Examples with ResourceHandlerException org.apache.hadoop.yarn.server.nodemanager.containermanager.linux.resources.ResourceHandlerException used on opensource projects

Example 1 with ResourceHandlerException

use of org.apache.hadoop.yarn.server.nodemanager.containermanager.linux.resources.ResourceHandlerException in project hadoop by apache.

the class LinuxContainerExecutor method launchContainer.

@Override
public int launchContainer(ContainerStartContext ctx) throws IOException {
    Container container = ctx.getContainer();
    Path nmPrivateContainerScriptPath = ctx.getNmPrivateContainerScriptPath();
    Path nmPrivateTokensPath = ctx.getNmPrivateTokensPath();
    String user = ctx.getUser();
    String appId = ctx.getAppId();
    Path containerWorkDir = ctx.getContainerWorkDir();
    List<String> localDirs = ctx.getLocalDirs();
    List<String> logDirs = ctx.getLogDirs();
    List<String> filecacheDirs = ctx.getFilecacheDirs();
    List<String> userLocalDirs = ctx.getUserLocalDirs();
    List<String> containerLocalDirs = ctx.getContainerLocalDirs();
    List<String> containerLogDirs = ctx.getContainerLogDirs();
    Map<Path, List<String>> localizedResources = ctx.getLocalizedResources();
    verifyUsernamePattern(user);
    String runAsUser = getRunAsUser(user);
    ContainerId containerId = container.getContainerId();
    String containerIdStr = containerId.toString();
    resourcesHandler.preExecute(containerId, container.getResource());
    String resourcesOptions = resourcesHandler.getResourcesOption(containerId);
    String tcCommandFile = null;
    try {
        if (resourceHandlerChain != null) {
            List<PrivilegedOperation> ops = resourceHandlerChain.preStart(container);
            if (ops != null) {
                List<PrivilegedOperation> resourceOps = new ArrayList<>();
                resourceOps.add(new PrivilegedOperation(PrivilegedOperation.OperationType.ADD_PID_TO_CGROUP, resourcesOptions));
                for (PrivilegedOperation op : ops) {
                    switch(op.getOperationType()) {
                        case ADD_PID_TO_CGROUP:
                            resourceOps.add(op);
                            break;
                        case TC_MODIFY_STATE:
                            tcCommandFile = op.getArguments().get(0);
                            break;
                        default:
                            LOG.warn("PrivilegedOperation type unsupported in launch: " + op.getOperationType());
                    }
                }
                if (resourceOps.size() > 1) {
                    //squash resource operations
                    try {
                        PrivilegedOperation operation = PrivilegedOperationExecutor.squashCGroupOperations(resourceOps);
                        resourcesOptions = operation.getArguments().get(0);
                    } catch (PrivilegedOperationException e) {
                        LOG.error("Failed to squash cgroup operations!", e);
                        throw new ResourceHandlerException("Failed to squash cgroup operations!");
                    }
                }
            }
        }
    } catch (ResourceHandlerException e) {
        LOG.error("ResourceHandlerChain.preStart() failed!", e);
        throw new IOException("ResourceHandlerChain.preStart() failed!", e);
    }
    try {
        Path pidFilePath = getPidFilePath(containerId);
        if (pidFilePath != null) {
            List<String> prefixCommands = new ArrayList<>();
            ContainerRuntimeContext.Builder builder = new ContainerRuntimeContext.Builder(container);
            addSchedPriorityCommand(prefixCommands);
            if (prefixCommands.size() > 0) {
                builder.setExecutionAttribute(CONTAINER_LAUNCH_PREFIX_COMMANDS, prefixCommands);
            }
            builder.setExecutionAttribute(LOCALIZED_RESOURCES, localizedResources).setExecutionAttribute(RUN_AS_USER, runAsUser).setExecutionAttribute(USER, user).setExecutionAttribute(APPID, appId).setExecutionAttribute(CONTAINER_ID_STR, containerIdStr).setExecutionAttribute(CONTAINER_WORK_DIR, containerWorkDir).setExecutionAttribute(NM_PRIVATE_CONTAINER_SCRIPT_PATH, nmPrivateContainerScriptPath).setExecutionAttribute(NM_PRIVATE_TOKENS_PATH, nmPrivateTokensPath).setExecutionAttribute(PID_FILE_PATH, pidFilePath).setExecutionAttribute(LOCAL_DIRS, localDirs).setExecutionAttribute(LOG_DIRS, logDirs).setExecutionAttribute(FILECACHE_DIRS, filecacheDirs).setExecutionAttribute(USER_LOCAL_DIRS, userLocalDirs).setExecutionAttribute(CONTAINER_LOCAL_DIRS, containerLocalDirs).setExecutionAttribute(CONTAINER_LOG_DIRS, containerLogDirs).setExecutionAttribute(RESOURCES_OPTIONS, resourcesOptions);
            if (tcCommandFile != null) {
                builder.setExecutionAttribute(TC_COMMAND_FILE, tcCommandFile);
            }
            linuxContainerRuntime.launchContainer(builder.build());
        } else {
            LOG.info("Container was marked as inactive. Returning terminated error");
            return ExitCode.TERMINATED.getExitCode();
        }
    } catch (ContainerExecutionException e) {
        int exitCode = e.getExitCode();
        LOG.warn("Exit code from container " + containerId + " is : " + exitCode);
        // output
        if (exitCode != ExitCode.FORCE_KILLED.getExitCode() && exitCode != ExitCode.TERMINATED.getExitCode()) {
            LOG.warn("Exception from container-launch with container ID: " + containerId + " and exit code: " + exitCode, e);
            StringBuilder builder = new StringBuilder();
            builder.append("Exception from container-launch.\n");
            builder.append("Container id: " + containerId + "\n");
            builder.append("Exit code: " + exitCode + "\n");
            if (!Optional.fromNullable(e.getErrorOutput()).or("").isEmpty()) {
                builder.append("Exception message: " + e.getErrorOutput() + "\n");
            }
            builder.append("Stack trace: " + StringUtils.stringifyException(e) + "\n");
            if (!e.getOutput().isEmpty()) {
                builder.append("Shell output: " + e.getOutput() + "\n");
            }
            String diagnostics = builder.toString();
            logOutput(diagnostics);
            container.handle(new ContainerDiagnosticsUpdateEvent(containerId, diagnostics));
        } else {
            container.handle(new ContainerDiagnosticsUpdateEvent(containerId, "Container killed on request. Exit code is " + exitCode));
        }
        return exitCode;
    } finally {
        resourcesHandler.postExecute(containerId);
        try {
            if (resourceHandlerChain != null) {
                resourceHandlerChain.postComplete(containerId);
            }
        } catch (ResourceHandlerException e) {
            LOG.warn("ResourceHandlerChain.postComplete failed for " + "containerId: " + containerId + ". Exception: " + e);
        }
    }
    return 0;
}

