feat: helm chart for clickhouse setup (#479)

* minor change for volume permission spec

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* added basic files of clickhouse chart

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* added a simple deployment yaml

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* added clickhouse support in signoz

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* clickhouse working

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* chore: helm charts wip

* chore: fixing path of otel-path in hotrod

* chore: wip running clickhouse in templates

* chore: clickhouse working in templates

* chore: clickhouse helm chart upgraded to latest query-service and frontend images

* chore: cleanup and upgrading signoz chart version

* chore: adding alertmanager and minor fixes

* chore: persistence enabled for query-service and clickhouse

* chore: scrape interval reduced to 30s

* chore: changed crd api version from v1beta1 to v1

* chore: removed druid parts in values.yaml

* chore: log container removed from clickhouse

* chore: removed *.tgz from gitignore to add charts

* chore: added dependency charts

* chore: added clickhouse-operator templates

Co-authored-by: Yash Sharma <yashrsharma44@gmail.com>

.gitignore

@@ -35,7 +35,6 @@ frontend/cypress.env.json
 .idea
 
 **/.vscode
-*.tgz
 **/build
 **/storage
 **/locust-scripts/__pycache__/

deploy/kubernetes/jobs/retention/retention-config.yaml

@@ -1,7 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: retention-config
-data:
-  retention-spec.json: |
-    [{"period":"P3D","includeFuture":true,"tieredReplicants":{"_default_tier":1},"type":"loadByPeriod"},{"type":"dropForever"}]

deploy/kubernetes/jobs/retention/retention.yaml

@@ -1,29 +0,0 @@
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: set-retention
-  annotations:
-    "helm.sh/hook": post-install,post-upgrade
-spec:
-  ttlSecondsAfterFinished: 100
-  template:
-    spec:
-      containers:
-          - name: set-retention
-            image: theithollow/hollowapp-blog:curl
-            volumeMounts:
-            - name: retention-config-volume
-              mountPath: /app/retention-spec.json
-              subPath: retention-spec.json
-            args:
-            - /bin/sh
-            - -c
-            - "curl -X POST -H 'Content-Type: application/json' -d @/app/retention-spec.json http://signoz-druid-router:8888/druid/coordinator/v1/rules/flattened_spans"
-
-      volumes:
-          - name: retention-config-volume
-            configMap:
-              name: retention-config
-
-      restartPolicy: Never
-  backoffLimit: 8

deploy/kubernetes/jobs/supervisor/supervisor-config.yaml

@@ -1,76 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: supervisor-config
-data:
-  supervisor-spec.json: |
-    {
-        "type": "kafka",
-        "dataSchema": {
-          "dataSource": "flattened_spans",
-          "parser": {
-            "type": "string",
-            "parseSpec": {
-              "format": "json",
-              "timestampSpec": {
-                "column": "StartTimeUnixNano",
-                "format": "nano"
-              },
-              "dimensionsSpec": {
-                "dimensions": [
-                  "TraceId",
-                  "SpanId",
-                  "ParentSpanId",
-                  "Name",
-                  "ServiceName",
-                  "References",
-                  "Tags",
-                  "ExternalHttpMethod",
-                  "ExternalHttpUrl",
-                  "Component",
-                  "DBSystem",
-                  "DBName",
-                  "DBOperation",
-                  "PeerService",
-                  { 
-                      "type": "string",
-                      "name": "TagsKeys", 
-                      "multiValueHandling": "ARRAY" 
-                  },
-                  { 
-                      "type": "string",
-                      "name": "TagsValues", 
-                      "multiValueHandling": "ARRAY" 
-                  },
-                  { "name": "DurationNano", "type": "Long" },
-                  { "name": "Kind", "type": "int" },
-                  { "name": "StatusCode", "type": "int" }
-                ]
-              }
-            }
-          },
-          "metricsSpec" : [
-              { "type": "quantilesDoublesSketch", "name": "QuantileDuration", "fieldName": "DurationNano" }
-          ],
-          "granularitySpec": {
-            "type": "uniform",
-            "segmentGranularity": "DAY",
-            "queryGranularity": "NONE",
-            "rollup": false
-          }
-        },
-        "tuningConfig": {
-          "type": "kafka",
-          "reportParseExceptions": true
-        },
-        "ioConfig": {
-          "topic": "flattened_spans",
-          "replicas": 1,
-          "taskDuration": "PT20M",
-          "completionTimeout": "PT30M",
-          "consumerProperties": {
-            "bootstrap.servers": "signoz-kafka:9092"
-          }
-        }
-      }
-

deploy/kubernetes/jobs/supervisor/supervisor.yaml

@@ -1,27 +0,0 @@
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: create-supervisor
-  annotations:
-    "helm.sh/hook": post-install,post-upgrade
-spec:
-  ttlSecondsAfterFinished: 100
-  template:
-    spec:
-      containers:
-          - name: create-supervisor
-            image: theithollow/hollowapp-blog:curl
-            volumeMounts:
-            - name: supervisor-config-volume
-              mountPath: /app/supervisor-spec.json
-              subPath: supervisor-spec.json
-            args:
-            - /bin/sh
-            - -c
-            - "curl -X POST -H 'Content-Type: application/json' -d @/app/supervisor-spec.json http://signoz-druid-router:8888/druid/indexer/v1/supervisor"
-      volumes:
-          - name: supervisor-config-volume
-            configMap:
-              name: supervisor-config
-      restartPolicy: Never
-  backoffLimit: 8

deploy/kubernetes/otel-collector/config.yaml

@@ -1,60 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: otel-collector-conf
-  labels:
-    app: opentelemetry
-    component: otel-collector-conf
-data:
-  otel-collector-config: |
-    receivers:
-      otlp:
-        protocols:
-          grpc:
-          http:
-      jaeger:
-        protocols:
-          grpc:
-          thrift_http:
-    processors:
-      batch:
-        send_batch_size: 1000
-        timeout: 10s
-      memory_limiter:
-        # Same as --mem-ballast-size-mib CLI argument
-        ballast_size_mib: 683
-        # 80% of maximum memory up to 2G
-        limit_mib: 1500
-        # 25% of limit up to 2G
-        spike_limit_mib: 512
-        check_interval: 5s
-      queued_retry:
-        num_workers: 4
-        queue_size: 100
-        retry_on_failure: true
-    extensions:
-      health_check: {}
-      zpages: {}
-    exporters:
-      kafka/traces:
-        brokers:
-          - signoz-kafka:9092
-        topic: 'otlp_spans'
-        protocol_version: 2.0.0
-
-      kafka/metrics:
-        brokers:
-          - signoz-kafka:9092
-        topic: 'otlp_metrics'
-        protocol_version: 2.0.0
-    service:
-      extensions: [health_check, zpages]
-      pipelines:
-        traces:
-          receivers: [jaeger, otlp]
-          processors: [memory_limiter, batch, queued_retry]
-          exporters: [kafka/traces]
-        metrics:
-          receivers: [otlp]
-          processors: [batch]
-          exporters: [kafka/metrics]

deploy/kubernetes/platform/Chart.lock

@@ -2,20 +2,14 @@ dependencies:
 - name: zookeeper
   repository: https://charts.bitnami.com/bitnami
   version: 6.0.0
-- name: kafka
-  repository: https://charts.bitnami.com/bitnami
-  version: 12.0.0
-- name: druid
-  repository: https://charts.helm.sh/incubator
-  version: 0.2.18
-- name: flattener-processor
-  repository: file://./signoz-charts/flattener-processor
-  version: 0.3.6
 - name: query-service
   repository: file://./signoz-charts/query-service
-  version: 0.3.6
+  version: 0.5.1
 - name: frontend
   repository: file://./signoz-charts/frontend
-  version: 0.3.6
+  version: 0.5.2
-digest: sha256:b160e903c630a90644683c512eb8ba018e18d2c08051e255edd3749cb9cc7228
+- name: alertmanager
-generated: "2021-08-23T12:06:37.231066+05:30"
+  repository: file://./signoz-charts/alertmanager
+  version: 0.5.0
+digest: sha256:f1fac36fa869480261d1bf091b95e18147654e52b891ed743d7e3d985fa6ed18
+generated: "2021-12-09T17:07:48.919918+05:30"

deploy/kubernetes/platform/Chart.yaml

@@ -15,29 +15,23 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.3.2
+version: 0.5.2
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
-appVersion: 0.3.2
+appVersion: 0.5.2
 
 dependencies:
   - name: zookeeper
     repository: "https://charts.bitnami.com/bitnami"
     version: 6.0.0
-  - name: kafka
-    repository: "https://charts.bitnami.com/bitnami"
-    version: 12.0.0
-  - name: druid
-    repository: "https://charts.helm.sh/incubator"
-    version: 0.2.18
-  - name: flattener-processor
-    repository: "file://./signoz-charts/flattener-processor"
-    version: 0.3.6
   - name: query-service
     repository: "file://./signoz-charts/query-service"
-    version: 0.3.6
+    version: 0.5.1
   - name: frontend
     repository: "file://./signoz-charts/frontend"
-    version: 0.3.6
+    version: 0.5.2
+  - name: alertmanager
+    repository: "file://./signoz-charts/alertmanager"
+    version: 0.5.0

deploy/kubernetes/platform/signoz-charts/alertmanager/.helmignore

@@ -21,3 +21,5 @@
 .idea/
 *.tmproj
 .vscode/
+
+unittests/

deploy/kubernetes/platform/signoz-charts/alertmanager/Chart.yaml

@@ -0,0 +1,7 @@
+apiVersion: v2
+name: alertmanager
+description: The Alertmanager handles alerts sent by client applications such as the Prometheus server.
+type: application
+version: 0.5.0
+appVersion: 0.5.0
+

deploy/kubernetes/platform/signoz-charts/alertmanager/ci/config-reload-values.yaml

