अपाचे सीटनल ज़ीटा इंजन का स्रोत कोड विश्लेषण (भाग 3): सर्वर-साइड कार्य सबमिशन

यह अपाचे सीटनल ज़ीटा इंजन स्रोत कोड का विश्लेषण करने के लिए श्रृंखला लेखों का अंतिम भाग है; पूरी जानकारी प्राप्त करने के लिए पिछली श्रृंखला की समीक्षा करें: अपाचे सीटनल ज़ीटा इंजन का स्रोत कोड विश्लेषण (भाग 1): सर्वर आरंभीकरण अपाचे सीटनल ज़ीटा इंजन का स्रोत कोड विश्लेषण (भाग 2): क्लाइंट साइड पर कार्य प्रस्तुतीकरण प्रक्रिया आइए उन घटकों की समीक्षा करें जो सर्वर शुरू होने के बाद निष्पादित होते हैं: : केवल मास्टर/स्टैंडबाय नोड्स पर सक्षम, क्लस्टर स्थिति को सुनता है, और मास्टर-स्टैंडबाय फेलओवर को संभालता है। समन्वयक सेवा : कार्यकर्ता नोड्स पर सक्षम, समय-समय पर मास्टर को अपनी स्थिति की रिपोर्ट करता है। स्लॉट सर्विस : कार्यकर्ता नोड्स पर सक्षम, समय-समय पर कार्य मेट्रिक्स को IMAP में अद्यतन करता है। TaskExecutionService जब क्लस्टर को कोई कार्य प्राप्त नहीं होता है, तो ये घटक चलते हैं। हालाँकि, जब कोई क्लाइंट सर्वर को संदेश भेजता है, तो सर्वर इसे कैसे संभालता है? SeaTunnelSubmitJobCodec संदेश प्राप्ति चूंकि क्लाइंट और सर्वर अलग-अलग मशीनों पर हैं, इसलिए विधि कॉल का उपयोग नहीं किया जा सकता है; इसके बजाय, संदेश पासिंग का उपयोग किया जाता है। संदेश प्राप्त होने पर, सर्वर इसे कैसे संसाधित करता है? सबसे पहले, क्लाइंट प्रकार का एक संदेश भेजता है: SeaTunnelSubmitJobCodec // Client code ClientMessage request = SeaTunnelSubmitJobCodec.encodeRequest( jobImmutableInformation.getJobId(), seaTunnelHazelcastClient .getSerializationService() .toData(jobImmutableInformation), jobImmutableInformation.isStartWithSavePoint()); PassiveCompletableFuture submitJobFuture = seaTunnelHazelcastClient.requestOnMasterAndGetCompletableFuture(request); क्लास में, यह क्लास से जुड़ा हुआ है, जो मैसेज टाइप को क्लास में मैप करता है। के लिए, यह क्लास में मैप करता है: SeaTunnelSubmitJobCodec SeaTunnelMessageTaskFactoryProvider MessageTask SeaTunnelSubmitJobCodec SubmitJobTask private final Int2ObjectHashMap factories = new Int2ObjectHashMap<>(60); private void initFactories() { factories.put( SeaTunnelPrintMessageCodec.REQUEST_MESSAGE_TYPE, (clientMessage, connection) -> new PrintMessageTask(clientMessage, node, connection)); factories.put( SeaTunnelSubmitJobCodec.REQUEST_MESSAGE_TYPE, (clientMessage, connection) -> new SubmitJobTask(clientMessage, node, connection)); ..... } वर्ग की जांच करते समय, यह वर्ग को आमंत्रित करता है: SubmitJobTask SubmitJobOperation @Override protected Operation prepareOperation() { return new SubmitJobOperation( parameters.jobId, parameters.jobImmutableInformation, parameters.isStartWithSavePoint); } वर्ग में, कार्य जानकारी को उसके विधि के माध्यम से घटक को सौंप दिया जाता है: SubmitJobOperation submitJob CoordinatorService @Override protected PassiveCompletableFuture doRun() throws Exception { SeaTunnelServer seaTunnelServer = getService(); return seaTunnelServer .getCoordinatorService() .submitJob(jobId, jobImmutableInformation, isStartWithSavePoint); } इस बिंदु पर, क्लाइंट संदेश प्रभावी रूप से विधि आह्वान के लिए सर्वर को सौंप दिया जाता है। अन्य प्रकार के संचालनों का पता इसी तरह लगाया जा सकता है। समन्वयकसेवा आगे, आइए देखें कि नौकरी प्रस्तुतियों को कैसे संभालता है: CoordinatorService public PassiveCompletableFuture submitJob( long jobId, Data jobImmutableInformation, boolean isStartWithSavePoint) { CompletableFuture jobSubmitFuture = new CompletableFuture<>(); // First, check if a job with the same ID already exists if (getJobMaster(jobId) != null) { logger.warning( String.format( "The job %s is currently running; no need to submit again.", jobId)); jobSubmitFuture.complete(null); return new PassiveCompletableFuture<>(jobSubmitFuture); } // Initialize JobMaster object JobMaster jobMaster = new JobMaster( jobImmutableInformation, this.nodeEngine, executorService, getResourceManager(), getJobHistoryService(), runningJobStateIMap, runningJobStateTimestampsIMap, ownedSlotProfilesIMap, runningJobInfoIMap, metricsImap, engineConfig, seaTunnelServer); executorService.submit( () -> { try { // Ensure no duplicate tasks with the same ID if (!isStartWithSavePoint && getJobHistoryService().getJobMetrics(jobId) != null) { throw new JobException( String.format( "The job id %s has already been submitted and is not starting with a savepoint.", jobId)); } // Add task info to IMAP runningJobInfoIMap.put( jobId, new JobInfo(System.currentTimeMillis(), jobImmutableInformation)); runningJobMasterMap.put(jobId, jobMaster); // Initialize JobMaster jobMaster.init( runningJobInfoIMap.get(jobId).getInitializationTimestamp(), false); // Task creation successful jobSubmitFuture.complete(null); } catch (Throwable e) { String errorMsg = ExceptionUtils.getMessage(e); logger.severe(String.format("submit job %s error %s ", jobId, errorMsg)); jobSubmitFuture.completeExceptionally(new JobException(errorMsg)); } if (!jobSubmitFuture.isCompletedExceptionally()) { // Start job execution try { jobMaster.run(); } finally { // Remove jobMaster from map if not cancelled if (!jobMaster.getJobMasterCompleteFuture().isCancelled()) { runningJobMasterMap.remove(jobId); } } } else { runningJobInfoIMap.remove(jobId); runningJobMasterMap.remove(jobId); } }); return new PassiveCompletableFuture<>(jobSubmitFuture); } सर्वर में, व्यक्तिगत कार्य को प्रबंधित करने के लिए एक ऑब्जेक्ट बनाया जाता है। निर्माण के दौरान, यह के माध्यम से संसाधन प्रबंधक और के माध्यम से नौकरी इतिहास की जानकारी प्राप्त करता है। स्टार्टअप पर आरंभ किया जाता है, जबकि पहले कार्य सबमिशन पर आलसी तरीके से लोड किया जाता है: JobMaster JobMaster getResourceManager() getJobHistoryService() jobHistoryService ResourceManager /** Lazy load for resource manager */ public ResourceManager getResourceManager() { if (resourceManager == null) { synchronized (this) { if (resourceManager == null) { ResourceManager manager = new ResourceManagerFactory(nodeEngine, engineConfig) .getResourceManager(); manager.init(); resourceManager = manager; } } } return resourceManager; } संसाधन प्रबंधक वर्तमान में, SeaTunnel केवल स्टैंडअलोन परिनियोजन का समर्थन करता है। को आरंभ करते समय, यह सभी क्लस्टर नोड्स को इकट्ठा करता है और नोड जानकारी प्राप्त करने के लिए एक भेजता है, आंतरिक स्थिति को अपडेट करता है: ResourceManager SyncWorkerProfileOperation registerWorker @Override public void init() { log.info("Init ResourceManager"); initWorker(); } private void initWorker() { log.info("initWorker... "); List aliveNode = nodeEngine.getClusterService().getMembers().stream() .map(Member::getAddress) .collect(Collectors.toList()); log.info("init live nodes: {}", aliveNode); List > futures = aliveNode.stream() .map( node -> sendToMember(new SyncWorkerProfileOperation(), node) .thenAccept( p -> { if (p != null) { registerWorker.put( node, (WorkerProfile) p); log.info( "received new worker register: " + ((WorkerProfile) p) .getAddress()); } })) .collect(Collectors.toList()); futures.forEach(CompletableFuture::join); log.info("registerWorker: {}", registerWorker); } पहले, हमने देखा कि समय-समय पर प्रत्येक नोड से मास्टर को हार्टबीट संदेश भेजता है। इन हार्टबीट को प्राप्त करने पर, अपनी आंतरिक स्थिति में नोड की स्थिति को अपडेट करता है। SlotService ResourceManager @Override public void heartbeat(WorkerProfile workerProfile) { if (!registerWorker.containsKey(workerProfile.getAddress())) { log.info("received new worker register: " + workerProfile.getAddress()); sendToMember(new ResetResourceOperation(), workerProfile.getAddress()).join(); } else { log.debug("received worker heartbeat from: " + workerProfile.getAddress()); } registerWorker.put(workerProfile.getAddress(), workerProfile); } जॉबमास्टर में, एक इंस्टेंस बनाया जाता है और इसकी विधि को कॉल किया जाता है। जब विधि पूरी हो जाती है, तो यह माना जाता है कि कार्य निर्माण सफल रहा है। फिर कार्य को औपचारिक रूप से निष्पादित करने के लिए विधि को कॉल किया जाता है। CoordinatorService JobMaster init init run आइए आरंभीकरण और विधि पर नजर डालें। init public JobMaster( @NonNull Data jobImmutableInformationData, @NonNull NodeEngine nodeEngine, @NonNull ExecutorService executorService, @NonNull ResourceManager resourceManager, @NonNull JobHistoryService jobHistoryService, @NonNull IMap runningJobStateIMap, @NonNull IMap runningJobStateTimestampsIMap, @NonNull IMap ownedSlotProfilesIMap, @NonNull IMap runningJobInfoIMap, @NonNull IMap > metricsImap, EngineConfig engineConfig, SeaTunnelServer seaTunnelServer) { this.jobImmutableInformationData = jobImmutableInformationData; this.nodeEngine = nodeEngine; this.executorService = executorService; flakeIdGenerator = this.nodeEngine .getHazelcastInstance() .getFlakeIdGenerator(Constant.SEATUNNEL_ID_GENERATOR_NAME); this.ownedSlotProfilesIMap = ownedSlotProfilesIMap; this.resourceManager = resourceManager; this.jobHistoryService = jobHistoryService; this.runningJobStateIMap = runningJobStateIMap; this.runningJobStateTimestampsIMap = runningJobStateTimestampsIMap; this.runningJobInfoIMap = runningJobInfoIMap; this.engineConfig = engineConfig; this.metricsImap = metricsImap; this.seaTunnelServer = seaTunnelServer; this.releasedSlotWhenTaskGroupFinished = new ConcurrentHashMap<>(); } आरंभीकरण के दौरान, बिना किसी महत्वपूर्ण ऑपरेशन के केवल सरल चर असाइनमेंट निष्पादित किए जाते हैं। हमें विधि पर ध्यान केंद्रित करने की आवश्यकता है। init public synchronized void init(long initializationTimestamp, boolean restart) throws Exception { // The server receives a binary object from the client, // which is first converted to a JobImmutableInformation object, the same object sent by the client jobImmutableInformation = nodeEngine.getSerializationService().toObject(jobImmutableInformationData); // Get the checkpoint configuration, such as the interval, timeout, etc. jobCheckpointConfig = createJobCheckpointConfig( engineConfig.getCheckpointConfig(), jobImmutableInformation.getJobConfig()); LOGGER.info( String.format( "Init JobMaster for Job %s (%s) ", jobImmutableInformation.getJobConfig().getName(), jobImmutableInformation.getJobId())); LOGGER.info( String.format( "Job %s (%s) needed jar urls %s", jobImmutableInformation.getJobConfig().getName(), jobImmutableInformation.getJobId(), jobImmutableInformation.getPluginJarsUrls())); ClassLoader appClassLoader = Thread.currentThread().getContextClassLoader(); // Get the ClassLoader ClassLoader classLoader = seaTunnelServer .getClassLoaderService() .getClassLoader( jobImmutableInformation.getJobId(), jobImmutableInformation.getPluginJarsUrls()); // Deserialize the logical DAG from the client-provided information logicalDag = CustomClassLoadedObject.deserializeWithCustomClassLoader( nodeEngine.getSerializationService(), classLoader, jobImmutableInformation.getLogicalDag()); try { Thread.currentThread().setContextClassLoader(classLoader); // Execute save mode functionality, such as table creation and deletion if (!restart && !logicalDag.isStartWithSavePoint() && ReadonlyConfig.fromMap(logicalDag.getJobConfig().getEnvOptions()) .get(EnvCommonOptions.SAVEMODE_EXECUTE_LOCATION) .equals(SaveModeExecuteLocation.CLUSTER)) { logicalDag.getLogicalVertexMap().values().stream() .map(LogicalVertex::getAction) .filter(action -> action instanceof SinkAction) .map(sink -> ((SinkAction ) sink).getSink()) .forEach(JobMaster::handleSaveMode); } // Parse the logical plan into a physical plan final Tuple2 > planTuple = PlanUtils.fromLogicalDAG( logicalDag, nodeEngine, jobImmutableInformation, initializationTimestamp, executorService, flakeIdGenerator, runningJobStateIMap, runningJobStateTimestampsIMap, engineConfig.getQueueType(), engineConfig); this.physicalPlan = planTuple.f0(); this.physicalPlan.setJobMaster(this); this.checkpointPlanMap = planTuple.f1(); } finally { // Reset the current thread's ClassLoader and release the created classLoader Thread.currentThread().setContextClassLoader(appClassLoader); seaTunnelServer .getClassLoaderService() .releaseClassLoader( jobImmutableInformation.getJobId(), jobImmutableInformation.getPluginJarsUrls()); } Exception initException = null; try { // Initialize the checkpoint manager this.initCheckPointManager(restart); } catch (Exception e) { initException = e; } // Add some callback functions for job state listening this.initStateFuture(); if (initException != null) { if (restart) { cancelJob(); } throw initException; } } अंत में, आइए विधि पर नजर डालें: run public void run() { try { physicalPlan.startJob(); } catch (Throwable e) { LOGGER.severe( String.format( "Job %s (%s) run error with: %s", physicalPlan.getJobImmutableInformation().getJobConfig().getName(), physicalPlan.getJobImmutableInformation().getJobId(), ExceptionUtils.getMessage(e))); } finally { jobMasterCompleteFuture.join(); if (engineConfig.getConnectorJarStorageConfig().getEnable()) { List pluginJarIdentifiers = jobImmutableInformation.getPluginJarIdentifiers(); seaTunnelServer .getConnectorPackageService() .cleanUpWhenJobFinished( jobImmutableInformation.getJobId(), pluginJarIdentifiers); } } } यह विधि अपेक्षाकृत सरल है, जो उत्पन्न भौतिक योजना को निष्पादित करने के लिए को कॉल करती है। physicalPlan.startJob() उपरोक्त कोड से, यह स्पष्ट है कि सर्वर द्वारा क्लाइंट कार्य सबमिशन अनुरोध प्राप्त करने के बाद, यह क्लास को प्रारंभ करता है, जो तार्किक योजना से भौतिक योजना उत्पन्न करता है, और फिर भौतिक योजना को निष्पादित करता है। JobMaster इसके बाद, हमें यह जानने की आवश्यकता है कि तार्किक योजना को भौतिक योजना में कैसे परिवर्तित किया जाता है। तार्किक योजना से भौतिक योजना में रूपांतरण भौतिक योजना का निर्माण में निम्नलिखित विधि को कॉल करके किया जाता है: JobMaster final Tuple2 > planTuple = PlanUtils.fromLogicalDAG( logicalDag, nodeEngine, jobImmutableInformation, initializationTimestamp, executorService, flakeIdGenerator, runningJobStateIMap, runningJobStateTimestampsIMap, engineConfig.getQueueType(), engineConfig); भौतिक योजना बनाने की विधि में, तार्किक योजना को पहले निष्पादन योजना में परिवर्तित किया जाता है, और फिर निष्पादन योजना को भौतिक योजना में परिवर्तित किया जाता है। public static Tuple2 > fromLogicalDAG( @NonNull LogicalDag logicalDag, @NonNull NodeEngine nodeEngine, @NonNull JobImmutableInformation jobImmutableInformation, long initializationTimestamp, @NonNull ExecutorService executorService, @NonNull FlakeIdGenerator flakeIdGenerator, @NonNull IMap runningJobStateIMap, @NonNull IMap runningJobStateTimestampsIMap, @NonNull QueueType queueType, @NonNull EngineConfig engineConfig) { return new PhysicalPlanGenerator( new ExecutionPlanGenerator( logicalDag, jobImmutableInformation, engineConfig) .generate(), nodeEngine, jobImmutableInformation, initializationTimestamp, executorService, flakeIdGenerator, runningJobStateIMap, runningJobStateTimestampsIMap, queueType) .generate(); } निष्पादन योजना का निर्माण public ExecutionPlanGenerator( @NonNull LogicalDag logicalPlan, @NonNull JobImmutableInformation jobImmutableInformation, @NonNull EngineConfig engineConfig) { checkArgument( logicalPlan.getEdges().size() > 0, "ExecutionPlan Builder must have LogicalPlan."); this.logicalPlan = logicalPlan; this.jobImmutableInformation = jobImmutableInformation; this.engineConfig = engineConfig; } public ExecutionPlan generate() { log.debug("Generate execution plan using logical plan:"); Set executionEdges = generateExecutionEdges(logicalPlan.getEdges()); log.debug("Phase 1: generate execution edge list {}", executionEdges); executionEdges = generateShuffleEdges(executionEdges); log.debug("Phase 2: generate shuffle edge list {}", executionEdges); executionEdges = generateTransformChainEdges(executionEdges); log.debug("Phase 3: generate transform chain edge list {}", executionEdges); List pipelines = generatePipelines(executionEdges); log.debug("Phase 4: generate pipeline list {}", pipelines); ExecutionPlan executionPlan = new ExecutionPlan(pipelines, jobImmutableInformation); log.debug("Phase 5 : generate execution plan {}", executionPlan); return executionPlan; } वर्ग एक तार्किक योजना लेता है और चरणों की एक श्रृंखला के माध्यम से एक निष्पादन योजना तैयार करता है, जिसमें निष्पादन किनारे, शफल किनारे, रूपांतरण श्रृंखला किनारे और अंततः पाइपलाइनों का निर्माण शामिल है। ExecutionPlanGenerator भौतिक योजना का निर्माण वर्ग निष्पादन योजना को भौतिक योजना में परिवर्तित करता है: PhysicalPlanGenerator public PhysicalPlanGenerator( @NonNull ExecutionPlan executionPlan, @NonNull NodeEngine nodeEngine, @NonNull JobImmutableInformation jobImmutableInformation, long initializationTimestamp, @NonNull ExecutorService executorService, @NonNull FlakeIdGenerator flakeIdGenerator, @NonNull IMap runningJobStateIMap, @NonNull IMap runningJobStateTimestampsIMap, @NonNull QueueType queueType) { this.executionPlan = executionPlan; this.nodeEngine = nodeEngine; this.jobImmutableInformation = jobImmutableInformation; this.initializationTimestamp = initializationTimestamp; this.executorService = executorService; this.flakeIdGenerator = flakeIdGenerator; this.runningJobStateIMap = runningJobStateIMap; this.runningJobStateTimestampsIMap = runningJobStateTimestampsIMap; this.queueType = queueType; } public PhysicalPlan generate() { List physicalVertices = generatePhysicalVertices(executionPlan); List physicalEdges = generatePhysicalEdges(executionPlan); PhysicalPlan physicalPlan = new PhysicalPlan(physicalVertices, physicalEdges); log.debug("Generate physical plan: {}", physicalPlan); return physicalPlan; } आइये इन दोनों वर्गों की विषय-वस्तु की जांच करें। public class ExecutionPlan { private final List pipelines; private final JobImmutableInformation jobImmutableInformation; } public class Pipeline { /** The ID of the pipeline. */ private final Integer id; private final List edges; private final Map vertexes; } public class ExecutionEdge { private ExecutionVertex leftVertex; private ExecutionVertex rightVertex; } public class ExecutionVertex { private Long vertexId; private Action action; private int parallelism; } आइये इसकी तुलना तार्किक योजना से करें: public class LogicalDag implements IdentifiedDataSerializable { @Getter private JobConfig jobConfig; private final Set edges = new LinkedHashSet<>(); private final Map logicalVertexMap = new LinkedHashMap<>(); private IdGenerator idGenerator; private boolean isStartWithSavePoint = false; } public class LogicalEdge implements IdentifiedDataSerializable { private LogicalVertex inputVertex; private LogicalVertex targetVertex; private Long inputVertexId; private Long targetVertexId; } public class LogicalVertex implements IdentifiedDataSerializable { private Long vertexId; private Action action; private int parallelism; } ऐसा लगता है कि प्रत्येक पाइपलाइन एक तार्किक योजना जैसा दिखता है। हमें इस परिवर्तन चरण की आवश्यकता क्यों है? आइए तार्किक योजना बनाने की प्रक्रिया पर करीब से नज़र डालें। जैसा कि ऊपर दिखाया गया है, निष्पादन योजना तैयार करने में पांच चरण शामिल हैं, जिनकी हम एक-एक करके समीक्षा करेंगे। चरण 1: तार्किक योजना को निष्पादन योजना में परिवर्तित करना // Input is a set of logical plan edges, where each edge stores upstream and downstream nodes private Set generateExecutionEdges(Set logicalEdges) { Set executionEdges = new LinkedHashSet<>(); Map logicalVertexIdToExecutionVertexMap = new HashMap(); // Sort in order: first by input node, then by output node List sortedLogicalEdges = new ArrayList<>(logicalEdges); Collections.sort( sortedLogicalEdges, (o1, o2) -> { if (o1.getInputVertexId() != o2.getInputVertexId()) { return o1.getInputVertexId() > o2.getInputVertexId() ? 1 : -1; } if (o1.getTargetVertexId() != o2.getTargetVertexId()) { return o1.getTargetVertexId() > o2.getTargetVertexId() ? 1 : -1; } return 0; }); // Loop to convert each logical plan edge to an execution plan edge for (LogicalEdge logicalEdge : sortedLogicalEdges) { LogicalVertex logicalInputVertex = logicalEdge.getInputVertex(); ExecutionVertex executionInputVertex = logicalVertexIdToExecutionVertexMap.computeIfAbsent( logicalInputVertex.getVertexId(), vertexId -> { long newId = idGenerator.getNextId(); // Recreate Action for each logical plan node Action newLogicalInputAction = recreateAction( logicalInputVertex.getAction(), newId, logicalInputVertex.getParallelism()); // Convert to execution plan node return new ExecutionVertex( newId, newLogicalInputAction, logicalInputVertex.getParallelism()); }); // Similarly, recreate execution plan nodes for target nodes LogicalVertex logicalTargetVertex = logicalEdge.getTargetVertex(); ExecutionVertex executionTargetVertex = logicalVertexIdToExecutionVertexMap.computeIfAbsent( logicalTargetVertex.getVertexId(), vertexId -> { long newId = idGenerator.getNextId(); Action newLogicalTargetAction = recreateAction( logicalTargetVertex.getAction(), newId, logicalTargetVertex.getParallelism()); return new ExecutionVertex( newId, newLogicalTargetAction, logicalTargetVertex.getParallelism()); }); // Generate execution plan edge ExecutionEdge executionEdge = new ExecutionEdge(executionInputVertex, executionTargetVertex); executionEdges.add(executionEdge); } return executionEdges; } चरण दो private Set generateShuffleEdges(Set executionEdges) { // Map of upstream node ID to list of downstream nodes Map > targetVerticesMap = new LinkedHashMap<>(); // Store only nodes of type Source Set sourceExecutionVertices = new HashSet<>(); executionEdges.forEach( edge -> { ExecutionVertex leftVertex = edge.getLeftVertex(); ExecutionVertex rightVertex = edge.getRightVertex(); if (leftVertex.getAction() instanceof SourceAction) { sourceExecutionVertices.add(leftVertex); } targetVerticesMap .computeIfAbsent(leftVertex.getVertexId(), id -> new ArrayList<>()) .add(rightVertex); }); if (sourceExecutionVertices.size() != 1) { return executionEdges; } ExecutionVertex sourceExecutionVertex = sourceExecutionVertices.stream().findFirst().get(); Action sourceAction = sourceExecutionVertex.getAction(); List producedCatalogTables = new ArrayList<>(); if (sourceAction instanceof SourceAction) { try { producedCatalogTables = ((SourceAction ) sourceAction) .getSource() .getProducedCatalogTables(); } catch (UnsupportedOperationException e) { } } else if (sourceAction instanceof TransformChainAction) { return executionEdges; } else { throw new SeaTunnelException( "source action must be SourceAction or TransformChainAction"); } // If the source produces a single table or // the source has only one downstream output, return directly if (producedCatalogTables.size() sinkVertices = targetVerticesMap.get(sourceExecutionVertex.getVertexId()); // Check if there are other types of actions, currently downstream nodes should ideally have two types: Transform and Sink; here we check if only Sink type is present Optional hasOtherAction = sinkVertices.stream() .filter(vertex -> !(vertex.getAction() instanceof SinkAction)) .findFirst(); checkArgument(!hasOtherAction.isPresent()); // After executing the above code, the current scenario is: // There is only one data source, this source produces multiple tables, and multiple sink nodes depend on these tables // This means the task has only two types of nodes: a source node that produces multiple tables and a group of sink nodes depending on this source // A new shuffle node will be created and added between the source and sinks // Modify the dependency relationship to source -> shuffle -> multiple sinks Set newExecutionEdges = new LinkedHashSet<>(); // Shuffle strategy will not be explored in detail here ShuffleStrategy shuffleStrategy = ShuffleMultipleRowStrategy.builder() .jobId(jobImmutableInformation.getJobId()) .inputPartitions(sourceAction.getParallelism()) .catalogTables(producedCatalogTables) .queueEmptyQueueTtl( (int) (engineConfig.getCheckpointConfig().getCheckpointInterval() * 3)) .build(); ShuffleConfig shuffleConfig = ShuffleConfig.builder().shuffleStrategy(shuffleStrategy).build(); long shuffleVertexId = idGenerator.getNextId(); String shuffleActionName = String.format("Shuffle [%s]", sourceAction.getName()); ShuffleAction shuffleAction = new ShuffleAction(shuffleVertexId, shuffleActionName, shuffleConfig); shuffleAction.setParallelism(sourceAction.getParallelism()); ExecutionVertex shuffleVertex = new ExecutionVertex(shuffleVertexId, shuffleAction, shuffleAction.getParallelism()); ExecutionEdge sourceToShuffleEdge = new ExecutionEdge(sourceExecutionVertex, shuffleVertex); newExecutionEdges.add(sourceToShuffleEdge); // Set the parallelism of multiple sink nodes to 1 for (ExecutionVertex sinkVertex : sinkVertices) { sinkVertex.setParallelism(1); sinkVertex.getAction().setParallelism(1); ExecutionEdge shuffleToSinkEdge = new ExecutionEdge(shuffleVertex, sinkVertex); newExecutionEdges.add(shuffleToSinkEdge); } return newExecutionEdges; } शफल चरण उन विशिष्ट परिदृश्यों को संबोधित करता है जहां स्रोत कई तालिकाओं को पढ़ने का समर्थन करता है, और इस स्रोत पर निर्भर कई सिंक नोड हैं। ऐसे मामलों में, बीच में एक शफल नोड जोड़ा जाता है। चरण 3 private Set generateTransformChainEdges(Set executionEdges) { // Uses three structures: stores all Source nodes and the input/output nodes for each // inputVerticesMap stores all upstream input nodes by