Skip to content

Commit bf093ed

Browse files
zalegralazalegrala
authored
Merge branch 'main' into feat-remove-svc-add-podmonitor
2 parents d37364f + 76072d4 commit bf093ed

File tree

12 files changed

+218
-22
lines changed

12 files changed

+218
-22
lines changed

‎charts/grafana/Chart.yaml

+2-2
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
apiVersion: v2
22
name: grafana
3-
version: 8.6.0
4-
appVersion: 11.3.0
3+
version: 8.6.4
4+
appVersion: 11.3.1
55
kubeVersion: "^1.8.0-0"
66
description: The leading tool for querying and visualizing time series and metrics.
77
home: https://grafana.com

‎charts/grafana/templates/_pod.tpl

+60
Original file line numberDiff line numberDiff line change
@@ -402,6 +402,18 @@ containers:
402402
- name: WATCH_CLIENT_TIMEOUT
403403
value: "{{ .Values.sidecar.alerts.watchClientTimeout }}"
404404
{{- end }}
405+
{{- if .Values.sidecar.alerts.maxTotalRetries }}
406+
- name: REQ_RETRY_TOTAL
407+
value: "{{ .Values.sidecar.alerts.maxTotalRetries }}"
408+
{{- end }}
409+
{{- if .Values.sidecar.alerts.maxConnectRetries }}
410+
- name: REQ_RETRY_CONNECT
411+
value: "{{ .Values.sidecar.alerts.maxConnectRetries }}"
412+
{{- end }}
413+
{{- if .Values.sidecar.alerts.maxReadRetries }}
414+
- name: REQ_RETRY_READ
415+
value: "{{ .Values.sidecar.alerts.maxReadRetries }}"
416+
{{- end }}
405417
{{- with .Values.sidecar.livenessProbe }}
406418
livenessProbe:
407419
{{- toYaml . | nindent 6 }}
@@ -518,6 +530,18 @@ containers:
518530
- name: WATCH_CLIENT_TIMEOUT
519531
value: {{ .Values.sidecar.dashboards.watchClientTimeout | quote }}
520532
{{- end }}
533+
{{- if .Values.sidecar.dashboards.maxTotalRetries }}
534+
- name: REQ_RETRY_TOTAL
535+
value: "{{ .Values.sidecar.dashboards.maxTotalRetries }}"
536+
{{- end }}
537+
{{- if .Values.sidecar.dashboards.maxConnectRetries }}
538+
- name: REQ_RETRY_CONNECT
539+
value: "{{ .Values.sidecar.dashboards.maxConnectRetries }}"
540+
{{- end }}
541+
{{- if .Values.sidecar.dashboards.maxReadRetries }}
542+
- name: REQ_RETRY_READ
543+
value: "{{ .Values.sidecar.dashboards.maxReadRetries }}"
544+
{{- end }}
521545
{{- with .Values.sidecar.livenessProbe }}
522546
livenessProbe:
523547
{{- toYaml . | nindent 6 }}
@@ -630,6 +654,18 @@ containers:
630654
- name: WATCH_CLIENT_TIMEOUT
631655
value: "{{ .Values.sidecar.datasources.watchClientTimeout }}"
632656
{{- end }}
657+
{{- if .Values.sidecar.datasources.maxTotalRetries }}
658+
- name: REQ_RETRY_TOTAL
659+
value: "{{ .Values.sidecar.datasources.maxTotalRetries }}"
660+
{{- end }}
661+
{{- if .Values.sidecar.datasources.maxConnectRetries }}
662+
- name: REQ_RETRY_CONNECT
663+
value: "{{ .Values.sidecar.datasources.maxConnectRetries }}"
664+
{{- end }}
665+
{{- if .Values.sidecar.datasources.maxReadRetries }}
666+
- name: REQ_RETRY_READ
667+
value: "{{ .Values.sidecar.datasources.maxReadRetries }}"
668+
{{- end }}
633669
{{- with .Values.sidecar.livenessProbe }}
634670
livenessProbe:
635671
{{- toYaml . | nindent 6 }}
@@ -737,6 +773,18 @@ containers:
737773
- name: WATCH_CLIENT_TIMEOUT
738774
value: "{{ .Values.sidecar.notifiers.watchClientTimeout }}"
739775
{{- end }}
776+
{{- if .Values.sidecar.notifiers.maxTotalRetries }}
777+
- name: REQ_RETRY_TOTAL
778+
value: "{{ .Values.sidecar.notifiers.maxTotalRetries }}"
779+
{{- end }}
780+
{{- if .Values.sidecar.notifiers.maxConnectRetries }}
781+
- name: REQ_RETRY_CONNECT
782+
value: "{{ .Values.sidecar.notifiers.maxConnectRetries }}"
783+
{{- end }}
784+
{{- if .Values.sidecar.notifiers.maxReadRetries }}
785+
- name: REQ_RETRY_READ
786+
value: "{{ .Values.sidecar.notifiers.maxReadRetries }}"
787+
{{- end }}
740788
{{- with .Values.sidecar.livenessProbe }}
741789
livenessProbe:
742790
{{- toYaml . | nindent 6 }}
@@ -844,6 +892,18 @@ containers:
844892
- name: WATCH_CLIENT_TIMEOUT
845893
value: "{{ .Values.sidecar.plugins.watchClientTimeout }}"
846894
{{- end }}
895+
{{- if .Values.sidecar.plugins.maxTotalRetries }}
896+
- name: REQ_RETRY_TOTAL
897+
value: "{{ .Values.sidecar.plugins.maxTotalRetries }}"
898+
{{- end }}
899+
{{- if .Values.sidecar.plugins.maxConnectRetries }}
900+
- name: REQ_RETRY_CONNECT
901+
value: "{{ .Values.sidecar.plugins.maxConnectRetries }}"
902+
{{- end }}
903+
{{- if .Values.sidecar.plugins.maxReadRetries }}
904+
- name: REQ_RETRY_READ
905+
value: "{{ .Values.sidecar.plugins.maxReadRetries }}"
906+
{{- end }}
847907
{{- with .Values.sidecar.livenessProbe }}
848908
livenessProbe:
849909
{{- toYaml . | nindent 6 }}

