Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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 perses/charts/Chart.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ name: perses
description: A Helm chart for Perses
icon: https://avatars.githubusercontent.com/u/77209215?s=200&v=4
type: application
version: 0.17.2
version: 0.17.3
maintainers:
- name: richardtief
- name: ibakshay
Expand Down
26 changes: 14 additions & 12 deletions perses/charts/alerts/perses.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,10 @@ groups:
rules:
- alert: PersesServiceDown
annotations:
description: Perses service has disappeared. Prometheus target for the component cannot be discovered.
summary: Perses service is down.
description: "The pod {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}} is down for more than 10 minutes"
summary: "Perses service is down"
expr: |
absent(up{job=~".*perses.*"} == 1)
up{job=~".*perses.*"} == 0
for: 10m
labels:
severity: warning
Expand All @@ -15,10 +15,12 @@ groups:

- alert: PersesHealthEndpointFailure
annotations:
description: Perses health endpoint hasn't responded with a successful status for 15 minutes.
description: The pod {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}} is running but the health endpoint has not returned a success status for 15 minutes.
summary: Perses health endpoint is failing.
expr: |
sum(rate(perses_http_request_total{handler="{{ .Values.perses.config.api_prefix }}/api/v1/health",code="200"}[5m])) == 0
sum by (pod, namespace) (
rate(perses_http_request_total{handler="{{ .Values.perses.config.api_prefix }}/api/v1/health",code="200"}[5m])
) == 0
for: 15m
labels:
severity: warning
Expand All @@ -27,13 +29,13 @@ groups:

- alert: PersesHighHttpErrorRate
annotations:
description: Perses is failing to handle {{`{{$value | humanize}}`}}% of HTTP requests.
summary: Perses has an elevated HTTP error rate.
description: The pod {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}} is failing {{`{{ $value | humanize }}`}}% of requests.
summary: High HTTP error rate on {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}}
expr: |
(
sum(rate(perses_http_request_total{code=~"5..|4.."}[5m]))
sum by (pod, namespace) (rate(perses_http_request_total{code=~"5..|4..", code!="404"}[5m]))
/
sum(rate(perses_http_request_total[5m]))
sum by (pod, namespace)(rate(perses_http_request_total[5m]))
) * 100 > 5
for: 10m
labels:
Expand All @@ -46,7 +48,7 @@ groups:
description: Perses failed to load plugin schemas {{`{{$value}}`}} times.
summary: Perses plugin schema loading has failures.
expr: |
sum(perses_plugin_schemas_load_attempts{status="error"}) > 0
sum by (pod, namespace) (increase(perses_plugin_schemas_load_attempts{status="error"}[15m])) > 0
for: 15m
labels:
severity: warning
Expand All @@ -55,8 +57,8 @@ groups:

- alert: PersesHighFileDescriptorUsage
annotations:
description: Perses is using {{`{{$value | humanize}}`}}% of available file descriptors.
summary: Perses file descriptor usage is high.
description: The pod {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}} is using {{`{{ $value | humanize }}`}}% of available file descriptors.
summary: High FD usage on {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}}
expr: |
(process_open_fds / process_max_fds) * 100 > 70
for: 15m
Expand Down
4 changes: 2 additions & 2 deletions perses/plugindefinition.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -3,15 +3,15 @@ kind: PluginDefinition
metadata:
name: perses
spec:
version: 0.10.1
version: 0.10.2
displayName: Perses
description: "Perses is a dashboard tooling to visualize metrics and traces produced by observability tools such as Prometheus/Thanos/Jaeger"
docMarkDownUrl: https://raw.githubusercontent.com/cloudoperators/greenhouse-extensions/main/perses/README.md
icon: https://raw.githubusercontent.com/cloudoperators/greenhouse-extensions/main/perses/logo.png
helmChart:
name: perses
repository: oci://ghcr.io/cloudoperators/greenhouse-extensions/charts
version: 0.17.2
version: 0.17.3
options:
- description: "The image version of the Perses app. If not provided, the latest version will be used"
name: perses.image.version
Expand Down
Loading