downstream node id as the key // targetVerticesMap stores all downstream output nodes by upstream node id as the key Map > inputVerticesMap = new HashMap<>(); Map > targetVerticesMap = new HashMap<>(); Set sourceExecutionVertices = new HashSet<>(); executionEdges.forEach( edge -> { ExecutionVertex leftVertex = edge.getLeftVertex(); ExecutionVertex rightVertex = edge.getRightVertex(); if (leftVertex.getAction() instanceof SourceAction) { sourceExecutionVertices.add(leftVertex); } inputVerticesMap .computeIfAbsent(rightVertex.getVertexId(), id -> new ArrayList<>()) .add(leftVertex); targetVerticesMap .computeIfAbsent(leftVertex.getVertexId(), id -> new ArrayList<>()) .add(rightVertex); }); Map transformChainVertexMap = new HashMap<>(); Map chainedTransformVerticesMapping = new HashMap<>(); // Loop over each source, starting with all head nodes in the DAG for (ExecutionVertex sourceVertex : sourceExecutionVertices) { List vertices = new ArrayList<>(); vertices.add(sourceVertex); for (int index = 0; index < vertices.size(); index++) { ExecutionVertex vertex = vertices.get(index); fillChainedTransformExecutionVertex( vertex, chainedTransformVerticesMapping, transformChainVertexMap, executionEdges, Collections.unmodifiableMap(inputVerticesMap), Collections.unmodifiableMap(targetVerticesMap)); // If the current node has downstream nodes, add all downstream nodes to the list // The second loop will recalculate the newly added downstream nodes, which could be Transform nodes or Sink nodes if (targetVerticesMap.containsKey(vertex.getVertexId())) { vertices.addAll(targetVerticesMap.get(vertex.getVertexId())); } } } // After looping, chained Transform nodes will be chained, and the chainable edges will be removed from the execution plan // Therefore, the logical plan at this point cannot form the graph relationship and needs to be rebuilt Set transformChainEdges = new LinkedHashSet<>(); // Loop over existing relationships for (ExecutionEdge executionEdge : executionEdges) { ExecutionVertex leftVertex = executionEdge.getLeftVertex(); ExecutionVertex rightVertex = executionEdge.getRightVertex(); boolean needRebuild = false; // Check if the input or output nodes of the current edge are in the chain mapping // If so, the node has been chained, and we need to find the chained node in the mapping // and rebuild the DAG if (chainedTransformVerticesMapping.containsKey(leftVertex.getVertexId())) { needRebuild = true; leftVertex = transformChainVertexMap.get( chainedTransformVerticesMapping.get(leftVertex.getVertexId())); } if (chainedTransformVerticesMapping.containsKey(rightVertex.getVertexId())) { needRebuild = true; rightVertex = transformChainVertexMap.get( chainedTransformVerticesMapping.get(rightVertex.getVertexId())); } if (needRebuild) { executionEdge = new ExecutionEdge(leftVertex, rightVertex); } transformChainEdges.add(executionEdge); } return transformChainEdges; } private void fillChainedTransformExecutionVertex( ExecutionVertex currentVertex, Map chainedTransformVerticesMapping, Map transformChainVertexMap, Set executionEdges, Map > inputVerticesMap, Map > targetVerticesMap) { // Exit if the map already contains the current node if (chainedTransformVerticesMapping.containsKey(currentVertex.getVertexId())) { return; } List transformChainedVertices = new ArrayList<>(); collectChainedVertices( currentVertex, transformChainedVertices, executionEdges, inputVerticesMap, targetVerticesMap); // If the list is not empty, it means the Transform nodes in the list can be merged into one if (transformChainedVertices.size() > 0) { long newVertexId = idGenerator.getNextId(); List transforms = new ArrayList<>(transformChainedVertices.size()); List names = new ArrayList<>(transformChainedVertices.size()); Set jars = new HashSet<>(); Set identifiers = new HashSet<>(); transformChainedVertices.stream() .peek( // Add all historical node IDs and new node IDs to the mapping vertex -> chainedTransformVerticesMapping.put( vertex.getVertexId(), newVertexId)) .map(ExecutionVertex::getAction) .map(action -> (TransformAction) action) .forEach( action -> { transforms.add(action.getTransform()); jars.addAll(action.getJarUrls()); identifiers.addAll(action.getConnectorJarIdentifiers()); names.add(action.getName()); }); String transformChainActionName = String.format("TransformChain[%s]", String.join("->", names)); // Merge multiple TransformActions into one TransformChainAction TransformChainAction transformChainAction = new TransformChainAction( newVertexId, transformChainActionName, jars, identifiers, transforms); transformChainAction.setParallelism(currentVertex.getAction().getParallelism()); ExecutionVertex executionVertex = new ExecutionVertex( newVertexId, transformChainAction, currentVertex.getParallelism()); // Store the modified node information in the state transformChainVertexMap.put(newVertexId, executionVertex); chainedTransformVerticesMapping.put( currentVertex.getVertexId(), executionVertex.getVertexId()); } } private void collectChainedVertices( ExecutionVertex currentVertex, List chainedVertices, Set executionEdges, Map > inputVerticesMap, Map > targetVerticesMap) { Action action = currentVertex.getAction(); // Only merge TransformAction if (action instanceof TransformAction) { if (chainedVertices.size() == 0) { // If the list of vertices to be merged is empty, add itself to the list // The condition for entering this branch is that the current node is a TransformAction and the list to be merged is empty // There may be several scenarios: the first Transform node enters, and this Transform node has no constraints chainedVertices.add(currentVertex); } else if (inputVerticesMap.get(currentVertex.getVertexId()).size() == 1) { // When this condition is entered, it means: // The list of vertices to be merged already has at least one TransformAction // The scenario at this point is that the upstream Transform node has only one downstream node, ie, the current node. This constraint is ensured by the following judgment // Chain the current TransformAction node with the previous TransformAction node // Delete this relationship from the execution plan executionEdges.remove( new ExecutionEdge( chainedVertices.get(chainedVertices.size() - 1), currentVertex)); // Add itself to the list of nodes to be merged chainedVertices.add(currentVertex); } else { return; } } else { return; } // It cannot chain to any target vertex if it has multiple target vertices. if (targetVerticesMap.get(currentVertex.getVertexId()).size() == 1) { // If the current node has only one downstream node, try chaining again // If the current node has multiple downstream nodes, it will not chain the downstream nodes, so it can be ensured that the above chaining is a one-to-one relationship // This call occurs when the Transform node has only one downstream node collectChainedVertices( targetVerticesMap.get(currentVertex.getVertexId()).get(0), chainedVertices, executionEdges, inputVerticesMap, targetVerticesMap); } } चरण 4 private List generatePipelines(Set executionEdges) { // Stores each execution plan node Set executionVertices = new LinkedHashSet<>(); for (ExecutionEdge edge : executionEdges) { executionVertices.add(edge.getLeftVertex()); executionVertices.add(edge.getRightVertex()); } // Calls the Pipeline generator to convert the execution plan into Pipelines PipelineGenerator pipelineGenerator = new PipelineGenerator(executionVertices, new ArrayList<>(executionEdges)); List pipelines = pipelineGenerator.generatePipelines(); Set duplicatedActionNames = new HashSet<>(); Set actionNames = new HashSet<>(); for (Pipeline pipeline : pipelines) { Integer pipelineId = pipeline.getId(); for (ExecutionVertex vertex : pipeline.getVertexes().values()) { // Get each execution node of the current Pipeline, reset the Action name, and add the pipeline name Action action = vertex.getAction(); String actionName = String.format("pipeline-%s [%s]", pipelineId, action.getName()); action.setName(actionName); if (actionNames.contains(actionName)) { duplicatedActionNames.add(actionName); } actionNames.add(action Name); } } if (duplicatedActionNames.size() > 0) { throw new RuntimeException( String.format( "Duplicated Action names found: %s", duplicatedActionNames)); } return