Merge branch 'main' into tempo_add_topology_spread_constraints

charts/grafana/Chart.yaml

@@ -1,6 +1,6 @@
 apiVersion: v2
 name: grafana
-version: 8.6.3
+version: 8.6.4
 appVersion: 11.3.1
 kubeVersion: "^1.8.0-0"
 description: The leading tool for querying and visualizing time series and metrics.

charts/grafana/templates/_pod.tpl

@@ -402,6 +402,18 @@ containers:
       - name: WATCH_CLIENT_TIMEOUT
         value: "{{ .Values.sidecar.alerts.watchClientTimeout }}"
       {{- end }}
+      {{- if .Values.sidecar.alerts.maxTotalRetries }}
+      - name: REQ_RETRY_TOTAL
+        value: "{{ .Values.sidecar.alerts.maxTotalRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.alerts.maxConnectRetries }}
+      - name: REQ_RETRY_CONNECT
+        value: "{{ .Values.sidecar.alerts.maxConnectRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.alerts.maxReadRetries }}
+      - name: REQ_RETRY_READ
+        value: "{{ .Values.sidecar.alerts.maxReadRetries }}"
+      {{- end }}
     {{- with .Values.sidecar.livenessProbe }}
     livenessProbe:
       {{- toYaml . | nindent 6 }}
@@ -518,6 +530,18 @@ containers:
       - name: WATCH_CLIENT_TIMEOUT
         value: {{ .Values.sidecar.dashboards.watchClientTimeout | quote }}
       {{- end }}
+      {{- if .Values.sidecar.dashboards.maxTotalRetries }}
+      - name: REQ_RETRY_TOTAL
+        value: "{{ .Values.sidecar.dashboards.maxTotalRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.dashboards.maxConnectRetries }}
+      - name: REQ_RETRY_CONNECT
+        value: "{{ .Values.sidecar.dashboards.maxConnectRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.dashboards.maxReadRetries }}
+      - name: REQ_RETRY_READ
+        value: "{{ .Values.sidecar.dashboards.maxReadRetries }}"
+      {{- end }}
     {{- with .Values.sidecar.livenessProbe }}
     livenessProbe:
       {{- toYaml . | nindent 6 }}
@@ -630,6 +654,18 @@ containers:
       - name: WATCH_CLIENT_TIMEOUT
         value: "{{ .Values.sidecar.datasources.watchClientTimeout }}"
       {{- end }}
+      {{- if .Values.sidecar.datasources.maxTotalRetries }}
+      - name: REQ_RETRY_TOTAL
+        value: "{{ .Values.sidecar.datasources.maxTotalRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.datasources.maxConnectRetries }}
+      - name: REQ_RETRY_CONNECT
+        value: "{{ .Values.sidecar.datasources.maxConnectRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.datasources.maxReadRetries }}
+      - name: REQ_RETRY_READ
+        value: "{{ .Values.sidecar.datasources.maxReadRetries }}"
+      {{- end }}
     {{- with .Values.sidecar.livenessProbe }}
     livenessProbe:
       {{- toYaml . | nindent 6 }}
@@ -737,6 +773,18 @@ containers:
       - name: WATCH_CLIENT_TIMEOUT
         value: "{{ .Values.sidecar.notifiers.watchClientTimeout }}"
       {{- end }}
+      {{- if .Values.sidecar.notifiers.maxTotalRetries }}
+      - name: REQ_RETRY_TOTAL
+        value: "{{ .Values.sidecar.notifiers.maxTotalRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.notifiers.maxConnectRetries }}
+      - name: REQ_RETRY_CONNECT
+        value: "{{ .Values.sidecar.notifiers.maxConnectRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.notifiers.maxReadRetries }}
+      - name: REQ_RETRY_READ
+        value: "{{ .Values.sidecar.notifiers.maxReadRetries }}"
+      {{- end }}
     {{- with .Values.sidecar.livenessProbe }}
     livenessProbe:
       {{- toYaml . | nindent 6 }}
@@ -844,6 +892,18 @@ containers:
       - name: WATCH_CLIENT_TIMEOUT
         value: "{{ .Values.sidecar.plugins.watchClientTimeout }}"
       {{- end }}
+      {{- if .Values.sidecar.plugins.maxTotalRetries }}
+      - name: REQ_RETRY_TOTAL
+        value: "{{ .Values.sidecar.plugins.maxTotalRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.plugins.maxConnectRetries }}
+      - name: REQ_RETRY_CONNECT
+        value: "{{ .Values.sidecar.plugins.maxConnectRetries }}"
+      {{- end }}
+      {{- if .Values.sidecar.plugins.maxReadRetries }}
+      - name: REQ_RETRY_READ
+        value: "{{ .Values.sidecar.plugins.maxReadRetries }}"
+      {{- end }}
     {{- with .Values.sidecar.livenessProbe }}
     livenessProbe:
       {{- toYaml . | nindent 6 }}

