0119同步
This commit is contained in:
13553
OpenTelemetry/Collector_v3/01-cert-manager.yaml
Normal file
13553
OpenTelemetry/Collector_v3/01-cert-manager.yaml
Normal file
File diff suppressed because it is too large
Load Diff
17874
OpenTelemetry/Collector_v3/02-opentelemetry-operator.yaml
Normal file
17874
OpenTelemetry/Collector_v3/02-opentelemetry-operator.yaml
Normal file
File diff suppressed because it is too large
Load Diff
96
OpenTelemetry/Collector_v3/03-otel-gateway.yaml
Normal file
96
OpenTelemetry/Collector_v3/03-otel-gateway.yaml
Normal file
@@ -0,0 +1,96 @@
|
||||
apiVersion: opentelemetry.io/v1beta1
|
||||
kind: OpenTelemetryCollector
|
||||
metadata:
|
||||
name: otel-gateway
|
||||
namespace: opentelemetry-operator-system
|
||||
spec:
|
||||
mode: deployment
|
||||
replicas: 1
|
||||
serviceAccount: otel-gateway-collector # Operator 会自动创建并绑定权限
|
||||
config:
|
||||
receivers:
|
||||
otlp:
|
||||
protocols:
|
||||
grpc:
|
||||
endpoint: 0.0.0.0:4317
|
||||
http:
|
||||
endpoint: 0.0.0.0:4318
|
||||
|
||||
# --- 核心：采集 K8s 集群状态指标 ---
|
||||
# 采集 Deployment, DaemonSet, StatefulSet, HPA, Node 等资源的状态
|
||||
k8s_cluster:
|
||||
collection_interval: 30s
|
||||
node_conditions_to_report: [Ready, MemoryPressure, DiskPressure, PIDPressure]
|
||||
allocatable_types_to_report: [cpu, memory]
|
||||
|
||||
processors:
|
||||
batch:
|
||||
send_batch_size: 1000
|
||||
timeout: 10s
|
||||
memory_limiter:
|
||||
check_interval: 1s
|
||||
limit_percentage: 70
|
||||
spike_limit_percentage: 30
|
||||
|
||||
# 增加 K8s 元数据标签 (这也是 Gateway 的重要作用)
|
||||
k8sattributes:
|
||||
extract:
|
||||
metadata:
|
||||
- k8s.namespace.name
|
||||
- k8s.pod.name
|
||||
- k8s.deployment.name
|
||||
- k8s.statefulset.name
|
||||
- k8s.daemonset.name
|
||||
- k8s.cronjob.name
|
||||
- k8s.job.name
|
||||
- k8s.node.name
|
||||
pod_association:
|
||||
- sources:
|
||||
- from: resource_attribute
|
||||
name: k8s.pod.ip
|
||||
- sources:
|
||||
- from: resource_attribute
|
||||
name: k8s.pod.uid
|
||||
- sources:
|
||||
- from: connection
|
||||
|
||||
exporters:
|
||||
# 1. 导出 Metrics 到外部 Prometheus (使用 Remote Write)
|
||||
prometheusremotewrite:
|
||||
endpoint: "http://10.0.0.38:9090/api/v1/write"
|
||||
# 如果有 Basic Auth，在此配置
|
||||
# external_labels:
|
||||
# cluster: "test-k8s-cluster"
|
||||
|
||||
# 2. 导出 Traces 到外部 Tempo (使用 OTLP gRPC)
|
||||
# otlp/tempo:
|
||||
# endpoint: "<你的TEMPO_IP>:4317"
|
||||
# tls:
|
||||
# insecure: true
|
||||
|
||||
# 3. 导出 Logs 到外部 Elasticsearch (可选)
|
||||
# elasticsearch:
|
||||
# endpoints: ["http://<你的ES_IP>:9200"]
|
||||
# logs_index: "k8s-logs"
|
||||
|
||||
debug:
|
||||
verbosity: basic
|
||||
|
||||
service:
|
||||
pipelines:
|
||||
metrics:
|
||||
receivers: [otlp, k8s_cluster]
|
||||
processors: [memory_limiter, batch]
|
||||
# 确保 k8sattributes 在 batch 之前或之后取决于架构，Gateway通常主要做转发
|
||||
# 这里 k8s_cluster 产生的数据自带标签，otlp 来的数据应在 Agent 端打好标签
|
||||
exporters: [prometheusremotewrite]
|
||||
|
||||
traces:
|
||||
receivers: [otlp]
|
||||
processors: [memory_limiter, batch]
|
||||
exporters: [otlp/tempo]
|
||||
|
||||
# logs:
|
||||
# receivers: [otlp]
|
||||
# processors: [memory_limiter, batch]
|
||||
# exporters: [elasticsearch]
|
||||
88
OpenTelemetry/Collector_v3/04-otel-agent.yaml
Normal file
88
OpenTelemetry/Collector_v3/04-otel-agent.yaml
Normal file
@@ -0,0 +1,88 @@
|
||||
apiVersion: opentelemetry.io/v1beta1
|
||||
kind: OpenTelemetryCollector
|
||||
metadata:
|
||||
name: otel-agent
|
||||
namespace: opentelemetry-operator-system
|
||||
spec:
|
||||
mode: daemonset
|
||||
hostNetwork: true # 建议开启，以便更准确获取 Host 指标
|
||||
config:
|
||||
receivers:
|
||||
# 1. 采集 Pod 和 容器 的资源使用情况 (CPU/Mem)
|
||||
kubeletstats:
|
||||
collection_interval: 20s
|
||||
auth_type: "serviceAccount"
|
||||
endpoint: "${env:K8S_NODE_NAME}:10250"
|
||||
insecure_skip_verify: true
|
||||
metric_groups:
|
||||
- node
|
||||
- pod
|
||||
- container
|
||||
|
||||
# 2. 采集宿主机物理指标
|
||||
hostmetrics:
|
||||
collection_interval: 20s
|
||||
scrapers:
|
||||
cpu:
|
||||
memory:
|
||||
load:
|
||||
filesystem:
|
||||
network:
