在k8s中运行kafka

1,250次阅读
没有评论

共计 23121 个字符,预计需要花费 58 分钟才能阅读完成。

在k8s中运行kafka

kafka是一个分布式的流处理平台,如何在k8s中运行一个呢?

使用terraform+ansiablie快速创建一个k8s集群

[root@master-0 ~]# kubectl get nodes
NAME       STATUS   ROLES                  AGE     VERSION
master-0   Ready    control-plane,master   8m41s   v1.22.15
worker-0   Ready    <none>                 6m12s   v1.22.15
worker-1   Ready    <none>                 5m32s   v1.22.15
worker-2   Ready    <none>                 5m2s    v1.22.15

存储类的选择

对于存储类,以往博主会用nfs等网络存储来提供,但是性能方面没有本地盘高,所以还是选择使用本地存储类来提供存储,对于这种分布式的中间件,数据同步则通过其自身的特性来提供是再好不过了

local-path存储类

[root@master-0 ~]# kubectl apply -f https://raw.githubusercontent.com/rancher/local-path-provisioner/master/deploy/local-path-storage.yaml
namespace/local-path-storage created
serviceaccount/local-path-provisioner-service-account created
clusterrole.rbac.authorization.k8s.io/local-path-provisioner-role created
clusterrolebinding.rbac.authorization.k8s.io/local-path-provisioner-bind created
deployment.apps/local-path-provisioner created
storageclass.storage.k8s.io/local-path created
configmap/local-path-config created

[root@master-0 ~]# cat local-path-storage.yaml 
apiVersion: v1
kind: Namespace
metadata:
  name: local-path-storage

---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: local-path-provisioner-service-account
  namespace: local-path-storage

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: local-path-provisioner-role
rules:
  - apiGroups: [ "" ]
    resources: [ "nodes", "persistentvolumeclaims", "configmaps" ]
    verbs: [ "get", "list", "watch" ]
  - apiGroups: [ "" ]
    resources: [ "endpoints", "persistentvolumes", "pods" ]
    verbs: [ "*" ]
  - apiGroups: [ "" ]
    resources: [ "events" ]
    verbs: [ "create", "patch" ]
  - apiGroups: [ "storage.k8s.io" ]
    resources: [ "storageclasses" ]
    verbs: [ "get", "list", "watch" ]

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: local-path-provisioner-bind
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: local-path-provisioner-role
subjects:
  - kind: ServiceAccount
    name: local-path-provisioner-service-account
    namespace: local-path-storage

---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: local-path-provisioner
  namespace: local-path-storage
spec:
  replicas: 1
  selector:
    matchLabels:
      app: local-path-provisioner
  template:
    metadata:
      labels:
        app: local-path-provisioner
    spec:
      serviceAccountName: local-path-provisioner-service-account
      containers:
        - name: local-path-provisioner
          image: rancher/local-path-provisioner:master-head
          imagePullPolicy: IfNotPresent
          command:
            - local-path-provisioner
            - --debug
            - start
            - --config
            - /etc/config/config.json
          volumeMounts:
            - name: config-volume
              mountPath: /etc/config/
          env:
            - name: POD_NAMESPACE
              valueFrom:
                fieldRef:
                  fieldPath: metadata.namespace
      volumes:
        - name: config-volume
          configMap:
            name: local-path-config

---
apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
  name: local-path
provisioner: rancher.io/local-path
volumeBindingMode: WaitForFirstConsumer
reclaimPolicy: Delete