@@ -0,0 +1,2 @@
+configmapReload:
+  enabled: true

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/NOTES.txt

@@ -2,20 +2,20 @@
 {{- if .Values.ingress.enabled }}
 {{- range $host := .Values.ingress.hosts }}
   {{- range .paths }}
-  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ . }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
   {{- end }}
 {{- end }}
 {{- else if contains "NodePort" .Values.service.type }}
-  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "flattener-processor.fullname" . }})
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "alertmanager.fullname" . }})
   export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
   echo http://$NODE_IP:$NODE_PORT
 {{- else if contains "LoadBalancer" .Values.service.type }}
      NOTE: It may take a few minutes for the LoadBalancer IP to be available.
-           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "flattener-processor.fullname" . }}'
+           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "alertmanager.fullname" . }}'
-  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "flattener-processor.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "alertmanager.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
   echo http://$SERVICE_IP:{{ .Values.service.port }}
 {{- else if contains "ClusterIP" .Values.service.type }}
-  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "flattener-processor.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "alertmanager.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
-  echo "Visit http://127.0.0.1:8080 to use your application"
+  echo "Visit http://127.0.0.1:{{ .Values.service.port }} to use your application"
-  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:80
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME {{ .Values.service.port }}:80
 {{- end }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/_helpers.tpl

@@ -2,7 +2,7 @@
 {{/*
 Expand the name of the chart.
 */}}
-{{- define "flattener-processor.name" -}}
+{{- define "alertmanager.name" -}}
 {{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
 {{- end -}}
 
@@ -11,7 +11,7 @@ Create a default fully qualified app name.
 We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
 If release name contains chart name it will be used as a full name.
 */}}
-{{- define "flattener-processor.fullname" -}}
+{{- define "alertmanager.fullname" -}}
 {{- if .Values.fullnameOverride -}}
 {{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
 {{- else -}}
@@ -27,16 +27,16 @@ If release name contains chart name it will be used as a full name.
 {{/*
 Create chart name and version as used by the chart label.
 */}}
-{{- define "flattener-processor.chart" -}}
+{{- define "alertmanager.chart" -}}
 {{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
 {{- end -}}
 
 {{/*
 Common labels
 */}}
-{{- define "flattener-processor.labels" -}}
+{{- define "alertmanager.labels" -}}
-helm.sh/chart: {{ include "flattener-processor.chart" . }}
+helm.sh/chart: {{ include "alertmanager.chart" . }}
-{{ include "flattener-processor.selectorLabels" . }}
+{{ include "alertmanager.selectorLabels" . }}
 {{- if .Chart.AppVersion }}
 app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
 {{- end }}
@@ -46,17 +46,17 @@ app.kubernetes.io/managed-by: {{ .Release.Service }}
 {{/*
 Selector labels
 */}}
-{{- define "flattener-processor.selectorLabels" -}}
+{{- define "alertmanager.selectorLabels" -}}
-app.kubernetes.io/name: {{ include "flattener-processor.name" . }}
+app.kubernetes.io/name: {{ include "alertmanager.name" . }}
 app.kubernetes.io/instance: {{ .Release.Name }}
 {{- end -}}
 
 {{/*
 Create the name of the service account to use
 */}}
-{{- define "flattener-processor.serviceAccountName" -}}
+{{- define "alertmanager.serviceAccountName" -}}
 {{- if .Values.serviceAccount.create -}}
-    {{ default (include "flattener-processor.fullname" .) .Values.serviceAccount.name }}
+    {{ default (include "alertmanager.fullname" .) .Values.serviceAccount.name }}
 {{- else -}}
     {{ default "default" .Values.serviceAccount.name }}
 {{- end -}}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/configmap.yaml

@@ -0,0 +1,15 @@
+{{- if .Values.config }}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "alertmanager.fullname" . }}
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+data:
+  alertmanager.yml: |
+    {{- toYaml .Values.config | default "{}" | nindent 4 }}
+  {{- range $key, $value := .Values.templates }}
+  {{ $key }}: |-
+    {{- $value | nindent 4 }}
+  {{- end }}
+{{- end }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/ingress.yaml

@@ -0,0 +1,61 @@
+{{- if .Values.ingress.enabled -}}
+{{- $fullName := include "alertmanager.fullname" . -}}
+{{- $svcPort := .Values.service.port -}}
+{{- if and .Values.ingress.className (not (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion)) }}
+  {{- if not (hasKey .Values.ingress.annotations "kubernetes.io/ingress.class") }}
+  {{- $_ := set .Values.ingress.annotations "kubernetes.io/ingress.class" .Values.ingress.className}}
+  {{- end }}
+{{- end }}
+{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1
+{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1beta1
+{{- else -}}
+apiVersion: extensions/v1beta1
+{{- end }}
+kind: Ingress
+metadata:
+  name: {{ $fullName }}
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- if and .Values.ingress.className (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion) }}
+  ingressClassName: {{ .Values.ingress.className }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            {{- if and .pathType (semverCompare ">=1.18-0" $.Capabilities.KubeVersion.GitVersion) }}
+            pathType: {{ .pathType }}
+            {{- end }}
+            backend:
+              {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }}
+              service:
+                name: {{ $fullName }}
+                port:
+                  number: {{ $svcPort }}
+              {{- else }}
+              serviceName: {{ $fullName }}
+              servicePort: {{ $svcPort }}
+              {{- end }}
+          {{- end }}
+    {{- end }}
+{{- end }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/pdb.yaml

@@ -0,0 +1,13 @@
+{{- if .Values.podDisruptionBudget -}}
+apiVersion: policy/v1beta1
+kind: PodDisruptionBudget
+metadata:
+  name: {{ template "alertmanager.fullname" . }}
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+spec:
+  selector:
+    matchLabels:
+      {{- include "alertmanager.selectorLabels" . | nindent 6 }}
+{{ toYaml .Values.podDisruptionBudget | indent 2 }}
+{{- end -}}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/serviceaccount.yaml

@@ -2,9 +2,9 @@
 apiVersion: v1
 kind: ServiceAccount
 metadata:
-  name: {{ include "flattener-processor.serviceAccountName" . }}
+  name: {{ include "alertmanager.serviceAccountName" . }}
   labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
+    {{- include "alertmanager.labels" . | nindent 4 }}
   {{- with .Values.serviceAccount.annotations }}
   annotations:
     {{- toYaml . | nindent 4 }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/services.yaml

@@ -0,0 +1,48 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: alertmanager
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+{{- if .Values.service.annotations }}
+  annotations:
+    {{- toYaml .Values.service.annotations | nindent 4 }}
+{{- end }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+      {{- if (and (eq .Values.service.type "NodePort") .Values.service.nodePort) }}
+      nodePort: {{ .Values.service.nodePort }}
+      {{- end }}
+  selector:
+    {{- include "alertmanager.selectorLabels" . | nindent 4 }}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "alertmanager.fullname" . }}-headless
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+spec:
+  clusterIP: None
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+    {{- if or (gt .Values.replicaCount 1.0) (.Values.additionalPeers) }}
+    - port: 9094
+      targetPort: 9094
+      protocol: TCP
+      name: cluster-tcp
+    - port: 9094
+      targetPort: 9094
+      protocol: UDP
+      name: cluster-udp
+    {{- end }}
+  selector:
+    {{- include "alertmanager.selectorLabels" . | nindent 4 }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/statefulset.yaml

@@ -0,0 +1,152 @@
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: {{ include "alertmanager.fullname" . }}
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+{{- if .Values.statefulSet.annotations }}
+  annotations:
+    {{ toYaml .Values.statefulSet.annotations | nindent 4 }}
+{{- end }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "alertmanager.selectorLabels" . | nindent 6 }}
+  serviceName: {{ include "alertmanager.fullname" . }}-headless
+  template:
+    metadata:
+      labels:
+        {{- include "alertmanager.selectorLabels" . | nindent 8 }}
+{{- if .Values.podLabels }}
+        {{ toYaml .Values.podLabels | nindent 8 }}
+{{- end }}
+      annotations:
+      {{- if not .Values.configmapReload.enabled }}
+        checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
+      {{- end }}
+{{- if .Values.podAnnotations }}
+        {{- toYaml .Values.podAnnotations | nindent 8 }}
+{{- end }}
+    spec:
+    {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+      serviceAccountName: {{ include "alertmanager.serviceAccountName" . }}
+    {{- with .Values.dnsConfig }}
+      dnsConfig:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+    {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+    {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+    {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        {{- if and (.Values.configmapReload.enabled) (.Values.config) }}
+        - name: {{ .Chart.Name }}-{{ .Values.configmapReload.name }}
+          image: "{{ .Values.configmapReload.image.repository }}:{{ .Values.configmapReload.image.tag }}"
+          imagePullPolicy: "{{ .Values.configmapReload.image.pullPolicy }}"
+          args:
+            - --volume-dir=/etc/alertmanager
+            - --webhook-url=http://127.0.0.1:{{ .Values.service.port }}/-/reload
+          resources:
+            {{- toYaml .Values.configmapReload.resources | nindent 12 }}
+          volumeMounts:
+            - name: config
+              mountPath: /etc/alertmanager
+        {{- end }}
+        - name: {{ .Chart.Name }}
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          env:
+            - name: POD_IP
+              valueFrom:
+                fieldRef:
+                  apiVersion: v1
+                  fieldPath: status.podIP
+{{- if .Values.command }}
+          command:
+            {{- toYaml .Values.command | nindent 12 }}
+{{- end }}
+          args:
+            - --storage.path=/alertmanager
+            - --config.file=/etc/alertmanager/alertmanager.yml
+            {{- if or (gt .Values.replicaCount 1.0) (.Values.additionalPeers) }}
+            - --cluster.advertise-address=$(POD_IP):9094
+            - --cluster.listen-address=0.0.0.0:9094
+            {{- end }}
+            {{- if gt .Values.replicaCount 1.0}}
+            {{- $fullName := include "alertmanager.fullname" . }}
+            {{- range $i := until (int .Values.replicaCount) }}
+            - --cluster.peer={{ $fullName }}-{{ $i }}.{{ $fullName }}-headless:9094
+            {{- end }}
+            {{- end }}
+            {{- if .Values.additionalPeers }}
+            {{- range $item := .Values.additionalPeers }}
+            - --cluster.peer={{ $item }}
+            {{- end }}
+            {{- end }}
+            {{- range $key, $value := .Values.extraArgs }}
+            - --{{ $key }}={{ $value }}
+            {{- end }}
+          ports:
+            - name: http
+              containerPort: 9093
+              protocol: TCP
+          livenessProbe:
+            httpGet:
+              path: /
+              port: http
+          readinessProbe:
+            httpGet:
+              path: /
+              port: http
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+          volumeMounts:
+            {{- if .Values.config }}
+            - name: config
+              mountPath: /etc/alertmanager
+            {{- end }}
+            - name: storage
+              mountPath: /alertmanager
+      {{- if .Values.config }}
+      volumes:
+        - name: config
+          configMap:
+            name: {{ include "alertmanager.fullname" . }}
+      {{- end }}
+      {{- if .Values.persistence.enabled }}
+  volumeClaimTemplates:
+    - metadata:
+        name: storage
+      spec:
+        accessModes:
+          {{- toYaml .Values.persistence.accessModes | nindent 10 }}
+        resources:
+          requests:
+            storage: {{ .Values.persistence.size }}
+      {{- if .Values.persistence.storageClass }}
+      {{- if (eq "-" .Values.persistence.storageClass) }}
+        storageClassName: ""
+      {{- else }}
+        storageClassName: {{ .Values.persistence.storageClass }}
+      {{- end }}
+      {{- end }}
+{{- else }}
+        - name: storage
+          emptyDir: {}
+{{- end -}}