‎charts/grafana/templates/deployment.yaml

+1-1
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,7 @@ spec:
2828
template:
2929
metadata:
3030
labels:
31-
{{- include "grafana.selectorLabels" . | nindent 8 }}
31+
{{- include "grafana.labels" . | nindent 8 }}
3232
{{- with .Values.podLabels }}
3333
{{- toYaml . | nindent 8 }}
3434
{{- end }}

‎charts/grafana/templates/statefulset.yaml

+1-1
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ spec:
2020
template:
2121
metadata:
2222
labels:
23-
{{- include "grafana.selectorLabels" . | nindent 8 }}
23+
{{- include "grafana.labels" . | nindent 8 }}
2424
{{- with .Values.podLabels }}
2525
{{- toYaml . | nindent 8 }}
2626
{{- end }}

‎charts/grafana/values.yaml

+114-1
Original file line numberDiff line numberDiff line change
@@ -673,9 +673,15 @@ datasources: {}
673673
# - name: Prometheus
674674

675675
## Configure grafana alerting (can be templated)
676-
## ref: http://docs.grafana.org/administration/provisioning/#alerting
676+
## ref: https://docs.grafana.com/alerting/set-up/provision-alerting-resources/file-provisioning/
677677
##
678678
alerting: {}
679+
# policies.yaml:
680+
# apiVersion: 1
681+
# policies:
682+
# - orgId: 1
683+
# receiver: first_uid
684+
#
679685
# rules.yaml:
680686
# apiVersion: 1
681687
# groups:
@@ -720,6 +726,7 @@ alerting: {}
720726
# some_key: some_value
721727
# labels:
722728
# team: sre_team_1
729+
#
723730
# contactpoints.yaml:
724731
# secret:
725732
# apiVersion: 1
@@ -737,6 +744,26 @@ alerting: {}
737744
# group: app-stack
738745
# summary: |
739746
# {{ `{{ include "default.message" . }}` }}
747+
#
748+
# templates.yaml:
749+
# apiVersion: 1
750+
# templates:
751+
# - orgId: 1
752+
# name: my_first_template
753+
# template: |
754+
# {{ `
755+
# {{ define "my_first_template" }}
756+
# Custom notification message
757+
# {{ end }}
758+
# ` }}
759+
#
760+
# mutetimes.yaml
761+
# apiVersion: 1
762+
# muteTimes:
763+
# - orgId: 1
764+
# name: mti_1
765+
# # refer to https://prometheus.io/docs/alerting/latest/configuration/#time_interval-0
766+
# time_intervals: {}
740767