---
kind: ConfigMap
apiVersion: v1
metadata:
  name: local-path-config
  namespace: local-path-storage
data:
  config.json: |-
    {
            "nodePathMap":[
            {
                    "node":"DEFAULT_PATH_FOR_NON_LISTED_NODES",
                    "paths":["/opt/local-path-provisioner"]
            }
            ]
    }
  setup: |-
    #!/bin/sh
    set -eu
    mkdir -m 0777 -p "$VOL_DIR"
  teardown: |-
    #!/bin/sh
    set -eu
    rm -rf "$VOL_DIR"
  helperPod.yaml: |-
    apiVersion: v1
    kind: Pod
    metadata:
      name: helper-pod
    spec:
      containers:
      - name: helper-pod
        image: busybox
        imagePullPolicy: IfNotPresent

kafka部署

operator部署

kafka的operator比较流行的有两种,此处使用strimiz-operator来运行

# 创建ns
[root@master-0 ~]# kubectl create namespace kafka

# 部署operator
[root@master-0 ~]# wget --no-check-certificate 'https://strimzi.io/install/latest?namespace=kafka' -O install.yaml

[root@master-0 ~]# kubectl apply -f install.yaml
[root@master-0 ~]# kubectl get pods -n kafka
NAME                                        READY   STATUS    RESTARTS   AGE
strimzi-cluster-operator-7b4f8f8496-gsnt5   1/1     Running   0          3m55s
[root@master-0 ~]# 
[root@master-0 ~]# kubectl  get all -n kafka
NAME                                            READY   STATUS    RESTARTS   AGE
pod/strimzi-cluster-operator-7b4f8f8496-gsnt5   1/1     Running   0          4m2s

NAME                                       READY   UP-TO-DATE   AVAILABLE   AGE
deployment.apps/strimzi-cluster-operator   1/1     1            1           4m2s

NAME                                                  DESIRED   CURRENT   READY   AGE
replicaset.apps/strimzi-cluster-operator-7b4f8f8496   1         1         1       4m2s

kafka部署

创建一个本地盘持久化的kafka集群

# 下载持久化模板
[root@master-0 ~]# wget --no-check-certificate https://strimzi.io/examples/latest/kafka/kafka-persistent-single.yaml

# 调整该样例文件并接入prometheus监控
[root@master-0 ~]# cat kafka-persistent-single.yaml 
apiVersion: kafka.strimzi.io/v1beta2
kind: Kafka
metadata:
  name: my-cluster
  namespace: kafka
spec:
  kafka:
    version: 3.4.0
    replicas: 3
    listeners:
      - name: plain
        port: 9092
        type: internal
        tls: false
      - name: tls
        port: 9093
        type: internal
        tls: true
    config:
      offsets.topic.replication.factor: 3
      transaction.state.log.replication.factor: 3
      transaction.state.log.min.isr: 1
      default.replication.factor: 3
      min.insync.replicas: 1
      inter.broker.protocol.version: "3.4"
    storage:
      type: jbod
      volumes:
      - id: 0
        type: persistent-claim
        class: local-path
        size: 30Gi
        deleteClaim: false
    metricsConfig:
      type: jmxPrometheusExporter
      valueFrom:
        configMapKeyRef:
          name: kafka-metrics
          key: kafka-metrics-config.yml
  zookeeper:
    replicas: 1
    storage:
      type: persistent-claim
      size: 30Gi
      class: local-path
      deleteClaim: false
    metricsConfig:
      type: jmxPrometheusExporter
      valueFrom:
        configMapKeyRef:
          name: kafka-metrics
          key: zookeeper-metrics-config.yml
  entityOperator:
    topicOperator: {}
    userOperator: {}
  kafkaExporter:
    topicRegex: ".*"
    groupRegex: ".*"

