namespace: pulsar-demo

tls:
  enabled: false
  proxy:
    enabled: false

zookeeper:
  replicaCount: 3
  resources:
    requests:
      memory: 500Mi
      cpu: 100m
  volumes:
    useSeparateDiskForTxlog: true
    data:
      name: data
      size: 10Gi
      # set your own storage class name or use the default storage class
      #storageClassName: local-ssd
    dataLog:
      name: datalog
      size: 10Gi
      # set your own storage class name or use the default storage class
      #storageClassName: local-hdd
  configData:
    PULSAR_MEM: >
      -Xms300M -Xmx300M
    PULSAR_EXTRA_OPTS: >
      -Dzookeeper.snapCount=1000000
    PULSAR_PREFIX_maxClientCnxns: "1000"

bookkeeper:
  replicaCount: 3
  resources:
    limits:
      cpu: 100m
      memory: 500Mi
    requests:
      cpu: 100m
      memory: 500Mi
  volumes:
    journal:
      name: journal
      size: 5Gi
      # set your own storage class name or use the default storage class
      #storageClassName: local-ssd
    ledgers:
      name: ledgers
      size: 10Gi
      # set your own storage class name or use the default storage class
      #storageClassName: local-hdd
  configData:
    PULSAR_GC: >
      -XX:+ExitOnOutOfMemoryError
    PULSAR_MEM: >
      -Xms100M
      -Xmx100M
      -XX:MaxDirectMemorySize=100M
    PULSAR_EXTRA_OPTS: >
      -Dpulsar.allocator.exit_on_oom=true
      -Dio.netty.recycler.maxCapacity.default=1000
      -Dio.netty.recycler.linkCapacity=1024
      -Dnetworkaddress.cache.ttl=60
    gcWaitTime: "900000"
    journalFormatVersionToWrite: "6"
    # set fileInfoFormatVersionToWrite to `1` in order to enable journal format version `6`
    fileInfoFormatVersionToWrite: "1"
    minorCompactionInterval: "3600"
    majorCompactionInterval: "86400"
    isThrottleByBytes: "true"
    compactionRateByBytes: "10485760"
    PULSAR_PREFIX_useTransactionalCompaction: "true"
    PULSAR_PREFIX_persistBookieStatusEnabled: "false"

broker:
  # set your own domain for accesing kop outside from the cluster
  #advertisedDomain: "kop.sn.dev"
  #kop:
  #  enabled: false
  #  tls:
  #    enabled: true
  #    # create a secret with keystore.jks and truststore.jks for kop tls security
  #    certSecretName: "kop-secret"
  #    # create a secret for keystore and truststore cert
  #    passwordSecretRef:
  #      key: password
  #      name: kop-keystore-password
  #istio:
  #  gateway:
  #    selector:
  #      # set your istio gateway label here
  #      istio: "ingressgateway"

  replicaCount: 2
  resources:
    requests:
      cpu: 100m
      memory: 500Mi
  configData:
    PULSAR_MEM: >
      -Xms100M
      -Xmx100M
      -XX:MaxDirectMemorySize=100M
    PULSAR_GC: >
      -XX:+ExitOnOutOfMemoryError
    PULSAR_EXTRA_OPTS: >
      -Dpulsar.allocator.exit_on_oom=true
      -Dio.netty.recycler.maxCapacity.default=1000
      -Dio.netty.recycler.linkCapacity=1024
      -Dnetworkaddress.cache.ttl=60
    managedLedgerDefaultEnsembleSize: "2"
    managedLedgerDefaultWriteQuorum: "2"
    managedLedgerDefaultAckQuorum: "2"

    # For audit log
    PULSAR_PREFIX_brokerInterceptors: "audit-log"
    PULSAR_PREFIX_brokerInterceptorsDirectory: "./interceptors"
    PULSAR_PREFIX_snAuditLogConfig: >
      {"defaultTopics":{"allowed":"persistent://sn/system/audit_log_allowed","denied":"persistent://sn/system/audit_log_denied"}}

proxy:
  replicaCount: 1
  resources:
    requests:
      cpu: 100m
      memory: 500Mi
  configData:
    PULSAR_MEM: >
      -Xms100M -Xmx100M -XX:MaxDirectMemorySize=100M
    PULSAR_GC: >
      -XX:+ExitOnOutOfMemoryError
    PULSAR_EXTRA_OPTS: >
      -Dpulsar.allocator.exit_on_oom=true
      -Dio.netty.recycler.maxCapacity.default=1000
      -Dio.netty.recycler.linkCapacity=1024
      -Dnetworkaddress.cache.ttl=60
  tlsSecretName: "demo-sn-pulsar-proxy-tls"

