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

KEDA autoscaling additional requirement #10266

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

KEDA autoscaling additional requirement #10266

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5180939
Add extra fields for keda triggers and add authentication
bjorns163 Dec 13, 2024
06148db
Merge branch 'grafana:main' into keda-fields
bjorns163 Dec 16, 2024
2eb4f0b
Add customLabelFilter
bjorns163 Dec 17, 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
1 change: 1 addition & 0 deletions operations/helm/charts/mimir-distributed/CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@ Entries should include a reference to the Pull Request that introduced the chang

## main / unreleased

* [ENHANCEMENT] Add extra values for KEDA auto scaling. #10265
* [CHANGE] Update rollout-operator version to 0.20.0. #9995
* [CHANGE] Remove the `track_sizes` feature for Memcached pods since it is unused. #10032
* [FEATURE] Add support for GEM's federation-frontend. See the `federation_frontend` section in the values file. #9673
Expand Down
26 changes: 22 additions & 4 deletions operations/helm/charts/mimir-distributed/templates/distributor/distributor-so.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,21 +24,39 @@ spec:
kind: Deployment
triggers:
- metadata:
query: max_over_time(sum(sum by (pod) (rate(container_cpu_usage_seconds_total{container="distributor",namespace="{{ .Release.Namespace }}"}[5m])) and max by (pod) (up{container="distributor",namespace="{{ .Release.Namespace }}"}) > 0)[15m:]) * 1000
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
query: max_over_time(sum(sum by (pod) (rate(container_cpu_usage_seconds_total{container="distributor",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[5m])) and max by (pod) (up{container="distributor",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}) > 0)[15m:]) * 1000
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
{{- $cpu_request := dig "requests" "cpu" nil .Values.distributor.resources }}
threshold: {{ mulf (include "mimir.cpuToMilliCPU" (dict "value" $cpu_request)) (divf .Values.distributor.kedaAutoscaling.targetCPUUtilizationPercentage 100) | floor | int64 | quote }}
{{- if .Values.kedaAutoscaling.customHeaders }}
customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }}
{{- end }}
ignoreNullValues: "{{ .Values.kedaAutoscaling.ignoreNullValues }}"
unsafeSsl: "{{ .Values.kedaAutoscaling.unsafeSsl }}"
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authModes: "{{ .Values.kedaAutoscaling.authentication.authModes }}"
{{- end }}
type: prometheus
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authenticationRef:
name: keda-triggger-auth
{{- end }}
- metadata:
query: max_over_time(sum((sum by (pod) (container_memory_working_set_bytes{container="distributor",namespace="{{ .Release.Namespace }}"}) and max by (pod) (up{container="distributor",namespace="{{ .Release.Namespace }}"}) > 0) or vector(0))[15m:]) + sum(sum by (pod) (max_over_time(kube_pod_container_resource_requests{container="distributor",namespace="{{ .Release.Namespace }}", resource="memory"}[15m])) and max by (pod) (changes(kube_pod_container_status_restarts_total{container="distributor",namespace="{{ .Release.Namespace }}"}[15m]) > 0) and max by (pod) (kube_pod_container_status_last_terminated_reason{container="distributor",namespace="{{ .Release.Namespace }}", reason="OOMKilled"}) or vector(0))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
query: max_over_time(sum((sum by (pod) (container_memory_working_set_bytes{container="distributor",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}) and max by (pod) (up{container="distributor",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}) > 0) or vector(0))[15m:]) + sum(sum by (pod) (max_over_time(kube_pod_container_resource_requests{container="distributor",namespace="{{ .Release.Namespace }}", resource="memory"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[15m])) and max by (pod) (changes(kube_pod_container_status_restarts_total{container="distributor",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[15m]) > 0) and max by (pod) (kube_pod_container_status_last_terminated_reason{container="distributor",namespace="{{ .Release.Namespace }}", reason="OOMKilled"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}) or vector(0))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
