ElasticSearch源码分析一 es启动
最近没什么事，就翻了翻es的源码，之前看过lucene的也简单看过solr的，给我最大的感受就是，写这些项目的人真是相当棒的，看人家的代码学到很多东西，es启动过程特别繁杂，所以就直接贴代码了，在代码里注释
es启动入口在booststrap包下elasticsearch.java,首先是添加了一个钩子作用是这里就只是一个打印而已后面还有一个狗子方法作用是 ： 程序正常退出 使用System.exit() 终端使用Ctrl+C触发的中断 系统关闭 OutOfMemory宕机 使用Kill pid命令干掉进程（注：在使用kill -9 pid时，是不会被调用的）
有几个executer 没有什么好说的直接到关键部分
public static Environment prepareEnvironment(Settings input, Terminal terminal, Map<String, String> properties, Path configPath) { // just create enough settings to build the environment, to get the config dir Settings.Builder output = Settings.builder(); initializeSettings(output, input, properties); Environment environment = new Environment(output.build(), configPath);//默认环境 if (Files.exists(environment.configFile().resolve("elasticsearch.yaml"))) { throw new SettingsException("elasticsearch.yaml was deprecated in 5.5.0 and must be renamed to elasticsearch.yml"); } if (Files.exists(environment.configFile().resolve("elasticsearch.json"))) { throw new SettingsException("elasticsearch.json was deprecated in 5.5.0 and must be converted to elasticsearch.yml"); } output = Settings.builder(); // start with a fresh output Path path = environment.configFile().resolve("elasticsearch.yml");//判断是否使用用户的自定义配置文件 if (Files.exists(path)) { try { output.loadFromPath(path); } catch (IOException e) { throw new SettingsException("Failed to load settings from " + path.toString(), e); } } // re-initialize settings now that the config file has been loaded initializeSettings(output, input, properties); finalizeSettings(output, terminal); //添加用户自定义配置文件 并刷新环境 至于为什么三次初始化environment 我认为第一次为默认环境 第二次为加载用户自定义 初始化的时候会检查错误 如果没有错误会进行第三次环境加载 其中会加入日志的配置 environment = new Environment(output.build(), configPath); // we put back the path.logs so we can use it in the logging configuration file output.put(Environment.PATH_LOGS_SETTING.getKey(), environment.logsFile().toAbsolutePath().normalize().toString()); return new Environment(output.build(), configPath); }
环境生成完毕后进入init方法中间有检测lucene和es版本方法
private void setup(boolean addShutdownHook, Environment environment) throws BootstrapException { Settings settings = environment.settings(); try { spawner.spawnNativePluginControllers(environment);//设置plguin(插件)的controller } catch (IOException e) { throw new BootstrapException(e); } initializeNatives(//初始化本地配置 如是否锁定内存 是否是root用户等等 environment.tmpFile(), BootstrapSettings.MEMORY_LOCK_SETTING.get(settings), BootstrapSettings.SYSTEM_CALL_FILTER_SETTING.get(settings), BootstrapSettings.CTRLHANDLER_SETTING.get(settings)); // initialize probes before the security manager is installed initializeProbes(); if (addShutdownHook) {//当程序异常退出处理方法 程序正常退出 使用System.exit() 终端使用Ctrl+C触发的中断 系统关闭 OutOfMemory宕机 使用Kill pid命令干掉进程（注：在使用kill -9 pid时，是不会被调用的） Runtime.getRuntime().addShutdownHook(new Thread() { @Override public void run() { try { IOUtils.close(node, spawner); LoggerContext context = (LoggerContext) LogManager.getContext(false); Configurator.shutdown(context); } catch (IOException ex) { throw new ElasticsearchException("failed to stop node", ex); } } }); } try { // look for jar hell JarHell.checkJarHell(); } catch (IOException | URISyntaxException e) { throw new BootstrapException(e); } // Log ifconfig output before SecurityManager is installed IfConfig.logIfNecessary(); // install SM after natives, shutdown hooks, etc. try { Security.configure(environment, BootstrapSettings.SECURITY_FILTER_BAD_DEFAULTS_SETTING.get(settings)); } catch (IOException | NoSuchAlgorithmException e) { throw new BootstrapException(e); } node = new Node(environment) {//关键部分 @Override protected void validateNodeBeforeAcceptingRequests( final BootstrapContext context, final BoundTransportAddress boundTransportAddress, List<BootstrapCheck> checks) throws NodeValidationException { BootstrapChecks.check(context, boundTransportAddress, checks); } }; }
