使用docker部署skywalking集群

环境准备

节点名称	ip地址
node1	192.168.130.20
node2	192.168.130.19
node2	192.168.130.21

安装docker

略

安装zookeeper集群

参考:https://blog.csdn.net/kk3909/article/details/111937681

安装elasticsearch7

参考:https://blog.csdn.net/kk3909/article/details/111937621

skywalking安装

1. 创建配置目录

mkdir -p /root/skywalking/config

2. 创建配置

cd /root/skywalking/config
vim application.yml

添加内容如下:

cluster:
  selector: ${SW_CLUSTER:zookeeper}
  standalone:
  # Please check your ZooKeeper is 3.5+, However, it is also compatible with ZooKeeper 3.4.x. Replace the ZooKeeper 3.5+
  # library the oap-libs folder with your ZooKeeper 3.4.x library.
  zookeeper:
    nameSpace: ${
    
    SW_NAMESPACE:""}
    hostPort: ${SW_CLUSTER_ZK_HOST_PORT:192.168.130.20:2181,192.168.130.19:2181,192.168.130.21:2181}
    # Retry Policy
    baseSleepTimeMs: ${SW_CLUSTER_ZK_SLEEP_TIME:1000} # initial amount of time to wait between retries
    maxRetries: ${SW_CLUSTER_ZK_MAX_RETRIES:3} # max number of times to retry
    # Enable ACL
    enableACL: ${SW_ZK_ENABLE_ACL:false} # disable ACL in default
    schema: ${SW_ZK_SCHEMA:digest} # only support digest schema
    expression: ${SW_ZK_EXPRESSION:skywalking:skywalking}
  kubernetes:
    watchTimeoutSeconds: ${SW_CLUSTER_K8S_WATCH_TIMEOUT:60}
    namespace: ${SW_CLUSTER_K8S_NAMESPACE:default}
    labelSelector: ${SW_CLUSTER_K8S_LABEL:app=collector,release=skywalking}
    uidEnvName: ${SW_CLUSTER_K8S_UID:SKYWALKING_COLLECTOR_UID}
  consul:
    serviceName: ${
    
    SW_SERVICE_NAME:"SkyWalking_OAP_Cluster"}
    # Consul cluster nodes, example: 10.0.0.1:8500,10.0.0.2:8500,10.0.0.3:8500
    hostPort: ${SW_CLUSTER_CONSUL_HOST_PORT:localhost:8500}
    aclToken: ${
    
    SW_CLUSTER_CONSUL_ACLTOKEN:""}
  nacos:
    serviceName: ${
    
    SW_SERVICE_NAME:"SkyWalking_OAP_Cluster"}
    hostPort: ${SW_CLUSTER_NACOS_HOST_PORT:localhost:8848}
    # Nacos Configuration namespace
    namespace: ${
    
    SW_CLUSTER_NACOS_NAMESPACE:"public"}
  etcd:
    serviceName: ${
    
    SW_SERVICE_NAME:"SkyWalking_OAP_Cluster"}
    # etcd cluster nodes, example: 10.0.0.1:2379,10.0.0.2:2379,10.0.0.3:2379
    hostPort: ${SW_CLUSTER_ETCD_HOST_PORT:localhost:2379}

core:
  selector: ${SW_CORE:default}
  default:
    # Mixed: Receive agent data, Level 1 aggregate, Level 2 aggregate
    # Receiver: Receive agent data, Level 1 aggregate
    # Aggregator: Level 2 aggregate
    role: ${SW_CORE_ROLE:Mixed} # Mixed/Receiver/Aggregator
    restHost: ${SW_CORE_REST_HOST:0.0.0.0}
    restPort: ${SW_CORE_REST_PORT:12800}
    restContextPath: ${SW_CORE_REST_CONTEXT_PATH:/}
    gRPCHost: ${SW_CORE_GRPC_HOST:0.0.0.0}
    gRPCPort: ${SW_CORE_GRPC_PORT:11800}
    gRPCSslEnabled: ${SW_CORE_GRPC_SSL_ENABLED:false}
    gRPCSslKeyPath: ${
    
