深度了解flink(十) JobManager(4) ResourceManager HA

橙子qyfftf

于 2024-10-31 21:55:33 发布

阅读量559

点赞数 5

CC 4.0 BY-SA版权

文章标签： flink 大数据

本文链接：https://blog.csdn.net/qq_40689430/article/details/143418429

ResourceManager（ZK模式）的高可用启动流程

ResourceManager启动流程在DefaultDispatcherResourceManagerComponentFactory#create中

public DispatcherResourceManagerComponent create(
            Configuration configuration,
            ResourceID resourceId,
            Executor ioExecutor,
            RpcService rpcService,
            HighAvailabilityServices highAvailabilityServices,
            BlobServer blobServer,
            HeartbeatServices heartbeatServices,
            DelegationTokenManager delegationTokenManager,
            MetricRegistry metricRegistry,
            ExecutionGraphInfoStore executionGraphInfoStore,
            MetricQueryServiceRetriever metricQueryServiceRetriever,
            Collection<FailureEnricher> failureEnrichers,
            FatalErrorHandler fatalErrorHandler)
            throws Exception {
        //resourcemanager的选举服务
        LeaderRetrievalService resourceManagerRetrievalService = null;
        ResourceManagerService resourceManagerService = null;

        try {
            //resourceManager leader 获取服务
            resourceManagerRetrievalService =
                    highAvailabilityServices.getResourceManagerLeaderRetriever();
            //LeaderGatewayRetriever实现了LeaderRetrievalListener接口
            final LeaderGatewayRetriever<ResourceManagerGateway> resourceManagerGatewayRetriever =
                    new RpcGatewayRetriever<>(
                            rpcService,
                            ResourceManagerGateway.class,
                            ResourceManagerId::fromUuid,
                            new ExponentialBackoffRetryStrategy(
                                    12, Duration.ofMillis(10), Duration.ofMillis(50)));

            
            resourceManagerService =
                    ResourceManagerServiceImpl.create(
                            resourceManagerFactory,
                            configuration,
                            resourceId,
                            rpcService,
                            highAvailabilityServices,
                            heartbeatServices,
                            delegationTokenManager,
                            fatalErrorHandler,
                            new ClusterInformation(hostname, blobServer.getPort()),
                            webMonitorEndpoint.getRestBaseUrl(),
                            metricRegistry,
                            hostname,
                            ioExecutor);

            //启动resourceManagerService start方法会调用具体的选举方法
            resourceManagerService.start();
            //启动etrievalService服务的start方法，
            resourceManagerRetrievalService.start(resourceManagerGatewayRetriever);

            return new DispatcherResourceManagerComponent(
                    dispatcherRunner,