# streamnative_console
streamnative_console:
  component: streamnative-console
  ports:
    frontend: 9527
    backend: 7750
  replicaCount: 1
  volumes:
    #persistence: true
    data:
      name: data
      size: 5Gi
      #storageClassName: local-ssd
  configData:
    DEFAULT_ORGANIZATION: streamnative
    DEFAULT_NAME: streamnative
    INSTANCE_NAME: pulsar

prometheus:
  # keep request = limit to keep this container in guaranteed class
  resources:
    requests:
      cpu: 100m
      memory: 100Mi
  volumes:
    data:
      name: data
      size: 5Gi
      #storageClassName: local-ssd
grafana:
  resources:
    # keep request = limit to keep this container in guaranteed class
    requests:
      cpu: 100m
      memory: 100Mi
    limits:
      cpu: 100m
      memory: 200Mi
  volumes:
    data:
      name: data
      size: 5Gi
      #storageClassName: local-ssd
alert_manager:
  resources:
    requests:
      memory: 100Mi
      cpu: 100m
  config:
    global:
      resolve_timeout: 1m
  rules:
    groups:
      - name: node
        rules:
          - alert: InstanceDown
            expr: up == 0
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "Instance {{ $labels.kubernetes_pod_name }} down."
              description: "{{ $labels.kubernetes_pod_name }} of job {{ $labels.job }} has been down for more than 5 minutes."

          - alert: CpuUsage
            expr: 100 * (1 - avg by(instance)(rate(node_cpu_seconds_total{mode='idle'}[1m]))) > 85
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "Instance {{ $labels.instance }} has high CPU usage: {{ $value }}%"

          - alert: PersistentVolumeSpace
            expr: 100 * (1 - (kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes)) > 85
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "Space used on {{ $labels.persistentvolumeclaim }} is above the critical threshold -- value: {{ $value }}%"

          - alert: HighIOUtils
            expr: irate(node_disk_io_time_seconds_total[1m]) > 0.8
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "High IO utils."
              description: "High IO utils on instance {{ $labels.instance }} of job {{ $labels.job }} over than 80%, current value is {{ $value }}%"

          - alert: HighDiskUsage
            expr: (node_filesystem_size_bytes - node_filesystem_avail_bytes)  / node_filesystem_size_bytes > 0.8
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "High disk usage"
              description: "High IO utils on instance {{ $labels.instance }} of job {{ $labels.job }} over than 80%, current value is {{ $value }}%"

          - alert: HighInboundNetwork
            expr: rate(node_network_receive_bytes_total{instance="$instance", device!="lo"}[30s]) or irate(node_network_receive_bytes_total{instance="$instance", device!="lo"}[30s]) / 1024 / 1024 > 512
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "High inbound network"
              description: "High inbound network on instance {{ $labels.instance }} of job {{ $labels.job }} over than 512MB/s, current value is {{ $value }}/s"

      - name: zookeeper
        rules:
          - alert: HighWatchers
            expr: zookeeper_server_watches_count{job="zookeeper"} > 1000000
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "Watchers of Zookeeper server is over than 1000k."
              description: "Watchers of Zookeeper server {{ $labels.kubernetes_pod_name }} is over than 1000k, current value is {{ $value }}."

          - alert: HighEphemerals
            expr: zookeeper_server_ephemerals_count{job="zookeeper"} > 10000
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "Ephemeral nodes of Zookeeper server is over than 10k."
              description: "Ephemeral nodes of Zookeeper server {{ $labels.kubernetes_pod_name }} is over than 10k, current value is {{ $value }}."

          - alert: HighConnections
            expr: zookeeper_server_connections{job="zookeeper"} > 10000
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "Connections of Zookeeper server is over than 10k."
              description: "Connections of Zookeeper server {{ $labels.kubernetes_pod_name }} is over than 10k, current value is {{ $value }}."

          - alert: HighDataSize
            expr: zookeeper_server_data_size_bytes{job="zookeeper"} > 2147483648
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "Data size of Zookeeper server is over than 2GB."
              description: "Data size of Zookeeper server {{ $labels.instance }} is over than 2GB, current value is {{ $value }}."

