mirrors/monitoring-mixins-website
1
0
Fork 0
mirror of https://github.com/monitoring-mixins/website.git synced 2024-12-14 11:37:31 +00:00
Code Activity

assets,site/content: daily assets regeneration

Browse source
This commit is contained in:
github-actions[bot] 2023-04-26 03:20:51 +00:00
parent 1874d3a9ff
commit bf2a2fd292
2 changed files with 70 additions and 51 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

61
assets/coredns/alerts.yaml
View file

@ -3,8 +3,9 @@ groups:
rules: rules:
- alert: CoreDNSDown - alert: CoreDNSDown
annotations: annotations:
message: CoreDNS has disappeared from Prometheus target discovery. description: CoreDNS has disappeared from Prometheus target discovery.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsdown runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsdown
summary: CoreDNS has disappeared from Prometheus target discovery.
expr: | expr: |
absent(up{job="kube-dns"} == 1) absent(up{job="kube-dns"} == 1)
for: 15m for: 15m
@ -12,35 +13,38 @@ groups:
severity: critical severity: critical
- alert: CoreDNSLatencyHigh - alert: CoreDNSLatencyHigh
annotations: annotations:
message: CoreDNS has 99th percentile latency of {{ $value }} seconds for server description: CoreDNS has 99th percentile latency of {{ $value }} seconds for
{{ $labels.server }} zone {{ $labels.zone }} . server {{ $labels.server }} zone {{ $labels.zone }} .
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednslatencyhigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednslatencyhigh
summary: CoreDNS is experiencing high 99th percentile latency.
expr: | expr: |
histogram_quantile(0.99, sum(rate(coredns_dns_request_duration_seconds_bucket{job="kube-dns"}[5m])) by(server, zone, le)) > 4 histogram_quantile(0.99, sum(rate(coredns_dns_request_duration_seconds_bucket{job="kube-dns"}[5m])) without (instance,pod)) > 4
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
- alert: CoreDNSErrorsHigh - alert: CoreDNSErrorsHigh
annotations: annotations:
message: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }} description: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage
of requests. }} of requests.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednserrorshigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednserrorshigh
summary: CoreDNS is returning SERVFAIL.
expr: | expr: |
sum(rate(coredns_dns_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m])) sum without (pod, instance, server, zone, view, rcode, plugin) (rate(coredns_dns_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m]))
/ /
sum(rate(coredns_dns_responses_total{job="kube-dns"}[5m])) > 0.03 sum without (pod, instance, server, zone, view, rcode, plugin) (rate(coredns_dns_responses_total{job="kube-dns"}[5m])) > 0.03
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
- alert: CoreDNSErrorsHigh - alert: CoreDNSErrorsHigh
annotations: annotations:
message: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }} description: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage
of requests. }} of requests.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednserrorshigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednserrorshigh
summary: CoreDNS is returning SERVFAIL.
expr: | expr: |
sum(rate(coredns_dns_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m])) sum without (pod, instance, server, zone, view, rcode, plugin) (rate(coredns_dns_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m]))
/ /
sum(rate(coredns_dns_responses_total{job="kube-dns"}[5m])) > 0.01 sum without (pod, instance, server, zone, view, rcode, plugin) (rate(coredns_dns_responses_total{job="kube-dns"}[5m])) > 0.01
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@ -48,54 +52,59 @@ groups:
rules: rules:
- alert: CoreDNSForwardLatencyHigh - alert: CoreDNSForwardLatencyHigh
annotations: annotations:
message: CoreDNS has 99th percentile latency of {{ $value }} seconds forwarding description: CoreDNS has 99th percentile latency of {{ $value }} seconds forwarding
requests to {{ $labels.to }}. requests to {{ $labels.to }}.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardlatencyhigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardlatencyhigh
summary: CoreDNS is experiencing high latency forwarding requests.
expr: | expr: |
histogram_quantile(0.99, sum(rate(coredns_forward_request_duration_seconds_bucket{job="kube-dns"}[5m])) by(to, le)) > 4 histogram_quantile(0.99, sum(rate(coredns_forward_request_duration_seconds_bucket{job="kube-dns"}[5m])) without (pod, instance, rcode)) > 4
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
- alert: CoreDNSForwardErrorsHigh - alert: CoreDNSForwardErrorsHigh
annotations: annotations:
message: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }} description: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage
of forward requests to {{ $labels.to }}. }} of forward requests to {{ $labels.to }}.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwarderrorshigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwarderrorshigh
summary: CoreDNS is returning SERVFAIL for forward requests.
expr: | expr: |
sum(rate(coredns_forward_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m])) sum without (pod, instance, rcode) (rate(coredns_forward_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m]))
/ /
sum(rate(coredns_forward_responses_total{job="kube-dns"}[5m])) > 0.03 sum without (pod, instance, rcode) (rate(coredns_forward_responses_total{job="kube-dns"}[5m])) > 0.03
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
- alert: CoreDNSForwardErrorsHigh - alert: CoreDNSForwardErrorsHigh
annotations: annotations:
message: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }} description: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage
of forward requests to {{ $labels.to }}. }} of forward requests to {{ $labels.to }}.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwarderrorshigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwarderrorshigh
summary: CoreDNS is returning SERVFAIL for forward requests.
expr: | expr: |
sum(rate(coredns_forward_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m])) sum without (pod, instance, rcode) (rate(coredns_forward_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m]))
/ /
sum(rate(coredns_forward_responses_total{job="kube-dns"}[5m])) > 0.01 sum without (pod, instance, rcode) (rate(coredns_forward_responses_total{job="kube-dns"}[5m])) > 0.01
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
- alert: CoreDNSForwardHealthcheckFailureCount - alert: CoreDNSForwardHealthcheckFailureCount
annotations: annotations:
message: CoreDNS health checks have failed to upstream server {{ $labels.to description: CoreDNS health checks have failed to upstream server {{ $labels.to
}}. }}.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardhealthcheckfailurecount runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardhealthcheckfailurecount
summary: CoreDNS health checks have failed to upstream server.
expr: | expr: |
sum(rate(coredns_forward_healthcheck_failures_total{job="kube-dns"}[5m])) by (to) > 0 sum without (pod, instance) (rate(coredns_forward_healthcheck_failures_total{job="kube-dns"}[5m])) > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
- alert: CoreDNSForwardHealthcheckBrokenCount - alert: CoreDNSForwardHealthcheckBrokenCount
annotations: annotations:
message: CoreDNS health checks have failed for all upstream servers. description: CoreDNS health checks have failed for all upstream servers.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardhealthcheckbrokencount runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardhealthcheckbrokencount
summary: CoreDNS health checks have failed for all upstream servers.
expr: | expr: |
sum(rate(coredns_forward_healthcheck_broken_total{job="kube-dns"}[5m])) > 0 sum without (pod, instance) (rate(coredns_forward_healthcheck_broken_total{job="kube-dns"}[5m])) > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning

60
site/content/coredns/_index.md
View file

@ -24,8 +24,9 @@ https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-core
{{< code lang="yaml" >}} {{< code lang="yaml" >}}
alert: CoreDNSDown alert: CoreDNSDown
annotations: annotations:
message: CoreDNS has disappeared from Prometheus target discovery. description: CoreDNS has disappeared from Prometheus target discovery.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsdown runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsdown
summary: CoreDNS has disappeared from Prometheus target discovery.
expr: | expr: |
absent(up{job="kube-dns"} == 1) absent(up{job="kube-dns"} == 1)
for: 15m for: 15m
@ -39,11 +40,12 @@ https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-core
{{< code lang="yaml" >}} {{< code lang="yaml" >}}
alert: CoreDNSLatencyHigh alert: CoreDNSLatencyHigh
annotations: annotations:
message: CoreDNS has 99th percentile latency of {{ $value }} seconds for server description: CoreDNS has 99th percentile latency of {{ $value }} seconds for server
{{ $labels.server }} zone {{ $labels.zone }} . {{ $labels.server }} zone {{ $labels.zone }} .
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednslatencyhigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednslatencyhigh
summary: CoreDNS is experiencing high 99th percentile latency.
expr: | expr: |
histogram_quantile(0.99, sum(rate(coredns_dns_request_duration_seconds_bucket{job="kube-dns"}[5m])) by(server, zone, le)) > 4 histogram_quantile(0.99, sum(rate(coredns_dns_request_duration_seconds_bucket{job="kube-dns"}[5m])) without (instance,pod)) > 4
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
@ -55,13 +57,14 @@ https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-core
{{< code lang="yaml" >}} {{< code lang="yaml" >}}
alert: CoreDNSErrorsHigh alert: CoreDNSErrorsHigh
annotations: annotations:
message: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }} of description: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }}
requests. of requests.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednserrorshigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednserrorshigh
summary: CoreDNS is returning SERVFAIL.
expr: | expr: |
sum(rate(coredns_dns_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m])) sum without (pod, instance, server, zone, view, rcode, plugin) (rate(coredns_dns_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m]))
/ /
sum(rate(coredns_dns_responses_total{job="kube-dns"}[5m])) > 0.03 sum without (pod, instance, server, zone, view, rcode, plugin) (rate(coredns_dns_responses_total{job="kube-dns"}[5m])) > 0.03
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
@ -73,13 +76,14 @@ https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-core
{{< code lang="yaml" >}} {{< code lang="yaml" >}}
alert: CoreDNSErrorsHigh alert: CoreDNSErrorsHigh
annotations: annotations:
message: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }} of description: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }}
requests. of requests.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednserrorshigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednserrorshigh
summary: CoreDNS is returning SERVFAIL.
expr: | expr: |
sum(rate(coredns_dns_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m])) sum without (pod, instance, server, zone, view, rcode, plugin) (rate(coredns_dns_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m]))
/ /
sum(rate(coredns_dns_responses_total{job="kube-dns"}[5m])) > 0.01 sum without (pod, instance, server, zone, view, rcode, plugin) (rate(coredns_dns_responses_total{job="kube-dns"}[5m])) > 0.01
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@ -93,11 +97,12 @@ https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-core
{{< code lang="yaml" >}} {{< code lang="yaml" >}}
alert: CoreDNSForwardLatencyHigh alert: CoreDNSForwardLatencyHigh
annotations: annotations:
message: CoreDNS has 99th percentile latency of {{ $value }} seconds forwarding description: CoreDNS has 99th percentile latency of {{ $value }} seconds forwarding
requests to {{ $labels.to }}. requests to {{ $labels.to }}.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardlatencyhigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardlatencyhigh
summary: CoreDNS is experiencing high latency forwarding requests.