pipelines; } public PipelineGenerator(Collection vertices, List edges) { this.vertices = vertices; this.edges = edges; } public List generatePipelines() { List executionEdges = expandEdgeByParallelism(edges); // Split the execution plan into unrelated execution plans based on their relationships // Divide into several unrelated execution plans List > edgesList = splitUnrelatedEdges(executionEdges); edgesList = edgesList.stream() .flatMap(e -> this.splitUnionEdge(e).stream()) .collect(Collectors.toList()); // Just convert execution plan to pipeline at now. We should split it to multi pipeline with // cache in the future IdGenerator idGenerator = new IdGenerator(); // Convert execution plan graph to Pipeline return edgesList.stream() .map( e -> { Map vertexes = new HashMap<>(); List pipelineEdges = e.stream() .map( edge -> { if (!vertexes.containsKey( edge.getLeftVertexId())) { vertexes.put( edge.getLeftVertexId(), edge.getLeftVertex()); } ExecutionVertex source = vertexes.get( edge.getLeftVertexId()); if (!vertexes.containsKey( edge.getRightVertexId())) { vertexes.put( edge.getRightVertexId(), edge.getRightVertex()); } ExecutionVertex destination = vertexes.get( edge.getRightVertexId()); return new ExecutionEdge( source, destination); }) .collect(Collectors.toList()); return new Pipeline( (int) idGenerator.getNextId(), pipelineEdges, vertexes); }) .collect(Collectors.toList()); } चरण 5 चरण पांच में निष्पादन योजना इंस्टैंस तैयार करना, चरण चार में तैयार किए गए पाइपलाइन पैरामीटर्स को पास करना शामिल है। सारांश: निष्पादन योजना तार्किक योजना पर निम्नलिखित कार्य निष्पादित करती है: जब कोई स्रोत अनेक तालिकाएं उत्पन्न करता है और अनेक सिंक नोड इस स्रोत पर निर्भर होते हैं, तो बीच में एक शफल नोड जोड़ दिया जाता है। एकाधिक रूपांतरण नोड्स को एक नोड में संयोजित करते हुए रूपांतरण नोड्स को श्रृंखलाबद्ध रूप से मर्ज करने का प्रयास करें। कार्यों को विभाजित करें, कई असंबंधित कार्यों में विभाजित करें जिन्हें के रूप में दर्शाया गया है। configuration file/LogicalDag List भौतिक योजना निर्माण भौतिक योजना निर्माण में आगे बढ़ने से पहले, आइए सबसे पहले यह समीक्षा करें कि उत्पन्न भौतिक योजना में कौन सी जानकारी शामिल है और इसके आंतरिक घटकों की जांच करें। public class PhysicalPlan { private final List pipelineList; private final AtomicInteger finishedPipelineNum = new AtomicInteger(0); private final AtomicInteger canceledPipelineNum = new AtomicInteger(0); private final AtomicInteger failedPipelineNum = new AtomicInteger(0); private final JobImmutableInformation jobImmutableInformation; private final IMap runningJobStateIMap; private final IMap runningJobStateTimestampsIMap; private CompletableFuture jobEndFuture; private final AtomicReference errorBySubPlan = new AtomicReference<>(); private final String jobFullName; private final long jobId; private JobMaster jobMaster; private boolean makeJobEndWhenPipelineEnded = true; private volatile boolean isRunning = false; } इस वर्ग में, कुंजी फ़ील्ड है, जो उदाहरणों की एक सूची है: pipelineList SubPlan public class SubPlan { private final int pipelineMaxRestoreNum; private final int pipelineRestoreIntervalSeconds; private final List physicalVertexList; private final List coordinatorVertexList; private final int pipelineId; private final AtomicInteger finishedTaskNum = new AtomicInteger(0); private final AtomicInteger canceledTaskNum = new AtomicInteger(0); private final AtomicInteger failedTaskNum = new AtomicInteger(0); private final String pipelineFullName; private final IMap runningJobStateIMap; private final Map tags; private final IMap runningJobStateTimestampsIMap; private CompletableFuture pipelineFuture; private final PipelineLocation pipelineLocation; private AtomicReference errorByPhysicalVertex = new AtomicReference<>(); private final ExecutorService executorService; private JobMaster jobMaster; private PassiveCompletableFuture reSchedulerPipelineFuture; private Integer pipelineRestoreNum; private final Object restoreLock = new Object(); private volatile PipelineStatus currPipelineStatus; public volatile boolean isRunning = false; private Map slotProfiles; } वर्ग उदाहरणों की एक सूची बनाए रखता है, जो भौतिक योजना नोड्स और समन्वयक नोड्स में विभाजित है: SubPlan PhysicalVertex public class PhysicalVertex { private final TaskGroupLocation taskGroupLocation; private final String taskFullName; private final TaskGroupDefaultImpl taskGroup; private final ExecutorService executorService; private final FlakeIdGenerator flakeIdGenerator; private final Set pluginJarsUrls; private final Set connectorJarIdentifiers; private final IMap runningJobStateIMap; private CompletableFuture taskFuture; private final IMap runningJobStateTimestampsIMap; private final NodeEngine nodeEngine; private JobMaster jobMaster; private volatile ExecutionState currExecutionState = ExecutionState.CREATED; public volatile boolean isRunning = false; private AtomicReference errorByPhysicalVertex = new AtomicReference<>(); } public class TaskGroupDefaultImpl implements TaskGroup { private final TaskGroupLocation taskGroupLocation; private final String taskGroupName; // Stores the tasks that the physical node needs to execute // Each task could be for reading data, writing data, data splitting, checkpoint tasks, etc. private final Map tasks; } निष्पादन योजना को में परिवर्तित करने और निष्पादन के दौरान विभिन्न समन्वय कार्यों जैसे डेटा विभाजन, डेटा कमिटिंग और चेकपॉइंट कार्यों को जोड़ने के लिए जिम्मेदार है। PhysicalPlanGenerator SeaTunnelTask public PhysicalPlanGenerator( @NonNull ExecutionPlan executionPlan, @NonNull NodeEngine nodeEngine, @NonNull JobImmutableInformation jobImmutableInformation, long initializationTimestamp, @NonNull ExecutorService executorService, @NonNull FlakeIdGenerator flakeIdGenerator, @NonNull IMap runningJobStateIMap, @NonNull IMap runningJobStateTimestampsIMap, @NonNull QueueType queueType) { this.pipelines = executionPlan.getPipelines(); this.nodeEngine = nodeEngine; this.jobImmutableInformation = jobImmutableInformation; this.initializationTimestamp = initializationTimestamp; this.executorService = executorService; this.flakeIdGenerator = flakeIdGenerator; // the checkpoint of a pipeline this.pipelineTasks = new HashSet<>(); this.startingTasks = new HashSet<>(); this.subtaskActions = new HashMap<>(); this.runningJobStateIMap = runningJobStateIMap; this.runningJobStateTimestampsIMap = runningJobStateTimestampsIMap; this.queueType = queueType; } public Tuple2 > generate() { // Get the node filter conditions from user configuration to select the nodes where tasks will run Map tagFilter = (Map ) jobImmutableInformation .getJobConfig() .getEnvOptions() .get(EnvCommonOptions.NODE_TAG_FILTER.key()); // TODO Determine which tasks do not need to be restored according to state CopyOnWriteArrayList > waitForCompleteBySubPlanList = new CopyOnWriteArrayList<>(); Map checkpointPlans = new HashMap<>(); final int totalPipelineNum = pipelines.size(); Stream subPlanStream = pipelines.stream() .map( pipeline -> { // Clear the state each time this.pipelineTasks.clear(); this.startingTasks.clear(); this.subtaskActions.clear(); final int pipelineId = pipeline.getId(); // Get current task information final List edges = pipeline.getEdges(); // Get all SourceActions List > sources = findSourceAction(edges); // Generate Source data slice tasks, ie, SourceSplitEnumeratorTask // This task calls the SourceSplitEnumerator class in the connector if supported List coordinatorVertexList = getEnumeratorTask( sources, pipelineId, totalPipelineNum); // Generate Sink commit tasks, ie, SinkAggregatedCommitterTask // This task calls the SinkAggregatedCommitter class in the connector if supported // These two tasks are executed as coordination tasks coordinatorVertexList.addAll( getCommitterTask(edges, pipelineId, totalPipelineNum)); List physicalVertexList = getSourceTask( edges, sources, pipelineId, totalPipelineNum); // physicalVertexList.addAll( getShuffleTask(edges, pipelineId, totalPipelineNum)); CompletableFuture pipelineFuture = new CompletableFuture<>(); waitForCompleteBySubPlanList.add( new PassiveCompletableFuture<>(pipelineFuture)); // Add checkpoint tasks checkpointPlans.put( pipelineId, CheckpointPlan.builder() .pipelineId(pipelineId) .pipelineSubtasks(pipelineTasks) .startingSubtasks(startingTasks) .pipelineActions(pipeline.getActions()) .subtaskActions(subtaskActions) .build()); return