          - alert: HighRequestThroughput
            expr: sum(irate(zookeeper_server_requests{job="zookeeper"}[30s])) by (type) > 1000
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "Request throughput on Zookeeper server is over than 1000 in 5m."
              description: "Request throughput of {{ $labels.type}} on Zookeeper server {{ $labels.instance }} is over than 1k, current value is {{ $value }}."

          - alert: HighRequestLatency
            expr: zookeeper_server_requests_latency_ms{job="zookeeper", quantile="0.99"} > 100
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "Request latency on Zookeeper server is over than 100ms."
              description: "Request latency {{ $labels.type }} in p99 on Zookeeper server {{ $labels.instance }} is over than 100ms, current value is {{ $value }} ms."

      - name: bookie
        rules:
          - alert: HighEntryAddLatency
            expr: bookkeeper_server_ADD_ENTRY_REQUEST{job="bookie", quantile="0.99", success="true"} > 200
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "Entry add latency is over than 200ms"
              description: "Entry add latency on bookie {{ $labels.instance }} is over than 200ms, current value is {{ $value }}."

          - alert: HighEntryReadLatency
            expr: bookkeeper_server_READ_ENTRY_REQUEST{job="bookie", quantile="0.99", success="true"} > 1000
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "Entry read latency is over than 1s"
              description: "Entry read latency on bookie {{ $labels.instance }} is over than 1s, current value is {{ $value }}."

      - name: broker
        rules:
          - alert: HighStorageWriteLatency
            expr: pulsar_storage_write_latency_le_1000{job="broker"} > 1000
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "Pulsar storage write latency is over than 1s"
              description: "Pulsar storage write latency is over than 1s on topic {{ $labels.topic }}, current value is {{ $value }}."

          - alert: TooManyTopics
            expr: sum(pulsar_topics_count{job="broker"}) by (cluster) > 1000000
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "Topic count are over than 1000000."
              description: "Topic count in cluster {{ $labels.cluster }} is more than 1000000, current value is {{ $value }}."

          - alert: TooManyProducersOnTopic
            expr: pulsar_producers_count > 10000
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "Producers on topic are more than 10000."
              description: "Producers on topic {{ $labels.topic }} is more than 10000, current value is {{ $value }}."

          - alert: TooManySubscriptionsOnTopic
            expr: pulsar_subscriptions_count > 10000
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "Subscriptions on topic are more than 10000."
              description: "Subscriptions on topic {{ $labels.topic }} is more than 10000, current value is {{ $value }}."

          - alert: TooManyConsumersOnTopic
            expr: pulsar_consumers_count > 10000
            for: 5m
            labels:
              status: warning
            annotations:
              summary: "Consumers on topic are more than 10000."
              description: "Consumers on topic {{ $labels.topic }} is more than 10000 , current value is {{ $value }}."

          - alert: HighTopicGeoBacklog
            expr: pulsar_replication_backlog > 1000000
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "High number of messages in topic geo replication backlog."
              description: "High Number of messages in the geo-replication backlog of topic {{ $labels.topic }} is more than 1000000, current value is {{ $value }}."

      - name: jvm
        rules:
          - alert: JvmHeapLimit
            # Alert when a JVM process is using all heap memory
            expr: (100 * jvm_memory_bytes_used{area="heap"} / jvm_memory_bytes_max{area="heap"}) > 95
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "High JVM heap memory usage"
              description: "JVM heap memory usage of {{ $labels.kubernetes_pod_name }} - {{ $value }} is larger than 95%"

          - alert: JvmDirectMemLimit
            # Alert when a JVM process is using all direct memory
            expr: (100 * jvm_memory_direct_bytes_used / jvm_memory_direct_bytes_max) > 95
            for: 5m
            labels:
              severity: page
            annotations:
              summary: "High JVM direct memory usage"
              description: "JVM direct memory usage of {{ $labels.kubernetes_pod_name }} - {{ $value }} is larger than 95%"

# At most case, you don't need to change this
vault:
  volume:
    persistence: true
    name: "raft"
    size: 10Gi
    local_storage: true
    # set your own storage class name or use the default storage class
    #storageClassName: "local-hdd"

  volumeMounts:
  - name: vault-raft
    mountPath: /vault/file

  # use raft protocol for a vault cluster
  config:
    storage:
      raft:
        path: "/vault/file"
    listener:
      tcp:
        tls_disable: true
        address: "0.0.0.0:8200"
    api_addr: "http://${.Env.POD_NAME}:8200"
    cluster_addr: "http://${.Env.POD_NAME}:8201"
    ui: true