{{- $mem_request := dig "requests" "memory" nil .Values.distributor.resources }}
threshold: {{ mulf (include "mimir.siToBytes" (dict "value" $mem_request)) (divf .Values.distributor.kedaAutoscaling.targetMemoryUtilizationPercentage 100) | floor | int64 | quote }}
{{- if .Values.kedaAutoscaling.customHeaders }}
customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }}
{{- end }}
ignoreNullValues: "{{ .Values.kedaAutoscaling.ignoreNullValues }}"
unsafeSsl: "{{ .Values.kedaAutoscaling.unsafeSsl }}"
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authModes: "{{ .Values.kedaAutoscaling.authentication.authModes }}"
{{- end }}
type: prometheus
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authenticationRef:
name: keda-triggger-auth
{{- end }}
{{- end }}
12 changes: 12 additions & 0 deletions operations/helm/charts/mimir-distributed/templates/keda/keda-trigger-auth.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
{{- if .Values.kedaAutoscaling.authentication.enabled }}
apiVersion: keda.sh/v1alpha1
kind: TriggerAuthentication
metadata:
name: keda-triggger-auth
namespace: {{ .Release.Namespace | quote }}
spec:
secretTargetRef:
{{- with .Values.kedaAutoscaling.authentication.secretTargetRef }}
{{- toYaml . | nindent 2 }}
{{- end }}
{{- end }}
17 changes: 17 additions & 0 deletions operations/helm/charts/mimir-distributed/templates/lib/CustomLabels.tpl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
{{/*
Convert labels to string like: key1=value1, key2=value2, ...
Example:
customLabelFilter:
cluster: "my-cluster-name"
becomes:
cluster="my-cluster-name"
*/}}
{{- define "customLabelFilter" -}}
{{- if . }}
{{- $labels := "" }}
{{- range $key, $value := . }}
{{- $labels = printf "%s%s=\"%s\"," $labels $key $value }}
{{- end }}
{{- trimSuffix "," $labels -}}
{{- end }}
{{- end }}
37 changes: 32 additions & 5 deletions operations/helm/charts/mimir-distributed/templates/querier/querier-so.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,33 +27,60 @@ spec:
kind: Deployment
triggers:
- metadata:
query: sum(max_over_time(cortex_query_scheduler_inflight_requests{container="query-scheduler",namespace="{{ .Release.Namespace }}",quantile="0.5"}[1m]))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
query: sum(max_over_time(cortex_query_scheduler_inflight_requests{container="query-scheduler",namespace="{{ .Release.Namespace }}",quantile="0.5"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[1m]))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
threshold: {{ .Values.querier.kedaAutoscaling.querySchedulerInflightRequestsThreshold | quote }}
{{- if .Values.kedaAutoscaling.customHeaders }}
customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }}
{{- end }}
ignoreNullValues: "{{ .Values.kedaAutoscaling.ignoreNullValues }}"
unsafeSsl: "{{ .Values.kedaAutoscaling.unsafeSsl }}"
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authModes: "{{ .Values.kedaAutoscaling.authentication.authModes }}"
{{- end }}
name: cortex_querier_hpa_default
type: prometheus
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authenticationRef:
name: keda-triggger-auth
{{- end }}
- metadata:
query: sum(rate(cortex_querier_request_duration_seconds_sum{container="querier",namespace="{{ .Release.Namespace }}"}[1m]))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
query: sum(rate(cortex_querier_request_duration_seconds_sum{container="querier",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[1m]))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
threshold: {{ .Values.querier.kedaAutoscaling.querySchedulerInflightRequestsThreshold | quote }}
{{- if .Values.kedaAutoscaling.customHeaders }}
customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }}
{{- end }}
ignoreNullValues: "{{ .Values.kedaAutoscaling.ignoreNullValues }}"
unsafeSsl: "{{ .Values.kedaAutoscaling.unsafeSsl }}"
