0119同步

OpenTelemetry/Collector_v2/01-otel-gateway-rbac.yaml

@@ -0,0 +1,39 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+---
+# 1. 权限配置 (RBAC)
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: otel-gateway
+  namespace: monitoring
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: otel-gateway-role
+rules:
+  # 允许读取 Pods, Nodes, Namespaces 用于打标和获取元数据
+  - apiGroups: [""]
+    resources: ["pods", "nodes", "namespaces", "services", "endpoints"]
+    verbs: ["get", "list", "watch"]
+  # 允许读取 Events (用于采集 K8s 事件)
+  - apiGroups: [""]
+    resources: ["events"]
+    verbs: ["get", "list", "watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: otel-gateway-binding
+subjects:
+  - kind: ServiceAccount
+    name: otel-gateway
+    namespace: monitoring
+roleRef:
+  kind: ClusterRole
+  name: otel-gateway-role
+  apiGroup: rbac.authorization.k8s.io
+

OpenTelemetry/Collector_v2/02-otel-gateway-config.yaml

@@ -0,0 +1,82 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: otel-gateway-config
+  namespace: monitoring
+data:
+  config.yaml: |
+    receivers:
+      # 接收来自 Agent 的数据 (gRPC 4317, HTTP 4318)
+      otlp:
+        protocols:
+          grpc:
+            endpoint: 0.0.0.0:4317
+          http:
+            endpoint: 0.0.0.0:4318
+
+      # 1. 集群宏观: K8s 事件
+      k8s_events:
+        auth_type: serviceAccount
+
+      # 2. 集群宏观：拉取 TKE 自带的 tke-kube-state-metrics (Kube-State-Metrics)
+      prometheus:
+        config:
+          scrape_configs:
+            - job_name: 'tke-kube-state-metrics'
+              scrape_interval: 30s
+              static_configs:
+                - targets: ['tke-kube-state-metrics.kube-system.svc.cluster.local:8180']
+
+    processors:
+      batch:
+        send_batch_size: 2000
+        timeout: 10s
+      
+      resourcedetection:
+        detectors: [env, system]
+        override: true
+      
+      # 3. 注入集群 ID, 解决 Prometheus 重复采样报错
+      resource:
+        attributes:
+          - key: cluster.name
+            value: "test-k8s"
+            action: upsert
+      
+      # 将 OTLP Resource 属性转换为 Metric 标签，确保 Prometheus 能够区分不同 Pod/Node
+      transform:
+        metric_statements:
+          - context: datapoint
+            statements:
+              - set(attributes["k8s_pod_name"], resource.attributes["k8s.pod.name"])
+              - set(attributes["k8s_node_name"], resource.attributes["k8s.node.name"])
+              - set(attributes["k8s_namespace_name"], resource.attributes["k8s.namespace.name"])
+              - set(attributes["k8s_container_name"], resource.attributes["k8s.container.name"])
+              - set(attributes["cluster_name"], resource.attributes["cluster.name"])
+
+      memory_limiter:
+        check_interval: 1s
+        limit_mib: 1500
+        spike_limit_mib: 512
+
+    exporters:
+      # 对接 Prometheus
+      otlphttp/prometheus:
+        endpoint: "http://10.0.0.38:9090/api/v1/write"
+        tls:
+          insecure: true
+      
+      # 打印日志（用于排查）
+      debug:
+        verbosity: detailed
+
+    service:
+      pipelines:
+        metrics:
+          receivers: [otlp, prometheus] # 汇聚微观(otlp)和宏观(prometheus)指标
+          processors: [memory_limiter, resourcedetection, resource, transform, batch]
+          exporters: [otlphttp/prometheus]
+        logs:
+          receivers: [k8s_events]
+          processors: [memory_limiter, resourcedetection, resource, batch]
+          exporters: [debug]