---
kind: ConfigMap
apiVersion: v1
metadata:
  name: kafka-metrics
  namespace: kafka # 这里要加上命名空间
  labels:
    app: strimzi
data:
  kafka-metrics-config.yml: |
    # See https://github.com/prometheus/jmx_exporter for more info about JMX Prometheus Exporter metrics
    lowercaseOutputName: true
    rules:
    # Special cases and very specific rules
    - pattern: kafka.server<type=(.+), name=(.+), clientId=(.+), topic=(.+), partition=(.*)><>Value
      name: kafka_server_$1_$2
      type: GAUGE
      labels:
       clientId: "$3"
       topic: "$4"
       partition: "$5"
    - pattern: kafka.server<type=(.+), name=(.+), clientId=(.+), brokerHost=(.+), brokerPort=(.+)><>Value
      name: kafka_server_$1_$2
      type: GAUGE
      labels:
       clientId: "$3"
       broker: "$4:$5"
    - pattern: kafka.server<type=(.+), cipher=(.+), protocol=(.+), listener=(.+), networkProcessor=(.+)><>connections
      name: kafka_server_$1_connections_tls_info
      type: GAUGE
      labels:
        cipher: "$2"
        protocol: "$3"
        listener: "$4"
        networkProcessor: "$5"
    - pattern: kafka.server<type=(.+), clientSoftwareName=(.+), clientSoftwareVersion=(.+), listener=(.+), networkProcessor=(.+)><>connections
      name: kafka_server_$1_connections_software
      type: GAUGE
      labels:
        clientSoftwareName: "$2"
        clientSoftwareVersion: "$3"
        listener: "$4"
        networkProcessor: "$5"
    - pattern: "kafka.server<type=(.+), listener=(.+), networkProcessor=(.+)><>(.+):"
      name: kafka_server_$1_$4
      type: GAUGE
      labels:
       listener: "$2"
       networkProcessor: "$3"
    - pattern: kafka.server<type=(.+), listener=(.+), networkProcessor=(.+)><>(.+)
      name: kafka_server_$1_$4
      type: GAUGE
      labels:
       listener: "$2"
       networkProcessor: "$3"
    # Some percent metrics use MeanRate attribute
    # Ex) kafka.server<type=(KafkaRequestHandlerPool), name=(RequestHandlerAvgIdlePercent)><>MeanRate
    - pattern: kafka.(\w+)<type=(.+), name=(.+)Percent\w*><>MeanRate
      name: kafka_$1_$2_$3_percent
      type: GAUGE
    # Generic gauges for percents
    - pattern: kafka.(\w+)<type=(.+), name=(.+)Percent\w*><>Value
      name: kafka_$1_$2_$3_percent
      type: GAUGE
    - pattern: kafka.(\w+)<type=(.+), name=(.+)Percent\w*, (.+)=(.+)><>Value
      name: kafka_$1_$2_$3_percent
      type: GAUGE
      labels:
        "$4": "$5"
    # Generic per-second counters with 0-2 key/value pairs
    - pattern: kafka.(\w+)<type=(.+), name=(.+)PerSec\w*, (.+)=(.+), (.+)=(.+)><>Count
      name: kafka_$1_$2_$3_total
      type: COUNTER
      labels:
        "$4": "$5"
        "$6": "$7"
    - pattern: kafka.(\w+)<type=(.+), name=(.+)PerSec\w*, (.+)=(.+)><>Count
      name: kafka_$1_$2_$3_total
      type: COUNTER
      labels:
        "$4": "$5"
    - pattern: kafka.(\w+)<type=(.+), name=(.+)PerSec\w*><>Count
      name: kafka_$1_$2_$3_total
      type: COUNTER
    # Generic gauges with 0-2 key/value pairs
    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+), (.+)=(.+)><>Value
      name: kafka_$1_$2_$3
      type: GAUGE
      labels:
        "$4": "$5"
        "$6": "$7"
    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+)><>Value
      name: kafka_$1_$2_$3
      type: GAUGE
      labels:
        "$4": "$5"
    - pattern: kafka.(\w+)<type=(.+), name=(.+)><>Value
      name: kafka_$1_$2_$3
      type: GAUGE
    # Emulate Prometheus 'Summary' metrics for the exported 'Histogram's.
    # Note that these are missing the '_sum' metric!
    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+), (.+)=(.+)><>Count
      name: kafka_$1_$2_$3_count
      type: COUNTER
      labels:
        "$4": "$5"
        "$6": "$7"
    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.*), (.+)=(.+)><>(\d+)thPercentile
      name: kafka_$1_$2_$3
      type: GAUGE
      labels:
        "$4": "$5"
        "$6": "$7"
        quantile: "0.$8"
    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+)><>Count
      name: kafka_$1_$2_$3_count
      type: COUNTER
      labels:
        "$4": "$5"
    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.*)><>(\d+)thPercentile
      name: kafka_$1_$2_$3
      type: GAUGE
      labels:
        "$4": "$5"
        quantile: "0.$6"
    - pattern: kafka.(\w+)<type=(.+), name=(.+)><>Count
      name: kafka_$1_$2_$3_count
      type: COUNTER
    - pattern: kafka.(\w+)<type=(.+), name=(.+)><>(\d+)thPercentile
      name: kafka_$1_$2_$3
      type: GAUGE
      labels:
        quantile: "0.$4"
  zookeeper-metrics-config.yml: |
    # See https://github.com/prometheus/jmx_exporter for more info about JMX Prometheus Exporter metrics
    lowercaseOutputName: true
    rules:
    # replicated Zookeeper
    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+)><>(\\w+)"
      name: "zookeeper_$2"
      type: GAUGE
    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+)><>(\\w+)"
      name: "zookeeper_$3"
      type: GAUGE
      labels:
        replicaId: "$2"
    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+), name2=(\\w+)><>(Packets\\w+)"
      name: "zookeeper_$4"
      type: COUNTER
      labels:
        replicaId: "$2"
        memberType: "$3"
    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+), name2=(\\w+)><>(\\w+)"
      name: "zookeeper_$4"
      type: GAUGE
      labels:
        replicaId: "$2"
        memberType: "$3"
    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+), name2=(\\w+), name3=(\\w+)><>(\\w+)"
      name: "zookeeper_$4_$5"
      type: GAUGE
      labels:
        replicaId: "$2"
        memberType: "$3"