  #resources:
  #  limits:
  #    memory: "4Gi"
  #    cpu: "200m"
  #  requests:
  #    memory: "4Gi"
  #    cpu: "200m"
  


#monitoring:
#  # monitoring - prometheus
#  prometheus: false
#  # monitoring - grafana
#  grafana: false
#  # monitoring - node_exporter
#  node_exporter: false
#  # alerting - alert-manager
#  alert_manager: false

## Ingresses for exposing Pulsar services
ingress:
  ## Ingresses for exposing pulsar service publicly
  proxy:
    enabled: false
    type: LoadBalancer
    tls:
      # If you enable proxy tls, you should enable this too.
      enabled: false
    annotations:
      # If you use aws lb, recommend to add this
      service.beta.kubernetes.io/aws-load-balancer-type: nlb
  ## Ingresses for exposing monitoring/management services publicly
  controller:
    enabled: false
    annotations: 
      # If you use aws lb, recommend to add this
      service.beta.kubernetes.io/aws-load-balancer-type: nlb
  control_center:
    enabled: false
    # Set external domain of the load balancer of ingress controller
    # external_domain: 
    # external_domain_scheme: https://

## Images
##
## Control what images to use for each component
images:
  zookeeper:
    repository: streamnative/sn-platform
    tag: "2.8.0.5"
    pullPolicy: IfNotPresent
  bookie:
    repository: streamnative/sn-platform
    tag: "2.8.0.5"
    pullPolicy: IfNotPresent
  presto:
    repository: streamnative/sn-platform
    tag: "2.8.0.5"
    pullPolicy: IfNotPresent
  # NOTE: allow overriding the presto worker image
  # presto_worker:
  #   repository: streamnative/sn-platform
  #   tag: 2.7.0.4
  #   pullPolicy: IfNotPresent
  autorecovery:
    repository: streamnative/sn-platform
    tag: "2.8.0.5"
    pullPolicy: IfNotPresent
  broker:
    repository: streamnative/sn-platform
    tag: "2.8.0.5"
    pullPolicy: IfNotPresent
  proxy:
    repository: streamnative/sn-platform
    tag: "2.8.0.5"
    pullPolicy: IfNotPresent
  pulsar_detector:
    repository: streamnative/sn-platform
    tag: "2.8.0.5"
    pullPolicy: IfNotPresent
  functions:
    repository: streamnative/sn-platform
    tag: "2.8.0.5"
    pullPolicy: IfNotPresent
  # NOTE: allow overriding the toolset image
  # toolset:
  #   repository: streamnative/sn-platform
  #   tag: "2.8.0.5"
  #   pullPolicy: IfNotPresent
  prometheus:
    repository: prom/prometheus
    tag: "v2.17.2"
    pullPolicy: IfNotPresent
  alert_manager:
    repository: prom/alertmanager
    tag: "v0.20.0"
    pullPolicy: IfNotPresent
  grafana:
    repository: streamnative/apache-pulsar-grafana-dashboard-k8s
    tag: "0.0.16"
    pullPolicy: IfNotPresent
  streamnative_console:
    repository: streamnative/sn-platform-console
    tag: "1.0"
    pullPolicy: IfNotPresent
    hasCommand: false
  node_exporter:
    repository: prom/node-exporter
    tag: "v0.16.0"
    pullPolicy: "IfNotPresent"
  nginx_ingress_controller:
    repository: streamnative/nginx-ingress-controller
    tag: "0.26.2"
    pullPolicy: "IfNotPresent"
  vault:
    repository: vault
    tag: "1.7.0"
    pullPolicy: "IfNotPresent"
  vault_init:
    repository: streamnative/pulsar_vault_init
    tag: "v1.0.2"

configmapReload:
  prometheus:
    ## configmap-reload container image
    ##
    image:
      repository: jimmidyson/configmap-reload
      tag: v0.3.0
      pullPolicy: IfNotPresent
  alertmanager:
    ## configmap-reload container image
    ##
    image:
      repository: jimmidyson/configmap-reload
      tag: v0.3.0
      pullPolicy: IfNotPresent