OpenTelemetry/Collector_v2/03-otel-gateway-deployment.yaml

@@ -0,0 +1,60 @@
+# 部署主体 (Deployment)
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: otel-gateway
+  namespace: monitoring
+  labels:
+    app: otel-gateway
+spec:
+  replicas: 1 # 采集 Events 和 KSM 建议单副本，避免数据重复
+  selector:
+    matchLabels:
+      app: otel-gateway
+  template:
+    metadata:
+      labels:
+        app: otel-gateway
+    spec:
+      serviceAccountName: otel-gateway
+      containers:
+        - name: otel-collector
+          image: otel/opentelemetry-collector-contrib:latest
+          command:
+            - "/otelcol-contrib"
+          args:
+            - "--config=/conf/config.yaml"
+          volumeMounts:
+            - name: config-vol
+              mountPath: /conf
+          resources:
+            limits:
+              cpu: 1
+              memory: 2Gi
+            requests:
+              cpu: 200m
+              memory: 400Mi
+      volumes:
+        - name: config-vol
+          configMap:
+            name: otel-gateway-config
+---
+# 服务暴露 (Service)
+apiVersion: v1
+kind: Service
+metadata:
+  name: otel-gateway
+  namespace: monitoring
+spec:
+  clusterIP: None
+  selector:
+    app: otel-gateway
+  ports:
+    - name: grpc
+      port: 4317
+      targetPort: 4317
+      protocol: TCP
+    - name: http
+      port: 4318
+      targetPort: 4318
+      protocol: TCP

OpenTelemetry/Collector_v2/11-otel-agent-rbac.yaml

@@ -0,0 +1,39 @@
+# 1. 权限配置
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: otel-agent
+  namespace: monitoring
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: otel-agent-role
+rules:
+  # 允许读取 Pod 和 Node 信息
+  - apiGroups: [""]
+    resources: ["nodes", "nodes/stats", "nodes/proxy", "pods", "services", "endpoints"]
+    verbs: ["get", "watch", "list"]
+
+  # 允许读取 ReplicaSets，以便 k8sattributes 处理器解析 Deployment 名称
+  - apiGroups: ["apps"]
+    resources: ["replicasets"]
+    verbs: ["get", "watch", "list"]
+
+  # 非资源型 URL 权限 (访问 Kubelet 统计接口)
+  - nonResourceURLs: ["/metrics", "/metrics/cadvisor"]
+    verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: otel-agent-binding
+subjects:
+  - kind: ServiceAccount
+    name: otel-agent
+    namespace: monitoring
+roleRef:
+  kind: ClusterRole
+  name: otel-agent-role
+  apiGroup: rbac.authorization.k8s.io
+

OpenTelemetry/Collector_v2/12-otel-agent-config.yaml

@@ -0,0 +1,75 @@
+# Agent 配置文件
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: otel-agent-config
+  namespace: monitoring
+data:
+  config.yaml: |
+    receivers:
+      # 1. 采集宿主机宏观指标
+      hostmetrics:
+        collection_interval: 30s
+        root_path: /hostfs
+        scrapers:
+          cpu: {}
+          memory: {}
+          load: {}
+          disk: {}
+          filesystem: {}
+          network: {}
+          paging: {}
+          processes: {}
+
+      # 2. 采集 Pod/Container/Volume 微观指标
+      kubeletstats:
+        collection_interval: 30s
+        auth_type: "serviceAccount"
+        endpoint: "https://${env:K8S_NODE_NAME}:10250" # 使用环境变量定位本地 Kubelet
+        insecure_skip_verify: true
+        metric_groups:
+          - node
+          - pod
+          - container
+          - volume
+
+    processors:
+      batch:
+        send_batch_size: 1000
+        timeout: 10s
+      
+      resourcedetection:
+        detectors: [env, system]
+      
+      # 3. 提取 K8s 详细标签，确保指标唯一性
+      k8sattributes:
+        auth_type: "serviceAccount"
+        passthrough: false
+        extract:
+          metadata:
+            - k8s.pod.name
+            - k8s.pod.uid
+            - k8s.namespace.name
+            - k8s.node.name
+            - k8s.deployment.name
+            - k8s.container.name
+        pod_association:
+          - sources:
+              - from: resource_attribute
+                name: k8s.pod.uid
+          - sources:
+              - from: connection
+
+    exporters:
+      # 发送给集群内的 Gateway Service
+      otlp:
+        endpoint: "otel-gateway.monitoring.svc.cluster.local:4317"
+        tls:
+          insecure: true
+
+    service:
+      pipelines:
+        metrics:
+          receivers: [hostmetrics, kubeletstats]
+          processors: [resourcedetection, k8sattributes, batch]
+          exporters: [otlp]