741768
## Configure notifiers
742769
## ref: http://docs.grafana.org/administration/provisioning/#alert-notification-channels
@@ -955,6 +982,23 @@ sidecar:
955982
# defaults to 66sec (sic!)
956983
# watchClientTimeout: 60
957984
#
985+
# maxTotalRetries: Total number of retries to allow for any http request.
986+
# Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
987+
# Set to 0 to fail on the first retry.
988+
# maxTotalRetries: 5
989+
#
990+
# maxConnectRetries: How many connection-related errors to retry on for any http request.
991+
# These are errors raised before the request is sent to the remote server, which we assume has not triggered the server to process the request.
992+
# Applies to all requests to reloadURL and k8s api requests.
993+
# Set to 0 to fail on the first retry of this type.
994+
# maxConnectRetries: 10
995+
#
996+
# maxReadRetries: How many times to retry on read errors for any http request
997+
# These errors are raised after the request was sent to the server, so the request may have side-effects.
998+
# Applies to all requests to reloadURL and k8s api requests.
999+
# Set to 0 to fail on the first retry of this type.
1000+
# maxReadRetries: 5
1001+
#
9581002
# Endpoint to send request to reload alerts
9591003
reloadURL: "http://localhost:3000/api/admin/provisioning/alerting/reload"
9601004
# Absolute path to shell script to execute after a alert got reloaded
@@ -1008,6 +1052,24 @@ sidecar:
10081052
# If specified, the sidecar will look for annotation with this name to create folder and put graph here.
10091053
# You can use this parameter together with `provider.foldersFromFilesStructure`to annotate configmaps and create folder structure.
10101054
folderAnnotation: null
1055+
#
1056+
# maxTotalRetries: Total number of retries to allow for any http request.
1057+
# Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
1058+
# Set to 0 to fail on the first retry.
1059+
# maxTotalRetries: 5
1060+
#
1061+
# maxConnectRetries: How many connection-related errors to retry on for any http request.
1062+
# These are errors raised before the request is sent to the remote server, which we assume has not triggered the server to process the request.
1063+
# Applies to all requests to reloadURL and k8s api requests.
1064+
# Set to 0 to fail on the first retry of this type.
1065+
# maxConnectRetries: 10
1066+
#
1067+
# maxReadRetries: How many times to retry on read errors for any http request
1068+
# These errors are raised after the request was sent to the server, so the request may have side-effects.
1069+
# Applies to all requests to reloadURL and k8s api requests.
1070+
# Set to 0 to fail on the first retry of this type.
1071+
# maxReadRetries: 5
1072+
#
10111073
# Endpoint to send request to reload alerts
10121074
reloadURL: "http://localhost:3000/api/admin/provisioning/dashboards/reload"
10131075
# Absolute path to shell script to execute after a configmap got reloaded
@@ -1088,6 +1150,23 @@ sidecar:
10881150
# defaults to 66sec (sic!)
10891151
# watchClientTimeout: 60
10901152
#
1153+
# maxTotalRetries: Total number of retries to allow for any http request.
1154+
# Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
1155+
# Set to 0 to fail on the first retry.
1156+
# maxTotalRetries: 5
1157+
#
1158+
# maxConnectRetries: How many connection-related errors to retry on for any http request.
1159+
# These are errors raised before the request is sent to the remote server, which we assume has not triggered the server to process the request.
1160+
# Applies to all requests to reloadURL and k8s api requests.
1161+
# Set to 0 to fail on the first retry of this type.
1162+
# maxConnectRetries: 10
1163+
#
1164+
# maxReadRetries: How many times to retry on read errors for any http request
1165+
# These errors are raised after the request was sent to the server, so the request may have side-effects.
1166+
# Applies to all requests to reloadURL and k8s api requests.
1167+
# Set to 0 to fail on the first retry of this type.
1168+
# maxReadRetries: 5
1169+
#
10911170
# Endpoint to send request to reload datasources
10921171
reloadURL: "http://localhost:3000/api/admin/provisioning/datasources/reload"
10931172
# Absolute path to shell script to execute after a datasource got reloaded
@@ -1130,6 +1209,23 @@ sidecar:
11301209
# defaults to 66sec (sic!)
11311210
# watchClientTimeout: 60
11321211
#
1212+
# maxTotalRetries: Total number of retries to allow for any http request.
1213+
# Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
1214+
# Set to 0 to fail on the first retry.
1215+
# maxTotalRetries: 5
1216+
#
1217+
# maxConnectRetries: How many connection-related errors to retry on for any http request.
1218+
# These are errors raised before the request is sent to the remote server, which we assume has not triggered the server to process the request.
1219+
# Applies to all requests to reloadURL and k8s api requests.
1220+
# Set to 0 to fail on the first retry of this type.
1221+
# maxConnectRetries: 10
1222+
#
1223+
# maxReadRetries: How many times to retry on read errors for any http request
1224+
# These errors are raised after the request was sent to the server, so the request may have side-effects.
1225+
# Applies to all requests to reloadURL and k8s api requests.
1226+
# Set to 0 to fail on the first retry of this type.
1227+
# maxReadRetries: 5
1228+
#
11331229
# Endpoint to send request to reload plugins
11341230
reloadURL: "http://localhost:3000/api/admin/provisioning/plugins/reload"
11351231
# Absolute path to shell script to execute after a plugin got reloaded
@@ -1172,6 +1268,23 @@ sidecar:
11721268
# defaults to 66sec (sic!)
11731269
# watchClientTimeout: 60
11741270
#
1271+
# maxTotalRetries: Total number of retries to allow for any http request.
1272+
# Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
1273+
# Set to 0 to fail on the first retry.
1274+
# maxTotalRetries: 5
1275+
#
1276+
# maxConnectRetries: How many connection-related errors to retry on for any http request.
1277+
# These are errors raised before the request is sent to the remote server, which we assume has not triggered the server to process the request.
1278+
# Applies to all requests to reloadURL and k8s api requests.
1279+
# Set to 0 to fail on the first retry of this type.
1280+
# maxConnectRetries: 10
1281+
#
1282+
# maxReadRetries: How many times to retry on read errors for any http request
1283+
# These errors are raised after the request was sent to the server, so the request may have side-effects.
1284+
# Applies to all requests to reloadURL and k8s api requests.
1285+
# Set to 0 to fail on the first retry of this type.
1286+
# maxReadRetries: 5
1287+
#
11751288
# Endpoint to send request to reload notifiers
11761289
reloadURL: "http://localhost:3000/api/admin/provisioning/notifications/reload"
11771290
# Absolute path to shell script to execute after a notifier got reloaded