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authModes: "{{ .Values.kedaAutoscaling.authentication.authModes }}"
{{- end }}
name: cortex_querier_hpa_default_requests_duration
type: prometheus
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authenticationRef:
name: keda-triggger-auth
{{- end }}
{{- $autoscaling := .Values.querier.kedaAutoscaling -}}
{{- if .Values.querier.kedaAutoscaling.predictiveScalingEnabled }}
- metadata:
query: sum(max_over_time(cortex_query_scheduler_inflight_requests{container="query-scheduler",namespace="{{ .Release.Namespace }}",quantile="0.5"}[{{$autoscaling.predictiveScalingLookback}}] offset {{$autoscaling.predictiveScalingPeriod}}))
query: sum(max_over_time(cortex_query_scheduler_inflight_requests{container="query-scheduler",namespace="{{ .Release.Namespace }}",quantile="0.5"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[{{$autoscaling.predictiveScalingLookback}}] offset {{$autoscaling.predictiveScalingPeriod}}))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
threshold: {{ $autoscaling.querySchedulerInflightRequestsThreshold | quote }}
{{- if .Values.kedaAutoscaling.customHeaders }}
customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }}
{{- end }}
ignoreNullValues: "{{ .Values.kedaAutoscaling.ignoreNullValues }}"
unsafeSsl: "{{ .Values.kedaAutoscaling.unsafeSsl }}"
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authModes: "{{ .Values.kedaAutoscaling.authentication.authModes }}"
{{- end }}
name: cortex_querier_hpa_default_predictive
type: prometheus
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authenticationRef:
name: keda-triggger-auth
{{- end }}
{{- end }}
{{- end }}
26 changes: 22 additions & 4 deletions operations/helm/charts/mimir-distributed/templates/query-frontend/query-frontend-so.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,21 +24,39 @@ spec:
kind: Deployment
triggers:
- metadata:
query: max_over_time(sum(sum by (pod) (rate(container_cpu_usage_seconds_total{container="query-frontend",namespace="{{ .Release.Namespace }}"}[5m])) and max by (pod) (up{container="query-frontend",namespace="{{ .Release.Namespace }}"}) > 0)[15m:]) * 1000
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
query: max_over_time(sum(sum by (pod) (rate(container_cpu_usage_seconds_total{container="query-frontend",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[5m])) and max by (pod) (up{container="query-frontend",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}) > 0)[15m:]) * 1000
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
{{- $cpu_request := dig "requests" "cpu" nil .Values.query_frontend.resources }}
threshold: {{ mulf (include "mimir.cpuToMilliCPU" (dict "value" $cpu_request)) (divf .Values.query_frontend.kedaAutoscaling.targetCPUUtilizationPercentage 100) | floor | int64 | quote }}
{{- if .Values.kedaAutoscaling.customHeaders }}
customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }}
{{- end }}
ignoreNullValues: "{{ .Values.kedaAutoscaling.ignoreNullValues }}"
unsafeSsl: "{{ .Values.kedaAutoscaling.unsafeSsl }}"
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authModes: "{{ .Values.kedaAutoscaling.authentication.authModes }}"
{{- end }}
type: prometheus
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authenticationRef:
name: keda-triggger-auth
{{- end }}
- metadata:
query: max_over_time(sum((sum by (pod) (container_memory_working_set_bytes{container="query-frontend",namespace="{{ .Release.Namespace }}"}) and max by (pod) (up{container="query-frontend",namespace="{{ .Release.Namespace }}"}) > 0) or vector(0))[15m:]) + sum(sum by (pod) (max_over_time(kube_pod_container_resource_requests{container="query-frontend",namespace="{{ .Release.Namespace }}", resource="memory"}[15m])) and max by (pod) (changes(kube_pod_container_status_restarts_total{container="query-frontend",namespace="{{ .Release.Namespace }}"}[15m]) > 0) and max by (pod) (kube_pod_container_status_last_terminated_reason{container="query-frontend",namespace="{{ .Release.Namespace }}", reason="OOMKilled"}) or vector(0))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