OpenTelemetry/Collector_v2/13-otel-agent-daemonset.yaml

@@ -0,0 +1,55 @@
+# 部署主体 (DaemonSet)
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: otel-agent
+  namespace: monitoring
+  labels:
+    app: otel-agent
+spec:
+  selector:
+    matchLabels:
+      app: otel-agent
+  template:
+    metadata:
+      labels:
+        app: otel-agent
+    spec:
+      hostNetwork: true
+      dnsPolicy: ClusterFirstWithHostNet
+      serviceAccountName: otel-agent
+      containers:
+        - name: otel-collector
+          image: otel/opentelemetry-collector-contrib:latest
+          command:
+            - "/otelcol-contrib"
+          args:
+            - "--config=/conf/config.yaml"
+          env:
+            # 获取当前节点名称，传给 kubeletstats 使用
+            - name: K8S_NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+          volumeMounts:
+            - name: config-vol
+              mountPath: /conf
+            # 挂载宿主机根目录，以便采集宿主机指标
+            - name: hostfs
+              mountPath: /hostfs
+              readOnly: true
+              mountPropagation: HostToContainer
+          resources:
+            limits:
+              cpu: 500m
+              memory: 500Mi
+            requests:
+              cpu: 100m
+              memory: 200Mi
+      volumes:
+        - name: config-vol
+          configMap:
+            name: otel-agent-config
+        - name: hostfs
+          hostPath:
+            path: /

OpenTelemetry/Collector_v3/03-otel-gateway.yaml

@@ -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]

OpenTelemetry/Collector_v3/04-otel-agent.yaml

@@ -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]

OpenTelemetry/Collector_v3/monitoring-namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring

OpenTelemetry/Collector_v3/opentelemetry-ns-terminating.yaml

@@ -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:

OpenTelemetry/Collector_v3/readme.txt

@@ -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

OpenTelemetry/prometheus/二进制部署/prometheus/dm.bash

@@ -27,14 +27,21 @@ Type=simple
 ExecStart=/data/prometheus/prometheus \
     --config.file=/data/prometheus/prometheus.yml \
     --storage.tsdb.path=/data/prometheus/data \
+    --web.enable-remote-write-receiver \
     --web.console.templates=/data/prometheus/consoles \
-    --web.console.libraries=/data/prometheus/console_libraries
+    --web.console.libraries=/data/prometheus/console_libraries \
+    --storage.tsdb.retention.time=60d \
+    --storage.tsdb.retention.size=60GB
 
 Restart=always
 
 [Install]
 WantedBy=multi-user.target
 
+
+# ----------------------------------------
+
+
 # 创建文件 /etc/systemd/system/alertmanager.service
 [Unit]
 Description=Alertmanager

OpenTelemetry/readme.txt

@@ -25,7 +25,6 @@ graph TD
     F -->|转发| G[集群外Prometheus]
 
 
-
 2. 日志数据（最终到 ES）
     采集方：OTel Collector（DaemonSet 模式）
         采集内容：k8s 节点/var/log/containers目录下的容器日志（替代 Filebeat）。