protected Node(final Environment environment, Collection<Class<? extends Plugin>> classpathPlugins) { final List<Closeable> resourcesToClose = new ArrayList<>(); // register everything we need to release in the case of an error boolean success = false; { // use temp logger just to say we are starting. we can't use it later on because the node name might not be set Logger logger = Loggers.getLogger(Node.class, NODE_NAME_SETTING.get(environment.settings())); logger.info("initializing ..."); } try { Settings tmpSettings = Settings.builder().put(environment.settings())//添加配置表更新当前结点类型 （node ，cluster ） .put(Client.CLIENT_TYPE_SETTING_S.getKey(), CLIENT_TYPE).build(); // create the node environment as soon as possible, to recover the node id and enable logging try { nodeEnvironment = new NodeEnvironment(tmpSettings, environment);//当前结点index的所有状态 初始化了一个FSDDirector 锁文件 等 resourcesToClose.add(nodeEnvironment); } catch (IOException ex) { throw new IllegalStateException("Failed to create node environment", ex); } final boolean hadPredefinedNodeName = NODE_NAME_SETTING.exists(tmpSettings);//检查节点名称是否已经存在 Logger logger = Loggers.getLogger(Node.class, tmpSettings); final String nodeId = nodeEnvironment.nodeId(); tmpSettings = addNodeNameIfNeeded(tmpSettings, nodeId);//判断是否已经存在当前nodeId 如果存在直接返回当前setting 否则新实例化一个Setting // this must be captured after the node name is possibly added to the settings final String nodeName = NODE_NAME_SETTING.get(tmpSettings); if (hadPredefinedNodeName == false) { logger.info("node name [{}] derived from node ID [{}]; set [{}] to override", nodeName, nodeId, NODE_NAME_SETTING.getKey()); } else { logger.info("node name [{}], node ID [{}]", nodeName, nodeId); } final JvmInfo jvmInfo = JvmInfo.jvmInfo(); logger.info( "version[{}], pid[{}], build[{}/{}], OS[{}/{}/{}], JVM[{}/{}/{}/{}]", Version.displayVersion(Version.CURRENT, Build.CURRENT.isSnapshot()), jvmInfo.pid(), Build.CURRENT.shortHash(), Build.CURRENT.date(), Constants.OS_NAME, Constants.OS_VERSION, Constants.OS_ARCH, Constants.JVM_VENDOR, Constants.JVM_NAME, Constants.JAVA_VERSION, Constants.JVM_VERSION); logger.info("JVM arguments {}", Arrays.toString(jvmInfo.getInputArguments())); warnIfPreRelease(Version.CURRENT, Build.CURRENT.isSnapshot(), logger); if (logger.isDebugEnabled()) { logger.debug("using config [{}], data [{}], logs [{}], plugins [{}]", environment.configFile(), Arrays.toString(environment.dataFiles()), environment.logsFile(), environment.pluginsFile()); } this.pluginsService = new PluginsService(tmpSettings, environment.configFile(), environment.modulesFile(), environment.pluginsFile(), classpathPlugins);//实例化插件服务 this.settings = pluginsService.updatedSettings(); localNodeFactory = new LocalNodeFactory(settings, nodeEnvironment.nodeId()); // create the environment based on the finalized (processed) view of the settings // this is just to makes sure that people get the same settings, no matter where they ask them from this.environment = new Environment(this.settings, environment.configFile()); Environment.assertEquivalent(environment, this.environment);//判断是否旧环境已经存在新的环境的配置 final List<ExecutorBuilder<?>> executorBuilders = pluginsService.getExecutorBuilders(settings);//初始化一个空的executorBuilders 其实就是执行器集合 final ThreadPool threadPool = new ThreadPool(settings, executorBuilders.toArray(new ExecutorBuilder[0]));//线程池 resourcesToClose.add(() -> ThreadPool.terminate(threadPool, 10, TimeUnit.SECONDS)); // adds the context to the DeprecationLogger so that it does not need to be injected everywhere DeprecationLogger.setThreadContext(threadPool.getThreadContext()); resourcesToClose.add(() -> DeprecationLogger.removeThreadContext(threadPool.getThreadContext())); final List<Setting<?