deploy/kubernetes/platform/signoz-charts/alertmanager/unittests/__snapshot__/ingress_test.yaml.snap

@@ -0,0 +1,48 @@
+should match snapshot of default values:
+  1: |
+    apiVersion: networking.k8s.io/v1
+    kind: Ingress
+    metadata:
+      labels:
+        app.kubernetes.io/instance: RELEASE-NAME
+        app.kubernetes.io/managed-by: Helm
+        app.kubernetes.io/name: alertmanager
+        app.kubernetes.io/version: 1.0.0
+        helm.sh/chart: alertmanager-1.0.0
+      name: RELEASE-NAME-alertmanager
+    spec:
+      ingressClassName: nginx-test
+      rules:
+      - host: alertmanager.domain.com
+        http:
+          paths:
+          - backend:
+              service:
+                name: RELEASE-NAME-alertmanager
+                port:
+                  number: 9093
+            path: /
+            pathType: ImplementationSpecific
+should match snapshot of default values with old kubernetes ingress:
+  1: |
+    apiVersion: networking.k8s.io/v1beta1
+    kind: Ingress
+    metadata:
+      annotations:
+        kubernetes.io/ingress.class: nginx-test
+      labels:
+        app.kubernetes.io/instance: RELEASE-NAME
+        app.kubernetes.io/managed-by: Helm
+        app.kubernetes.io/name: alertmanager
+        app.kubernetes.io/version: 1.0.0
+        helm.sh/chart: alertmanager-1.0.0
+      name: RELEASE-NAME-alertmanager
+    spec:
+      rules:
+      - host: alertmanager.domain.com
+        http:
+          paths:
+          - backend:
+              serviceName: RELEASE-NAME-alertmanager
+              servicePort: 9093
+            path: /

deploy/kubernetes/platform/signoz-charts/alertmanager/unittests/ingress_test.yaml

@@ -0,0 +1,81 @@
+suite: test ingress
+templates:
+  - ingress.yaml
+tests:
+  - it: should be empty if ingress is not enabled
+    asserts:
+      - hasDocuments:
+          count: 0
+  - it: should have apiVersion extensions/v1beta1 for k8s < 1.14
+    set:
+      ingress.enabled: true
+    capabilities:
+      majorVersion: 1
+      minorVersion: 13
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Ingress
+      - isAPIVersion:
+          of: extensions/v1beta1
+  - it: should have apiVersion networking.k8s.io/v1beta1 for k8s < 1.19
+    set:
+      ingress.enabled: true
+    capabilities:
+      majorVersion: 1
+      minorVersion: 18
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Ingress
+      - isAPIVersion:
+          of: networking.k8s.io/v1beta1
+  - it: should have apiVersion networking.k8s.io/v1 for k8s >= 1.19
+    set:
+      ingress.enabled: true
+    capabilities:
+      majorVersion: 1
+      minorVersion: 19
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Ingress
+      - isAPIVersion:
+          of: networking.k8s.io/v1
+  - it: should have an ingressClassName for k8s >= 1.19
+    set:
+      ingress.enabled: true
+      ingress.className: nginx-test
+    capabilities:
+      majorVersion: 1
+      minorVersion: 19
+    asserts:
+      - hasDocuments:
+          count: 1
+      - equal:
+          path: spec.ingressClassName
+          value: nginx-test
+  - it: should match snapshot of default values
+    set:
+      ingress.enabled: true
+      ingress.className: nginx-test
+    chart:
+      version: 1.0.0
+      appVersion: 1.0.0
+    asserts:
+      - matchSnapshot: { }
+  - it: should match snapshot of default values with old kubernetes ingress
+    set:
+      ingress.enabled: true
+      ingress.className: nginx-test
+    capabilities:
+      majorVersion: 1
+      minorVersion: 17
+    chart:
+      version: 1.0.0
+      appVersion: 1.0.0
+    asserts:
+      - matchSnapshot: { }

deploy/kubernetes/platform/signoz-charts/alertmanager/values.yaml

@@ -0,0 +1,189 @@
+# Default values for alertmanager.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+replicaCount: 1
+
+image:
+  repository: signoz/alertmanager
+  pullPolicy: IfNotPresent
+  # Overrides the image tag whose default is the chart appVersion.
+  tag: "0.5.0"
+
+extraArgs: {}
+
+imagePullSecrets: []
+nameOverride: ""
+fullnameOverride: ""
+
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: true
+  # Annotations to add to the service account
+  annotations: {}
+  # The name of the service account to use.
+  # If not set and create is true, a name is generated using the fullname template
+  name:
+
+podSecurityContext:
+  fsGroup: 65534
+dnsConfig: {}
+  # nameservers:
+  #   - 1.2.3.4
+  # searches:
+  #   - ns1.svc.cluster-domain.example
+  #   - my.dns.search.suffix
+  # options:
+  #   - name: ndots
+  #     value: "2"
+  #   - name: edns0
+securityContext:
+  # capabilities:
+  #   drop:
+  #   - ALL
+  # readOnlyRootFilesystem: true
+  runAsUser: 65534
+  runAsNonRoot: true
+  runAsGroup: 65534
+
+additionalPeers: []
+
+service:
+  annotations: {}
+  type: ClusterIP
+  port: 9093
+  # if you want to force a specific nodePort. Must be use with service.type=NodePort
+  # nodePort:
+
+ingress:
+  enabled: false
+  className: ""
+  annotations: {}
+    # kubernetes.io/ingress.class: nginx
+    # kubernetes.io/tls-acme: "true"
+  hosts:
+    - host: alertmanager.domain.com
+      paths:
+        - path: /
+          pathType: ImplementationSpecific
+  tls: []
+  #  - secretName: chart-example-tls
+  #    hosts:
+  #      - alertmanager.domain.com
+
+resources: {}
+  # We usually recommend not to specify default resources and to leave this as a conscious
+  # choice for the user. This also increases chances charts run on environments with little
+  # resources, such as Minikube. If you do want to specify resources, uncomment the following
+  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
+  # limits:
+  #   cpu: 100m
+  #   memory: 128Mi
+  # requests:
+  #   cpu: 10m
+  #   memory: 32Mi
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
+statefulSet:
+  annotations: {}
+
+podAnnotations: {}
+podLabels: {}
+
+# Ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/
+podDisruptionBudget: {}
+  # maxUnavailable: 1
+  # minAvailable: 1
+
+command: []
+
+persistence:
+  enabled: true
+  ## Persistent Volume Storage Class
+  ## If defined, storageClassName: <storageClass>
+  ## If set to "-", storageClassName: "", which disables dynamic provisioning
+  ## If undefined (the default) or set to null, no storageClassName spec is
+  ## set, choosing the default provisioner.
+  ##
+  # storageClass: "-"
+  accessModes:
+    - ReadWriteOnce
+  size: 100Mi
+
+config:
+  global: 
+    resolve_timeout: 1m
+    slack_api_url: 'https://hooks.slack.com/services/xxx'
+
+  templates:
+    - '/etc/alertmanager/*.tmpl'
+
+  receivers:
+  - name: 'slack-notifications'
+    slack_configs:
+    - channel: '#alerts'
+      send_resolved: true
+      icon_url: https://avatars3.githubusercontent.com/u/3380462
+      title: '{{ template "slack.title" . }}'
+      text: '{{ template "slack.text" . }}'
+
+
+  route:
+    receiver: 'slack-notifications'
+
+## Monitors ConfigMap changes and POSTs to a URL
+## Ref: https://github.com/jimmidyson/configmap-reload
+##
+configmapReload:
+  ## If false, the configmap-reload container will not be deployed
+  ##
+  enabled: false
+
+  ## configmap-reload container name
+  ##
+  name: configmap-reload
+
+  ## configmap-reload container image
+  ##
+  image:
+    repository: jimmidyson/configmap-reload
+    tag: v0.5.0
+    pullPolicy: IfNotPresent
+
+  ## configmap-reload resource requests and limits
+  ## Ref: http://kubernetes.io/docs/user-guide/compute-resources/
+  ##
+  resources: {}
+
+templates: 
+  title.tmpl: |-
+      {{ define "slack.title" }}
+      [{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}
+      {{- if gt (len .CommonLabels) (len .GroupLabels) -}}
+        {{" "}}(
+        {{- with .CommonLabels.Remove .GroupLabels.Names }}
+          {{- range $index, $label := .SortedPairs -}}
+            {{ if $index }}, {{ end }}
+            {{- $label.Name }}="{{ $label.Value -}}"
+          {{- end }}
+        {{- end -}}
+        )
+      {{- end }}
+      {{ end }}
+  text.tmpl: |-
+      {{ define "slack.text" }}
+      {{ range .Alerts -}}
+      *Alert:* {{ .Annotations.title }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}
+
+      *Description:* {{ .Annotations.description }}
+
+      *Details:*
+        {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`
+        {{ end }}
+      {{ end }}
+      {{ end }}

deploy/kubernetes/platform/signoz-charts/flattener-processor/Chart.yaml

@@ -1,21 +0,0 @@
-apiVersion: v2
-name: flattener-processor
-description: A Helm chart for Kubernetes
-
-# A chart can be either an 'application' or a 'library' chart.
-#
-# Application charts are a collection of templates that can be packaged into versioned archives
-# to be deployed.
-#
-# Library charts provide useful utilities or functions for the chart developer. They're included as
-# a dependency of application charts to inject those utilities and functions into the rendering
-# pipeline. Library charts do not define any templates and therefore cannot be deployed.
-type: application
-
-# This is the chart version. This version number should be incremented each time you make changes
-# to the chart and its templates, including the app version.
-version: 0.3.6
-
-# This is the version number of the application being deployed. This version number should be
-# incremented each time you make changes to the application.
-appVersion: 0.3.6

deploy/kubernetes/platform/signoz-charts/flattener-processor/templates/deployment.yaml

@@ -1,65 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ include "flattener-processor.fullname" . }}
-  labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
-spec:
-  replicas: {{ .Values.replicaCount }}
-  selector:
-    matchLabels:
-      {{- include "flattener-processor.selectorLabels" . | nindent 6 }}
-  template:
-    metadata:
-      labels:
-        {{- include "flattener-processor.selectorLabels" . | nindent 8 }}
-    spec:
-    {{- with .Values.imagePullSecrets }}
-      imagePullSecrets:
-        {{- toYaml . | nindent 8 }}
-    {{- end }}
-      serviceAccountName: {{ include "flattener-processor.serviceAccountName" . }}
-      securityContext:
-        {{- toYaml .Values.podSecurityContext | nindent 8 }}
-      containers:
-        - name: {{ .Chart.Name }}
-          securityContext:
-            {{- toYaml .Values.securityContext | nindent 12 }}
-          image: "{{ .Values.image.repository }}:{{ .Chart.AppVersion }}"
-          imagePullPolicy: {{ .Values.image.pullPolicy }}
-          command:
-          - "/root/flattener"
-          ports:
-          - name: http
-            containerPort: 8080
-            protocol: TCP
-          env:
-          - name: KAFKA_BROKER
-            value: {{ .Values.configVars.KAFKA_BROKER }}
-          - name: KAFKA_INPUT_TOPIC
-            value: {{ .Values.configVars.KAFKA_INPUT_TOPIC }}
-          - name: KAFKA_OUTPUT_TOPIC
-            value: {{ .Values.configVars.KAFKA_OUTPUT_TOPIC }}
-            
-          # livenessProbe:
-          #   httpGet:
-          #     path: /
-          #     port: http
-          # readinessProbe:
-          #   httpGet:
-          #     path: /
-          #     port: http
-          resources:
-            {{- toYaml .Values.resources | nindent 12 }}
-      {{- with .Values.nodeSelector }}
-      nodeSelector:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-    {{- with .Values.affinity }}
-      affinity:
-        {{- toYaml . | nindent 8 }}
-    {{- end }}
-    {{- with .Values.tolerations }}
-      tolerations:
-        {{- toYaml . | nindent 8 }}
-    {{- end }}

deploy/kubernetes/platform/signoz-charts/flattener-processor/templates/ingress.yaml

@@ -1,41 +0,0 @@
-{{- if .Values.ingress.enabled -}}
-{{- $fullName := include "flattener-processor.fullname" . -}}
-{{- $svcPort := .Values.service.port -}}
-{{- if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
-apiVersion: networking.k8s.io/v1beta1
-{{- else -}}
-apiVersion: extensions/v1beta1
-{{- end }}
-kind: Ingress
-metadata:
-  name: {{ $fullName }}
-  labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
-  {{- with .Values.ingress.annotations }}
-  annotations:
-    {{- toYaml . | nindent 4 }}
-  {{- end }}
-spec:
-{{- if .Values.ingress.tls }}
-  tls:
-  {{- range .Values.ingress.tls }}
-    - hosts:
-      {{- range .hosts }}
-        - {{ . | quote }}
-      {{- end }}
-      secretName: {{ .secretName }}
-  {{- end }}
-{{- end }}
-  rules:
-  {{- range .Values.ingress.hosts }}
-    - host: {{ .host | quote }}
-      http:
-        paths:
-        {{- range .paths }}
-          - path: {{ . }}
-            backend:
-              serviceName: {{ $fullName }}
-              servicePort: {{ $svcPort }}
-        {{- end }}
-  {{- end }}
-{{- end }}

deploy/kubernetes/platform/signoz-charts/flattener-processor/templates/service.yaml

@@ -1,15 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: {{ include "flattener-processor.fullname" . }}
-  labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
-spec:
-  type: {{ .Values.service.type }}
-  ports:
-    - port: {{ .Values.service.port }}
-      targetPort: http
-      protocol: TCP
-      name: http
-  selector:
-    {{- include "flattener-processor.selectorLabels" . | nindent 4 }}

deploy/kubernetes/platform/signoz-charts/flattener-processor/templates/tests/test-connection.yaml

@@ -1,15 +0,0 @@
-apiVersion: v1
-kind: Pod
-metadata:
-  name: "{{ include "flattener-processor.fullname" . }}-test-connection"
-  labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
-  annotations:
-    "helm.sh/hook": test-success
-spec:
-  containers:
-    - name: wget
-      image: busybox
-      command: ['wget']
-      args: ['{{ include "flattener-processor.fullname" . }}:{{ .Values.service.port }}']
-  restartPolicy: Never

deploy/kubernetes/platform/signoz-charts/flattener-processor/values.yaml

@@ -1,74 +0,0 @@
-# Default values for flattener-processor.
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-
-replicaCount: 1
-
-image:
-  repository: signoz/flattener-processor
-  pullPolicy: IfNotPresent
-
-imagePullSecrets: []
-nameOverride: ""
-fullnameOverride: ""
-
-
-configVars:
-  KAFKA_BROKER: signoz-kafka:9092
-  KAFKA_INPUT_TOPIC: otlp_spans
-  KAFKA_OUTPUT_TOPIC: flattened_spans
-
-serviceAccount:
-  # Specifies whether a service account should be created
-  create: false
-  # Annotations to add to the service account
-  annotations: {}
-  # The name of the service account to use.
-  # If not set and create is true, a name is generated using the fullname template
-  name:
-
-podSecurityContext: {}
-  # fsGroup: 2000
-
-securityContext: {}
-  # capabilities:
-  #   drop:
-  #   - ALL
-  # readOnlyRootFilesystem: true
-  # runAsNonRoot: true
-  # runAsUser: 1000
-
-service:
-  type: ClusterIP
-  port: 8080
-
-ingress:
-  enabled: false
-  annotations: {}
-    # kubernetes.io/ingress.class: nginx
-    # kubernetes.io/tls-acme: "true"
-  hosts:
-    - host: chart-example.local
-      paths: []
-  tls: []
-  #  - secretName: chart-example-tls
-  #    hosts:
-  #      - chart-example.local
-
-resources: {}
-  # We usually recommend not to specify default resources and to leave this as a conscious
-  # choice for the user. This also increases chances charts run on environments with little
-  # resources, such as Minikube. If you do want to specify resources, uncomment the following
-  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
-  # limits:
-  #   cpu: 100m
-  #   memory: 128Mi
-  # requests:
-  #   cpu: 100m
-  #   memory: 128Mi
-
-nodeSelector: {}
-
-tolerations: []
-
-affinity: {}

deploy/kubernetes/platform/signoz-charts/frontend/Chart.yaml

@@ -14,8 +14,8 @@ type: application
 
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.3.6
+version: 0.5.2
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
-appVersion: 0.3.6
+appVersion: 0.5.2

deploy/kubernetes/platform/signoz-charts/frontend/templates/config.yaml

@@ -24,6 +24,9 @@ data:
         index  index.html index.htm;
         try_files $uri $uri/ /index.html;
       }
+      location /api/alertmanager{
+        proxy_pass http://{{ .Values.config.alertmanagerUrl }}/api/v2;
+      }
       location /api {
         proxy_pass http://{{ .Values.config.queryServiceUrl }}/api;
       }

deploy/kubernetes/platform/signoz-charts/frontend/values.yaml

@@ -17,6 +17,7 @@ configVars: {}
 config:
   name: signoz-nginx-config
   queryServiceUrl: signoz-query-service:8080
+  alertmanagerUrl: alertmanager:9093
 
 serviceAccount:
   # Specifies whether a service account should be created

deploy/kubernetes/platform/signoz-charts/query-service/Chart.yaml

@@ -14,8 +14,8 @@ type: application
 
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.3.6
+version: 0.5.1
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
-appVersion: 0.3.6
+appVersion: 0.5.1

deploy/kubernetes/platform/signoz-charts/query-service/templates/prometheus-configmap.yaml

@@ -0,0 +1,33 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus-config
+data:
+  prometheus.yml: |
+    # my global config
+    global:
+      scrape_interval:     5s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
+      evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
+      # scrape_timeout is set to the global default (10s).
+
+    # Alertmanager configuration
+    alerting:
+      alertmanagers:
+      - static_configs:
+        - targets:
+          - alertmanager:9093
+
+    # Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
+    rule_files:
+      # - "first_rules.yml"
+      # - "second_rules.yml"
+      - 'alerts.yml'
+
+    # A scrape configuration containing exactly one endpoint to scrape:
+    # Here it's Prometheus itself.
+    scrape_configs:
+      
+
+    remote_read:
+      - url: tcp://signoz-clickhouse:9000/?database=signoz_metrics&username=clickhouse_operator&password=clickhouse_operator_password
+

deploy/kubernetes/platform/signoz-charts/query-service/templates/statefulset.yaml