filebast/s5-lessie-server01/filebeat.yml

@@ -0,0 +1,94 @@
+# 配置索引模板名称和模式
+setup.template.name: "lessie-sit"
+setup.template.pattern: "lessie-sit*"
+setup.template.enabled: true
+setup.ilm.enabled: true
+
+#主配置文件加载子配置文件
+filebeat.config.inputs:
+  enabled: true
+  path: /etc/filebeat/inputs.d/*.yml
+  reload.enabled: true
+  reload.period: 10s
+
+
+# 处理器
+processors:
+# lessie -------------------------
+
+  - dissect:
+      when:
+        equals:
+          log_type: lessie_search.log
+      tokenizer: '%{timestamp} - %{level} - %{module} - %{function} - %{message}'
+      field: "message"
+      target_prefix: "mylog"
+      ignore_missing: true
+      overwrite_keys: true
+
+  # 针对带有 [level: | event: | msg: | context:] 的日志，再做一次 dissect
+  - dissect:
+      when:
+        regexp:
+          mylog.message: '^\[level:.*\]'
+      tokenizer: '[level: %{event_level} | event: %{event} | msg: %{msg} | context: %{context}]'
+      field: "mylog.message"
+      target_prefix: "mylog"
+      ignore_missing: true
+      overwrite_keys: true
+
+  # 把 context 再拆成独立字段
+  - script:
+      lang: javascript
+      id: parse_context
+      source: >
+        function process(event) {
+          var ctx = event.Get("mylog.context");
+          if (ctx) {
+            var parts = ctx.split(",");
+            parts.forEach(function(p) {
+              var kv = p.split(":");
+              if (kv.length == 2) {
+                event.Put("mylog." + kv[0].trim(), kv[1].trim());
+              }
+            });
+          }
+        }
+# lessie ------------------------
+
+  - decode_json_fields:
+      when:
+        equals:
+          log_type: go.log
+      fields: ["message"]
+      target: ""
+      overwrite_keys: true
+      add_error_key: true
+
+
+#输出
+output.elasticsearch:
+  hosts: ["http://106.53.194.199:9200"]
+  username: "admin"
+  password: "123456"
+  index: "%{[environment]}-%{[application]}-%{+yyyy.MM.dd}"  # 按天分割索引
+  bulk_max_size: 50       # 单批次传输最大文档数
+  worker: 1                # 并行工作线程数
+  timeout: 15s
+
+# 日志记录
+logging.level: info
+logging.to_files: true
+logging.files:
+  path: /var/log/filebeat
+  name: filebeat.log
+  keepfiles: 7
+  permissions: 0644
+
+# 设置队列和内存使用
+queue.mem:
+  events: 1024
+  flush.min_events: 512
+  flush.timeout: 10s
+
+

filebast/s5-lessie-server01/s5_lessie_search.yml

@@ -0,0 +1,25 @@
+- type: log
+  id: s5_lessie_search
+  enabled: true
+  paths: 
+    - /data/webapps/lessie_sourcing_agents_s5/logs/lessie_sourcing_agents*.log
+  include_lines: ['^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2},\d{3}'] # 只包含匹配该正则表达式的行
+  fields:
+    application: lessie_search
+    log_type: lessie_search.log
+    environment: s5
+    instance: webdrive-server
+    ip: 49.51.33.153
+  fields_under_root: true
+  # multiline.pattern: '^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2},\d{3}'
+  # multiline.negate: true
+  # multiline.match: after
+  ignore_older: 24h   # 忽略旧日志文件（避免处理已归档的日志）
+  scan_frequency: 10s   # 定期扫描新文件的频率
+  clean_inactive: 25h   # 清除超过一天未更新的文件
+  close_inactive: 5m    # 文件超过5分钟无更新则关闭
+  close_renamed: true   # 处理被重命名的文件
+  start_position: beginning   # 从文件的开头读取
+
+
+

nginx/lessie_official_web.conf

@@ -207,3 +207,215 @@ server {
 
 
 
+# ---------------修改，官网项目合成一个项目，使用新的框架----------------------------------
+
+
+# upstream official_backend {
+#     server 10.0.0.5:3000;
+#     server 10.0.0.15:3000;
+# }
+
+upstream new_official_backend {
+    server 10.0.0.5:3003;
+    server 10.0.0.15:3003;
+}
+
+log_format  official_log  '$remote_addr - $remote_user [$time_local] '
+                          '"$request" $status $body_bytes_sent '
+                          '"$http_referer" "$http_user_agent" '
+                          'upstream_addr=$upstream_addr '
+                          'upstream_status=$upstream_status '
+                          'upstream_response_time=$upstream_response_time '
+                          'request_time=$request_time';
+
+ # 1. 强制 HTTP 转 HTTPS（统一跳转到 www.lessie.ai）
+server {
+    listen 80;
+    server_name lessie.ai www.lessie.ai;
+    return 301 https://lessie.ai$request_uri;
+}
+
+ # 2. 统一将 www.lessie.ai 重定向到 lessie.ai（HTTPS 保留）
+server {
+    listen 443 ssl;
+    server_name www.lessie.ai;
+
+    ssl_certificate /data/tengine/certificate/lessie.ai.pem;
+    ssl_certificate_key /data/tengine/certificate/lessie.ai.key;
+
+    ssl_protocols TLSv1.2 TLSv1.3;
+    ssl_ciphers HIGH:!aNULL:!MD5;
+
+     # 清除 HSTS
+    add_header Strict-Transport-Security "max-age=0; includeSubDomains" always;
+
+    return 301 https://lessie.ai$request_uri;
+}
+
+ # 3. 正式服务站点（https://lessie.ai）
+server {
+    listen 443 ssl;
+    server_name lessie.ai;
+
+    ssl_certificate /data/tengine/certificate/lessie.ai.pem;
+    ssl_certificate_key /data/tengine/certificate/lessie.ai.key;
+
+    ssl_protocols TLSv1.2 TLSv1.3;
+    ssl_ciphers HIGH:!aNULL:!MD5;
+
+    access_log /data/tengine/logs/lessie.ai.access.log  official_log;
+    error_log /data/tengine/logs/lessie.ai.error.log;
+
+    # SSR 场景放大超时
+    proxy_connect_timeout 300s;
+    proxy_send_timeout    300s;
+    proxy_read_timeout    300s;
+
+    # 拦截 PHP / WordPress 扫描
+    location ~* \.php$ {
+        return 444;
+    }
+
+    # 新框架的业务页面逻辑
+    # location ~ "^/([a-z]{2}(-[a-z]{2})?/)?(influencer-marketing|b2b-lead-generation|investor-scouting|recruiting|partnerships)" {
+    #     proxy_pass http://new_official_backend;
+    #     proxy_http_version 1.1;
+    #     proxy_set_header Host $host;
+    #     proxy_set_header X-Real-IP $remote_addr;
+    #     proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    #     proxy_set_header X-Forwarded-Proto $scheme;
+    # }
+
+    # Next.js 静态 & data
+    # location ^~ /_next/ {
+    #     proxy_pass http://new_official_backend;
+    #     proxy_http_version 1.1;
+    #     proxy_set_header Host $host;
+    #     proxy_set_header X-Real-IP $remote_addr;
+    # }
+
+    # Nuxt 静态资源
+    # location ^~ /_nuxt/ {
+    #     proxy_pass http://official_backend;
+    #     proxy_set_header Host $host;
+    #     proxy_set_header X-Real-IP $remote_addr;
+    # }
+
+    # Nuxt data / 其他 json
+    # location ~ \.json$ {
+    #     proxy_pass http://official_backend;
+    #     proxy_set_header Host $host;
+    #     proxy_set_header X-Real-IP $remote_addr;
+    # }
+
+    # 新站（Next SSR）
+    location / {
+        proxy_pass http://new_official_backend;
+        proxy_http_version 1.1;
+        proxy_set_header Host              $host;
+        proxy_set_header X-Real-IP         $remote_addr;
+        proxy_set_header X-Forwarded-For   $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+    }
+
+    location /video/ {
+        root /data/tengine/html/lessie_official;
+        expires 30d;
+        add_header Cache-Control "public";
+        add_header Accept-Ranges bytes;
+    }
+
+    # 禁止 logo 缓存（默认给用户方形）
+    location = /favicon.svg {
+        # 判断 UA，如果是 Googlebot，改写路径
+        if ($http_user_agent ~* "(Googlebot|Bingbot)") {
+            rewrite ^/favicon.svg$ /favicon-google.svg last;
+        }
+
+        proxy_pass http://new_official_backend;
+        proxy_set_header Host $host;
+
+        add_header Cache-Control "no-cache, no-store, must-revalidate" always;
+        add_header Pragma "no-cache" always;
+        add_header Expires 0 always;
+    }
+
+    # Googlebot 专用 favicon 文件（圆形图标）
+    location = /favicon-google.svg {
+        root /data/tengine/html/lessie_official;
+        add_header Cache-Control "no-cache, no-store, must-revalidate" always;
+        add_header Pragma "no-cache" always;
+        add_header Expires 0 always;
+    }
+
+    # 第三方邮件件平台调国内email（crm）
+    location /prod-api/webhook/ {
+        proxy_pass http://129.204.158.54:4997/webhook/; 
+        proxy_set_header Host 129.204.158.54;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+
+        proxy_intercept_errors off;
+        proxy_buffering off;
+        proxy_cache off;
+        proxy_set_header Connection keep-alive;
+
+        add_header 'Access-Control-Allow-Origin' "$http_origin" always;
+        add_header 'Access-Control-Allow-Credentials' 'true' always;
+        add_header 'Access-Control-Allow-Methods' 'GET, POST, OPTIONS, PUT, DELETE' always;
+        add_header 'Access-Control-Allow-Headers' 'Authorization,Content-Type,X-Requested-With,Accept,Origin' always;
+
+       if ($request_method = OPTIONS ) {
+          return 204;
+       }
+    }
+
+    # 第三方邮件SendGrid平台调用
+    location /prod-api/webhook/us {
+        proxy_pass http://10.0.0.10:4997/webhook/us;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+
+        proxy_intercept_errors off;
+        proxy_buffering off;
+        proxy_cache off;
+        proxy_set_header Connection keep-alive;
+
+        add_header 'Access-Control-Allow-Origin' "$http_origin" always;
+        add_header 'Access-Control-Allow-Credentials' 'true' always;
+        add_header 'Access-Control-Allow-Methods' 'GET, POST, OPTIONS, PUT, DELETE' always;
+        add_header 'Access-Control-Allow-Headers' 'Authorization,Content-Type,X-Requested-With,Accept,Origin' always;
+
+       if ($request_method = OPTIONS ) {
+          return 204;
+       }
+    }
+
+    # 第三方支付平台调用
+    location /payment/ {
+        proxy_pass http://10.0.0.8:8090;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+
+        proxy_intercept_errors off;
+        proxy_buffering off;
+        proxy_cache off;
+        proxy_set_header Connection keep-alive;
+
+        add_header 'Access-Control-Allow-Origin' "$http_origin" always;
+        add_header 'Access-Control-Allow-Credentials' 'true' always;
+        add_header 'Access-Control-Allow-Methods' 'GET, POST, OPTIONS, PUT, DELETE' always;
+        add_header 'Access-Control-Allow-Headers' 'Authorization,Content-Type,X-Requested-With,Accept,Origin' always;
+
+       if ($request_method = OPTIONS ) {
+          return 204;
+       }
+    }
+}
+
+
+
+
+