[root@master-0 ~]# kubectl apply -f kafka-persistent-single.yaml 
kafka.kafka.strimzi.io/my-cluster created
configmap/kafka-metrics created


[root@master-0 ~]# kubectl  get all -n kafka
NAME                                             READY   STATUS    RESTARTS   AGE
pod/my-cluster-entity-operator-8bd4548d9-vg6x2   2/3     Running   0          117s
pod/my-cluster-kafka-0                           1/1     Running   0          3m3s
pod/my-cluster-kafka-1                           1/1     Running   0          3m3s
pod/my-cluster-kafka-2                           1/1     Running   0          3m3s
pod/my-cluster-zookeeper-0                       1/1     Running   0          4m18s
pod/strimzi-cluster-operator-7b4f8f8496-gsnt5    1/1     Running   0          10m

NAME                                  TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)                                        AGE
service/my-cluster-kafka-bootstrap    ClusterIP   10.105.141.167   <none>        9091/TCP,9092/TCP,9093/TCP                     3m4s
service/my-cluster-kafka-brokers      ClusterIP   None             <none>        9090/TCP,9091/TCP,8443/TCP,9092/TCP,9093/TCP   3m4s
service/my-cluster-zookeeper-client   ClusterIP   10.101.129.39    <none>        2181/TCP                                       4m19s
service/my-cluster-zookeeper-nodes    ClusterIP   None             <none>        2181/TCP,2888/TCP,3888/TCP                     4m19s

NAME                                         READY   UP-TO-DATE   AVAILABLE   AGE
deployment.apps/my-cluster-entity-operator   0/1     1            0           117s
deployment.apps/strimzi-cluster-operator     1/1     1            1           10m

NAME                                                   DESIRED   CURRENT   READY   AGE
replicaset.apps/my-cluster-entity-operator-8bd4548d9   1         1         0       117s
replicaset.apps/strimzi-cluster-operator-7b4f8f8496    1         1         1       10m


prometheus监控kafka

[root@master-0 ~]# git clone https://github.com/prometheus-operator/kube-prometheus
Cloning into 'kube-prometheus'...
remote: Enumerating objects: 18329, done.
remote: Counting objects: 100% (2775/2775), done.
remote: Compressing objects: 100% (222/222), done.
remote: Total 18329 (delta 2632), reused 2585 (delta 2546), pack-reused 15554
Receiving objects: 100% (18329/18329), 9.64 MiB | 7.30 MiB/s, done.
Resolving deltas: 100% (12260/12260), done.
[root@master-0 ~]# cd kube-prometheus/
[root@master-0 kube-prometheus]# git checkout release-0.9
Branch release-0.9 set up to track remote branch release-0.9 from origin.
Switched to a new branch 'release-0.9'
[root@master-0 kube-prometheus]# cd manifests/
[root@master-0 manifests]# cat prometheus-clusterRole.yaml 
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    app.kubernetes.io/component: prometheus
    app.kubernetes.io/name: prometheus
    app.kubernetes.io/part-of: kube-prometheus
    app.kubernetes.io/version: 2.29.1
  name: prometheus-k8s
rules:
- apiGroups:
  - ""
  resources:
  - nodes/metrics
  - services
  - endpoints
  - pods
  verbs: # 这里要改
  - get
  - list
  - watch
- nonResourceURLs:
  - /metrics
  verbs:
  - get

[root@master-0 manifests]# kubectl apply -f setup/
namespace/monitoring created
customresourcedefinition.apiextensions.k8s.io/alertmanagerconfigs.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/alertmanagers.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/podmonitors.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/probes.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/prometheuses.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/prometheusrules.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/servicemonitors.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/thanosrulers.monitoring.coreos.com created
clusterrole.rbac.authorization.k8s.io/prometheus-operator created
clusterrolebinding.rbac.authorization.k8s.io/prometheus-operator created
deployment.apps/prometheus-operator created
service/prometheus-operator created
serviceaccount/prometheus-operator created