query: max_over_time(sum((sum by (pod) (container_memory_working_set_bytes{container="query-frontend",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}) and max by (pod) (up{container="query-frontend",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}) > 0) or vector(0))[15m:]) + sum(sum by (pod) (max_over_time(kube_pod_container_resource_requests{container="query-frontend",namespace="{{ .Release.Namespace }}", resource="memory"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[15m])) and max by (pod) (changes(kube_pod_container_status_restarts_total{container="query-frontend",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[15m]) > 0) and max by (pod) (kube_pod_container_status_last_terminated_reason{container="query-frontend",namespace="{{ .Release.Namespace }}", reason="OOMKilled"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}) or vector(0))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
{{- $mem_request := dig "requests" "memory" nil .Values.query_frontend.resources }}
threshold: {{ mulf (include "mimir.siToBytes" (dict "value" $mem_request)) (divf .Values.query_frontend.kedaAutoscaling.targetMemoryUtilizationPercentage 100) | floor | int64 | quote }}
{{- if .Values.kedaAutoscaling.customHeaders }}
customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }}
{{- end }}
ignoreNullValues: "{{ .Values.kedaAutoscaling.ignoreNullValues }}"
unsafeSsl: "{{ .Values.kedaAutoscaling.unsafeSsl }}"
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authModes: "{{ .Values.kedaAutoscaling.authentication.authModes }}"
{{- end }}
type: prometheus
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authenticationRef:
name: keda-triggger-auth
{{- end }}
{{- end }}
26 changes: 22 additions & 4 deletions operations/helm/charts/mimir-distributed/templates/ruler-querier/ruler-querier-so.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,22 +25,40 @@ spec:
kind: Deployment
triggers:
- metadata:
query: sum(max_over_time(cortex_query_scheduler_inflight_requests{container="ruler-query-scheduler",namespace="{{ .Release.Namespace }}",quantile="0.5"}[1m]))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
query: sum(max_over_time(cortex_query_scheduler_inflight_requests{container="ruler-query-scheduler",namespace="{{ .Release.Namespace }}",quantile="0.5"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[1m]))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
threshold: {{ .Values.ruler_querier.kedaAutoscaling.querySchedulerInflightRequestsThreshold | quote }}
{{- if .Values.kedaAutoscaling.customHeaders }}
customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }}
{{- end }}
ignoreNullValues: "{{ .Values.kedaAutoscaling.ignoreNullValues }}"
unsafeSsl: "{{ .Values.kedaAutoscaling.unsafeSsl }}"
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authModes: "{{ .Values.kedaAutoscaling.authentication.authModes }}"
{{- end }}
name: cortex_querier_hpa_default
type: prometheus
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authenticationRef:
name: keda-triggger-auth
{{- end }}
- metadata:
query: sum(rate(cortex_querier_request_duration_seconds_sum{container="ruler-querier",namespace="{{ .Release.Namespace }}"}[1m]))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
query: sum(rate(cortex_querier_request_duration_seconds_sum{container="ruler-querier",namespace="{{ .Release.Namespace }}"{{- if .Values.kedaAutoscaling.customLabelFilter }}, {{ include "customLabelFilter" .Values.kedaAutoscaling.customLabelFilter }}{{- end }}}[1m]))
serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }}
threshold: {{ .Values.ruler_querier.kedaAutoscaling.querySchedulerInflightRequestsThreshold | quote }}
{{- if .Values.kedaAutoscaling.customHeaders }}
customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }}
{{- end }}
ignoreNullValues: "{{ .Values.kedaAutoscaling.ignoreNullValues }}"
unsafeSsl: "{{ .Values.kedaAutoscaling.unsafeSsl }}"
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authModes: "{{ .Values.kedaAutoscaling.authentication.authModes }}"
{{- end }}
name: cortex_querier_hpa_default_requests_duration
type: prometheus
{{- if .Values.kedaAutoscaling.authentication.enabled }}
authenticationRef:
name: keda-triggger-auth
{{- end }}
{{- end }}
{{- end }}
Loading
Loading