new SubPlan( pipelineId, totalPipelineNum, initializationTimestamp, physicalVertexList, coordinatorVertexList, jobImmutableInformation, executorService, runningJobStateIMap, runningJobStateTimestampsIMap, tagFilter); }); PhysicalPlan physicalPlan = new PhysicalPlan( subPlanStream.collect(Collectors.toList()), executorService, jobImmutableInformation, initializationTimestamp, runningJobStateIMap, runningJobStateTimestampsIMap); return Tuple2.tuple2(physicalPlan, checkpointPlans); } भौतिक योजना तैयार करने की प्रक्रिया में निष्पादन योजना को में परिवर्तित करना और विभिन्न समन्वय कार्यों को जोड़ना शामिल है, जैसे डेटा विभाजन कार्य, डेटा प्रतिबद्ध कार्य और चेकपॉइंट कार्य। SeaTunnelTask में, कार्यों को , , , , में परिवर्तित किया जाता है। SeaTunnelTask SourceFlowLifeCycle SinkFlowLifeCycle TransformFlowLifeCycle ShuffleSinkFlowLifeCycle ShuffleSourceFlowLifeCycle उदाहरण के लिए, और वर्ग इस प्रकार हैं: SourceFlowLifeCycle SinkFlowLifeCycle स्रोतप्रवाहजीवनचक्र @Override public void init() throws Exception { this.splitSerializer = sourceAction.getSource().getSplitSerializer(); this.reader = sourceAction .getSource() .createReader( new SourceReaderContext( indexID, sourceAction.getSource().getBoundedness(), this, metricsContext, eventListener)); this.enumeratorTaskAddress = getEnumeratorTaskAddress(); } @Override public void open() throws Exception { reader.open(); register(); } public void collect() throws Exception { if (!prepareClose) { if (schemaChanging()) { log.debug("schema is changing, stop reader collect records"); Thread.sleep(200); return; } reader.pollNext(collector); if (collector.isEmptyThisPollNext()) { Thread.sleep(100); } else { collector.resetEmptyThisPollNext(); /** * The current thread obtain a checkpoint lock in the method {@link * SourceReader#pollNext( Collector)}. When trigger the checkpoint or savepoint, * other threads try to obtain the lock in the method {@link * SourceFlowLifeCycle#triggerBarrier(Barrier)}. When high CPU load, checkpoint * process may be blocked as long time. So we need sleep to free the CPU. */ Thread.sleep(0L); } if (collector.captureSchemaChangeBeforeCheckpointSignal()) { if (schemaChangePhase.get() != null) { throw new IllegalStateException( "previous schema changes in progress, schemaChangePhase: " + schemaChangePhase.get()); } schemaChangePhase.set(SchemaChangePhase.createBeforePhase()); runningTask.triggerSchemaChangeBeforeCheckpoint().get(); log.info("triggered schema-change-before checkpoint, stopping collect data"); } else if (collector.captureSchemaChangeAfterCheckpointSignal()) { if (schemaChangePhase.get() != null) { throw new IllegalStateException( "previous schema changes in progress, schemaChangePhase: " + schemaChangePhase.get()); } schemaChangePhase.set(SchemaChangePhase.createAfterPhase()); runningTask.triggerSchemaChangeAfterCheckpoint().get(); log.info("triggered schema-change-after checkpoint, stopping collect data"); } } else { Thread.sleep(100); } } में, डेटा रीडिंग विधि में की जाती है। एक बार डेटा पढ़ लेने के बाद, इसे में डाल दिया जाता है। जब डेटा प्राप्त होता है, तो कलेक्टर मेट्रिक्स को अपडेट करता है और डेटा को डाउनस्ट्रीम घटकों को भेजता है। SourceFlowLifeCycle collect SeaTunnelSourceCollector @Override public void collect(T row) { try { if (row instanceof SeaTunnelRow) { String tableId = ((SeaTunnelRow) row).getTableId(); int size; if (rowType instanceof SeaTunnelRowType) { size = ((SeaTunnelRow) row).getBytesSize((SeaTunnelRowType) rowType); } else if (rowType instanceof MultipleRowType) { size = ((SeaTunnelRow) row).getBytesSize(rowTypeMap.get(tableId)); } else { throw new SeaTunnelEngineException( "Unsupported row type: " + rowType.getClass().getName()); } sourceReceivedBytes.inc(size); sourceReceivedBytesPerSeconds.markEvent(size); flowControlGate.audit((SeaTunnelRow) row); if (StringUtils.isNotEmpty(tableId)) { String tableName = getFullName(TablePath.of(tableId)); Counter sourceTableCounter = sourceReceivedCountPerTable.get(tableName); if (Objects.nonNull(sourceTableCounter)) { sourceTableCounter.inc(); } else { Counter counter = metricsContext.counter(SOURCE_RECEIVED_COUNT + "#" + tableName); counter.inc(); sourceReceivedCountPerTable.put(tableName, counter); } } } sendRecordToNext(new Record<>(row)); emptyThisPollNext = false; sourceReceivedCount.inc(); sourceReceivedQPS.markEvent(); } catch (IOException e) { throw new RuntimeException(e); } } public void sendRecordToNext(Record record) throws IOException { synchronized (checkpointLock) { for (OneInputFlowLifeCycle > output : outputs) { output.received(record); } } } सिंकफ्लोलाइफसाइकिल @Override public void received(Record record) { try { if (record.getData() instanceof Barrier) { long startTime = System.currentTimeMillis(); Barrier barrier = (Barrier) record.getData(); if (barrier.prepareClose(this.taskLocation)) { prepareClose = true; } if (barrier.snapshot()) { try { lastCommitInfo = writer.prepareCommit(); } catch (Exception e) { writer.abortPrepare(); throw e; } List states = writer.snapshotState(barrier.getId()); if (!writerStateSerializer.isPresent()) { runningTask.addState( barrier, ActionStateKey.of(sinkAction), Collections.emptyList()); } else { runningTask.addState( barrier, ActionStateKey.of(sinkAction), serializeStates(writerStateSerializer.get(), states)); } if (containAggCommitter) { CommitInfoT commitInfoT = null; if (lastCommitInfo.isPresent()) { commitInfoT = lastCommitInfo.get(); } runningTask .getExecutionContext() .sendToMember( new SinkPrepareCommitOperation ( barrier, committerTaskLocation, commitInfoSerializer.isPresent() ? commitInfoSerializer .get() .serialize(commitInfoT) : null), committerTaskAddress) .join(); } } else { if (containAggCommitter) { runningTask .getExecutionContext() .sendToMember( new BarrierFlowOperation(barrier, committerTaskLocation), committerTaskAddress) .join(); } } runningTask.ack(barrier); log.debug( "trigger barrier [{}] finished, cost {}ms. taskLocation [{}]", barrier.getId(), System.currentTimeMillis() - startTime, taskLocation); } else if (record.getData() instanceof SchemaChangeEvent) { if (prepareClose) { return; } SchemaChangeEvent event = (SchemaChangeEvent) record.getData(); writer.applySchemaChange(event); } else { if (prepareClose) { return; } writer.write((T) record.getData()); sinkWriteCount.inc(); sinkWriteQPS.markEvent(); if (record.getData() instanceof SeaTunnelRow) { long size = ((SeaTunnelRow) record.getData()).getBytesSize(); sinkWriteBytes.inc(size); sinkWriteBytesPerSeconds.markEvent(size); String tableId = ((SeaTunnelRow) record.getData()).getTableId(); if (StringUtils.isNotBlank(tableId)) { String tableName = getFullName(TablePath.of(tableId)); Counter sinkTableCounter = sinkWriteCountPerTable.get(tableName); if (Objects.nonNull(sinkTableCounter)) { sinkTableCounter.inc(); } else { Counter counter = metricsContext.counter(SINK_WRITE_COUNT + "#" + tableName); counter.inc(); sinkWriteCountPerTable.put(tableName, counter); } } } } } catch (Exception e) { throw new RuntimeException(e); } } कार्य निष्पादन में, विधि के माध्यम से एक भौतिक योजना तैयार की जाती है, और फिर कार्य को वास्तव में शुरू करने के लिए विधि को बुलाया जाता है। CoordinatorService init run CoordinatorService { jobMaster.init( runningJobInfoIMap.get(jobId).getInitializationTimestamp(), false); ... jobMaster.run(); } JobMaster { public void run() { ... physicalPlan.startJob(); ... } } में, कार्य शुरू करते समय, यह की विधि को कॉल करता है। JobMaster PhysicalPlan startJob public void startJob() { isRunning = true; log.info("{} state process is start", getJobFullName()); stateProcess(); } private synchronized void stateProcess() { if (!isRunning) { log.warn(String.format("%s state process is stopped", jobFullName)); return; } switch (getJobStatus()) { case CREATED: updateJobState(JobStatus.SCHEDULED); break; case SCHEDULED: getPipelineList() .forEach( subPlan -> { if (PipelineStatus.CREATED.equals( subPlan.getCurrPipelineStatus())) { subPlan.startSubPlanStateProcess(); } }); updateJobState(JobStatus.RUNNING); break; case RUNNING: case DOING_SAVEPOINT: break; case FAILING: case CANCELING: jobMaster.neverNeedRestore(); getPipelineList().forEach(SubPlan::cancelPipeline); break; case