>> additionalSettings = new ArrayList<>(pluginsService.getPluginSettings()); final List<String> additionalSettingsFilter = new ArrayList<>(pluginsService.getPluginSettingsFilter()); for (final ExecutorBuilder<?> builder : threadPool.builders()) { additionalSettings.addAll(builder.getRegisteredSettings()); } client = new NodeClient(settings, threadPool); final ResourceWatcherService resourceWatcherService = new ResourceWatcherService(settings, threadPool);//分为三种模式 高中低 ，大概是隔一段时间去检测一下plugin防止与其他观察者plugin冲突 The setting names for configuring the resource watcher have been renamed to prevent clashes with the watcher plugin final ScriptModule scriptModule = new ScriptModule(settings, pluginsService.filterPlugins(ScriptPlugin.class)); AnalysisModule analysisModule = new AnalysisModule(this.environment, pluginsService.filterPlugins(AnalysisPlugin.class)); // this is as early as we can validate settings at this point. we already pass them to ScriptModule as well as ThreadPool // so we might be late here already final SettingsModule settingsModule = new SettingsModule(this.settings, additionalSettings, additionalSettingsFilter);//所有配置文件信息模块 scriptModule.registerClusterSettingsListeners(settingsModule.getClusterSettings()); resourcesToClose.add(resourceWatcherService); final NetworkService networkService = new NetworkService( getCustomNameResolvers(pluginsService.filterPlugins(DiscoveryPlugin.class))); List<ClusterPlugin> clusterPlugins = pluginsService.filterPlugins(ClusterPlugin.class); final ClusterService clusterService = new ClusterService(settings, settingsModule.getClusterSettings(), threadPool, ClusterModule.getClusterStateCustomSuppliers(clusterPlugins)); clusterService.addListener(scriptModule.getScriptService()); resourcesToClose.add(clusterService); final IngestService ingestService = new IngestService(settings, threadPool, this.environment, scriptModule.getScriptService(), analysisModule.getAnalysisRegistry(), pluginsService.filterPlugins(IngestPlugin.class)); final DiskThresholdMonitor listener = new DiskThresholdMonitor(settings, clusterService::state, clusterService.getClusterSettings(), client);//磁盘监控 里面包括相关的磁盘监控 final ClusterInfoService clusterInfoService = newClusterInfoService(settings, clusterService, threadPool, client, listener::onNewInfo); final UsageService usageService = new UsageService(settings); ModulesBuilder modules = new ModulesBuilder(); // plugin modules must be added here, before others or we can get crazy injection errors... for (Module pluginModule : pluginsService.createGuiceModules()) { modules.add(pluginModule); } final MonitorService monitorService = new MonitorService(settings, nodeEnvironment, threadPool, clusterInfoService);//监控组建 包括jvm gc cache 等 ClusterModule clusterModule = new ClusterModule(settings, clusterService, clusterPlugins, clusterInfoService);//cluster 模块 modules.add(clusterModule); IndicesModule indicesModule = new IndicesModule(pluginsService.filterPlugins(MapperPlugin.class));//index 模块 modules.add(indicesModule); SearchModule searchModule = new SearchModule(settings, false, pluginsService.filterPlugins(SearchPlugin.class));//查询组建 包括 sort 高亮 queryarse sortFunction fatch 等 CircuitBreakerService circuitBreakerService = createCircuitBreakerService(settingsModule.getSettings(), settingsModule.getClusterSettings());//断路器 不知道干啥的 估计是超过限制之后 宕掉？or 抛异常 ？ resourcesToClose.add(circuitBreakerService); ActionModule actionModule = new ActionModule(false, settings, clusterModule.getIndexNameExpressionResolver(), settingsModule.getIndexScopedSettings(), settingsModule.getClusterSettings(), settingsModule.getSettingsFilter(), threadPool, pluginsService.filterPlugins(ActionPlugin.class), client, circuitBreakerService, usageService);//很明显了 就是action了 查询 删除 更新 等等action modules.add(actionModule); modules.add(new GatewayModule());//路由模块 BigArrays bigArrays = createBigArrays(settings, circuitBreakerService);//不知道这是干啥用的 以后研究 resourcesToClose.add(bigArrays); modules.add(settingsModule); List<NamedWriteableRegistry.Entry> namedWriteables = Stream.of( NetworkModule.getNamedWriteables().stream(), indicesModule.getNamedWriteables().stream(), searchModule.getNamedWriteables().stream(), pluginsService.filterPlugins(Plugin.class).stream() .flatMap(p -> p.getNamedWriteables().stream()), ClusterModule.getNamedWriteables().stream()) .flatMap(Function.identity()).collect(Collectors.toList()); final NamedWriteableRegistry namedWriteableRegistry = new NamedWriteableRegistry(namedWriteables);//感觉像是所有操作方法对应的class NamedXContentRegistry xContentRegistry = new NamedXContentRegistry(Stream.of(//感觉和上一行代码操作差不多 具体是干什么的不知道 以后研究 NetworkModule.getNamedXContents().stream(), searchModule.getNamedXContents().stream(), pluginsService.filterPlugins(Plugin.class).stream() .flatMap(p -> p.getNamedXContent().stream()), ClusterModule.getNamedXWriteables().stream()) .flatMap(Function.identity()).collect(toList())); modules.add(new RepositoriesModule(this.environment, pluginsService.filterPlugins(RepositoryPlugin.class), xContentRegistry)); final MetaStateService metaStateService = new MetaStateService(settings, nodeEnvironment, xContentRegistry); final IndicesService indicesService = new IndicesService(settings, pluginsService, nodeEnvironment, xContentRegistry,//索引组件服务 通过api中client.indices()调用 里面包括所有的索引操作方法以及索引状态 analysisModule.getAnalysisRegistry(), clusterModule.getIndexNameExpressionResolver(), indicesModule.getMapperRegistry(), namedWriteableRegistry, threadPool, settingsModule.getIndexScopedSettings(), circuitBreakerService, bigArrays, scriptModule.getScriptService(), client, metaStateService); Collection<Object> pluginComponents = pluginsService.filterPlugins(Plugin.class).stream() .flatMap(p -> p.createComponents(client, clusterService, threadPool, resourceWatcherService, scriptModule.getScriptService(), xContentRegistry, environment, nodeEnvironment, namedWriteableRegistry).stream()) .collect(Collectors.toList()); final RestController restController = actionModule.getRestController(); final NetworkModule networkModule = new NetworkModule(settings, false, pluginsService.filterPlugins(NetworkPlugin.class), threadPool, bigArrays, circuitBreakerService, namedWriteableRegistry, xContentRegistry, networkService, restController);//网络服务组建 用的是netty 把setting threadpool 要使用restCOntroller等 Collection<UnaryOperator<Map<String, MetaData.Custom>>> customMetaDataUpgraders = pluginsService.filterPlugins(Plugin.class).stream() .map(Plugin::getCustomMetaDataUpgrader) .collect(Collectors.toList()); Collection<UnaryOperator<Map<String, IndexTemplateMetaData>>> indexTemplateMetaDataUpgraders = pluginsService.filterPlugins(Plugin.class).stream() .map(Plugin::getIndexTemplateMetaDataUpgrader) .collect(Collectors.toList()); Collection<UnaryOperator<IndexMetaData>> indexMetaDataUpgraders = pluginsService.filterPlugins(Plugin.class).stream() .map(Plugin::getIndexMetaDataUpgrader).collect(Collectors.toList()); final MetaDataUpgrader metaDataUpgrader = new MetaDataUpgrader(customMetaDataUpgraders, indexTemplateMetaDataUpgraders);//不知道做什么用的 看内容像是数据升级之后的操作 new TemplateUpgradeService(settings, client, clusterService, threadPool, indexTemplateMetaDataUpgraders); final Transport transport = networkModule.getTransportSupplier().get();//从之前的net模块中获取transport 本意为运输不太好翻译 但应该都明白这是什么 获取客户端用的就是 TransportClient