charts/grafana/values.yaml

@@ -982,6 +982,23 @@ sidecar:
     # defaults to 66sec (sic!)
     # watchClientTimeout: 60
     #
+    # maxTotalRetries: Total number of retries to allow for any http request.
+    # Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry.
+    # maxTotalRetries: 5
+    #
+    # maxConnectRetries: How many connection-related errors to retry on for any http request.
+    # 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.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxConnectRetries: 10
+    #
+    # maxReadRetries: How many times to retry on read errors for any http request
+    # These errors are raised after the request was sent to the server, so the request may have side-effects.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxReadRetries: 5
+    #
     # Endpoint to send request to reload alerts
     reloadURL: "http://localhost:3000/api/admin/provisioning/alerting/reload"
     # Absolute path to shell script to execute after a alert got reloaded
@@ -1035,6 +1052,24 @@ sidecar:
     # If specified, the sidecar will look for annotation with this name to create folder and put graph here.
     # You can use this parameter together with `provider.foldersFromFilesStructure`to annotate configmaps and create folder structure.
     folderAnnotation: null
+    #
+    # maxTotalRetries: Total number of retries to allow for any http request.
+    # Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry.
+    # maxTotalRetries: 5
+    #
+    # maxConnectRetries: How many connection-related errors to retry on for any http request.
+    # 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.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxConnectRetries: 10
+    #
+    # maxReadRetries: How many times to retry on read errors for any http request
+    # These errors are raised after the request was sent to the server, so the request may have side-effects.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxReadRetries: 5
+    #
     # Endpoint to send request to reload alerts
     reloadURL: "http://localhost:3000/api/admin/provisioning/dashboards/reload"
     # Absolute path to shell script to execute after a configmap got reloaded
@@ -1115,6 +1150,23 @@ sidecar:
     # defaults to 66sec (sic!)
     # watchClientTimeout: 60
     #
+    # maxTotalRetries: Total number of retries to allow for any http request.
+    # Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry.
+    # maxTotalRetries: 5
+    #
+    # maxConnectRetries: How many connection-related errors to retry on for any http request.
+    # 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.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxConnectRetries: 10
+    #
+    # maxReadRetries: How many times to retry on read errors for any http request
+    # These errors are raised after the request was sent to the server, so the request may have side-effects.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxReadRetries: 5
+    #
     # Endpoint to send request to reload datasources
     reloadURL: "http://localhost:3000/api/admin/provisioning/datasources/reload"
     # Absolute path to shell script to execute after a datasource got reloaded
@@ -1157,6 +1209,23 @@ sidecar:
     # defaults to 66sec (sic!)
     # watchClientTimeout: 60
     #
+    # maxTotalRetries: Total number of retries to allow for any http request.
+    # Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry.
+    # maxTotalRetries: 5
+    #
+    # maxConnectRetries: How many connection-related errors to retry on for any http request.
+    # 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.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxConnectRetries: 10
+    #
+    # maxReadRetries: How many times to retry on read errors for any http request
+    # These errors are raised after the request was sent to the server, so the request may have side-effects.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxReadRetries: 5
+    #
     # Endpoint to send request to reload plugins
     reloadURL: "http://localhost:3000/api/admin/provisioning/plugins/reload"
     # Absolute path to shell script to execute after a plugin got reloaded
@@ -1199,6 +1268,23 @@ sidecar:
     # defaults to 66sec (sic!)
     # watchClientTimeout: 60
     #
+    # maxTotalRetries: Total number of retries to allow for any http request.
+    # Takes precedence over other counts. Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry.
+    # maxTotalRetries: 5
+    #
+    # maxConnectRetries: How many connection-related errors to retry on for any http request.
+    # 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.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxConnectRetries: 10
+    #
+    # maxReadRetries: How many times to retry on read errors for any http request
+    # These errors are raised after the request was sent to the server, so the request may have side-effects.
+    # Applies to all requests to reloadURL and k8s api requests.
+    # Set to 0 to fail on the first retry of this type.
+    # maxReadRetries: 5
+    #
     # Endpoint to send request to reload notifiers
     reloadURL: "http://localhost:3000/api/admin/provisioning/notifications/reload"
     # Absolute path to shell script to execute after a notifier got reloaded

