use of org.opensearch.common.component.LifecycleComponent in project OpenSearch by opensearch-project.
the class Node method start.
/**
* Start the node. If the node is already started, this method is no-op.
*/
public Node start() throws NodeValidationException {
if (!lifecycle.moveToStarted()) {
return this;
}
logger.info("starting ...");
pluginLifecycleComponents.forEach(LifecycleComponent::start);
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(RepositoriesService.class).start();
injector.getInstance(SearchService.class).start();
injector.getInstance(FsHealthService.class).start();
nodeService.getMonitorService().start();
final ClusterService clusterService = injector.getInstance(ClusterService.class);
final NodeConnectionsService nodeConnectionsService = injector.getInstance(NodeConnectionsService.class);
nodeConnectionsService.start();
clusterService.setNodeConnectionsService(nodeConnectionsService);
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.getTaskManager().setTaskCancellationService(new TaskCancellationService(transportService));
transportService.start();
assert localNodeFactory.getNode() != null;
assert transportService.getLocalNode().equals(localNodeFactory.getNode()) : "transportService has a different local node than the factory provided";
injector.getInstance(PeerRecoverySourceService.class).start();
// Load (and maybe upgrade) the metadata stored on disk
final GatewayMetaState gatewayMetaState = injector.getInstance(GatewayMetaState.class);
gatewayMetaState.start(settings(), transportService, clusterService, injector.getInstance(MetaStateService.class), injector.getInstance(MetadataIndexUpgradeService.class), injector.getInstance(MetadataUpgrader.class), injector.getInstance(PersistedClusterStateService.class));
if (Assertions.ENABLED) {
try {
assert injector.getInstance(MetaStateService.class).loadFullState().v1().isEmpty();
final NodeMetadata nodeMetadata = NodeMetadata.FORMAT.loadLatestState(logger, NamedXContentRegistry.EMPTY, nodeEnvironment.nodeDataPaths());
assert nodeMetadata != null;
assert nodeMetadata.nodeVersion().equals(Version.CURRENT);
assert nodeMetadata.nodeId().equals(localNodeFactory.getNode().getId());
} catch (IOException e) {
assert false : e;
}
}
// 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.
final Metadata onDiskMetadata = gatewayMetaState.getPersistedState().getLastAcceptedState().metadata();
// this is never null
assert onDiskMetadata != null : "metadata is null but shouldn't";
validateNodeBeforeAcceptingRequests(new BootstrapContext(environment, onDiskMetadata), transportService.boundAddress(), pluginsService.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
// start before cluster service so that it can set initial state on ClusterApplierService
discovery.start();
clusterService.start();
assert clusterService.localNode().equals(localNodeFactory.getNode()) : "clusterService has a different local node than the factory provided";
transportService.acceptIncomingRequests();
discovery.startInitialJoin();
final TimeValue initialStateTimeout = DiscoverySettings.INITIAL_STATE_TIMEOUT_SETTING.get(settings());
configureNodeAndClusterIdStateListener(clusterService);
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());
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();
} catch (InterruptedException e) {
throw new OpenSearchTimeoutException("Interrupted while waiting for initial discovery state");
}
}
}
injector.getInstance(HttpServerTransport.class).start();
if (WRITE_PORTS_FILE_SETTING.get(settings())) {
TransportService transport = injector.getInstance(TransportService.class);
writePortsFile("transport", transport.boundAddress());
HttpServerTransport http = injector.getInstance(HttpServerTransport.class);
writePortsFile("http", http.boundAddress());
}
logger.info("started");
pluginsService.filterPlugins(ClusterPlugin.class).forEach(ClusterPlugin::onNodeStarted);
return this;
}
use of org.opensearch.common.component.LifecycleComponent in project OpenSearch by opensearch-project.
the class Node method close.
// During concurrent close() calls we want to make sure that all of them return after the node has completed it's shutdown cycle.