@@ -1,10 +1,11 @@
 apiVersion: apps/v1
-kind: Deployment
+kind: StatefulSet
 metadata:
   name: {{ include "query-service.fullname" . }}
   labels:
     {{- include "query-service.labels" . | nindent 4 }}
 spec:
+  serviceName: query-service
   replicas: {{ .Values.replicaCount }}
   selector:
     matchLabels:
@@ -14,19 +15,17 @@ spec:
       labels:
         {{- include "query-service.selectorLabels" . | nindent 8 }}
     spec:
-    {{- with .Values.imagePullSecrets }}
-      imagePullSecrets:
-        {{- toYaml . | nindent 8 }}
-    {{- end }}
-      serviceAccountName: {{ include "query-service.serviceAccountName" . }}
-      securityContext:
-        {{- toYaml .Values.podSecurityContext | nindent 8 }}
       containers:
         - name: {{ .Chart.Name }}
+        {{- with .Values.imagePullSecrets }}
+          imagePullSecrets:
+            {{- toYaml . | nindent 8 }}
+        {{- end }}
           securityContext:
             {{- toYaml .Values.securityContext | nindent 12 }}
           image: "{{ .Values.image.repository }}:{{ .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
+          args: ["-config=/root/config/prometheus.yml"]
           ports:
             - name: http
               containerPort: 8080
@@ -38,7 +37,10 @@ spec:
             value: {{ .Values.configVars.DruidDatasource }}
           - name: STORAGE
             value: {{ .Values.configVars.STORAGE }}
-            
+          - name: ClickHouseUrl
+            value: {{ .Values.configVars.ClickHouseUrl}}
+          - name: GODEBUG
+            value: netdns=go
           # livenessProbe:
           #   httpGet:
           #     path: /
@@ -47,6 +49,13 @@ spec:
           #   httpGet:
           #     path: /
           #     port: http
+          volumeMounts:
+          - name: prometheus
+            mountPath: /root/config
+          - name: signoz-db
+            mountPath: /var/lib/signoz/
+          - name: dashboards
+            mountPath: /root/config/dashboards
           resources:
             {{- toYaml .Values.resources | nindent 12 }}
       {{- with .Values.nodeSelector }}
@@ -61,3 +70,18 @@ spec:
       tolerations:
         {{- toYaml . | nindent 8 }}
     {{- end }}
+      volumes:
+      - name: prometheus
+        configMap:
+          name: prometheus-config
+      - name: dashboards
+        emptyDir: {}
+
+  volumeClaimTemplates:
+  - metadata:
+      name: signoz-db
+    spec:
+      accessModes: [ "ReadWriteOnce" ]
+      resources:
+        requests:
+          storage: 1Gi

deploy/kubernetes/platform/signoz-charts/query-service/values.yaml

@@ -16,7 +16,8 @@ fullnameOverride: ""
 configVars:
   DruidClientUrl: http://signoz-druid-router:8888
   DruidDatasource: flattened_spans
-  STORAGE: druid
+  ClickHouseUrl: http://signoz-clickhouse:9000?username=clickhouse_operator&password=clickhouse_operator_password
+  STORAGE: clickhouse
   POSTHOG_API_KEY: "H-htDCae7CR3RV57gUzmol6IAKtm5IMCvbcm_fwnL-w"
 
 

deploy/kubernetes/platform/templates/clickhouse-config.yaml

@@ -0,0 +1,33 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: initdb-config
+data:
+  init-db.sql: |-
+    CREATE TABLE IF NOT EXISTS signoz_index (
+    timestamp DateTime64(9) CODEC(Delta, ZSTD(1)),
+    traceID String CODEC(ZSTD(1)),
+    spanID String CODEC(ZSTD(1)),
+    parentSpanID String CODEC(ZSTD(1)),
+    serviceName LowCardinality(String) CODEC(ZSTD(1)),
+    name LowCardinality(String) CODEC(ZSTD(1)),
+    kind Int32 CODEC(ZSTD(1)),
+    durationNano UInt64 CODEC(ZSTD(1)),
+    tags Array(String) CODEC(ZSTD(1)),
+    tagsKeys Array(String) CODEC(ZSTD(1)),
+    tagsValues Array(String) CODEC(ZSTD(1)),
+    statusCode Int64 CODEC(ZSTD(1)),
+    references String CODEC(ZSTD(1)),
+    externalHttpMethod Nullable(String) CODEC(ZSTD(1)),
+    externalHttpUrl Nullable(String) CODEC(ZSTD(1)),
+    component Nullable(String) CODEC(ZSTD(1)),
+    dbSystem Nullable(String) CODEC(ZSTD(1)),
+    dbName Nullable(String) CODEC(ZSTD(1)),
+    dbOperation Nullable(String) CODEC(ZSTD(1)),
+    peerService Nullable(String) CODEC(ZSTD(1)),
+    INDEX idx_tagsKeys tagsKeys TYPE bloom_filter(0.01) GRANULARITY 64,
+    INDEX idx_tagsValues tagsValues TYPE bloom_filter(0.01) GRANULARITY 64,
+    INDEX idx_duration durationNano TYPE minmax GRANULARITY 1
+    ) ENGINE MergeTree()
+    PARTITION BY toDate(timestamp)
+    ORDER BY (serviceName, -toUnixTimestamp(timestamp))

deploy/kubernetes/platform/templates/clickhouse-instance.yaml

@@ -0,0 +1,104 @@
+{{ if (eq (.Values.cloud | toString) "gcp" )}}
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: gce-resizable
+provisioner: kubernetes.io/gce-pd
+parameters:
+  type: pd-standard
+  fstype: ext4
+  replication-type: none
+reclaimPolicy: Retain
+#volumeBindingMode: Immediate
+allowVolumeExpansion: true
+{{- else if (eq (.Values.cloud | toString) "aws") }}
+#
+# AWS resizable disk example
+#
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: gp2-resizable
+provisioner: kubernetes.io/aws-ebs
+parameters:
+  type: gp2
+reclaimPolicy: Retain
+#volumeBindingMode: Immediate
+allowVolumeExpansion: true
+{{- end }}
+---
+apiVersion: "clickhouse.altinity.com/v1"
+kind: "ClickHouseInstallation"
+metadata:
+  name: signoz
+spec:
+  defaults:
+    templates:
+      dataVolumeClaimTemplate: default-volume-claim
+      # logVolumeClaimTemplate: default-volume-claim
+      serviceTemplate: chi-service-template
+  configuration:
+    zookeeper:
+      nodes:
+        - host: signoz-zookeeper
+          port: 2181
+      session_timeout_ms: 6000
+    clusters:
+      - name: cluster
+        # Templates are specified for this cluster explicitly
+        templates:
+          dataVolumeClaimTemplate: default-volume-claim
+          # logVolumeClaimTemplate: default-volume-claim
+          podTemplate: pod-template-with-volume
+        layout:
+          shardsCount: 1
+          replicasCount: 1
+  templates:
+    hostTemplates:
+      - name: port-distribution
+        portDistribution:
+          - type: ClusterScopeIndex
+        spec:
+          tcpPort: 9000
+          httpPort: 8123
+          interserverHTTPPort: 9009
+
+    podTemplates:
+      - name: pod-template-with-volume
+        spec:
+          containers:
+            - name: clickhouse
+              image: yandex/clickhouse-server:21.7
+              volumeMounts:
+                - name: default-volume-claim
+                  mountPath: /var/lib/clickhouse
+                - name: initdb
+                  mountPath: /docker-entrypoint-initdb.d
+          volumes:
+            - name: initdb
+              configMap:
+                name: initdb-config
+    serviceTemplates:
+      - name: chi-service-template
+        generateName: signoz-clickhouse
+        spec:
+          ports:
+            - name: http
+              port: 8123
+            - name: tcp
+              port: 9000
+          type: {{ .Values.clickhouseOperator.serviceType }}
+    volumeClaimTemplates:
+      - name: default-volume-claim
+        reclaimPolicy: Retain
+        spec:
+          {{- if (eq (.Values.cloud | toString) "gcp" )}}
+          storageClassName: gce-resizable
+          {{- else if (eq (.Values.cloud | toString) "aws") }}
+          storageClassName: gp2-resizable
+          {{- end }}
+          accessModes:
+            - ReadWriteOnce
+          resources:
+            requests:
+              storage: {{ .Values.clickhouseOperator.storage | quote }}

deploy/kubernetes/platform/templates/clickhouse-operator/clusterrole.yaml

@@ -0,0 +1,157 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# NAMESPACE=posthog
+# COMMENT=#
+# ROLE_KIND=ClusterRole
+# ROLE_NAME=clickhouse-operator-posthog
+# ROLE_BINDING_KIND=ClusterRoleBinding
+# ROLE_BINDING_NAME=clickhouse-operator-posthog
+#
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: clickhouse-operator-posthog
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+rules:
+- apiGroups:
+    - ""
+  resources:
+    - configmaps
+    - services
+  verbs:
+    - create
+    - delete
+    - get
+    - patch
+    - update
+    - list
+    - watch
+- apiGroups:
+    - ""
+  resources:
+    - endpoints
+  verbs:
+    - get
+    - list
+    - watch
+- apiGroups:
+    - ""
+  resources:
+    - events
+  verbs:
+    - create
+- apiGroups:
+    - ""
+  resources:
+    - persistentvolumeclaims
+  verbs:
+    - delete
+    - get
+    - list
+    - patch
+    - update
+    - watch
+- apiGroups:
+    - ""
+  resources:
+    - persistentvolumes
+    - pods
+  verbs:
+    - get
+    - list
+    - patch
+    - update
+    - watch
+- apiGroups:
+    - apps
+  resources:
+    - statefulsets
+  verbs:
+    - create
+    - delete
+    - get
+    - patch
+    - update
+    - list
+    - watch
+- apiGroups:
+    - apps
+  resources:
+    - replicasets
+  verbs:
+    - delete
+    - get
+    - patch
+    - update
+- apiGroups:
+    - apps
+  resourceNames:
+    - clickhouse-operator
+  resources:
+    - deployments
+  verbs:
+    - get
+    - patch
+    - update
+    - delete
+- apiGroups:
+    - policy
+  resources:
+    - poddisruptionbudgets
+  verbs:
+    - create
+    - delete
+    - get
+    - patch
+    - update
+    - list
+    - watch
+- apiGroups:
+    - clickhouse.altinity.com
+  resources:
+    - clickhouseinstallations
+  verbs:
+    - delete
+    - get
+    - patch
+    - update
+- apiGroups:
+    - clickhouse.altinity.com
+  resources:
+    - clickhouseinstallations
+    - clickhouseinstallationtemplates
+    - clickhouseoperatorconfigurations
+  verbs:
+    - get
+    - list
+    - watch
+- apiGroups:
+    - clickhouse.altinity.com
+  resources:
+    - clickhouseinstallations/finalizers
+    - clickhouseinstallationtemplates/finalizers
+    - clickhouseoperatorconfigurations/finalizers
+  verbs:
+    - update
+- apiGroups:
+    - clickhouse.altinity.com
+  resources:
+    - clickhouseinstallations/status
+    - clickhouseinstallationtemplates/status
+    - clickhouseoperatorconfigurations/status
+  verbs:
+    - create
+    - delete
+    - get
+    - update
+    - patch
+- apiGroups:
+    - ""
+  resources:
+    - secrets
+  verbs:
+    - get
+    - list
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/clusterrolebinding.yaml