prometheus/process-exporter/weblessie-server-process-exporter.yml

@@ -4,26 +4,49 @@ process_names:
     cmdline:
       - ".*index.mjs.*"
 
-  - name: "weblessie-server_lessie_sourcing_8000"
+
+  - name: "weblessie-server_s1_lessie_sourcing_8000"
     cmdline:
-      - "/data/webapps/lessie_sourcing_agents"
+      - "gunicorn"
-      - ".*server.py*"
+      - ".*0.0.0.0:8000.*"
 
-  - name: "weblessie-server_lessie_sourcing_8002"
+  - name: "weblessie-server_s4_lessie_sourcing_8001"
     cmdline:
-      - "/data/webapps/lessie_sourcing_agents_02"
+      - "gunicorn"
-      - ".*server8002.*"
+      - ".*0.0.0.0:8001.*"
 
-  - name: "weblessie-server_lessie_sourcing_7001"
+  - name: "weblessie-server_s4_GO-lessie-sourcing-api"
     cmdline:
-      - "/data/webapps/prod_lessie_sourcing_agents"
+      - ".*lessie-sourcing-api-s4.*"
-      - ".*server7001.*"
 
-  - name: "weblessie-server_GO-lessie-sourcing-api"
+  - name: "weblessie-server_s1_GO-lessie-sourcing-api"
     cmdline:
-      - ".*lessie-sourcing-api.*"
+      - ".*lessie-sourcing-api$"
  
+  - name: "nexus"
+    cmdline:
+      - "sonatype-nexus-repository-3.86.2-01.jar"
 
+  - name: "jenkins"
+    cmdline:
+      - "jenkins.war"
 
+  - name: "nginx_master"
+    cmdline:
+      - "nginx: master process"
 
+  - name: "nginx_worker"
+    cmdline:
+      - "nginx: worker process"
 
+  - name: "weblessie-server_s4-lessie-email"
+    cmdline:
+      - '--port\s+8031$'
+
+  - name: "webapp_lessie_react"
+    cmdline:
+      - 'cwd=/data/webapps/lessie-react'
+    
+  - name: "webapp_lessie_next"
+    cmdline:
+      - 'cwd=/data/webapps/lessie-next'