charts/rollout-operator/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: rollout-operator
 description: "Grafana rollout-operator"
 type: application
-version: 0.20.0
-appVersion: v0.20.0
+version: 0.21.0
+appVersion: v0.21.0
 home: https://github.com/grafana/rollout-operator
 kubeVersion: ^1.10.0-0

charts/rollout-operator/README.md

@@ -4,7 +4,7 @@ Helm chart for deploying [Grafana rollout-operator](https://github.com/grafana/r
 
 # rollout-operator
 
-![Version: 0.20.0](https://img.shields.io/badge/Version-0.20.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: v0.20.0](https://img.shields.io/badge/AppVersion-v0.20.0-informational?style=flat-square)
+![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)
 
 Grafana rollout-operator
 

charts/tempo-distributed/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: tempo-distributed
 description: Grafana Tempo in MicroService mode
 type: application
-version: 1.23.1
+version: 1.23.2
 appVersion: 2.6.0
 engine: gotpl
 home: https://grafana.com/docs/tempo/latest/

charts/tempo-distributed/README.md

@@ -1,6 +1,6 @@
 # tempo-distributed
 
-![Version: 1.23.1](https://img.shields.io/badge/Version-1.23.1-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)
+![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)
 
 Grafana Tempo in MicroService mode
 

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

@@ -13,12 +13,10 @@
 {{- $requestedReplicas := .ctx.Values.ingester.replicas -}}
 {{- $replicaPerZone := div (add $requestedReplicas $numberOfZones -1) $numberOfZones -}}
 {{- range $idx, $rolloutZone := .ctx.Values.ingester.zoneAwareReplication.zones -}}
-{{- $_ := set $zonesMap $rolloutZone.name (dict
-"affinity" (($rolloutZone.extraAffinity | default (dict)) | mergeOverwrite (include "ingester.zoneAntiAffinity" (dict "rolloutZoneName" $rolloutZone.name "topologyKey" $.ctx.Values.ingester.zoneAwareReplication.topologyKey) | fromYaml))
-"nodeSelector" ($rolloutZone.nodeSelector | default (dict) )
-"replicas" $replicaPerZone
-"storageClass" $rolloutZone.storageClass
-) -}}
+{{- $extraAffinity := $rolloutZone.extraAffinity | default (dict) -}}
+{{- $zoneAntiAffinity := include "ingester.zoneAntiAffinity" (dict "rolloutZoneName" $rolloutZone.name "topologyKey" $.ctx.Values.ingester.zoneAwareReplication.topologyKey) | fromYaml -}}
+{{- $mergedAffinity := mergeOverwrite $extraAffinity $zoneAntiAffinity -}}
+{{- $_ := set $zonesMap $rolloutZone.name (dict "affinity" $mergedAffinity "nodeSelector" ($rolloutZone.nodeSelector | default (dict)) "replicas" $replicaPerZone  "storageClass" $rolloutZone.storageClass) -}}
 {{- end -}}
 {{- else -}}
 {{- $_ := set $zonesMap "" $defaultZone -}}

charts/tempo-vulture/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: tempo-vulture
 description: Grafana Tempo Vulture - A tool to monitor Tempo performance.
 type: application
-version: 0.7.0
+version: 0.7.1
 appVersion: 2.6.1
 engine: gotpl
 home: https://grafana.com/docs/tempo/latest/

charts/tempo-vulture/README.md

@@ -1,6 +1,6 @@
 # tempo-vulture
 
-![Version: 0.7.0](https://img.shields.io/badge/Version-0.7.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 2.6.1](https://img.shields.io/badge/AppVersion-2.6.1-informational?style=flat-square)
+![Version: 0.7.1](https://img.shields.io/badge/Version-0.7.1-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 2.6.1](https://img.shields.io/badge/AppVersion-2.6.1-informational?style=flat-square)
 
 Grafana Tempo Vulture - A tool to monitor Tempo performance.
 
