不确定我缺少了什么。请在下面找到我使用的所有配置脚本
2022-07-21T07:26:56.903Z info service/collector.go:220 Starting otelcol... {"service": "my-prom-instance", "Version": "0.54.0", "NumCPU": 4}
2022-07-21T07:26:56.903Z info service/collector.go:128 Everything is ready. Begin running and processing data. {"service": "my-prom-instance"}
2022-07-21T07:26:56.902Z debug discovery/manager.go:309 Discoverer channel closed {"service": "my-prom-instance", "kind": "receiver", "name": "prometheus", "pipeline": "metrics", "provider": "static/0"}
W0721 07:26:56.964183 1 reflector.go:324] k8s.io/client-go@v0.24.2/tools/cache/reflector.go:167: failed to list *v1.Pod: pods is forbidden: User "system:serviceaccount:monitoring:otel-collector-collector" cannot list resource "pods" in API group "" at the cluster scope
E0721 07:26:56.964871 1 reflector.go:138] k8s.io/client-go@v0.24.2/tools/cache/reflector.go:167: Failed to watch *v1.Pod: failed to list *v1.Pod: pods is forbidden: User "system:serviceaccount:monitoring:otel-collector-collector" cannot list resource "pods" in API group "" at the cluster scope
W0721 07:26:58.435237 1 reflector.go:324] k8s.io/client-go@v0.24.2/tools/cache/reflector.go:167: failed to list *v1.Pod: pods is forbidden: User "system:serviceaccount:monitoring:otel-collector-collector" cannot list resource "pods" in API group "" at the cluster scope
E0721 07:26:58.435924 1 reflector.go:138]
clusterRole.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: prometheus
namespace: monitoring
rules:
- apiGroups: [""]
resources:
- nodes
- nodes/proxy
- services
- endpoints
- pods
verbs: ["get", "list", "watch"]
- apiGroups:
- extensions
resources:
- ingresses
verbs: ["get", "list", "watch"]
- nonResourceURLs: ["/metrics"]
verbs: ["get"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: prometheus
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: prometheus
subjects:
- kind: ServiceAccount
name: default
namespace: monitoring
config-map.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-server-conf
labels:
name: prometheus-server-conf
namespace: monitoring
data:
prometheus.rules: |-
groups:
- name: devopscube demo alert
rules:
- alert: High Pod Memory
expr: sum(container_memory_usage_bytes) > 1
for: 1m
labels:
severity: slack
annotations:
summary: High Memory Usage
prometheus.yml: |-
global:
scrape_interval: 5s
evaluation_interval: 5s
rule_files:
- /etc/prometheus/prometheus.rules
alerting:
alertmanagers:
- scheme: http
static_configs:
- targets:
- "alertmanager.monitoring.svc:9093"
scrape_configs:
- job_name: 'node-exporter'
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- source_labels: [__meta_kubernetes_endpoints_name]
regex: 'node-exporter'
action: keep
- job_name: 'kubernetes-apiservers'
kubernetes_sd_configs:
- role: endpoints
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
action: keep
regex: default;kubernetes;https
- job_name: 'kubernetes-nodes'
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/${1}/proxy/metrics
- job_name: 'kubernetes-pods'
kubernetes_sd_configs:
- role: pod
relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
action: keep
regex: true
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
action: replace
regex: ([^:]+)(?::d+)?;(d+)
replacement: $1:$2
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: kubernetes_pod_name
- job_name: 'kube-state-metrics'
static_configs:
- targets: ['kube-state-metrics.kube-system.svc.cluster.local:8080']
- job_name: 'kubernetes-cadvisor'
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
- job_name: 'kubernetes-service-endpoints'
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
action: keep
regex: true
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
action: replace
target_label: __scheme__
regex: (https?)
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
action: replace
target_label: __address__
regex: ([^:]+)(?::d+)?;(d+)
replacement: $1:$2
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: kubernetes_name
普罗米修斯部署公司
apiVersion: apps/v1
kind: Deployment
metadata:
name: prometheus-deployment
namespace: monitoring
labels:
app: prometheus-server
spec:
replicas: 1
selector:
matchLabels:
app: prometheus-server
template:
metadata:
labels:
app: prometheus-server
spec:
containers:
- name: prometheus
image: prom/prometheus
args:
- "--config.file=/etc/prometheus/prometheus.yml"
- "--storage.tsdb.path=/prometheus/"
ports:
- containerPort: 9090
volumeMounts:
- name: prometheus-config-volume
mountPath: /etc/prometheus/
- name: prometheus-storage-volume
mountPath: /prometheus/
volumes:
- name: prometheus-config-volume
configMap:
defaultMode: 420
name: prometheus-server-conf
- name: prometheus-storage-volume
emptyDir: {}
otel-deployment.yaml
apiVersion: opentelemetry.io/v1alpha1
kind: OpenTelemetryCollector
metadata:
name: otel-collector
namespace: monitoring
spec:
config: |
receivers:
prometheus:
config:
scrape_configs:
- job_name: 'kube-state-metrics'
scrape_interval: 5s
scrape_timeout: 1s
static_configs:
- targets: ['kube-state-metrics.kube-system.svc.cluster.local:8080']
- job_name: k8s
kubernetes_sd_configs:
- role: pod
relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
regex: "true"
action: keep
metric_relabel_configs:
- source_labels: [__name__]
regex: "(request_duration_seconds.*|response_duration_seconds.*)"
action: keep
processors:
batch:
exporters:
logging:
service:
pipelines:
metrics:
receivers: [prometheus]
exporters: [logging]
telemetry:
logs:
level: debug
initial_fields:
service: my-prom-instance
otel-service.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: otel-collector-sa
namespace: monitoring
服务帐户是用名称otel collector sa定义的，并且您的ClusterRoleBinding链接到服务帐户默认