[root@master-0 manifests]# kubectl apply -f .
alertmanager.monitoring.coreos.com/main created
Warning: policy/v1beta1 PodDisruptionBudget is deprecated in v1.21+, unavailable in v1.25+; use policy/v1 PodDisruptionBudget
poddisruptionbudget.policy/alertmanager-main created
prometheusrule.monitoring.coreos.com/alertmanager-main-rules created
secret/alertmanager-main created
service/alertmanager-main created
serviceaccount/alertmanager-main created
servicemonitor.monitoring.coreos.com/alertmanager created
clusterrole.rbac.authorization.k8s.io/blackbox-exporter created
clusterrolebinding.rbac.authorization.k8s.io/blackbox-exporter created
configmap/blackbox-exporter-configuration created
deployment.apps/blackbox-exporter created
service/blackbox-exporter created
serviceaccount/blackbox-exporter created
servicemonitor.monitoring.coreos.com/blackbox-exporter created
secret/grafana-datasources created
configmap/grafana-dashboard-alertmanager-overview created
configmap/grafana-dashboard-apiserver created
configmap/grafana-dashboard-cluster-total created
configmap/grafana-dashboard-controller-manager created
configmap/grafana-dashboard-k8s-resources-cluster created
configmap/grafana-dashboard-k8s-resources-namespace created
configmap/grafana-dashboard-k8s-resources-node created
configmap/grafana-dashboard-k8s-resources-pod created
configmap/grafana-dashboard-k8s-resources-workload created
configmap/grafana-dashboard-k8s-resources-workloads-namespace created
configmap/grafana-dashboard-kubelet created
configmap/grafana-dashboard-namespace-by-pod created
configmap/grafana-dashboard-namespace-by-workload created
configmap/grafana-dashboard-node-cluster-rsrc-use created
configmap/grafana-dashboard-node-rsrc-use created
configmap/grafana-dashboard-nodes created
configmap/grafana-dashboard-persistentvolumesusage created
configmap/grafana-dashboard-pod-total created
configmap/grafana-dashboard-prometheus-remote-write created
configmap/grafana-dashboard-prometheus created
configmap/grafana-dashboard-proxy created
configmap/grafana-dashboard-scheduler created
configmap/grafana-dashboard-workload-total created
configmap/grafana-dashboards created
deployment.apps/grafana created
service/grafana created
serviceaccount/grafana created
servicemonitor.monitoring.coreos.com/grafana created
prometheusrule.monitoring.coreos.com/kube-prometheus-rules created
clusterrole.rbac.authorization.k8s.io/kube-state-metrics created
clusterrolebinding.rbac.authorization.k8s.io/kube-state-metrics created
deployment.apps/kube-state-metrics created
prometheusrule.monitoring.coreos.com/kube-state-metrics-rules created
service/kube-state-metrics created
serviceaccount/kube-state-metrics created
servicemonitor.monitoring.coreos.com/kube-state-metrics created
prometheusrule.monitoring.coreos.com/kubernetes-monitoring-rules created
servicemonitor.monitoring.coreos.com/kube-apiserver created
servicemonitor.monitoring.coreos.com/coredns created
servicemonitor.monitoring.coreos.com/kube-controller-manager created
servicemonitor.monitoring.coreos.com/kube-scheduler created
servicemonitor.monitoring.coreos.com/kubelet created
clusterrole.rbac.authorization.k8s.io/node-exporter created
clusterrolebinding.rbac.authorization.k8s.io/node-exporter created
daemonset.apps/node-exporter created
prometheusrule.monitoring.coreos.com/node-exporter-rules created
service/node-exporter created
serviceaccount/node-exporter created
servicemonitor.monitoring.coreos.com/node-exporter created
apiservice.apiregistration.k8s.io/v1beta1.metrics.k8s.io created
clusterrole.rbac.authorization.k8s.io/prometheus-adapter created
clusterrole.rbac.authorization.k8s.io/system:aggregated-metrics-reader created
clusterrolebinding.rbac.authorization.k8s.io/prometheus-adapter created
clusterrolebinding.rbac.authorization.k8s.io/resource-metrics:system:auth-delegator created
clusterrole.rbac.authorization.k8s.io/resource-metrics-server-resources created
configmap/adapter-config created
deployment.apps/prometheus-adapter created
poddisruptionbudget.policy/prometheus-adapter created
rolebinding.rbac.authorization.k8s.io/resource-metrics-auth-reader created
service/prometheus-adapter created
serviceaccount/prometheus-adapter created
servicemonitor.monitoring.coreos.com/prometheus-adapter created
clusterrole.rbac.authorization.k8s.io/prometheus-k8s created
clusterrolebinding.rbac.authorization.k8s.io/prometheus-k8s created
prometheusrule.monitoring.coreos.com/prometheus-operator-rules created
servicemonitor.monitoring.coreos.com/prometheus-operator created
poddisruptionbudget.policy/prometheus-k8s created
prometheus.monitoring.coreos.com/k8s created
prometheusrule.monitoring.coreos.com/prometheus-k8s-prometheus-rules created
rolebinding.rbac.authorization.k8s.io/prometheus-k8s-config created
rolebinding.rbac.authorization.k8s.io/prometheus-k8s created
rolebinding.rbac.authorization.k8s.io/prometheus-k8s created
rolebinding.rbac.authorization.k8s.io/prometheus-k8s created
role.rbac.authorization.k8s.io/prometheus-k8s-config created
role.rbac.authorization.k8s.io/prometheus-k8s created
role.rbac.authorization.k8s.io/prometheus-k8s created
role.rbac.authorization.k8s.io/prometheus-k8s created
service/prometheus-k8s created
serviceaccount/prometheus-k8s created
servicemonitor.monitoring.coreos.com/prometheus-k8s created