‎charts/rollout-operator/Chart.yaml

+2-2
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@ apiVersion: v2
22
name: rollout-operator
33
description: "Grafana rollout-operator"
44
type: application
5-
version: 0.19.1
6-
appVersion: v0.19.1
5+
version: 0.21.0
6+
appVersion: v0.21.0
77
home: https://github.com/grafana/rollout-operator
88
kubeVersion: ^1.10.0-0

‎charts/rollout-operator/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ Helm chart for deploying [Grafana rollout-operator](https://github.com/grafana/r
44

55
# rollout-operator
66

7-
![Version: 0.19.1](https://img.shields.io/badge/Version-0.19.1-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: v0.19.1](https://img.shields.io/badge/AppVersion-v0.19.1-informational?style=flat-square)
7+
![Version: 0.21.0](https://img.shields.io/badge/Version-0.21.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: v0.21.0](https://img.shields.io/badge/AppVersion-v0.21.0-informational?style=flat-square)
88

99
Grafana rollout-operator
1010

‎charts/tempo-distributed/Chart.yaml

+1-1
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@ apiVersion: v2
22
name: tempo-distributed
33
description: Grafana Tempo in MicroService mode
44
type: application
5-
version: 1.22.2
5+
version: 1.23.2
66
appVersion: 2.6.0
77
engine: gotpl
88
home: https://grafana.com/docs/tempo/latest/

‎charts/tempo-distributed/README.md

+8-2
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# tempo-distributed
22

3-
![Version: 1.22.2](https://img.shields.io/badge/Version-1.22.2-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 2.6.0](https://img.shields.io/badge/AppVersion-2.6.0-informational?style=flat-square)
3+
![Version: 1.23.2](https://img.shields.io/badge/Version-1.23.2-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 2.6.0](https://img.shields.io/badge/AppVersion-2.6.0-informational?style=flat-square)
44