FAILED: case CANCELED: case SAVEPOINT_DONE: case FINISHED: stopJobStateProcess(); jobEndFuture.complete(new JobResult(getJobStatus(), errorBySubPlan.get())); return; default: throw new IllegalArgumentException("Unknown Job State: " + getJobStatus()); } } में, किसी कार्य को प्रारंभ करने से कार्य की स्थिति में अपडेट हो जाती है और फिर की start विधि को कॉल करना जारी रहता है। PhysicalPlan SCHEDULED SubPlan public void startSubPlanStateProcess() { isRunning = true; log.info("{} state process is start", getPipelineFullName()); stateProcess(); } private synchronized void stateProcess() { if (!isRunning) { log.warn(String.format("%s state process not start", pipelineFullName)); return; } PipelineStatus state = getCurrPipelineStatus(); switch (state) { case CREATED: updatePipelineState(PipelineStatus.SCHEDULED); break; case SCHEDULED: try { ResourceUtils.applyResourceForPipeline(jobMaster.getResourceManager(), this); log.debug( "slotProfiles: {}, PipelineLocation: {}", slotProfiles, this.getPipelineLocation()); updatePipelineState(PipelineStatus.DEPLOYING); } catch (Exception e) { makePipelineFailing(e); } break; case DEPLOYING: coordinatorVertexList.forEach( task -> { if (task.getExecutionState().equals(ExecutionState.CREATED)) { task.startPhysicalVertex(); task.makeTaskGroupDeploy(); } }); physicalVertexList.forEach( task -> { if (task.getExecutionState().equals(ExecutionState.CREATED)) { task.startPhysicalVertex(); task.makeTaskGroupDeploy(); } }); updatePipelineState(PipelineStatus.RUNNING); break; case RUNNING: break; case FAILING: case CANCELING: coordinatorVertexList.forEach( task -> { task.startPhysicalVertex(); task.cancel(); }); physicalVertexList.forEach( task -> { task.startPhysicalVertex(); task.cancel(); }); break; case FAILED: case CANCELED: if (checkNeedRestore(state) && prepareRestorePipeline()) { jobMaster.releasePipelineResource(this); restorePipeline(); return; } subPlanDone(state); stopSubPlanStateProcess(); pipelineFuture.complete( new PipelineExecutionState(pipelineId, state, errorByPhysicalVertex.get())); return; case FINISHED: subPlanDone(state); stopSubPlanStateProcess(); pipelineFuture.complete( new PipelineExecutionState( pipelineId, getPipelineState(), errorByPhysicalVertex.get())); return; default: throw new IllegalArgumentException("Unknown Pipeline State: " + getPipelineState()); } } में, सभी कार्यों के लिए संसाधन लागू किए जाते हैं। संसाधन आवेदन के माध्यम से किया जाता है। संसाधन आवेदन के दौरान, नोड्स को उपयोगकर्ता-परिभाषित टैग के आधार पर चुना जाता है ताकि यह सुनिश्चित किया जा सके कि कार्य विशिष्ट नोड्स पर चलते हैं, जिससे संसाधन अलगाव प्राप्त होता है। SubPlan ResourceManager public static void applyResourceForPipeline( @NonNull ResourceManager resourceManager, @NonNull SubPlan subPlan) { Map > futures = new HashMap<>(); Map slotProfiles = new HashMap<>(); // TODO If there is no enough resources for tasks, we need add some wait profile subPlan.getCoordinatorVertexList() .forEach( coordinator -> futures.put( coordinator.getTaskGroupLocation(), applyResourceForTask( resourceManager, coordinator, subPlan.getTags()))); subPlan.getPhysicalVertexList() .forEach( task -> futures.put( task.getTaskGroupLocation(), applyResourceForTask( resourceManager, task, subPlan.getTags()))); futures.forEach( (key, value) -> { try { slotProfiles.put(key, value == null ? null : value.join()); } catch (CompletionException e) { // do nothing } }); // set it first, avoid can't get it when get resource not enough exception and need release // applied resource subPlan.getJobMaster().setOwnedSlotProfiles(subPlan.getPipelineLocation(), slotProfiles); if (futures.size() != slotProfiles.size()) { throw new NoEnoughResourceException(); } } public static CompletableFuture applyResourceForTask( ResourceManager resourceManager, PhysicalVertex task, Map tags) { // TODO custom resource size return resourceManager.applyResource( task.getTaskGroupLocation().getJobId(), new ResourceProfile(), tags); } public CompletableFuture > applyResources( long jobId, List resourceProfile, Map tagFilter) throws NoEnoughResourceException { waitingWorkerRegister(); ConcurrentMap matchedWorker = filterWorkerByTag(tagFilter); if (matchedWorker.isEmpty()) { log.error("No matched worker with tag filter {}.", tagFilter); throw new NoEnoughResourceException(); } return new ResourceRequestHandler(jobId, resourceProfile, matchedWorker, this) .request(tagFilter); } जब सभी उपलब्ध नोड प्राप्त हो जाते हैं, तो नोड्स को फेरबदल किया जाता है और आवश्यक संसाधनों से बड़े संसाधनों वाले नोड को यादृच्छिक रूप से चुना जाता है। फिर नोड से संपर्क किया जाता है, और उसे एक भेजा जाता है। RequestSlotOperation public Optional preCheckWorkerResource(ResourceProfile r) { // Shuffle the order to ensure random selection of workers List workerProfiles = Arrays.asList(registerWorker.values().toArray(new WorkerProfile[0])); Collections.shuffle(workerProfiles); // Check if there are still unassigned slots Optional workerProfile = workerProfiles.stream() .filter( worker -> Arrays.stream(worker.getUnassignedSlots()) .anyMatch( slot -> slot.getResourceProfile() .enoughThan(r))) .findAny(); if (!workerProfile.isPresent()) { // Check if there are still unassigned resources workerProfile = workerProfiles.stream() .filter(WorkerProfile::isDynamicSlot) .filter(worker -> worker.getUnassignedResource().enoughThan(r)) .findAny(); } return workerProfile; } private CompletableFuture singleResourceRequestToMember( int i, ResourceProfile r, WorkerProfile workerProfile) { CompletableFuture future = resourceManager.sendToMember( new RequestSlotOperation(jobId, r), workerProfile.getAddress()); return future.whenComplete( withTryCatch( LOGGER, (slotAndWorkerProfile, error) -> { if (error != null) { throw new RuntimeException(error); } else { resourceManager.heartbeat(slotAndWorkerProfile.getWorkerProfile()); addSlotToCacheMap(i, slotAndWorkerProfile.getSlotProfile()); } })); } जब नोड का अनुरोध प्राप्त करता है, तो यह अपनी जानकारी अपडेट करता है और इसे मास्टर नोड को वापस कर देता है। यदि संसाधन अनुरोध अपेक्षित परिणाम को पूरा नहीं करता है, फेंका जाता है, जो कार्य विफलता को दर्शाता है। जब संसाधन आवंटन सफल होता है, तो कार्य परिनियोजन के साथ शुरू होता है, जो कार्य को निष्पादन के लिए नोड को भेजता है। SlotService requestSlot NoEnoughResourceException task.makeTaskGroupDeploy() worker TaskDeployState deployState = deploy(jobMaster.getOwnedSlotProfiles(taskGroupLocation)); public TaskDeployState deploy(@NonNull SlotProfile slotProfile) { try { if (slotProfile.getWorker().equals(nodeEngine.getThisAddress())) { return deployOnLocal(slotProfile); } else { return deployOnRemote(slotProfile); } } catch (Throwable th) { return TaskDeployState.failed(th); } } private TaskDeployState deployOnRemote(@Non Null SlotProfile slotProfile) { return deployInternal( taskGroupImmutableInformation -> { try { return (TaskDeployState) NodeEngineUtil.sendOperationToMemberNode( nodeEngine, new DeployTaskOperation( slotProfile, nodeEngine .getSerializationService() .toData( taskGroupImmutableInformation)), slotProfile.getWorker()) .get(); } catch (Exception e) { if (getExecutionState().isEndState()) { log.warn(ExceptionUtils.getMessage(e)); log.warn( String.format( "%s deploy error, but the state is already in end state %s, skip this error", getTaskFullName(), currExecutionState)); return TaskDeployState.success(); } else { return TaskDeployState.failed(e); } } }); } कार्य परिनियोजन किसी कार्य को तैनात करते समय, कार्य की जानकारी संसाधन आवंटन के दौरान प्राप्त नोड को भेजी जाती है: public TaskDeployState deployTask(@NonNull Data taskImmutableInformation) { TaskGroupImmutableInformation taskImmutableInfo = nodeEngine.getSerializationService().toObject(taskImmutableInformation); return deployTask(taskImmutableInfo); } public TaskDeployState deployTask(@NonNull TaskGroupImmutableInformation taskImmutableInfo) { logger.info( String.format( "received deploying task executionId [%s]", taskImmutableInfo.getExecutionId())); TaskGroup taskGroup = null; try { Set connectorJarIdentifiers = taskImmutableInfo.getConnectorJarIdentifiers(); Set jars = new HashSet<>(); ClassLoader classLoader; if (!CollectionUtils.isEmpty(connectorJarIdentifiers)) { // Prioritize obtaining the jar