创建kafka-podmonitor

# 注意ns,以及namespaceSelector
[root@master-0 ~]# cat strimzi-pod-monitor.yaml 
apiVersion: monitoring.coreos.com/v1
kind: PodMonitor
metadata:
  name: cluster-operator-metrics
  labels:
    app: strimzi
spec:
  selector:
    matchLabels:
      strimzi.io/kind: cluster-operator
  namespaceSelector:
    matchNames:
      - kafka
  podMetricsEndpoints:
  - path: /metrics
    port: http
---
apiVersion: monitoring.coreos.com/v1
kind: PodMonitor
metadata:
  name: entity-operator-metrics
  labels:
    app: strimzi
spec:
  selector:
    matchLabels:
      app.kubernetes.io/name: entity-operator
  namespaceSelector:
    matchNames:
      - kafka
  podMetricsEndpoints:
  - path: /metrics
    port: healthcheck
---
apiVersion: monitoring.coreos.com/v1
kind: PodMonitor
metadata:
  name: bridge-metrics
  labels:
    app: strimzi
spec:
  selector:
    matchLabels:
      strimzi.io/kind: KafkaBridge
  namespaceSelector:
    matchNames:
      - kafka
  podMetricsEndpoints:
  - path: /metrics
    port: rest-api
---
apiVersion: monitoring.coreos.com/v1
kind: PodMonitor
metadata:
  name: kafka-resources-metrics
  labels:
    app: strimzi
spec:
  selector:
    matchExpressions:
      - key: "strimzi.io/kind"
        operator: In
        values: ["Kafka", "KafkaConnect", "KafkaMirrorMaker", "KafkaMirrorMaker2"]
  namespaceSelector:
    matchNames:
      - kafka
  podMetricsEndpoints:
  - path: /metrics
    port: tcp-prometheus
    relabelings:
    - separator: ;
      regex: __meta_kubernetes_pod_label_(strimzi_io_.+)
      replacement: $1
      action: labelmap
    - sourceLabels: [__meta_kubernetes_namespace]
      separator: ;
      regex: (.*)
      targetLabel: namespace
      replacement: $1
      action: replace
    - sourceLabels: [__meta_kubernetes_pod_name]
      separator: ;
      regex: (.*)
      targetLabel: kubernetes_pod_name
      replacement: $1
      action: replace
    - sourceLabels: [__meta_kubernetes_pod_node_name]
      separator: ;
      regex: (.*)
      targetLabel: node_name
      replacement: $1
      action: replace
    - sourceLabels: [__meta_kubernetes_pod_host_ip]
      separator: ;
      regex: (.*)
      targetLabel: node_ip
      replacement: $1
      action: replace
[root@master-0 ~]# kubectl apply -f strimzi-pod-monitor.yaml -n kafka
podmonitor.monitoring.coreos.com/cluster-operator-metrics created
podmonitor.monitoring.coreos.com/entity-operator-metrics created
podmonitor.monitoring.coreos.com/bridge-metrics created
podmonitor.monitoring.coreos.com/kafka-resources-metrics created

grafana面板

可以参考:https://github.com/strimzi/strimzi-kafka-operator/tree/main/examples/metrics/grafana-dashboards

在k8s中运行kafka
在k8s中运行kafka
在k8s中运行kafka
在k8s中运行kafka

kafka测试使用

创建topic

# 创建topics
kubectl -n kafka run kafka-perf -ti --image=quay.io/strimzi/kafka:0.35.1-kafka-3.4.0 --rm=true --restart=Never -- bin/kafka-topics.sh --bootstrap-server my-cluster-kafka-bootstrap:9092 --topic kafka_perf create --partitions 6 --replication-factor 3

测试消息生产

# 生产消息测试
[root@master-0 ~]# kubectl -n kafka run kafka-perf -ti --image=quay.io/strimzi/kafka:0.35.1-kafka-3.4.0 --rm=true --restart=Never -- bin/kafka-producer-perf-test.sh --record-size 128 --print-metrics --producer-props acks=all bootstrap.servers=my-cluster-kafka-bootstrap:9092 --topic kafka_perf --num-records 50000000 --throughput -1
If you don't see a command prompt, try pressing enter.
702101 records sent, 140420.2 records/sec (17.14 MB/sec), 1037.7 ms avg latency, 1498.0 ms max latency.
1325612 records sent, 265122.4 records/sec (32.36 MB/sec), 944.0 ms avg latency, 1318.0 ms max latency.
1706516 records sent, 341235.0 records/sec (41.65 MB/sec), 481.1 ms avg latency, 831.0 ms max latency.
1545044 records sent, 308947.0 records/sec (37.71 MB/sec), 221.1 ms avg latency, 645.0 ms max latency.
1716130 records sent, 343226.0 records/sec (41.90 MB/sec), 207.1 ms avg latency, 588.0 ms max latency.
1579438 records sent, 315887.6 records/sec (38.56 MB/sec), 24.9 ms avg latency, 117.0 ms max latency.