Example 2 with ResourceHandlerException

use of org.apache.hadoop.yarn.server.nodemanager.containermanager.linux.resources.ResourceHandlerException in project hadoop by apache.

the class LinuxContainerExecutor method init.

@Override
public void init() throws IOException {
    Configuration conf = super.getConf();
    // verify configuration/permissions and exit
    try {
        PrivilegedOperation checkSetupOp = new PrivilegedOperation(PrivilegedOperation.OperationType.CHECK_SETUP);
        PrivilegedOperationExecutor privilegedOperationExecutor = PrivilegedOperationExecutor.getInstance(conf);
        privilegedOperationExecutor.executePrivilegedOperation(checkSetupOp, false);
    } catch (PrivilegedOperationException e) {
        int exitCode = e.getExitCode();
        LOG.warn("Exit code from container executor initialization is : " + exitCode, e);
        throw new IOException("Linux container executor not configured properly" + " (error=" + exitCode + ")", e);
    }
    try {
        resourceHandlerChain = ResourceHandlerModule.getConfiguredResourceHandlerChain(conf);
        if (LOG.isDebugEnabled()) {
            LOG.debug("Resource handler chain enabled = " + (resourceHandlerChain == null));
        }
        if (resourceHandlerChain != null) {
            LOG.debug("Bootstrapping resource handler chain");
            resourceHandlerChain.bootstrap(conf);
        }
    } catch (ResourceHandlerException e) {
        LOG.error("Failed to bootstrap configured resource subsystems! ", e);
        throw new IOException("Failed to bootstrap configured resource subsystems!");
    }
    try {
        if (linuxContainerRuntime == null) {
            LinuxContainerRuntime runtime = new DelegatingLinuxContainerRuntime();
            runtime.initialize(conf);
            this.linuxContainerRuntime = runtime;
        }
    } catch (ContainerExecutionException e) {
        LOG.error("Failed to initialize linux container runtime(s)!", e);
        throw new IOException("Failed to initialize linux container runtime(s)!");
    }
    resourcesHandler.init(this);
}