package file required for the current task execution // from the local, if it does not exist locally, it will be downloaded from the // master node. jars = serverConnectorPackageClient.getConnectorJarFromLocal( connectorJarIdentifiers); } else if (!CollectionUtils.isEmpty(taskImmutableInfo.getJars())) { jars = taskImmutableInfo.getJars(); } classLoader = classLoaderService.getClassLoader( taskImmutableInfo.getJobId(), Lists.newArrayList(jars)); if (jars.isEmpty()) { taskGroup = nodeEngine.getSerializationService().toObject(taskImmutableInfo.getGroup()); } else { taskGroup = CustomClassLoadedObject.deserializeWithCustomClassLoader( nodeEngine.getSerializationService(), classLoader, taskImmutableInfo.getGroup()); } logger.info( String.format( "deploying task %s, executionId [%s]", taskGroup.getTaskGroupLocation(), taskImmutableInfo.getExecutionId())); synchronized (this) { if (executionContexts.containsKey(taskGroup.getTaskGroupLocation())) { throw new RuntimeException( String.format( "TaskGroupLocation: %s already exists", taskGroup.getTaskGroupLocation())); } deployLocalTask(taskGroup, classLoader, jars); return TaskDeployState.success(); } } catch (Throwable t) { logger.severe( String.format( "TaskGroupID : %s deploy error with Exception: %s", taskGroup != null && taskGroup.getTaskGroupLocation() != null ? taskGroup.getTaskGroupLocation().toString() : "taskGroupLocation is null", ExceptionUtils.getMessage(t))); return TaskDeployState.failed(t); } } जब कोई कार्यकर्ता नोड कार्य प्राप्त करता है, तो वह कार्य को स्टार्टअप पर बनाए गए थ्रेड पूल में सबमिट करने के लिए की विधि को कॉल करता है। TaskExecutionService deployTask जब कार्य थ्रेड पूल में सबमिट किया जाता है: private final class BlockingWorker implements Runnable { private final TaskTracker tracker; private final CountDownLatch startedLatch; private BlockingWorker(TaskTracker tracker, CountDownLatch startedLatch) { this.tracker = tracker; this.startedLatch = startedLatch; } @Override public void run() { TaskExecutionService.TaskGroupExecutionTracker taskGroupExecutionTracker = tracker.taskGroupExecutionTracker; ClassLoader classLoader = executionContexts .get(taskGroupExecutionTracker.taskGroup.getTaskGroupLocation()) .getClassLoader(); ClassLoader oldClassLoader = Thread.currentThread().getContextClassLoader(); Thread.currentThread().setContextClassLoader(classLoader); final Task t = tracker.task; ProgressState result = null; try { startedLatch.countDown(); t.init(); do { result = t.call(); } while (!result.isDone() && isRunning && !taskGroupExecutionTracker.executionCompletedExceptionally()); ... } } विधि लागू की जाती है, और इस प्रकार डेटा सिंक्रनाइज़ेशन कार्य सही रूप से निष्पादित होते हैं। Task.call क्लास लोडर SeaTunnel में, अन्य घटक वर्गों के साथ टकराव से बचने के लिए उपवर्गों को प्राथमिकता देने के लिए डिफ़ॉल्ट ClassLoader को संशोधित किया गया है: @Override public synchronized ClassLoader getClassLoader(long jobId, Collection jars) { log.debug("Get classloader for job {} with jars {}", jobId, jars); if (cacheMode) { // with cache mode, all jobs share the same classloader if the jars are the same jobId = 1L; } if (!classLoaderCache.containsKey(jobId)) { classLoaderCache.put(jobId, new ConcurrentHashMap<>()); classLoaderReferenceCount.put(jobId, new ConcurrentHashMap<>()); } Map classLoaderMap = classLoaderCache.get(jobId); String key = covertJarsToKey(jars); if (classLoaderMap.containsKey(key)) { classLoaderReferenceCount.get(jobId).get(key).incrementAndGet(); return classLoaderMap.get(key); } else { ClassLoader classLoader = new SeaTunnelChildFirstClassLoader(jars); log.info("Create classloader for job {} with jars {}", jobId, jars); classLoaderMap.put(key, classLoader); classLoaderReferenceCount.get(jobId).put(key, new AtomicInteger(1)); return classLoader; } } REST API कार्य प्रस्तुति SeaTunnel REST API के ज़रिए टास्क सबमिशन का भी समर्थन करता है। इस सुविधा को सक्षम करने के लिए, फ़ाइल में निम्न कॉन्फ़िगरेशन जोड़ें: hazelcast.yaml network: rest-api: enabled: true endpoint-groups: CLUSTER_WRITE: enabled: true DATA: enabled: true इस कॉन्फ़िगरेशन को जोड़ने के बाद, हेज़ेलकास्ट नोड HTTP अनुरोध प्राप्त करने में सक्षम होगा। कार्य प्रस्तुतीकरण के लिए REST API का उपयोग करते हुए, क्लाइंट HTTP अनुरोध भेजने वाला नोड बन जाता है, और सर्वर SeaTunnel क्लस्टर बन जाता है। जब सर्वर अनुरोध प्राप्त करता है, तो वह अनुरोध URI के आधार पर उपयुक्त विधि को कॉल करेगा: public void handle(HttpPostCommand httpPostCommand) { String uri = httpPostCommand.getURI(); try { if (uri.startsWith(SUBMIT_JOB_URL)) { handleSubmitJob(httpPostCommand, uri); } else if (uri.startsWith(STOP_JOB_URL)) { handleStopJob(httpPostCommand, uri); } else if (uri.startsWith(ENCRYPT_CONFIG)) { handleEncrypt(httpPostCommand); } else { original.handle(httpPostCommand); } } catch (IllegalArgumentException e) { prepareResponse(SC_400, httpPostCommand, exceptionResponse(e)); } catch (Throwable e) { logger.warning("An error occurred while handling request " + httpPostCommand, e); prepareResponse(SC_500, httpPostCommand, exceptionResponse(e)); } this.textCommandService.sendResponse(httpPostCommand); } नौकरी प्रस्तुतीकरण अनुरोध को संभालने की विधि पथ द्वारा निर्धारित की जाती है: private void handleSubmitJob(HttpPostCommand httpPostCommand, String uri) throws IllegalArgumentException { Map requestParams = new HashMap<>(); RestUtil.buildRequestParams(requestParams, uri); Config config = RestUtil.buildConfig(requestHandle(httpPostCommand), false); ReadonlyConfig envOptions = ReadonlyConfig.fromConfig(config.getConfig("env")); String jobName = envOptions.get(EnvCommonOptions.JOB_NAME); JobConfig jobConfig = new JobConfig(); jobConfig.setName( StringUtils.isEmpty(requestParams.get(RestConstant.JOB_NAME)) ? jobName : requestParams.get(RestConstant.JOB_NAME)); boolean startWithSavePoint = Boolean.parseBoolean(requestParams.get(RestConstant.IS_START_WITH_SAVE_POINT)); String jobIdStr = requestParams.get(RestConstant.JOB_ID); Long finalJobId = StringUtils.isNotBlank(jobIdStr) ? Long.parseLong(jobIdStr) : null; SeaTunnelServer seaTunnelServer = getSeaTunnelServer(); RestJobExecutionEnvironment restJobExecutionEnvironment = new RestJobExecutionEnvironment( seaTunnelServer, jobConfig, config, textCommandService.getNode(), startWithSavePoint, finalJobId); JobImmutableInformation jobImmutableInformation = restJobExecutionEnvironment.build(); long jobId = jobImmutableInformation.getJobId(); if (!seaTunnelServer.isMasterNode()) { NodeEngineUtil.sendOperationToMasterNode( getNode().nodeEngine, new SubmitJobOperation( jobId, getNode().nodeEngine.toData(jobImmutableInformation), jobImmutableInformation.isStartWithSavePoint())) .join(); } else { submitJob(seaTunnelServer, jobImmutableInformation, jobConfig); } this.prepareResponse( httpPostCommand, new JsonObject() .add(RestConstant.JOB_ID, String.valueOf(jobId)) .add(RestConstant.JOB_NAME, jobConfig.getName())); } यहाँ तर्क क्लाइंट-साइड के समान है। चूँकि कोई स्थानीय मोड नहीं है, इसलिए स्थानीय सेवा बनाने की आवश्यकता नहीं है। क्लाइंट पक्ष पर, वर्ग का उपयोग तार्किक योजना पार्सिंग के लिए किया जाता है, और इसी प्रकार, वर्ग समान कार्य करता है। ClientJobExecutionEnvironment RestJobExecutionEnvironment कार्य सबमिट करते समय, यदि वर्तमान नोड मास्टर नोड नहीं है, तो यह मास्टर नोड को जानकारी भेजेगा। मास्टर नोड कार्य सबमिशन को उसी तरह से हैंडल करेगा जैसे वह कमांड-लाइन क्लाइंट से कमांड को हैंडल करता है। यदि वर्तमान नोड मास्टर नोड है, तो यह सीधे विधि को कॉल करेगा, जो बाद की प्रक्रिया के लिए विधि को आमंत्रित करता है: submitJob coordinatorService.submitJob private void submitJob( SeaTunnelServer seaTunnelServer, JobImmutableInformation jobImmutableInformation, JobConfig jobConfig) { CoordinatorService coordinatorService = seaTunnelServer.getCoordinatorService(); Data data = textCommandService .getNode() .nodeEngine .getSerializationService() .toData(jobImmutableInformation); PassiveCompletableFuture voidPassiveCompletableFuture = coordinatorService.submitJob( Long.parseLong(jobConfig.getJobContext().getJobId()), data, jobImmutableInformation.isStartWithSavePoint()); voidPassiveCompletableFuture.join(); } दोनों सबमिशन विधियों में सबमिशन साइड पर लॉजिकल प्लान को पार्स करना और फिर मास्टर नोड को जानकारी भेजना शामिल है। मास्टर नोड फिर फिजिकल प्लान पार्सिंग, आवंटन और अन्य ऑपरेशन करता है।