|
||||
|
||||
# 3. (可选) 采集日志
|
||||
# filelog:
|
||||
# include: [/var/log/pods/*/*/*.log]
|
||||
# ...
|
||||
|
||||
processors:
|
||||
batch:
|
||||
send_batch_size: 500
|
||||
timeout: 5s
|
||||
memory_limiter:
|
||||
check_interval: 1s
|
||||
limit_mib: 400
|
||||
spike_limit_mib: 100
|
||||
|
||||
# 资源检测：自动识别云厂商(腾讯云)信息、主机名等
|
||||
resourcedetection:
|
||||
detectors: [system] # 如果在腾讯云CVM上，可以尝试加入 'tencentcloud' 但 system 通常足够
|
||||
timeout: 2s
|
||||
override: false
|
||||
|
||||
# 关键：给指标打上 K8s 标签 (Pod Name, Namespace, Node Name)
|
||||
k8sattributes:
|
||||
passthrough: false
|
||||
extract:
|
||||
metadata:
|
||||
- k8s.pod.name
|
||||
- k8s.pod.uid
|
||||
- k8s.deployment.name
|
||||
- k8s.namespace.name
|
||||
- k8s.node.name
|
||||
pod_association:
|
||||
- sources:
|
||||
- from: resource_attribute
|
||||
name: k8s.pod.uid
|
||||
- sources:
|
||||
- from: resource_attribute
|
||||
name: k8s.pod.ip
|
||||
- sources:
|
||||
- from: connection
|
||||
|
||||
exporters:
|
||||
# 发送给集群内的 Gateway Service
|
||||
otlp:
|
||||
endpoint: "otel-gateway-collector.opentelemetry-operator-system.svc.cluster.local:4317"
|
||||
tls:
|
||||
insecure: true
|
||||
|
||||
service:
|
||||
pipelines:
|
||||
metrics:
|
||||
receivers: [kubeletstats, hostmetrics]
|
||||
processors: [resourcedetection, k8sattributes, memory_limiter, batch]
|
||||
exporters: [otlp]
|
||||
|
||||
# traces: # 如果应用配置了 sidecar 或其他方式发送 trace 到本地 agent
|
||||
# receivers: [otlp]
|
||||
# exporters: [otlp]
|
||||
4
OpenTelemetry/Collector_v3/monitoring-namespace.yaml
Normal file
4
OpenTelemetry/Collector_v3/monitoring-namespace.yaml
Normal file
@@ -0,0 +1,4 @@
|
||||
apiVersion: v1
|
||||
kind: Namespace
|
||||
metadata:
|
||||
name: monitoring
|
||||
16
OpenTelemetry/Collector_v3/opentelemetry-ns-terminating.yaml
Normal file
16
OpenTelemetry/Collector_v3/opentelemetry-ns-terminating.yaml
Normal file
@@ -0,0 +1,16 @@
|
||||
apiVersion: v1
|
||||
kind: Namespace
|
||||
metadata:
|
||||
annotations:
|
||||
kubectl.kubernetes.io/last-applied-configuration: |
|
||||
{"apiVersion":"v1","kind":"Namespace","metadata":{"annotations":{},"labels":{"app.kubernetes.io/name":"opentelemetry-operator","control-plane":"controller-manager"},"name":"opentelemetry-operator-system"}}
|
||||
creationTimestamp: "2025-12-11T08:28:51Z"
|
||||
deletionTimestamp: "2025-12-12T08:33:24Z"
|
||||
labels:
|
||||
app.kubernetes.io/name: opentelemetry-operator
|
||||
control-plane: controller-manager
|
||||
kubernetes.io/metadata.name: opentelemetry-operator-system
|
||||
name: opentelemetry-operator-system
|
||||
resourceVersion: "4706820514"
|
||||
uid: 6ebd60fa-2155-4f6e-8c3c-6d83447713c1
|
||||
spec:
|
||||
72
OpenTelemetry/Collector_v3/readme.txt
Normal file
72
OpenTelemetry/Collector_v3/readme.txt
Normal file
@@ -0,0 +1,72 @@
|
||||
一、安装 cert-manager
|
||||
OpenTelemetry Operator 提供了 OpenTelemetryCollector CRD（自定义资源定义），能自动处理服务发现和 RBAC（基于角色的访问控制）
|
||||
该 Operator 需要 cert-manager 来支持准入 Webhook，部署步骤如下：
|
||||
|
||||
安装OpenTelemetry Operator 自定义资源，需先部署 cert-manager ，使用yaml 直接部署，文件：02-cert-manager.yaml (官方文档里)
|
||||
官方文档链接：https://cert-manager.io/docs/installation/kubectl/
|
||||
|
||||
cert-manager 将安装在cert-manager命名空间中，安装了cert-manager后，通过以下方式验证其部署是否正确 检查cert-manager命名空间:
|
||||
kubectl get pods --namespace cert-manager
|
||||
NAME READY STATUS RESTARTS AGE
|
||||
cert-manager-7b8b89f89d-tpchr 1/1 Running 0 24s
|
||||
cert-manager-cainjector-7f9fdd5dd5-px66h 1/1 Running 0 25s
|
||||
cert-manager-webhook-769f6b94cb-zmjmv 1/1 Running 0 24s
|
||||
|
||||
|
||||
|
||||
二、安装 OpenTelemetry Operator
|
||||
使用 helm 安装OpenTelemetry ，添加 Operator helm 仓库、更新、安装：
|
||||
helm repo add open-telemetry https://open-telemetry.github.io/opentelemetry-helm-charts
|
||||
helm repo update
|
||||
helm install opentelemetry-operator open-telemetry/opentelemetry-operator \
|
||||
--namespace opentelemetry-operator \
|
||||
--create-namespace
|
||||
|
||||
或者直接使用yaml部署：文件 03-opentelemetry-operator.yaml
|
||||
kubectl apply -f https://github.com/open-telemetry/opentelemetry-operator/releases/latest/download/opentelemetry-operator.yaml
|
||||
|
||||
kubectl delete -f https://github.com/open-telemetry/opentelemetry-operator/releases/latest/download/opentelemetry-operator.yaml
|
||||
|
||||
# 查看安装的CRD
|
||||
kubectl get crd | grep opentelemetry.io
|
||||
输出：
|
||||
instrumentations.opentelemetry.io 2025-12-11T09:02:11Z
|
||||
opampbridges.opentelemetry.io 2025-12-11T09:02:13Z
|
||||
opentelemetrycollectors.opentelemetry.io 2025-12-11T09:02:14Z
|
||||
targetallocators.opentelemetry.io 2025-12-11T09:02:17Z
|
||||
|
||||
# 查看安装的operator控制器 Pod 状态
|
||||
kubectl get pods -n opentelemetry-operator-system
|
||||
NAME READY STATUS RESTARTS AGE
|
||||
opentelemetry-operator-controller-manager-9c4b5467d-dhhp7 1/1 Running 0 3m10s
|
||||
|
||||
# 查看 Operator Deployment 状态
|
||||
kubectl get deploy opentelemetry-operator-controller-manager -n opentelemetry-operator-system
|
||||
NAME READY UP-TO-DATE AVAILABLE AGE
|
||||
opentelemetry-operator-controller-manager 1/1 1 1 4m43s
|
||||
|
||||
# 查看证书是否签发成功（验证与 cert-manager 协同正常）
|
||||
NAME READY SECRET AGE
|
||||
certificate.cert-manager.io/opentelemetry-operator-serving-cert True opentelemetry-operator-controller-manager-service-cert 6m13s
|
||||
NAME READY AGE
|
||||
issuer.cert-manager.io/opentelemetry-operator-selfsigned-issuer True 6m12s
|
||||
|
||||
# 查看 Operator 相关 CRD
|
||||
kubectl get crd | grep opentelemetry.io
|
||||
输出：
|
||||
instrumentations.opentelemetry.io 2026-01-14T07:28:56Z
|
||||
opampbridges.opentelemetry.io 2026-01-14T07:28:57Z
|
||||
opentelemetrycollectors.opentelemetry.io 2025-12-11T09:02:14Z
|
||||
targetallocators.opentelemetry.io 2026-01-14T07:29:03Z
|
||||
|
||||
|
||||
# 卸载命令
|
||||
# 格式：helm uninstall <Release 名称> -n <命名空间>
|
||||
helm uninstall opentelemetry-operator -n opentelemetry-operator
|
||||
|
||||
# 删除 CRD（仅当你确认不再需要任何 OTel 相关自定义资源实例时执行）
|
||||
# 批量删除 Operator 相关 CRD
|
||||
kubectl delete crd \
|
||||
instrumentations.opentelemetry.io \
|
||||
opentelemetrycollectors.opentelemetry.io \
|
||||
targetallocators.opentelemetry.io
|
||||
Reference in New Issue
Block a user