55
Grafana Tempo in MicroService mode
66

@@ -752,7 +752,13 @@ The memcached default args are removed and should be provided manually. The sett
752752
| queryFrontend.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the query-frontend |
753753
| queryFrontend.config.max_outstanding_per_tenant | int | `2000` | Maximum number of outstanding requests per tenant per frontend; requests beyond this error with HTTP 429. |
754754
| queryFrontend.config.max_retries | int | `2` | Number of times to retry a request sent to a querier |
755-
| queryFrontend.config.metrics.max_duration | string | `"3h"` | |
755+
| queryFrontend.config.metrics.concurrent_jobs | int | `1000` | The number of concurrent jobs to execute when querying the backend. |
756+
| queryFrontend.config.metrics.duration_slo | string | `"0s"` | If set to a non-zero value, it's value will be used to decide if query is within SLO or not. Query is within SLO if it returned 200 within duration_slo seconds OR processed throughput_slo bytes/s data. NOTE: `duration_slo` and `throughput_bytes_slo` both must be configured for it to work |
757+
| queryFrontend.config.metrics.interval | string | `"5m"` | The target length of time for each job to handle when querying the backend. |
758+
| queryFrontend.config.metrics.max_duration | string | `"3h"` | The maximum allowed time range for a metrics query. 0 disables this limit. |
759+
| queryFrontend.config.metrics.query_backend_after | string | `"30m"` | query_backend_after controls where the query-frontend searches for traces. Time ranges older than query_backend_after will be searched in the backend/object storage only. Time ranges between query_backend_after and now will be queried from the metrics-generators. |
760+
| queryFrontend.config.metrics.target_bytes_per_job | int | `104857600` | The target number of bytes for each job to handle when querying the backend. |
761+
| queryFrontend.config.metrics.throughput_bytes_slo | int | `0` | If set to a non-zero value, it's value will be used to decide if query is within SLO or not. Query is within SLO if it returned 200 within duration_slo seconds OR processed throughput_slo bytes/s data. |
756762
| queryFrontend.config.search.concurrent_jobs | int | `1000` | The number of concurrent jobs to execute when searching the backend |
757763
| queryFrontend.config.search.target_bytes_per_job | int | `104857600` | The target number of bytes for each job to handle when performing a backend search |
758764
| queryFrontend.config.trace_by_id | object | `{"query_shards":50}` | Trace by ID lookup configuration |

‎charts/tempo-distributed/templates/ingester/_helpers-ingester.tpl

+4-6
Original file line numberDiff line numberDiff line change
@@ -13,12 +13,10 @@
1313
{{- $requestedReplicas := .ctx.Values.ingester.replicas -}}
1414
{{- $replicaPerZone := div (add $requestedReplicas $numberOfZones -1) $numberOfZones -}}
1515
{{- range $idx, $rolloutZone := .ctx.Values.ingester.zoneAwareReplication.zones -}}
16-
{{- $_ := set $zonesMap $rolloutZone.name (dict
17-
"affinity" (($rolloutZone.extraAffinity | default (dict)) | mergeOverwrite (include "ingester.zoneAntiAffinity" (dict "rolloutZoneName" $rolloutZone.name "topologyKey" $.ctx.Values.ingester.zoneAwareReplication.topologyKey) | fromYaml))
18-
"nodeSelector" ($rolloutZone.nodeSelector | default (dict) )
19-
"replicas" $replicaPerZone
20-
"storageClass" $rolloutZone.storageClass
21-
) -}}
16+
{{- $extraAffinity := $rolloutZone.extraAffinity | default (dict) -}}
17+
{{- $zoneAntiAffinity := include "ingester.zoneAntiAffinity" (dict "rolloutZoneName" $rolloutZone.name "topologyKey" $.ctx.Values.ingester.zoneAwareReplication.topologyKey) | fromYaml -}}
18+
{{- $mergedAffinity := mergeOverwrite $extraAffinity $zoneAntiAffinity -}}
19+
{{- $_ := set $zonesMap $rolloutZone.name (dict "affinity" $mergedAffinity "nodeSelector" ($rolloutZone.nodeSelector | default (dict)) "replicas" $replicaPerZone "storageClass" $rolloutZone.storageClass) -}}
2220
{{- end -}}
2321
{{- else -}}
2422
{{- $_ := set $zonesMap "" $defaultZone -}}

‎charts/tempo-distributed/templates/ingester/statefulset-ingester.yaml

-3
Original file line numberDiff line numberDiff line change
@@ -42,9 +42,6 @@ spec:
4242
{{- with .Values.tempo.podLabels }}
4343
{{- toYaml . | nindent 8 }}
4444
{{- end }}
45-
{{- with .Values.ingester.podLabels }}
46-
{{- toYaml . | nindent 8 }}
47-
{{- end }}
4845
annotations:
4946
checksum/config: {{ include (print $.Template.BasePath "/configmap-tempo.yaml") . | sha256sum }}
5047
{{- with .Values.tempo.podAnnotations }}

0 commit comments

Comments
 (0)