final TransportService transportService = newTransportService(settings, transport, threadPool, networkModule.getTransportInterceptor(), localNodeFactory, settingsModule.getClusterSettings());//创建transport服务 final ResponseCollectorService responseCollectorService = new ResponseCollectorService(this.settings, clusterService);//看名字就应该知道是什么 final SearchTransportService searchTransportService = new SearchTransportService(settings, transportService, SearchExecutionStatsCollector.makeWrapper(responseCollectorService));//通过上面的transportService给search提供一个入口 final Consumer<Binder> httpBind; final HttpServerTransport httpServerTransport; if (networkModule.isHttpEnabled()) {//网络组建可有的话 绑定ip和端口 httpServerTransport = networkModule.getHttpServerTransportSupplier().get(); httpBind = b -> { b.bind(HttpServerTransport.class).toInstance(httpServerTransport); }; } else { httpBind = b -> { b.bind(HttpServerTransport.class).toProvider(Providers.of(null)); }; httpServerTransport = null; } final DiscoveryModule discoveryModule = new DiscoveryModule(this.settings, threadPool, transportService, namedWriteableRegistry,//发现模块 使用的是ZenDiscovery networkService, clusterService.getMasterService(), clusterService.getClusterApplierService(), clusterService.getClusterSettings(), pluginsService.filterPlugins(DiscoveryPlugin.class), clusterModule.getAllocationService()); this.nodeService = new NodeService(settings, threadPool, monitorService, discoveryModule.getDiscovery(), transportService, indicesService, pluginsService, circuitBreakerService, scriptModule.getScriptService(), httpServerTransport, ingestService, clusterService, settingsModule.getSettingsFilter()); modules.add(b -> { b.bind(Node.class).toInstance(this); b.bind(NodeService.class).toInstance(nodeService); b.bind(NamedXContentRegistry.class).toInstance(xContentRegistry); b.bind(PluginsService.class).toInstance(pluginsService); b.bind(Client.class).toInstance(client); b.bind(NodeClient.class).toInstance(client); b.bind(Environment.class).toInstance(this.environment); b.bind(ThreadPool.class).toInstance(threadPool); b.bind(NodeEnvironment.class).toInstance(nodeEnvironment); b.bind(ResourceWatcherService.class).toInstance(resourceWatcherService); b.bind(CircuitBreakerService.class).toInstance(circuitBreakerService); b.bind(BigArrays.class).toInstance(bigArrays); b.bind(ScriptService.class).toInstance(scriptModule.getScriptService()); b.bind(AnalysisRegistry.class).toInstance(analysisModule.getAnalysisRegistry()); b.bind(IngestService.class).toInstance(ingestService); b.bind(UsageService.class).toInstance(usageService); b.bind(NamedWriteableRegistry.class).toInstance(namedWriteableRegistry); b.bind(MetaDataUpgrader.class).toInstance(metaDataUpgrader); b.bind(MetaStateService.class).toInstance(metaStateService); b.bind(IndicesService.class).toInstance(indicesService); b.bind(SearchService.class).toInstance(newSearchService(clusterService, indicesService, threadPool, scriptModule.getScriptService(), bigArrays, searchModule.getFetchPhase(), responseCollectorService)); b.bind(SearchTransportService.class).toInstance(searchTransportService); b.bind(SearchPhaseController.class).toInstance(new SearchPhaseController(settings, bigArrays, scriptModule.getScriptService())); b.bind(Transport.class).toInstance(transport); b.bind(TransportService.class).toInstance(transportService); b.bind(NetworkService.class).toInstance(networkService); b.bind(UpdateHelper.class).toInstance(new UpdateHelper(settings, scriptModule.getScriptService())); b.bind(MetaDataIndexUpgradeService.class).toInstance(new MetaDataIndexUpgradeService(settings, xContentRegistry, indicesModule.getMapperRegistry(), settingsModule.getIndexScopedSettings(), indexMetaDataUpgraders)); b.bind(ClusterInfoService.class).toInstance(clusterInfoService); b.bind(Discovery.class).toInstance(discoveryModule.getDiscovery()); { RecoverySettings recoverySettings = new RecoverySettings(settings, settingsModule.getClusterSettings()); processRecoverySettings(settingsModule.getClusterSettings(), recoverySettings); b.bind(PeerRecoverySourceService.class).toInstance(new PeerRecoverySourceService(settings, transportService, indicesService, recoverySettings)); b.bind(PeerRecoveryTargetService.class).toInstance(new PeerRecoveryTargetService(settings, threadPool, transportService, recoverySettings, clusterService)); } httpBind.accept(b); pluginComponents.stream().forEach(p -> b.bind((Class) p.getClass()).toInstance(p)); } );//绑定事件 injector = modules.createInjector(); // TODO hack around circular dependencies problems in AllocationService clusterModule.getAllocationService().setGatewayAllocator(injector.getInstance(GatewayAllocator.class)); List<LifecycleComponent> pluginLifecycleComponents = pluginComponents.stream() .filter(p -> p instanceof LifecycleComponent)//节点的状态组件集合 .map(p -> (LifecycleComponent) p).collect(Collectors.toList()); pluginLifecycleComponents.addAll(pluginsService.getGuiceServiceClasses().stream() .map(injector::getInstance).collect(Collectors.toList())); resourcesToClose.addAll(pluginLifecycleComponents); this.pluginLifecycleComponents = Collections.unmodifiableList(pluginLifecycleComponents); client.initialize(injector.getInstance(new Key<Map<GenericAction, TransportAction>>() {}), () -> clusterService.localNode().getId()); if (NetworkModule.HTTP_ENABLED.get(settings)) { logger.debug("initializing HTTP handlers ..."); actionModule.initRestHandlers(() -> clusterService.state().nodes());//这里设置都可以接受那些action } logger.info("initialized"); success = true;//初始化完成 接下来是 调用start来启动node中的组件 } catch (IOException ex) { throw new ElasticsearchException("failed to bind service", ex); } finally { if (!success) { IOUtils.closeWhileHandlingException(resourcesToClose); } } }
public Node start() throws NodeValidationException { if (!lifecycle.moveToStarted()) { return this; } //感觉人家的代码相当的巧妙 Logger logger = Loggers.getLogger(Node.class, NODE_NAME_SETTING.get(settings)); logger.info("starting ..."); pluginLifecycleComponents.forEach(LifecycleComponent::start);//启用所有的模块组件 相当巧妙 所有的模块实现LifecycleComponent然后重写start方法 一行代码 启动所有组件 //获取每一个服务然后启动 dostart 启动过程中会更新state状态 injector.getInstance(MappingUpdatedAction.class).setClient(client); injector.getInstance(IndicesService.class).start(); injector.getInstance(IndicesClusterStateService.class).start(); injector.getInstance(SnapshotsService.class).start(); injector.getInstance(SnapshotShardsService.class).start(); injector.getInstance(RoutingService.class).start(); injector.getInstance(SearchService.class).start(); nodeService.getMonitorService().start(); final ClusterService clusterService = injector.getInstance(ClusterService.class); final NodeConnectionsService nodeConnectionsService = injector.getInstance(NodeConnectionsService.class);//节点链接服务 nodeConnectionsService.start(); clusterService.setNodeConnectionsService(nodeConnectionsService); injector.getInstance(ResourceWatcherService.class).start(); injector.getInstance(GatewayService.class).start(); Discovery discovery = injector.getInstance(Discovery.class); clusterService.getMasterService().setClusterStatePublisher(discovery::publish); // Start the transport service now so the publish address will be added to the local disco node in ClusterService TransportService transportService = injector.getInstance(TransportService.class); transportService.getTaskManager().setTaskResultsService(injector.getInstance(TaskResultsService.class)); transportService.start(); assert