Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: add missing cluster label to mixins #12870

Merged
merged 11 commits into from
Sep 19, 2024
+31 −31
Merged

feat: add missing cluster label to mixins #12870

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
07ac356
enhance: add missing cluster label to mixins
QuentinBisson May 3, 2024
7df8d53
Merge branch 'main' into loki-mixins-add-cluster-label
QuentinBisson May 3, 2024
27918f6
fix issues with pint
QuentinBisson May 6, 2024
33cc97f
Merge branch 'main' into loki-mixins-add-cluster-label
QuentinBisson May 6, 2024
471e11d
fix issues with pint
QuentinBisson May 6, 2024
f26b1bf
Merge branch 'main' into loki-mixins-add-cluster-label
QuentinBisson Sep 17, 2024
f8df502
Merge branch 'main' into loki-mixins-add-cluster-label
QuentinBisson Sep 17, 2024
9d5c001
Merge branch 'main' into loki-mixins-add-cluster-label
QuentinBisson Sep 18, 2024
57016f4
Merge branch 'main' into loki-mixins-add-cluster-label
vlad-diachenko Sep 18, 2024
3c640de
Merge branch 'main' into loki-mixins-add-cluster-label
cstyan Sep 19, 2024
ab7072d
Merge branch 'main' into loki-mixins-add-cluster-label
QuentinBisson Sep 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion production/helm/loki/src/alerts.yaml.tpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,7 @@ groups:
message: |
{{`{{`}} $labels.cluster {{`}}`}} {{`{{`}} $labels.namespace {{`}}`}} has had {{`{{`}} printf "%.0f" $value {{`}}`}} compactors running for more than 5m. Only one compactor should run at a time.
expr: |
sum(loki_boltdb_shipper_compactor_running) by (namespace, cluster) > 1
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Making sure they are all in the same order

sum(loki_boltdb_shipper_compactor_running) by (cluster, namespace) > 1
for: "5m"
labels:
severity: "warning"
Expand Down
14 changes: 7 additions & 7 deletions production/loki-mixin-compiled-ssd/alerts.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,29 +4,29 @@ groups:
- alert: LokiRequestErrors
annotations:
description: |
{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}% errors.
{{ $labels.cluster }} {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}% errors.
summary: Loki request error rate is high.
expr: |
100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[2m])) by (namespace, job, route)
100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[2m])) by (cluster, namespace, job, route)
/
sum(rate(loki_request_duration_seconds_count[2m])) by (namespace, job, route)
sum(rate(loki_request_duration_seconds_count[2m])) by (cluster, namespace, job, route)
> 10
for: 15m
labels:
severity: critical
- alert: LokiRequestPanics
annotations:
description: |
{{ $labels.job }} is experiencing {{ printf "%.2f" $value }}% increase of panics.
{{ $labels.cluster }} {{ $labels.job }} is experiencing {{ printf "%.2f" $value }}% increase of panics.
summary: Loki requests are causing code panics.
expr: |
sum(increase(loki_panic_total[10m])) by (namespace, job) > 0
sum(increase(loki_panic_total[10m])) by (cluster, namespace, job) > 0
labels:
severity: critical
- alert: LokiRequestLatency
annotations:
description: |
{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency.
{{ $labels.cluster }} {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency.
summary: Loki request error latency is high.
expr: |
cluster_namespace_job_route:loki_request_duration_seconds:99quantile{route!~"(?i).*tail.*|/schedulerpb.SchedulerForQuerier/QuerierLoop"} > 1
Expand All @@ -39,7 +39,7 @@ groups:
{{ $labels.cluster }} {{ $labels.namespace }} has had {{ printf "%.0f" $value }} compactors running for more than 5m. Only one compactor should run at a time.
summary: Loki deployment is running more than one compactor.
expr: |
sum(loki_boltdb_shipper_compactor_running) by (namespace, cluster) > 1
sum(loki_boltdb_shipper_compactor_running) by (cluster, namespace) > 1
for: 5m
labels:
severity: warning
14 changes: 7 additions & 7 deletions production/loki-mixin-compiled/alerts.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,29 +4,29 @@ groups:
- alert: LokiRequestErrors
annotations:
description: |
{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}% errors.
{{ $labels.cluster }} {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}% errors.
summary: Loki request error rate is high.
expr: |
100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[2m])) by (namespace, job, route)
100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[2m])) by (cluster, namespace, job, route)
/
sum(rate(loki_request_duration_seconds_count[2m])) by (namespace, job, route)
sum(rate(loki_request_duration_seconds_count[2m])) by (cluster, namespace, job, route)
> 10
for: 15m
labels:
severity: critical
- alert: LokiRequestPanics
annotations:
description: |
{{ $labels.job }} is experiencing {{ printf "%.2f" $value }}% increase of panics.
{{ $labels.cluster }} {{ $labels.job }} is experiencing {{ printf "%.2f" $value }}% increase of panics.
summary: Loki requests are causing code panics.
expr: |
sum(increase(loki_panic_total[10m])) by (namespace, job) > 0
sum(increase(loki_panic_total[10m])) by (cluster, namespace, job) > 0
labels:
severity: critical
- alert: LokiRequestLatency
annotations:
description: |
{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency.
{{ $labels.cluster }} {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency.
summary: Loki request error latency is high.
expr: |
cluster_namespace_job_route:loki_request_duration_seconds:99quantile{route!~"(?i).*tail.*|/schedulerpb.SchedulerForQuerier/QuerierLoop"} > 1
Expand All @@ -39,7 +39,7 @@ groups:
{{ $labels.cluster }} {{ $labels.namespace }} has had {{ printf "%.0f" $value }} compactors running for more than 5m. Only one compactor should run at a time.
summary: Loki deployment is running more than one compactor.
expr: |
sum(loki_boltdb_shipper_compactor_running) by (namespace, cluster) > 1
sum(loki_boltdb_shipper_compactor_running) by (cluster, namespace) > 1
for: 5m
labels:
severity: warning
32 changes: 16 additions & 16 deletions production/loki-mixin/alerts.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,36 +6,36 @@
rules: [
{
alert: 'LokiRequestErrors',
expr: |||
100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[2m])) by (namespace, job, route)
expr: std.strReplace(|||
100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[2m])) by (cluster, namespace, job, route)
/
sum(rate(loki_request_duration_seconds_count[2m])) by (namespace, job, route)
sum(rate(loki_request_duration_seconds_count[2m])) by (cluster, namespace, job, route)
> 10
|||,
|||, 'cluster', $._config.per_cluster_label),
'for': '15m',
labels: {
severity: 'critical',
},
annotations: {
summary: 'Loki request error rate is high.',
description: |||
{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}% errors.
|||,
description: std.strReplace(|||
{{ $labels.cluster }} {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}% errors.
|||, 'cluster', $._config.per_cluster_label),
},
},
{
alert: 'LokiRequestPanics',
expr: |||
sum(increase(loki_panic_total[10m])) by (namespace, job) > 0
|||,
sum(increase(loki_panic_total[10m])) by (%s, namespace, job) > 0
||| % $._config.per_cluster_label,
labels: {
severity: 'critical',
},
annotations: {
summary: 'Loki requests are causing code panics.',
description: |||
{{ $labels.job }} is experiencing {{ printf "%.2f" $value }}% increase of panics.
|||,
description: std.strReplace(|||
{{ $labels.cluster }} {{ $labels.job }} is experiencing {{ printf "%.2f" $value }}% increase of panics.
|||, 'cluster', $._config.per_cluster_label),
},
},
{
Expand All @@ -49,15 +49,15 @@
},
annotations: {
summary: 'Loki request error latency is high.',
description: |||
{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency.
|||,
description: std.strReplace(|||
{{ $labels.cluster }} {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency.
|||, 'cluster', $._config.per_cluster_label),
},
},
{
alert: 'LokiTooManyCompactorsRunning',
expr: |||
sum(loki_boltdb_shipper_compactor_running) by (namespace, %s) > 1
sum(loki_boltdb_shipper_compactor_running) by (%s, namespace) > 1
||| % $._config.per_cluster_label,
'for': '5m',
labels: {
Expand Down
Loading