@@ -0,0 +1,18 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Setup ClusterRoleBinding between ClusterRole and ServiceAccount.
+# ClusterRoleBinding is namespace-less and must have unique name
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: clickhouse-operator-posthog
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: clickhouse-operator-posthog
+subjects:
+- kind: ServiceAccount
+  name: clickhouse-operator
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/configmap.yaml

@@ -0,0 +1,418 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+  config.yaml: |
+    ################################################
+    ##
+    ## Watch Namespaces Section
+    ##
+    ################################################
+    
+    # List of namespaces where clickhouse-operator watches for events.
+    # Concurrently running operators should watch on different namespaces
+    #watchNamespaces: ["dev", "test"]
+    watchNamespaces: []
+    
+    ################################################
+    ##
+    ## Additional Configuration Files Section
+    ##
+    ################################################
+    
+    # Path to folder where ClickHouse configuration files common for all instances within CHI are located.
+    chCommonConfigsPath: config.d
+    
+    # Path to folder where ClickHouse configuration files unique for each instance (host) within CHI are located.
+    chHostConfigsPath: conf.d
+    
+    # Path to folder where ClickHouse configuration files with users settings are located.
+    # Files are common for all instances within CHI
+    chUsersConfigsPath: users.d
+    
+    # Path to folder where ClickHouseInstallation .yaml manifests are located.
+    # Manifests are applied in sorted alpha-numeric order
+    chiTemplatesPath: templates.d
+    
+    ################################################
+    ##
+    ## Cluster Create/Update/Delete Objects Section
+    ##
+    ################################################
+    
+    # How many seconds to wait for created/updated StatefulSet to be Ready
+    statefulSetUpdateTimeout: 300
+    
+    # How many seconds to wait between checks for created/updated StatefulSet status
+    statefulSetUpdatePollPeriod: 5
+    
+    # What to do in case created StatefulSet is not in Ready after `statefulSetUpdateTimeout` seconds
+    # Possible options:
+    # 1. abort - do nothing, just break the process and wait for admin
+    # 2. delete - delete newly created problematic StatefulSet
+    # 3. ignore - ignore error, pretend nothing happened and move on to the next StatefulSet
+    onStatefulSetCreateFailureAction: ignore
+    
+    # What to do in case updated StatefulSet is not in Ready after `statefulSetUpdateTimeout` seconds
+    # Possible options:
+    # 1. abort - do nothing, just break the process and wait for admin
+    # 2. rollback - delete Pod and rollback StatefulSet to previous Generation.
+    # Pod would be recreated by StatefulSet based on rollback-ed configuration
+    # 3. ignore - ignore error, pretend nothing happened and move on to the next StatefulSet
+    onStatefulSetUpdateFailureAction: rollback
+    
+    ################################################
+    ##
+    ## ClickHouse Settings Section
+    ##
+    ################################################
+    
+    # Default values for ClickHouse user configuration
+    # 1. user/profile - string
+    # 2. user/quota - string
+    # 3. user/networks/ip - multiple strings
+    # 4. user/password - string
+    chConfigUserDefaultProfile: default
+    chConfigUserDefaultQuota: default
+    chConfigUserDefaultNetworksIP:
+      - "::1"
+      - "127.0.0.1"
+    chConfigUserDefaultPassword: "default"
+    
+    # Default host_regexp to limit network connectivity from outside
+    chConfigNetworksHostRegexpTemplate: "(chi-{chi}-[^.]+\\d+-\\d+|clickhouse\\-{chi})\\.{namespace}\\.svc\\.cluster\\.local$"
+    
+    ################################################
+    ##
+    ## Access to ClickHouse instances
+    ##
+    ################################################
+    
+    # ClickHouse credentials (username, password and port) to be used by operator to connect to ClickHouse instances
+    # for:
+    # 1. Metrics requests
+    # 2. Schema maintenance
+    # 3. DROP DNS CACHE
+    # User with such credentials can be specified in additional ClickHouse .xml config files,
+    # located in `chUsersConfigsPath` folder
+    chUsername: "clickhouse_operator"
+    chPassword: "clickhouse_operator_password"
+    
+    # Location of k8s Secret with username and password to be used by operator to connect to ClickHouse instances
+    # Can be used instead of explicitly specified username and password
+    chCredentialsSecretNamespace: ""
+    chCredentialsSecretName: ""
+    
+    # Port where to connect to ClickHouse instances to
+    chPort: 8123
+    
+    ################################################
+    ##
+    ## Log parameters
+    ##
+    ################################################
+    
+    logtostderr: "true"
+    alsologtostderr: "false"
+    v: "1"
+    stderrthreshold: ""
+    vmodule: ""
+    log_backtrace_at: ""
+    
+    ################################################
+    ##
+    ## Runtime parameters
+    ##
+    ################################################
+    
+    # Max number of concurrent reconciles in progress
+    reconcileThreadsNumber: 10
+    reconcileWaitExclude: true
+    reconcileWaitInclude: false
+    
+    ################################################
+    ##
+    ## Labels management parameters
+    ##
+    ################################################
+    
+    # When propagating labels from the chi's `metadata.labels` section to child objects' `metadata.labels`,
+    # exclude labels from the following list:
+    #excludeFromPropagationLabels:
+    #  - "labelA"
+    #  - "labelB"
+    
+    # Whether to append *Scope* labels to StatefulSet and Pod.
+    # Full list of available *scope* labels check in labeler.go
+    #  LabelShardScopeIndex
+    #  LabelReplicaScopeIndex
+    #  LabelCHIScopeIndex
+    #  LabelCHIScopeCycleSize
+    #  LabelCHIScopeCycleIndex
+    #  LabelCHIScopeCycleOffset
+    #  LabelClusterScopeIndex
+    #  LabelClusterScopeCycleSize
+    #  LabelClusterScopeCycleIndex
+    #  LabelClusterScopeCycleOffset
+    appendScopeLabels: "no"
+    
+    ################################################
+    ##
+    ## Pod management parameters
+    ##
+    ################################################
+    # Grace period for Pod termination.
+    # How many seconds to wait between sending
+    # SIGTERM and SIGKILL during Pod termination process.
+    # Increase this number is case of slow shutdown.
+    terminationGracePeriod: 30
+
+---
+
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-confd-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-confd-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+
+---
+
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-configd-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-configd-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+  01-clickhouse-01-listen.xml: |
+    <yandex>
+        <!-- Listen wildcard address to allow accepting connections from other containers and host network. -->
+        <listen_host>::</listen_host>
+        <listen_host>0.0.0.0</listen_host>
+        <listen_try>1</listen_try>
+    </yandex>
+
+  01-clickhouse-02-logger.xml: |
+    <yandex>
+        <logger>
+            <!-- Possible levels: https://github.com/pocoproject/poco/blob/develop/Foundation/include/Poco/Logger.h#L105 -->
+            <level>debug</level>
+            <log>/var/log/clickhouse-server/clickhouse-server.log</log>
+            <errorlog>/var/log/clickhouse-server/clickhouse-server.err.log</errorlog>
+            <size>1000M</size>
+            <count>10</count>
+            <!-- Default behavior is autodetection (log to console if not daemon mode and is tty) -->
+            <console>1</console>
+        </logger>
+    </yandex>
+
+  01-clickhouse-03-query_log.xml: |
+    <yandex>
+        <query_log replace="1">
+            <database>system</database>
+            <table>query_log</table>
+            <engine>Engine = MergeTree PARTITION BY event_date ORDER BY event_time TTL event_date + interval 30 day</engine>
+            <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+        </query_log>
+        <query_thread_log remove="1"/>
+    </yandex>
+
+  01-clickhouse-04-part_log.xml: |
+    <yandex>
+        <part_log replace="1">
+            <database>system</database>
+            <table>part_log</table>
+            <engine>Engine = MergeTree PARTITION BY event_date ORDER BY event_time TTL event_date + interval 30 day</engine>
+            <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+        </part_log>
+    </yandex>
+
+---
+
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-templatesd-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-templatesd-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+  001-templates.json.example: |
+    {
+      "apiVersion": "clickhouse.altinity.com/v1",
+      "kind": "ClickHouseInstallationTemplate",
+      "metadata": {
+        "name": "01-default-volumeclaimtemplate"
+      },
+      "spec": {
+        "templates": {
+          "volumeClaimTemplates": [
+            {
+              "name": "chi-default-volume-claim-template",
+              "spec": {
+                "accessModes": [
+                  "ReadWriteOnce"
+                ],
+                "resources": {
+                  "requests": {
+                    "storage": "2Gi"
+                  }
+                }
+              }
+            }
+          ],
+          "podTemplates": [
+            {
+              "name": "chi-default-oneperhost-pod-template",
+              "distribution": "OnePerHost",
+              "spec": {
+                "containers" : [
+                  {
+                    "name": "clickhouse",
+                    "image": "yandex/clickhouse-server:19.3.7",
+                    "ports": [
+                      {
+                        "name": "http",
+                        "containerPort": 8123
+                      },
+                      {
+                        "name": "client",
+                        "containerPort": 9000
+                      },
+                      {
+                        "name": "interserver",
+                        "containerPort": 9009
+                      }
+                    ]
+                  }
+                ]
+              }
+            }
+          ]
+        }
+      }
+    }
+
+  default-pod-template.yaml.example: |
+    apiVersion: "clickhouse.altinity.com/v1"
+    kind: "ClickHouseInstallationTemplate"
+    metadata:
+      name: "default-oneperhost-pod-template"
+    spec:
+      templates:
+        podTemplates:
+          - name: default-oneperhost-pod-template
+            distribution: "OnePerHost"
+  default-storage-template.yaml.example: |
+    apiVersion: "clickhouse.altinity.com/v1"
+    kind: "ClickHouseInstallationTemplate"
+    metadata:
+      name: "default-storage-template-2Gi"
+    spec:
+      templates:
+        volumeClaimTemplates:
+          - name: default-storage-template-2Gi
+            spec:
+              accessModes:
+                - ReadWriteOnce
+              resources:
+                requests:
+                  storage: 2Gi
+
+  readme: |
+    Templates in this folder are packaged with an operator and available via 'useTemplate'
+
+---
+
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-usersd-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-usersd-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+  01-clickhouse-user.xml: |
+    <yandex>
+        <users>
+            <clickhouse_operator>
+                <networks>
+                    <ip>127.0.0.1</ip>
+                    <ip>0.0.0.0/0</ip>
+                    <ip>::/0</ip>
+                </networks>
+                <password_sha256_hex>716b36073a90c6fe1d445ac1af85f4777c5b7a155cea359961826a030513e448</password_sha256_hex>
+                <profile>clickhouse_operator</profile>
+                <quota>default</quota>
+            </clickhouse_operator>
+        </users>
+        <profiles>
+            <clickhouse_operator>
+                <log_queries>0</log_queries>
+                <skip_unavailable_shards>1</skip_unavailable_shards>
+                <http_connection_timeout>10</http_connection_timeout>
+            </clickhouse_operator>
+        </profiles>
+    </yandex>
+
+  02-clickhouse-default-profile.xml: |
+    <yandex>
+      <profiles>
+        <default>
+          <log_queries>1</log_queries>
+          <connect_timeout_with_failover_ms>1000</connect_timeout_with_failover_ms>
+          <distributed_aggregation_memory_efficient>1</distributed_aggregation_memory_efficient>
+          <parallel_view_processing>1</parallel_view_processing>
+        </default>
+      </profiles>
+    </yandex>
+  03-database-ordinary.xml: |
+    <!--  Remove it for ClickHouse versions before 20.4 -->
+    <yandex>
+        <profiles>
+            <default>
+                <default_database_engine>Ordinary</default_database_engine>
+            </default>
+        </profiles>
+    </yandex>
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/deployment.yaml