localNodeFactory.getNode() != null; assert transportService.getLocalNode().equals(localNodeFactory.getNode()) : "transportService has a different local node than the factory provided"; final MetaData onDiskMetadata; try { // we load the global state here (the persistent part of the cluster state stored on disk) to // pass it to the bootstrap checks to allow plugins to enforce certain preconditions based on the recovered state. if (DiscoveryNode.isMasterNode(settings) || DiscoveryNode.isDataNode(settings)) {//判断节点类型 来更新节点信息 onDiskMetadata = injector.getInstance(GatewayMetaState.class).loadMetaState(); } else { onDiskMetadata = MetaData.EMPTY_META_DATA; } assert onDiskMetadata != null : "metadata is null but shouldn't"; // this is never null } catch (IOException e) { throw new UncheckedIOException(e); } validateNodeBeforeAcceptingRequests(new BootstrapContext(settings, onDiskMetadata), transportService.boundAddress(), pluginsService//节点检查 包括 ClientJvmCheck,UseSerialGCCheck,SystemCallFilterCheck, OnErrorCheck,OnOutOfMemoryErrorCheck, EarlyAccessCheck, G1GCCheck()); .filterPlugins(Plugin .class) .stream() .flatMap(p -> p.getBootstrapChecks().stream()).collect(Collectors.toList())); clusterService.addStateApplier(transportService.getTaskManager()); // start after transport service so the local disco is known discovery.start(); // start before cluster service so that it can set initial state on ClusterApplierService clusterService.start();//集群服务启动 assert clusterService.localNode().equals(localNodeFactory.getNode()) : "clusterService has a different local node than the factory provided"; transportService.acceptIncomingRequests(); discovery.startInitialJoin();// 这个感觉是比较有深度的 知道是节点发现加入模块但刚跟进去就绕晕了 // tribe nodes don't have a master so we shouldn't register an observer s final TimeValue initialStateTimeout = DiscoverySettings.INITIAL_STATE_TIMEOUT_SETTING.get(settings); if (initialStateTimeout.millis() > 0) { final ThreadPool thread = injector.getInstance(ThreadPool.class); ClusterState clusterState = clusterService.state(); ClusterStateObserver observer = new ClusterStateObserver(clusterState, clusterService, null, logger, thread.getThreadContext());//发现模块初始化超时时间 if (clusterState.nodes().getMasterNodeId() == null) { logger.debug("waiting to join the cluster. timeout [{}]", initialStateTimeout); final CountDownLatch latch = new CountDownLatch(1); observer.waitForNextChange(new ClusterStateObserver.Listener() { @Override public void onNewClusterState(ClusterState state) { latch.countDown(); } @Override public void onClusterServiceClose() { latch.countDown(); } @Override public void onTimeout(TimeValue timeout) { logger.warn("timed out while waiting for initial discovery state - timeout: {}", initialStateTimeout); latch.countDown(); } }, state -> state.nodes().getMasterNodeId() != null, initialStateTimeout); try { latch.await();//等待新节点连接 超时时间为30s } catch (InterruptedException e) { throw new ElasticsearchTimeoutException("Interrupted while waiting for initial discovery state"); } } } if (NetworkModule.HTTP_ENABLED.get(settings)) { injector.getInstance(HttpServerTransport.class).start(); } if (WRITE_PORTS_FILE_SETTING.get(settings)) { if (NetworkModule.HTTP_ENABLED.get(settings)) { HttpServerTransport http = injector.getInstance(HttpServerTransport.class); writePortsFile("http", http.boundAddress()); } TransportService transport = injector.getInstance(TransportService.class); writePortsFile("transport", transport.boundAddress()); } logger.info("started"); pluginsService.filterPlugins(ClusterPlugin.class).forEach(ClusterPlugin::onNodeStarted);//filter 启动 return this; }
至此es节点就启动完成
总结起来启动一共分为三个步骤
1、启动环境的检查配置
2、Node的检查初始化以及服务组件的检查初始化
3、Node节点相关服务、监控启动