外部访问kafka

如果kafka集群需要外部访问,则需要在创建时指定通告地址

# 略
listeners:
  - name: plain
    port: 9092
    type: internal
    tls: false
  - name: tls
    port: 9093
    type: internal
    tls: true
  - name: external
    port: 9094
    type: nodeport
    tls: false
    configuration:
      bootstrap:
        nodePort: 32094
  - name: pubexternal # 公网访问的
    port: 9095
    type: nodeport
    tls: false
    configuration:
      bootstrap:
        nodePort: 32095 # nodeport端口
      brokers:
      - broker: 0
        advertisedHost: 8.56.23.0 # 公网ip
      - broker: 1
        advertisedHost: 8.32.5.45 # 公网ip
      - broker: 2
        advertisedHost: 84.54.156.4 # 公网ip
# 略

创建topic

使用TopicOperator来创建Topic

apiVersion: kafka.strimzi.io/v1beta2
kind: KafkaTopic
metadata:
  name: test-topic #主题名称
  namespace: kafka 
  labels:
    strimzi.io/cluster: "my-cluster" # 集群名
spec:
  partitions: 3 # 分区数
  replicas: 1 # 副本数

注意: 后续该topic分区数只能增,不能减少。而replicas不能修改。

创建user

使用UserOperator可以用来创建kafka用户

apiVersion: kafka.strimzi.io/v1beta2
kind: KafkaUser
metadata:
  name: my-user
  labels:
    strimzi.io/cluster: my-cluster
spec:
  authentication:
    type: tls
  authorization:
    type: simple
    acls:
      # Example consumer Acls for topic my-topic using consumer group my-group
      - resource:
          type: topic
          name: my-topic
          patternType: literal
        operation: Read
        host: "*"
      - resource:
          type: topic
          name: my-topic
          patternType: literal
        operation: Describe
        host: "*"
      - resource:
          type: group
          name: my-group
          patternType: literal
        operation: Read
        host: "*"
      # Example Producer Acls for topic my-topic
      - resource:
          type: topic
          name: my-topic
          patternType: literal
        operation: Write
        host: "*"
      - resource:
          type: topic
          name: my-topic
          patternType: literal
        operation: Create
        host: "*"
      - resource:
          type: topic
          name: my-topic
          patternType: literal
        operation: Describe
        host: "*"

kafka broker配置

apiVersion: kafka.strimzi.io/v1beta2
kind: Kafka
metadata:
  name: my-cluster
spec:
  kafka:
    # ...
    config:
      num.partitions: 1
      num.recovery.threads.per.data.dir: 1
      default.replication.factor: 3
      offsets.topic.replication.factor: 3
      transaction.state.log.replication.factor: 3
      transaction.state.log.min.isr: 1
      log.retention.hours: 168
      log.segment.bytes: 1073741824
      log.retention.check.interval.ms: 300000
      num.network.threads: 3
      num.io.threads: 8
      socket.send.buffer.bytes: 102400
      socket.receive.buffer.bytes: 102400
      socket.request.max.bytes: 104857600
      group.initial.rebalance.delay.ms: 0
      zookeeper.connection.timeout.ms: 6000
    # ...

kafka jvmoption配置

# ...
jvmOptions:
  "-Xmx": "2g"
  "-Xms": "2g"
  "-XX":
    "UseG1GC": true
    "MaxGCPauseMillis": 20
    "InitiatingHeapOccupancyPercent": 35
    "ExplicitGCInvokesConcurrent": true
  gcLoggingEnabled: true

正文完
 
xadocker
版权声明:本站原创文章,由 xadocker 2023-07-23发表,共计23121字。
转载说明:除特殊说明外本站文章皆由CC-4.0协议发布,转载请注明出处。
评论(没有评论)