@@ -64,20 +64,20 @@ tempoAddress:
 | nodeSelector | object | `{}` | Node selector for vulture pods |
 | podAnnotations | object | `{}` | Common annotations for all pods |
 | podLabels | object | `{}` | Common labels for all pods |
+| podMonitor.annotations | object | `{}` | PodMonitor annotations |
+| podMonitor.enabled | bool | `false` | If enabled, PodMonitor resources for Prometheus Operator are created |
+| podMonitor.interval | string | `nil` | PodMonitor scrape interval |
+| podMonitor.labels | object | `{}` | Additional PodMonitor labels |
+| podMonitor.namespace | string | `nil` | Alternative namespace for PodMonitor resources |
+| podMonitor.namespaceSelector | object | `{}` | Namespace selector for PodMonitor resources |
+| podMonitor.scrapeTimeout | string | `nil` | PodMonitor scrape timeout in Go duration format (e.g. 15s) |
 | replicas | int | `1` | Number of replicas of Tempo Vulture |
 | resources | object | `{}` | Resource requests and limits for the vulture |
 | revisionHistoryLimit | int | `10` | The number of old ReplicaSets to retain to allow rollback |
 | serviceAccount.annotations | object | `{}` | Annotations for the service account |
 | serviceAccount.create | bool | `true` | Specifies whether a ServiceAccount should be created |
 | serviceAccount.imagePullSecrets | list | `[]` | Image pull secrets for the service account |
 | serviceAccount.name | string | `nil` | The name of the ServiceAccount to use. If not set and create is true, a name is generated using the fullname template |
-| serviceMonitor.annotations | object | `{}` | ServiceMonitor annotations |
-| serviceMonitor.enabled | bool | `false` | If enabled, ServiceMonitor resources for Prometheus Operator are created |
-| serviceMonitor.interval | string | `nil` | ServiceMonitor scrape interval |
-| serviceMonitor.labels | object | `{}` | Additional ServiceMonitor labels |
-| serviceMonitor.namespace | string | `nil` | Alternative namespace for ServiceMonitor resources |
-| serviceMonitor.namespaceSelector | object | `{}` | Namespace selector for ServiceMonitor resources |
-| serviceMonitor.scrapeTimeout | string | `nil` | ServiceMonitor scrape timeout in Go duration format (e.g. 15s) |
 | tempoAddress.push | string | `nil` | the url towards your Tempo distributor, e.g. http://distributor |
 | tempoAddress.query | string | `nil` | the url towards your Tempo query-frontend, e.g. http://query-frontend:3100 |
 | tolerations | list | `[]` | Tolerations for vulture pods |

charts/tempo-vulture/templates/servicemonitor.yaml → charts/tempo-vulture/templates/podmonitor.yaml

@@ -1,7 +1,7 @@
-{{- with .Values.serviceMonitor }}
+{{- with .Values.podMonitor}}
 {{- if .enabled }}
 apiVersion: monitoring.coreos.com/v1
-kind: ServiceMonitor
+kind: PodMonitor
 metadata:
   name: {{ include "tempo-vulture.fullname" $ }}
   {{- with .namespace }}
@@ -24,7 +24,7 @@ spec:
   selector:
     matchLabels:
       {{- include "tempo-vulture.selectorLabels" $ | nindent 6 }}
-  endpoints:
+  podMetricsEndpoints:
     - port: prom-metrics
       {{- with .interval }}
       interval: {{ . }}

charts/tempo-vulture/values.yaml

@@ -58,21 +58,21 @@ serviceAccount:
   # -- Annotations for the service account
   annotations: {}
 
-# ServiceMonitor configuration
-serviceMonitor:
-  # -- If enabled, ServiceMonitor resources for Prometheus Operator are created
+# PodMonitor configuration
+podMonitor:
+  # -- If enabled, PodMonitor resources for Prometheus Operator are created
   enabled: false
-  # -- Alternative namespace for ServiceMonitor resources
+  # -- Alternative namespace for PodMonitor resources
   namespace: null
-  # -- Namespace selector for ServiceMonitor resources
+  # -- Namespace selector for PodMonitor resources
   namespaceSelector: {}
-  # -- ServiceMonitor annotations
+  # -- PodMonitor annotations
   annotations: {}
-  # -- Additional ServiceMonitor labels
+  # -- Additional PodMonitor labels
   labels: {}
-  # -- ServiceMonitor scrape interval
+  # -- PodMonitor scrape interval
   interval: null
-  # -- ServiceMonitor scrape timeout in Go duration format (e.g. 15s)
+  # -- PodMonitor scrape timeout in Go duration format (e.g. 15s)
   scrapeTimeout: null
 
 tempoAddress: