bakery-admin/bakery-ia
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Imporve monitoring 6

Browse Source
This commit is contained in:
Urtzi Alfaro
2026-01-10 13:43:38 +01:00
parent c05538cafb
commit b089c216db
13 changed files with 1248 additions and 2546 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
infrastructure/helm/signoz-values-dev.yaml
View File

@@ -779,33 +779,63 @@ otelCollector:
processors: [memory_limiter, batch, resourcedetection, k8sattributes]
exporters: [clickhouselogsexporter]
# ClusterRole configuration for Kubernetes monitoring
# CRITICAL: Required for k8s_cluster receiver to access Kubernetes API
# Without these permissions, k8s metrics will not appear in SigNoz UI
clusterRole:
create: true
name: "signoz-otel-collector-bakery-ia"
annotations: {}
# Complete RBAC rules required by k8sclusterreceiver
# Based on OpenTelemetry and SigNoz official documentation
rules:
# Core API group - fundamental Kubernetes resources
- apiGroups: [""]
resources:
- "events"
- "namespaces"
- "nodes"
- "nodes/proxy"
- "nodes/metrics"
- "nodes/spec"
- "pods"
- "pods/status"
- "replicationcontrollers"
- "replicationcontrollers/status"
- "resourcequotas"
- "services"
- "endpoints"
verbs: ["get", "list", "watch"]
# Apps API group - modern workload controllers
- apiGroups: ["apps"]
resources: ["deployments", "daemonsets", "statefulsets", "replicasets"]
verbs: ["get", "list", "watch"]
# Batch API group - job management
- apiGroups: ["batch"]
resources: ["jobs", "cronjobs"]
verbs: ["get", "list", "watch"]
# Autoscaling API group - HPA metrics (CRITICAL)
- apiGroups: ["autoscaling"]
resources: ["horizontalpodautoscalers"]
verbs: ["get", "list", "watch"]
# Extensions API group - legacy support
- apiGroups: ["extensions"]
resources: ["deployments", "daemonsets", "replicasets"]
verbs: ["get", "list", "watch"]
# Metrics API group - resource metrics
- apiGroups: ["metrics.k8s.io"]
resources: ["nodes", "pods"]
verbs: ["get", "list", "watch"]
clusterRoleBinding:
annotations: {}
name: "signoz-otel-collector-bakery-ia"
# Additional Configuration
serviceAccount:
create: true
annotations: {}
name: "signoz-otel-collector"
# RBAC Configuration for Kubernetes monitoring
# Required for k8s_cluster and kubeletstats receivers to access Kubernetes API
rbac:
create: true
rules:
- apiGroups: [""]
resources: ["nodes", "nodes/proxy", "nodes/metrics", "pods", "services", "endpoints", "namespaces"]
verbs: ["get", "list", "watch"]
- apiGroups: ["apps"]
resources: ["deployments", "daemonsets", "statefulsets", "replicasets"]
verbs: ["get", "list", "watch"]
- apiGroups: ["batch"]
resources: ["jobs", "cronjobs"]
verbs: ["get", "list", "watch"]
- apiGroups: ["extensions"]
resources: ["deployments", "daemonsets", "replicasets"]
verbs: ["get", "list", "watch"]
- apiGroups: ["metrics.k8s.io"]
resources: ["nodes", "pods"]
verbs: ["get", "list", "watch"]
# Security Context
securityContext:
runAsNonRoot: true

72
infrastructure/helm/signoz-values-prod.yaml
View File

@@ -893,6 +893,57 @@ otelCollector:
targetCPUUtilizationPercentage: 70
targetMemoryUtilizationPercentage: 80
# ClusterRole configuration for Kubernetes monitoring
# CRITICAL: Required for k8s_cluster receiver to access Kubernetes API
# Without these permissions, k8s metrics will not appear in SigNoz UI
clusterRole:
create: true
name: "signoz-otel-collector-bakery-ia"
annotations: {}
# Complete RBAC rules required by k8sclusterreceiver
# Based on OpenTelemetry and SigNoz official documentation
rules:
# Core API group - fundamental Kubernetes resources
- apiGroups: [""]
resources:
- "events"
- "namespaces"
- "nodes"
- "nodes/proxy"
- "nodes/metrics"
- "nodes/spec"
- "pods"
- "pods/status"
- "replicationcontrollers"
- "replicationcontrollers/status"
- "resourcequotas"
- "services"
- "endpoints"
verbs: ["get", "list", "watch"]
# Apps API group - modern workload controllers
- apiGroups: ["apps"]
resources: ["deployments", "daemonsets", "statefulsets", "replicasets"]
verbs: ["get", "list", "watch"]
# Batch API group - job management
- apiGroups: ["batch"]
resources: ["jobs", "cronjobs"]
verbs: ["get", "list", "watch"]
# Autoscaling API group - HPA metrics (CRITICAL)
- apiGroups: ["autoscaling"]
resources: ["horizontalpodautoscalers"]
verbs: ["get", "list", "watch"]
# Extensions API group - legacy support
- apiGroups: ["extensions"]
resources: ["deployments", "daemonsets", "replicasets"]
verbs: ["get", "list", "watch"]
# Metrics API group - resource metrics
- apiGroups: ["metrics.k8s.io"]
resources: ["nodes", "pods"]
verbs: ["get", "list", "watch"]
clusterRoleBinding:
annotations: {}
name: "signoz-otel-collector-bakery-ia"
# Schema Migrator - Manages ClickHouse schema migrations
schemaMigrator:
enabled: true
@@ -911,27 +962,6 @@ serviceAccount:
annotations: {}
name: "signoz"
# RBAC Configuration for Kubernetes monitoring
# Required for k8s_cluster receiver to access Kubernetes API
rbac:
create: true
rules:
- apiGroups: [""]
resources: ["nodes", "nodes/proxy", "nodes/metrics", "pods", "services", "endpoints", "namespaces"]
verbs: ["get", "list", "watch"]
- apiGroups: ["apps"]
resources: ["deployments", "daemonsets", "statefulsets", "replicasets"]
verbs: ["get", "list", "watch"]
- apiGroups: ["batch"]
resources: ["jobs", "cronjobs"]
verbs: ["get", "list", "watch"]
- apiGroups: ["extensions"]
resources: ["deployments", "daemonsets", "replicasets"]
verbs: ["get", "list", "watch"]
- apiGroups: ["metrics.k8s.io"]
resources: ["nodes", "pods"]
verbs: ["get", "list", "watch"]
# Security Context
securityContext:
runAsNonRoot: true

32
infrastructure/signoz/dashboards/infrastructure-monitoring.json
View File

@@ -99,10 +99,12 @@
"filters": {
"items": [
{
"id": "filter-k8s-namespace",
"key": {
"id": "k8s.namespace.name--string--tag--false",
"key": "k8s.namespace.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
},
"op": "=",
@@ -156,10 +158,12 @@
"filters": {
"items": [
{
"id": "filter-k8s-namespace",
"key": {
"id": "k8s.namespace.name--string--tag--false",
"key": "k8s.namespace.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
},
"op": "=",
@@ -220,10 +224,12 @@
"filters": {
"items": [
{
"id": "filter-k8s-namespace",
"key": {
"id": "k8s.namespace.name--string--tag--false",
"key": "k8s.namespace.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
},
"op": "=",
@@ -240,9 +246,10 @@
"orderBy": [],
"groupBy": [
{
"id": "k8s.pod.name--string--tag--false",
"key": "k8s.pod.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
}
],
@@ -293,9 +300,10 @@
"orderBy": [],
"groupBy": [
{
"id": "k8s.node.name--string--tag--false",
"key": "k8s.node.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
}
],
@@ -337,10 +345,12 @@
"filters": {
"items": [
{
"id": "filter-k8s-namespace",
"key": {
"id": "k8s.namespace.name--string--tag--false",
"key": "k8s.namespace.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
},
"op": "=",
@@ -357,9 +367,10 @@
"orderBy": [],
"groupBy": [
{
"id": "k8s.deployment.name--string--tag--false",
"key": "k8s.deployment.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
}
],
@@ -382,10 +393,12 @@
"filters": {
"items": [
{
"id": "filter-k8s-namespace",
"key": {
"id": "k8s.namespace.name--string--tag--false",
"key": "k8s.namespace.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
},
"op": "=",
@@ -402,9 +415,10 @@
"orderBy": [],
"groupBy": [
{
"id": "k8s.deployment.name--string--tag--false",
"key": "k8s.deployment.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
}
],

16
infrastructure/signoz/dashboards/system-health.json
View File

@@ -90,10 +90,12 @@
"filters": {
"items": [
{
"id": "filter-k8s-namespace",
"key": {
"id": "k8s.namespace.name--string--tag--false",
"key": "k8s.namespace.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
},
"op": "=",
@@ -147,10 +149,12 @@
"filters": {
"items": [
{
"id": "filter-k8s-namespace",
"key": {
"id": "k8s.namespace.name--string--tag--false",
"key": "k8s.namespace.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
},
"op": "=",
@@ -204,10 +208,12 @@
"filters": {
"items": [
{
"id": "filter-k8s-namespace",
"key": {
"id": "k8s.namespace.name--string--tag--false",
"key": "k8s.namespace.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
},
"op": "=",
@@ -261,10 +267,12 @@
"filters": {
"items": [
{
"id": "filter-k8s-namespace",
"key": {
"id": "k8s.namespace.name--string--tag--false",
"key": "k8s.namespace.name",
"dataType": "string",
"type": "resource",
"type": "tag",
"isColumn": false
},
"op": "=",