    SW_CORE_GRPC_SSL_KEY_PATH:""}
    gRPCSslCertChainPath: ${
    
    SW_CORE_GRPC_SSL_CERT_CHAIN_PATH:""}
    gRPCSslTrustedCAPath: ${
    
    SW_CORE_GRPC_SSL_TRUSTED_CA_PATH:""}
    downsampling:
      - Hour
      - Day
      - Month
    # Set a timeout on metrics data. After the timeout has expired, the metrics data will automatically be deleted.
    enableDataKeeperExecutor: ${SW_CORE_ENABLE_DATA_KEEPER_EXECUTOR:true} # Turn it off then automatically metrics data delete will be close.
    dataKeeperExecutePeriod: ${SW_CORE_DATA_KEEPER_EXECUTE_PERIOD:5} # How often the data keeper executor runs periodically, unit is minute
    recordDataTTL: ${SW_CORE_RECORD_DATA_TTL:90} # Unit is minute
    minuteMetricsDataTTL: ${SW_CORE_MINUTE_METRIC_DATA_TTL:90} # Unit is minute
    hourMetricsDataTTL: ${SW_CORE_HOUR_METRIC_DATA_TTL:36} # Unit is hour
    dayMetricsDataTTL: ${SW_CORE_DAY_METRIC_DATA_TTL:45} # Unit is day
    monthMetricsDataTTL: ${SW_CORE_MONTH_METRIC_DATA_TTL:18} # Unit is month
    # Cache metric data for 1 minute to reduce database queries, and if the OAP cluster changes within that minute,
    # the metrics may not be accurate within that minute.
    enableDatabaseSession: ${SW_CORE_ENABLE_DATABASE_SESSION:true}
    topNReportPeriod: ${SW_CORE_TOPN_REPORT_PERIOD:10} # top_n record worker report cycle, unit is minute
    # Extra model column are the column defined by in the codes, These columns of model are not required logically in aggregation or further query,
    # and it will cause more load for memory, network of OAP and storage.
    # But, being activated, user could see the name in the storage entities, which make users easier to use 3rd party tool, such as Kibana->ES, to query the data by themselves.
    activeExtraModelColumns: ${SW_CORE_ACTIVE_EXTRA_MODEL_COLUMNS:false}

storage:
  selector: ${SW_STORAGE:elasticsearch7}
  elasticsearch:
    nameSpace: ${
    
    SW_NAMESPACE:""}
    clusterNodes: ${SW_STORAGE_ES_CLUSTER_NODES:localhost:9200}
    protocol: ${
    
    SW_STORAGE_ES_HTTP_PROTOCOL:"http"}
    trustStorePath: ${
    
    SW_SW_STORAGE_ES_SSL_JKS_PATH:"../es_keystore.jks"}
    trustStorePass: ${
    
    SW_SW_STORAGE_ES_SSL_JKS_PASS:""}
    user: ${
    
    SW_ES_USER:""}
    password: ${
    
    SW_ES_PASSWORD:""}
    secretsManagementFile: ${
    
    SW_ES_SECRETS_MANAGEMENT_FILE:""} # Secrets management file in the properties format includes the username, password, which are managed by 3rd party tool.
    enablePackedDownsampling: ${SW_STORAGE_ENABLE_PACKED_DOWNSAMPLING:true} # Hour and Day metrics will be merged into minute index.
    dayStep: ${SW_STORAGE_DAY_STEP:1} # Represent the number of days in the one minute/hour/day index.
    indexShardsNumber: ${SW_STORAGE_ES_INDEX_SHARDS_NUMBER:2}
    indexReplicasNumber: ${SW_STORAGE_ES_INDEX_REPLICAS_NUMBER:0}
    # Those data TTL settings will override the same settings in core module.
    recordDataTTL: ${SW_STORAGE_ES_RECORD_DATA_TTL:7} # Unit is day
    otherMetricsDataTTL: ${SW_STORAGE_ES_OTHER_METRIC_DATA_TTL:45} # Unit is day
    monthMetricsDataTTL: ${SW_STORAGE_ES_MONTH_METRIC_DATA_TTL:18} # Unit is month
    # Batch process setting, refer to https://www.elastic.co/guide/en/elasticsearch/client/java-api/5.5/java-docs-bulk-processor.html
    bulkActions: ${SW_STORAGE_ES_BULK_ACTIONS:1000} # Execute the bulk every 1000 requests
    flushInterval: ${SW_STORAGE_ES_FLUSH_INTERVAL:10} # flush the bulk every 10 seconds whatever the number of requests
    concurrentRequests: ${SW_STORAGE_ES_CONCURRENT_REQUESTS:2} # the number of concurrent requests
    resultWindowMaxSize: ${SW_STORAGE_ES_QUERY_MAX_WINDOW_SIZE:10000}
    metadataQueryMaxSize: ${SW_STORAGE_ES_QUERY_MAX_SIZE:5000}
    segmentQueryMaxSize: ${SW_STORAGE_ES_QUERY_SEGMENT_SIZE:200}
    profileTaskQueryMaxSize: ${SW_STORAGE_ES_QUERY_PROFILE_TASK_SIZE:200}
    advanced: ${
    
    SW_STORAGE_ES_ADVANCED:""}
  elasticsearch7:
    nameSpace: ${
    
    SW_NAMESPACE:""}
    clusterNodes: ${SW_STORAGE_ES_CLUSTER_NODES:192.168.130.20:9200,192.168.130.19:9200,192.168.130.21:9200}
    protocol: ${
    
    SW_STORAGE_ES_HTTP_PROTOCOL:"http"}
    trustStorePath: ${
    
    SW_SW_STORAGE_ES_SSL_JKS_PATH:"../es_keystore.jks"}
    trustStorePass: ${
    
    SW_SW_STORAGE_ES_SSL_JKS_PASS:""}
    enablePackedDownsampling: ${SW_STORAGE_ENABLE_PACKED_DOWNSAMPLING:true} # Hour and Day metrics will be merged into minute index.
    dayStep: ${SW_STORAGE_DAY_STEP:1} # Represent the number of days in the one minute/hour/day index.
    user: ${
    
    SW_ES_USER:""}
    password: ${
    
    SW_ES_PASSWORD:""}
    secretsManagementFile: ${
    
    SW_ES_SECRETS_MANAGEMENT_FILE:""} # Secrets management file in the properties format includes the username, password, which are managed by 3rd party tool.
    indexShardsNumber: ${SW_STORAGE_ES_INDEX_SHARDS_NUMBER:2}
    indexReplicasNumber: ${SW_STORAGE_ES_INDEX_REPLICAS_NUMBER:0}
    # Those data TTL settings will override the same settings in core module.
    recordDataTTL: ${SW_STORAGE_ES_RECORD_DATA_TTL:7} # Unit is day
    otherMetricsDataTTL: ${SW_STORAGE_ES_OTHER_METRIC_DATA_TTL:45} # Unit is day
    monthMetricsDataTTL: ${SW_STORAGE_ES_MONTH_METRIC_DATA_TTL:18} # Unit is month
    # Batch process setting, refer to https://www.elastic.co/guide/en/elasticsearch/client/java-api/5.5/java-docs-bulk-processor.html
    bulkActions: ${SW_STORAGE_ES_BULK_ACTIONS:1000} # Execute the bulk every 1000 requests
    flushInterval: ${SW_STORAGE_ES_FLUSH_INTERVAL:10} # flush the bulk every 10 seconds whatever the number of requests
    concurrentRequests: ${SW_STORAGE_ES_CONCURRENT_REQUESTS:2} # the number of concurrent requests
    resultWindowMaxSize: ${SW_STORAGE_ES_QUERY_MAX_WINDOW_SIZE:10000}
    metadataQueryMaxSize: ${SW_STORAGE_ES_QUERY_MAX_SIZE:5000}
    segmentQueryMaxSize: ${SW_STORAGE_ES_QUERY_SEGMENT_SIZE:200}
    profileTaskQueryMaxSize: ${SW_STORAGE_ES_QUERY_PROFILE_TASK_SIZE:200}
    advanced: ${
    
    SW_STORAGE_ES_ADVANCED:""}
  h2:
    driver: ${SW_STORAGE_H2_DRIVER:org.h2.jdbcx.JdbcDataSource}
    url: ${SW_STORAGE_H2_URL:jdbc:h2:mem:skywalking-oap-db}
    user: ${SW_STORAGE_H2_USER:sa}
    metadataQueryMaxSize: ${SW_STORAGE_H2_QUERY_MAX_SIZE:5000}
  mysql:
    properties:
      jdbcUrl: ${
    
    SW_JDBC_URL:"jdbc:mysql://localhost:3306/swtest"}
      dataSource.user: ${SW_DATA_SOURCE_USER:root}
      dataSource.password: ${SW_DATA_SOURCE_PASSWORD:root@1234}
      dataSource.cachePrepStmts: ${SW_DATA_SOURCE_CACHE_PREP_STMTS:true}
      dataSource.prepStmtCacheSize: ${SW_DATA_SOURCE_PREP_STMT_CACHE_SQL_SIZE:250}
      dataSource.prepStmtCacheSqlLimit: ${SW_DATA_SOURCE_PREP_STMT_CACHE_SQL_LIMIT:2048}
      dataSource.useServerPrepStmts: ${SW_DATA_SOURCE_USE_SERVER_PREP_STMTS:true}
    metadataQueryMaxSize: ${SW_STORAGE_MYSQL_QUERY_MAX_SIZE:5000}
  influxdb:
    # Metadata storage provider configuration
    metabaseType: ${SW_STORAGE_METABASE_TYPE:H2} # There are 2 options as Metabase provider, H2 or MySQL.
    h2Props:
      dataSourceClassName: ${SW_STORAGE_METABASE_DRIVER:org.h2.jdbcx.JdbcDataSource}
      dataSource.url: ${SW_STORAGE_METABASE_URL:jdbc:h2:mem:skywalking-oap-db}
      dataSource.user: ${SW_STORAGE_METABASE_USER:sa}
      dataSource.password: ${SW_STORAGE_METABASE_PASSWORD:}
    mysqlProps:
      jdbcUrl: ${
    
    SW_STORAGE_METABASE_URL:"jdbc:mysql://localhost:3306/swtest"}
      dataSource.user: ${SW_STORAGE_METABASE_USER:root}
      dataSource.password: ${SW_STORAGE_METABASE_PASSWORD:root@1234}
      dataSource.cachePrepStmts: ${SW_STORAGE_METABASE_CACHE_PREP_STMTS:true}
      dataSource.prepStmtCacheSize: ${SW_STORAGE_METABASE_PREP_STMT_CACHE_SQL_SIZE:250}
      dataSource.prepStmtCacheSqlLimit: ${SW_STORAGE_METABASE_PREP_STMT_CACHE_SQL_LIMIT:2048}
      dataSource.useServerPrepStmts: ${SW_STORAGE_METABASE_USE_SERVER_PREP_STMTS:true}
    metadataQueryMaxSize: ${SW_STORAGE_METABASE_QUERY_MAX_SIZE:5000}
    # InfluxDB configuration
    url: ${SW_STORAGE_INFLUXDB_URL:http://localhost:8086}
    user: ${SW_STORAGE_INFLUXDB_USER:root}
    password: ${SW_STORAGE_INFLUXDB_PASSWORD:}
    database: ${SW_STORAGE_INFLUXDB_DATABASE:skywalking}
    actions: ${SW_STORAGE_INFLUXDB_ACTIONS:1000} # the number of actions to collect
    duration: ${SW_STORAGE_INFLUXDB_DURATION:1000} # the time to wait at most (milliseconds)
    fetchTaskLogMaxSize: ${SW_STORAGE_INFLUXDB_FETCH_TASK_LOG_MAX_SIZE:5000} # the max number of fetch task log in a request

receiver-sharing-server:
  selector: ${SW_RECEIVER_SHARING_SERVER:default}
  default:
    authentication: ${
    
    SW_AUTHENTICATION:""}
receiver-register:
  selector: ${SW_RECEIVER_REGISTER:default}
  default:

receiver-trace:
  selector: ${SW_RECEIVER_TRACE:default}
  default:
    bufferPath: ${SW_RECEIVER_BUFFER_PATH:../trace-buffer/}  # Path to trace buffer files, suggest to use absolute path
    bufferOffsetMaxFileSize: ${SW_RECEIVER_BUFFER_OFFSET_MAX_FILE_SIZE:100} # Unit is MB
    bufferDataMaxFileSize: ${SW_RECEIVER_BUFFER_DATA_MAX_FILE_SIZE:500} # Unit is MB
    bufferFileCleanWhenRestart: ${SW_RECEIVER_BUFFER_FILE_CLEAN_WHEN_RESTART:false}
    sampleRate: ${SW_TRACE_SAMPLE_RATE:10000} # The sample rate precision is 1/10000. 10000 means 100% sample in default.
    slowDBAccessThreshold: ${SW_SLOW_DB_THRESHOLD:default:200,mongodb:100} # The slow database access thresholds. Unit ms.

receiver-jvm:
  selector: ${SW_RECEIVER_JVM:default}
  default:

receiver-clr:
  selector: ${SW_RECEIVER_CLR:default}
  default:

receiver-profile:
  selector: ${SW_RECEIVER_PROFILE:default}
  default:

service-mesh:
  selector: ${SW_SERVICE_MESH:default}
  default:
    bufferPath: ${SW_SERVICE_MESH_BUFFER_PATH:../mesh-buffer/}  # Path to trace buffer files, suggest to use absolute path
    bufferOffsetMaxFileSize: ${SW_SERVICE_MESH_OFFSET_MAX_FILE_SIZE:100} # Unit is MB
    bufferDataMaxFileSize: ${SW_SERVICE_MESH_BUFFER_DATA_MAX_FILE_SIZE:500} # Unit is MB
    bufferFileCleanWhenRestart: ${SW_SERVICE_MESH_BUFFER_FILE_CLEAN_WHEN_RESTART:false}

istio-telemetry:
  selector: ${SW_ISTIO_TELEMETRY:default}
  default:

envoy-metric:
  selector: ${SW_ENVOY_METRIC:default}
  default:
    alsHTTPAnalysis: ${
    
    SW_ENVOY_METRIC_ALS_HTTP_ANALYSIS:""}

receiver_zipkin:
  selector: ${SW_RECEIVER_ZIPKIN:-}
  default:
    host: ${SW_RECEIVER_ZIPKIN_HOST:0.0.0.0}
    port: ${SW_RECEIVER_ZIPKIN_PORT:9411}
    contextPath: ${SW_RECEIVER_ZIPKIN_CONTEXT_PATH:/}

receiver_jaeger:
  selector: ${SW_RECEIVER_JAEGER:-}
  default:
    gRPCHost: ${SW_RECEIVER_JAEGER_HOST:0.0.0.0}
    gRPCPort: ${SW_RECEIVER_JAEGER_PORT:14250}

query:
  selector: ${SW_QUERY:graphql}
  graphql:
    path: ${SW_QUERY_GRAPHQL_PATH:/graphql}

alarm:
  selector: ${SW_ALARM:default}
  default:

telemetry:
  selector: ${SW_TELEMETRY:none}
  none:
  prometheus:
    host: ${SW_TELEMETRY_PROMETHEUS_HOST:0.0.0.0}
    port: ${SW_TELEMETRY_PROMETHEUS_PORT:1234}
  so11y:
    prometheusExporterEnabled: ${SW_TELEMETRY_SO11Y_PROMETHEUS_ENABLED:true}
    prometheusExporterHost: ${SW_TELEMETRY_PROMETHEUS_HOST:0.0.0.0}
    prometheusExporterPort: ${SW_TELEMETRY_PROMETHEUS_PORT:1234}

receiver-so11y:
  selector: ${SW_RECEIVER_SO11Y:-}
  default:

configuration:
  selector: ${SW_CONFIGURATION:none}
  none:
  apollo:
    apolloMeta: http://106.12.25.204:8080
    apolloCluster: default
    apolloEnv: ""
    appId: skywalking
    period: 5
  nacos:
    # Nacos Server Host
    serverAddr: 127.0.0.1
    # Nacos Server Port
    port: 8848
    # Nacos Configuration Group
    group: 'skywalking'
    # Nacos Configuration namespace
    namespace: ''
    # Unit seconds, sync period. Default fetch every 60 seconds.
    period : 60
    # the name of current cluster, set the name if you want to upstream system known.
    clusterName: "default"
  zookeeper:
    period : 60 # Unit seconds, sync period. Default fetch every 60 seconds.
    nameSpace: /default
    hostPort: localhost:2181
    # Retry Policy
    baseSleepTimeMs: 1000 # initial amount of time to wait between retries
    maxRetries: 3 # max number of times to retry
  etcd:
    period : 60 # Unit seconds, sync period. Default fetch every 60 seconds.
    group :  'skywalking'
    serverAddr: localhost:2379
    clusterName: "default"
  consul:
    # Consul host and ports, separated by comma, e.g. 1.2.3.4:8500,2.3.4.5:8500
    hostAndPorts: ${consul.address}
    # Sync period in seconds. Defaults to 60 seconds.
    period: 1
    # Consul aclToken
    #aclToken: ${consul.aclToken}

exporter:
  selector: ${SW_EXPORTER:-}
  grpc:
    targetHost: ${SW_EXPORTER_GRPC_HOST:127.0.0.1}
    targetPort: ${SW_EXPORTER_GRPC_PORT:9870}

主要修改cluster.zookeeper.hostPort、storage.elasticsearch7.clusterNodes

skywalking oap

node1

 docker run --name sk-node1 -d -p 1234:1234 -p 11800:11800 \
 -p 12800:12800 --restart always  \
 -e TZ=Asia/Shanghai \
 -e SW_STORAGE=elasticsearch7 \
 -e SW_STORAGE_ES_CLUSTER_NODES=192.168.130.20:9200,192.168.130.19:9200,192.168.130.21:9200 \
 -v /root/skywalking/config/application.yml:/skywalking/config/application.yml \
 apache/skywalking-oap-server:7.0.0-es7

node2

 docker run --name sk-node2 -d -p 1234:1234 -p 11800:11800 \
 -p 12800:12800 --restart always  \
 -e TZ=Asia/Shanghai \
 -e SW_STORAGE=elasticsearch7 \
 -e SW_STORAGE_ES_CLUSTER_NODES=192.168.130.20:9200,192.168.130.19:9200,192.168.130.21:9200 \
 -v /root/skywalking/config/application.yml:/skywalking/config/application.yml \
 apache/skywalking-oap-server:7.0.0-es7

skywalking ui

node1

docker run --name sk-ui-node1 -d -p 8080:8080  \
-e TZ=Asia/Shanghai \
-e SW_OAP_ADDRESS=192.168.130.20:12800 \
-e SW_TIMEOUT=20000 \
--restart always apache/skywalking-ui:7.0.0 

node2

docker run --name sk-ui-node2 -d -p 8080:8080  \
-e TZ=Asia/Shanghai \
-e SW_OAP_ADDRESS=192.168.130.19:12800 \
-e SW_TIMEOUT=20000 \
--restart always apache/skywalking-ui:7.0.0 

在前面再加个lb做负载