// If not, the hook that is added in Bootstrap#setup() will be useless:
// close() might not be executed, in case another (for example api) call to close() has already set some lifecycles to stopped.
// In this case the process will be terminated even if the first call to close() has not finished yet.
@Override
public synchronized void close() throws IOException {
synchronized (lifecycle) {
if (lifecycle.started()) {
stop();
}
if (!lifecycle.moveToClosed()) {
return;
}
}
logger.info("closing ...");
List<Closeable> toClose = new ArrayList<>();
StopWatch stopWatch = new StopWatch("node_close");
toClose.add(() -> stopWatch.start("node_service"));
toClose.add(nodeService);
toClose.add(() -> stopWatch.stop().start("http"));
toClose.add(injector.getInstance(HttpServerTransport.class));
toClose.add(() -> stopWatch.stop().start("snapshot_service"));
toClose.add(injector.getInstance(SnapshotsService.class));
toClose.add(injector.getInstance(SnapshotShardsService.class));
toClose.add(injector.getInstance(RepositoriesService.class));
toClose.add(() -> stopWatch.stop().start("client"));
Releasables.close(injector.getInstance(Client.class));
toClose.add(() -> stopWatch.stop().start("indices_cluster"));
toClose.add(injector.getInstance(IndicesClusterStateService.class));
toClose.add(() -> stopWatch.stop().start("indices"));
toClose.add(injector.getInstance(IndicesService.class));
// close filter/fielddata caches after indices
toClose.add(injector.getInstance(IndicesStore.class));
toClose.add(injector.getInstance(PeerRecoverySourceService.class));
toClose.add(() -> stopWatch.stop().start("cluster"));
toClose.add(injector.getInstance(ClusterService.class));
toClose.add(() -> stopWatch.stop().start("node_connections_service"));
toClose.add(injector.getInstance(NodeConnectionsService.class));
toClose.add(() -> stopWatch.stop().start("discovery"));
toClose.add(injector.getInstance(Discovery.class));
toClose.add(() -> stopWatch.stop().start("monitor"));
toClose.add(nodeService.getMonitorService());
toClose.add(() -> stopWatch.stop().start("fsHealth"));
toClose.add(injector.getInstance(FsHealthService.class));
toClose.add(() -> stopWatch.stop().start("gateway"));
toClose.add(injector.getInstance(GatewayService.class));
toClose.add(() -> stopWatch.stop().start("search"));
toClose.add(injector.getInstance(SearchService.class));
toClose.add(() -> stopWatch.stop().start("transport"));
toClose.add(injector.getInstance(TransportService.class));
for (LifecycleComponent plugin : pluginLifecycleComponents) {
toClose.add(() -> stopWatch.stop().start("plugin(" + plugin.getClass().getName() + ")"));
toClose.add(plugin);
}
toClose.addAll(pluginsService.filterPlugins(Plugin.class));
toClose.add(() -> stopWatch.stop().start("script"));
toClose.add(injector.getInstance(ScriptService.class));
toClose.add(() -> stopWatch.stop().start("thread_pool"));
toClose.add(() -> injector.getInstance(ThreadPool.class).shutdown());
// Don't call shutdownNow here, it might break ongoing operations on Lucene indices.
// See https://issues.apache.org/jira/browse/LUCENE-7248. We call shutdownNow in
// awaitClose if the node doesn't finish closing within the specified time.
toClose.add(() -> stopWatch.stop().start("gateway_meta_state"));
toClose.add(injector.getInstance(GatewayMetaState.class));
toClose.add(() -> stopWatch.stop().start("node_environment"));
toClose.add(injector.getInstance(NodeEnvironment.class));
toClose.add(stopWatch::stop);
if (logger.isTraceEnabled()) {
toClose.add(() -> logger.trace("Close times for each service:\n{}", stopWatch.prettyPrint()));
}
IOUtils.close(toClose);
logger.info("closed");
}
Aggregations