expr: | expr: |
histogram_quantile(0.99, sum(rate(coredns_forward_request_duration_seconds_bucket{job="kube-dns"}[5m])) by(to, le)) > 4 histogram_quantile(0.99, sum(rate(coredns_forward_request_duration_seconds_bucket{job="kube-dns"}[5m])) without (pod, instance, rcode)) > 4
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
@ -109,13 +114,14 @@ https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-core
{{< code lang="yaml" >}} {{< code lang="yaml" >}}
alert: CoreDNSForwardErrorsHigh alert: CoreDNSForwardErrorsHigh
annotations: annotations:
message: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }} of description: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }}
forward requests to {{ $labels.to }}. of forward requests to {{ $labels.to }}.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwarderrorshigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwarderrorshigh
summary: CoreDNS is returning SERVFAIL for forward requests.
expr: | expr: |
sum(rate(coredns_forward_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m])) sum without (pod, instance, rcode) (rate(coredns_forward_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m]))
/ /
sum(rate(coredns_forward_responses_total{job="kube-dns"}[5m])) > 0.03 sum without (pod, instance, rcode) (rate(coredns_forward_responses_total{job="kube-dns"}[5m])) > 0.03
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
@ -127,13 +133,14 @@ https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-core
{{< code lang="yaml" >}} {{< code lang="yaml" >}}
alert: CoreDNSForwardErrorsHigh alert: CoreDNSForwardErrorsHigh
annotations: annotations:
message: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }} of description: CoreDNS is returning SERVFAIL for {{ $value | humanizePercentage }}
forward requests to {{ $labels.to }}. of forward requests to {{ $labels.to }}.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwarderrorshigh runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwarderrorshigh
summary: CoreDNS is returning SERVFAIL for forward requests.
expr: | expr: |
sum(rate(coredns_forward_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m])) sum without (pod, instance, rcode) (rate(coredns_forward_responses_total{job="kube-dns",rcode="SERVFAIL"}[5m]))
/ /
sum(rate(coredns_forward_responses_total{job="kube-dns"}[5m])) > 0.01 sum without (pod, instance, rcode) (rate(coredns_forward_responses_total{job="kube-dns"}[5m])) > 0.01
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@ -145,10 +152,12 @@ https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-core
{{< code lang="yaml" >}} {{< code lang="yaml" >}}
alert: CoreDNSForwardHealthcheckFailureCount alert: CoreDNSForwardHealthcheckFailureCount
annotations: annotations:
message: CoreDNS health checks have failed to upstream server {{ $labels.to }}. description: CoreDNS health checks have failed to upstream server {{ $labels.to
}}.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardhealthcheckfailurecount runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardhealthcheckfailurecount
summary: CoreDNS health checks have failed to upstream server.
expr: | expr: |
sum(rate(coredns_forward_healthcheck_failures_total{job="kube-dns"}[5m])) by (to) > 0 sum without (pod, instance) (rate(coredns_forward_healthcheck_failures_total{job="kube-dns"}[5m])) > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@ -160,10 +169,11 @@ https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-core
{{< code lang="yaml" >}} {{< code lang="yaml" >}}
alert: CoreDNSForwardHealthcheckBrokenCount alert: CoreDNSForwardHealthcheckBrokenCount
annotations: annotations:
message: CoreDNS health checks have failed for all upstream servers. description: CoreDNS health checks have failed for all upstream servers.
runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardhealthcheckbrokencount runbook_url: https://github.com/povilasv/coredns-mixin/tree/master/runbook.md#alert-name-corednsforwardhealthcheckbrokencount
summary: CoreDNS health checks have failed for all upstream servers.
expr: | expr: |
sum(rate(coredns_forward_healthcheck_broken_total{job="kube-dns"}[5m])) > 0 sum without (pod, instance) (rate(coredns_forward_healthcheck_broken_total{job="kube-dns"}[5m])) > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning