
query: "sum by (instance) (irate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50"
query: "sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50"
severity: warning
- name: Host out of disk space
description: Disk is almost full (< 10% left)
@ -168,7 +168,7 @@ groups:
severity: warning
- name: Host high CPU load
description: CPU load is > 80%
query: '100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80'
query: '100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80'
severity: warning
- name: Host context switching
description: Context switching is growing on node (> 1000 / s)
@ -783,7 +783,7 @@ groups:
severity: warning
- name: Cassandra cool hacker
description: Increase of Cassandra authentication failures
query: 'irate(cassandra_stats{name="org:apache:cassandra:metrics:client:authfailure:count"}[1m]) > 5'
query: 'rate(cassandra_stats{name="org:apache:cassandra:metrics:client:authfailure:count"}[1m]) > 5'
severity: warning
- name: Cassandra node down
description: Cassandra node down
@ -915,19 +915,19 @@ groups:
severity: critical
- name: HAProxy high HTTP 4xx error rate backend
description: Too many HTTP requests with status 4xx (> 5%) on backend {{ $labels.fqdn }}/{{ $labels.backend }}
query: 'sum by (backend) irate(haproxy_server_http_responses_total{code="4xx"}[1m]) / sum by (backend) irate(haproxy_server_http_responses_total{}[1m]) * 100 > 5'
query: 'sum by (backend) rate(haproxy_server_http_responses_total{code="4xx"}[1m]) / sum by (backend) rate(haproxy_server_http_responses_total{}[1m]) * 100 > 5'
severity: critical
- name: HAProxy high HTTP 4xx error rate backend
description: Too many HTTP requests with status 5xx (> 5%) on backend {{ $labels.fqdn }}/{{ $labels.backend }}
query: 'sum by (backend) irate(haproxy_server_http_responses_total{code="5xx"}[1m]) / sum by (backend) irate(haproxy_server_http_responses_total{}[1m]) * 100 > 5'
query: 'sum by (backend) rate(haproxy_server_http_responses_total{code="5xx"}[1m]) / sum by (backend) rate(haproxy_server_http_responses_total{}[1m]) * 100 > 5'
severity: critical
- name: HAProxy high HTTP 4xx error rate server
description: Too many HTTP requests with status 4xx (> 5%) on server {{ $labels.server }}
query: 'sum by (server) irate(haproxy_server_http_responses_total{code="4xx"}[1m]) / sum by (backend) irate(haproxy_server_http_responses_total{}[1m]) * 100 > 5'
query: 'sum by (server) rate(haproxy_server_http_responses_total{code="4xx"}[1m]) / sum by (backend) rate(haproxy_server_http_responses_total{}[1m]) * 100 > 5'
severity: critical
- name: HAProxy high HTTP 5xx error rate server
description: Too many HTTP requests with status 5xx (> 5%) on server {{ $labels.server }}
query: 'sum by (server) irate(haproxy_server_http_responses_total{code="5xx"}[1m]) / sum by (backend) irate(haproxy_server_http_responses_total{}[1m]) * 100 > 5'
query: 'sum by (server) rate(haproxy_server_http_responses_total{code="5xx"}[1m]) / sum by (backend) rate(haproxy_server_http_responses_total{}[1m]) * 100 > 5'
severity: critical
- name: HAProxy backend connection errors
description: Too many connection errors to {{ $labels.fqdn }}/{{ $labels.backend }} backend (> 5%). Request throughput may be to high.
@ -1385,11 +1385,11 @@ groups:
severity: critical
- name: Juniper high Bandwith Usage 1GiB
description: Interface is highly saturated for at least 1 min. (> 0.90GiB/s)
query: "irate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.90"
query: "rate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.90"
severity: critical
- name: Juniper high Bandwith Usage 1GiB
description: Interface is getting saturated for at least 1 min. (> 0.80GiB/s)
query: "irate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.80"
query: "rate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.80"
severity: warning
- name: CoreDNS