@@ -0,0 +1,129 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# NAMESPACE=posthog
+# COMMENT=
+# OPERATOR_IMAGE=altinity/clickhouse-operator:latest
+# METRICS_EXPORTER_IMAGE=altinity/metrics-exporter:latest
+#
+# Setup Deployment for clickhouse-operator
+# Deployment would be created in kubectl-specified namespace
+kind: Deployment
+apiVersion: apps/v1
+metadata:
+  name: clickhouse-operator
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: clickhouse-operator
+  template:
+    metadata:
+      labels:
+        app: clickhouse-operator
+      annotations:
+        prometheus.io/port: '8888'
+        prometheus.io/scrape: 'true'
+    spec:
+      serviceAccountName: clickhouse-operator
+      volumes:
+        - name: etc-clickhouse-operator-folder
+          configMap:
+            name: etc-clickhouse-operator-files
+        - name: etc-clickhouse-operator-confd-folder
+          configMap:
+            name: etc-clickhouse-operator-confd-files
+        - name: etc-clickhouse-operator-configd-folder
+          configMap:
+            name: etc-clickhouse-operator-configd-files
+        - name: etc-clickhouse-operator-templatesd-folder
+          configMap:
+            name: etc-clickhouse-operator-templatesd-files
+        - name: etc-clickhouse-operator-usersd-folder
+          configMap:
+            name: etc-clickhouse-operator-usersd-files
+      containers:
+        - name: clickhouse-operator
+          image: altinity/clickhouse-operator:latest
+          imagePullPolicy: Always
+          volumeMounts:
+            - name: etc-clickhouse-operator-folder
+              mountPath: /etc/clickhouse-operator
+            - name: etc-clickhouse-operator-confd-folder
+              mountPath: /etc/clickhouse-operator/conf.d
+            - name: etc-clickhouse-operator-configd-folder
+              mountPath: /etc/clickhouse-operator/config.d
+            - name: etc-clickhouse-operator-templatesd-folder
+              mountPath: /etc/clickhouse-operator/templates.d
+            - name: etc-clickhouse-operator-usersd-folder
+              mountPath: /etc/clickhouse-operator/users.d
+          env:
+            # Pod-specific
+            # spec.nodeName: ip-172-20-52-62.ec2.internal
+            - name: OPERATOR_POD_NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+            # metadata.name: clickhouse-operator-6f87589dbb-ftcsf
+            - name: OPERATOR_POD_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.name
+            # metadata.namespace: kube-system
+            - name: OPERATOR_POD_NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+            # status.podIP: 100.96.3.2
+            - name: OPERATOR_POD_IP
+              valueFrom:
+                fieldRef:
+                  fieldPath: status.podIP
+            # spec.serviceAccount: clickhouse-operator
+            # spec.serviceAccountName: clickhouse-operator
+            - name: OPERATOR_POD_SERVICE_ACCOUNT
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.serviceAccountName
+
+            # Container-specific
+            - name: OPERATOR_CONTAINER_CPU_REQUEST
+              valueFrom:
+                resourceFieldRef:
+                  containerName: clickhouse-operator
+                  resource: requests.cpu
+            - name: OPERATOR_CONTAINER_CPU_LIMIT
+              valueFrom:
+                resourceFieldRef:
+                  containerName: clickhouse-operator
+                  resource: limits.cpu
+            - name: OPERATOR_CONTAINER_MEM_REQUEST
+              valueFrom:
+                resourceFieldRef:
+                  containerName: clickhouse-operator
+                  resource: requests.memory
+            - name: OPERATOR_CONTAINER_MEM_LIMIT
+              valueFrom:
+                resourceFieldRef:
+                  containerName: clickhouse-operator
+                  resource: limits.memory
+
+        - name: metrics-exporter
+          image: altinity/metrics-exporter:latest
+          imagePullPolicy: Always
+          volumeMounts:
+            - name: etc-clickhouse-operator-folder
+              mountPath: /etc/clickhouse-operator
+            - name: etc-clickhouse-operator-confd-folder
+              mountPath: /etc/clickhouse-operator/conf.d
+            - name: etc-clickhouse-operator-configd-folder
+              mountPath: /etc/clickhouse-operator/config.d
+            - name: etc-clickhouse-operator-templatesd-folder
+              mountPath: /etc/clickhouse-operator/templates.d
+            - name: etc-clickhouse-operator-usersd-folder
+              mountPath: /etc/clickhouse-operator/users.d
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/service.yaml

@@ -0,0 +1,26 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# NAMESPACE=posthog
+# COMMENT=
+#
+# Setup ClusterIP Service to provide monitoring metrics for Prometheus
+# Service would be created in kubectl-specified namespace
+# In order to get access outside of k8s it should be exposed as:
+# kubectl --namespace prometheus port-forward service/prometheus 9090
+# and point browser to localhost:9090
+kind: Service
+apiVersion: v1
+metadata:
+  name: clickhouse-operator-metrics
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+spec:
+  ports:
+    - port: 8888
+      name: clickhouse-operator-metrics
+  selector:
+    app: clickhouse-operator
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/serviceaccount.yaml

@@ -0,0 +1,15 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# COMMENT=
+# NAMESPACE=posthog
+# NAME=clickhouse-operator
+#
+# Setup ServiceAccount
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: clickhouse-operator
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+
+{{- end }}

deploy/kubernetes/platform/templates/otel-collector-metrics/otel-collector-metrics-config.yaml

@@ -0,0 +1,53 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: otel-collector-metrics-conf
+  labels:
+    app: opentelemetry
+    component: otel-collector-metrics-conf
+data:
+  otel-collector-metrics-config: |
+    receivers:
+      otlp:
+        protocols:
+          grpc:
+          http:
+
+      # Data sources: metrics
+      prometheus:
+        config:
+          scrape_configs:
+            - job_name: "otel-collector"
+              scrape_interval: 30s
+              static_configs:
+                - targets: ["otel-collector:8889"]
+    processors:
+      batch:
+        send_batch_size: 1000
+        timeout: 10s
+      memory_limiter:
+        # Same as --mem-ballast-size-mib CLI argument
+        ballast_size_mib: 683
+        # 80% of maximum memory up to 2G
+        limit_mib: 1500
+        # 25% of limit up to 2G
+        spike_limit_mib: 512
+        check_interval: 5s
+      # queued_retry:
+      #   num_workers: 4
+      #   queue_size: 100
+      #   retry_on_failure: true
+    extensions:
+      health_check: {}
+      zpages: {}
+    exporters:
+      clickhousemetricswrite:
+        endpoint: tcp://signoz-clickhouse:9000/?database=signoz_metrics&username=clickhouse_operator&password=clickhouse_operator_password
+
+    service:
+      extensions: [health_check, zpages]
+      pipelines:
+        metrics:
+          receivers: [otlp, prometheus]
+          processors: [batch]
+          exporters: [clickhousemetricswrite]

deploy/kubernetes/platform/templates/otel-collector-metrics/otel-collector-metrics-deployment.yaml

@@ -0,0 +1,72 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: otel-collector-metrics
+  labels:
+    app: opentelemetry
+    component: otel-collector-metrics
+spec:
+  selector:
+    matchLabels:
+      app: opentelemetry
+      component: otel-collector-metrics
+  minReadySeconds: 5
+  progressDeadlineSeconds: 120
+  replicas: 1 #TODO - adjust this to your own requirements
+  template:
+    metadata:
+      labels:
+        app: opentelemetry
+        component: otel-collector-metrics
+    spec:
+      containers:
+      - command:
+          - "/otelcontribcol"
+          - "--config=/conf/otel-collector-metrics-config.yaml"
+#           Memory Ballast size should be max 1/3 to 1/2 of memory.
+          - "--mem-ballast-size-mib=683"
+        image: signoz/otelcontribcol:0.4.2
+        name: otel-collector
+        resources:
+          limits:
+            cpu: 1
+            memory: 2Gi
+          requests:
+            cpu: 200m
+            memory: 400Mi
+        ports:
+        - containerPort: 55679 # Default endpoint for ZPages.
+        - containerPort: 55680 # Default endpoint for OpenTelemetry receiver.
+        - containerPort: 55681 # Default endpoint for OpenTelemetry HTTP/1.0 receiver.
+        - containerPort: 4317 # Default endpoint for OpenTelemetry GRPC receiver.
+        - containerPort: 14250 # Default endpoint for Jaeger GRPC receiver.
+        - containerPort: 14268 # Default endpoint for Jaeger HTTP receiver.
+        - containerPort: 9411 # Default endpoint for Zipkin receiver.
+        - containerPort: 8888  # Default endpoint for querying metrics.
+        volumeMounts:
+        - name: otel-collector-metrics-config-vol
+          mountPath: /conf
+#        - name: otel-collector-secrets
+#          mountPath: /secrets
+        livenessProbe:
+          httpGet:
+            path: /
+            port: 13133 # Health Check extension default port.
+        readinessProbe:
+          httpGet:
+            path: /
+            port: 13133 # Health Check extension default port.
+      volumes:
+        - configMap:
+            name: otel-collector-metrics-conf
+            items:
+              - key: otel-collector-metrics-config
+                path: otel-collector-metrics-config.yaml
+          name: otel-collector-metrics-config-vol
+#        - secret:
+#            name: otel-collector-secrets
+#            items:
+#              - key: cert.pem
+#                path: cert.pem
+#              - key: key.pem
+#                path: key.pem

deploy/kubernetes/platform/templates/otel-collector-metrics/otel-collector-metrics-service.yaml

@@ -0,0 +1,31 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: otel-collector-metrics
+  labels:
+    app: opentelemetry
+    component: otel-collector-metrics
+spec:
+  ports:
+  - name: otlp # Default endpoint for OpenTelemetry receiver.
+    port: 55680
+    protocol: TCP
+    targetPort: 55680
+  - name: otlp-http-legacy # Default endpoint for OpenTelemetry receiver.
+    port: 55681
+    protocol: TCP
+    targetPort: 55681
+  - name: otlp-grpc # Default endpoint for OpenTelemetry receiver.
+    port: 4317
+    protocol: TCP
+    targetPort: 4317
+  - name: jaeger-grpc # Default endpoing for Jaeger gRPC receiver
+    port: 14250
+  - name: jaeger-thrift-http # Default endpoint for Jaeger HTTP receiver.
+    port: 14268
+  - name: zipkin # Default endpoint for Zipkin receiver.
+    port: 9411
+  - name: metrics # Default endpoint for querying metrics.
+    port: 8888
+  selector:
+    component: otel-collector-metrics

deploy/kubernetes/platform/templates/otel-collector/otel-collector-config.yaml

@@ -0,0 +1,67 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: otel-collector-conf
+  labels:
+    app: opentelemetry
+    component: otel-collector-conf
+data:
+  otel-collector-config: |
+    receivers:
+      otlp/spanmetrics:
+        protocols:
+          grpc:
+            endpoint: "localhost:12345"
+      otlp:
+        protocols:
+          grpc:
+          http:
+      jaeger:
+        protocols:
+          grpc:
+          thrift_http:
+    processors:
+      batch:
+        send_batch_size: 1000
+        timeout: 10s
+      signozspanmetrics/prometheus:
+        metrics_exporter: prometheus
+        latency_histogram_buckets: [100us, 1ms, 2ms, 6ms, 10ms, 50ms, 100ms, 250ms, 500ms, 1000ms, 1400ms, 2000ms, 5s, 10s, 20s, 40s, 60s ]
+      memory_limiter:
+        # Same as --mem-ballast-size-mib CLI argument
+        ballast_size_mib: 683
+        # 80% of maximum memory up to 2G
+        limit_mib: 1500
+        # 25% of limit up to 2G
+        spike_limit_mib: 512
+        check_interval: 5s
+      # queued_retry:
+      #   num_workers: 4
+      #   queue_size: 100
+      #   retry_on_failure: true
+    extensions:
+      health_check: {}
+      zpages: {}
+    exporters:
+      clickhouse:
+        datasource: tcp://signoz-clickhouse:9000?username=clickhouse_operator&password=clickhouse_operator_password
+      clickhousemetricswrite:
+        endpoint: tcp://signoz-clickhouse:9000/?database=signoz_metrics&username=clickhouse_operator&password=clickhouse_operator_password
+        resource_to_telemetry_conversion:
+          enabled: true
+      prometheus:
+        endpoint: "0.0.0.0:8889"
+    service:
+      extensions: [health_check, zpages]
+      pipelines:
+        traces:
+          receivers: [jaeger, otlp]
+          processors: [signozspanmetrics/prometheus, batch]
+          exporters: [clickhouse]
+        metrics:
+          receivers: [otlp]
+          processors: [batch]
+          exporters: [clickhousemetricswrite]
+        metrics/spanmetrics:
+          receivers: [otlp/spanmetrics]
+          exporters: [prometheus]

deploy/kubernetes/platform/templates/otel-collector/otel-collector-deployment.yaml

@@ -21,11 +21,11 @@ spec:
     spec:
       containers:
       - command:
-          - "/otelcol"
+          - "/otelcontribcol"
           - "--config=/conf/otel-collector-config.yaml"
 #           Memory Ballast size should be max 1/3 to 1/2 of memory.
           - "--mem-ballast-size-mib=683"
-        image: otel/opentelemetry-collector:0.18.0
+        image: signoz/otelcontribcol:0.4.2
         name: otel-collector
         resources:
           limits:
@@ -43,6 +43,7 @@ spec:
         - containerPort: 14268 # Default endpoint for Jaeger HTTP receiver.
         - containerPort: 9411 # Default endpoint for Zipkin receiver.
         - containerPort: 8888  # Default endpoint for querying metrics.
+        - containerPort: 8889  # Default endpoint for prometheus exported metrics.
         volumeMounts:
         - name: otel-collector-config-vol
           mountPath: /conf

deploy/kubernetes/platform/templates/otel-collector/otel-collector-service.yaml

@@ -27,5 +27,7 @@ spec:
     port: 9411
   - name: metrics # Default endpoint for querying metrics.
     port: 8888
+  - name: prometheus-metrics # Default endpoint for querying prometheus metrics.
+    port: 8889
   selector:
     component: otel-collector

deploy/kubernetes/platform/values.yaml

@@ -1,51 +1,15 @@
 zookeeper:
-    autopurge:
+  autopurge:
-        purgeInterval: 1
+    purgeInterval: 1
-
-kafka:
-    zookeeper:
-        enabled: false
-    externalZookeeper:
-        servers: ["signoz-zookeeper:2181"]
-    zookeeperConnectionTimeoutMs: 6000
-
-druid:
-    image:
-        tag: 0.21.1-rc2
-
-    configVars:
-
-        # To store data on local disks attached
-        druid_extensions_loadList: '["druid-histogram", "druid-datasketches", "druid-lookups-cached-global", "postgresql-metadata-storage", "druid-kafka-indexing-service"]'
-        druid_storage_type: local
-
-
-        # # To store data in S3
-        # druid_extensions_loadList: '["druid-histogram", "druid-datasketches", "druid-lookups-cached-global", "postgresql-metadata-storage", "druid-kafka-indexing-service", "druid-s3-extensions"]'
-        # druid_storage_type: s3
-        # druid_storage_bucket: signoz-druid
-        # druid_storage_baseKey: baseKey
-        # AWS_ACCESS_KEY_ID: <your secret id>
-        # AWS_SECRET_ACCESS_KEY: <your secret key>
-        # AWS_REGION: <your region>
-
-    historical:
-        persistence:
-            size: "20Gi"
-
-    zkHosts: "signoz-zookeeper:2181"
-
-    zookeeper:
-        enabled: false
-
-flattener-processor:
-    configVars:
-        KAFKA_BROKER: signoz-kafka:9092
-        KAFKA_INPUT_TOPIC: otlp_spans
-        KAFKA_OUTPUT_TOPIC: flattened_spans
 
 query-service:
-    configVars:
+  configVars:
-        DruidClientUrl: http://signoz-druid-router:8888
+    ClickHouseUrl: http://signoz-clickhouse:9000?username=clickhouse_operator&password=clickhouse_operator_password
-        DruidDatasource: flattened_spans
+    STORAGE: clickhouse
-        STORAGE: druid
+
+cloud: aws
+
+clickhouseOperator:
+  enabled: true
+  storage: 20Gi
+  serviceType: ClusterIP

sample-apps/hotrod/deployment.yaml

@@ -16,14 +16,14 @@ spec:
         service: hotrod
     spec:
       containers:
-      - args:
+        - args:
-        - all
+            - all
-        env:
+          env:
-        - name: JAEGER_ENDPOINT
+            - name: JAEGER_ENDPOINT
-          value: http://otel-collector.platform.svc.cluster.local:14268/api/traces
+              value: http://otel-collector.platform.svc.cluster.local:14268/api/traces
-        image: jaegertracing/example-hotrod:latest
+          image: jaegertracing/example-hotrod:latest
-        imagePullPolicy: IfNotPresent
+          imagePullPolicy: IfNotPresent
-        name: hotrod
+          name: hotrod
-        ports:
+          ports:
-        - containerPort: 8080
+            - containerPort: 8080
       restartPolicy: Always