tillrohrmann commented on a change in pull request #11353: [FLINK-16438][yarn] Make YarnResourceManager starts workers using WorkerResourceSpec requested by SlotManager URL: https://github.com/apache/flink/pull/11353#discussion_r403090988
########## File path: flink-kubernetes/src/main/java/org/apache/flink/kubernetes/KubernetesResourceManager.java ########## @@ -232,57 +229,75 @@ private void recoverWorkerNodesFromPreviousAttempts() throws ResourceManagerExce ++currentMaxAttemptId); } - private void requestKubernetesPod() { - numPendingPodRequests++; + private void requestKubernetesPod(WorkerResourceSpec workerResourceSpec) { + final KubernetesTaskManagerParameters parameters = + createKubernetesTaskManagerParameters(workerResourceSpec); + + podWorkerResources.put(parameters.getPodName(), workerResourceSpec); + final int pendingWorkerNum = pendingWorkerCounter.increaseAndGet(workerResourceSpec); log.info("Requesting new TaskManager pod with <{},{}>. Number pending requests {}.", - defaultMemoryMB, - defaultCpus, - numPendingPodRequests); + parameters.getTaskManagerMemoryMB(), + parameters.getTaskManagerCPU(), + pendingWorkerNum); + log.info("TaskManager {} will be started with {}.", parameters.getPodName(), workerResourceSpec); + + final KubernetesPod taskManagerPod = + KubernetesTaskManagerFactory.createTaskManagerComponent(parameters); + kubeClient.createTaskManagerPod(taskManagerPod); + } + + private KubernetesTaskManagerParameters createKubernetesTaskManagerParameters(WorkerResourceSpec workerResourceSpec) { + // TODO: need to unset process/flink memory size from configuration if dynamic worker resource is activated + final TaskExecutorProcessSpec taskExecutorProcessSpec = + TaskExecutorProcessUtils.processSpecFromWorkerResourceSpec(flinkConfig, workerResourceSpec); final String podName = String.format( TASK_MANAGER_POD_FORMAT, clusterId, currentMaxAttemptId, ++currentMaxPodId); + final ContaineredTaskManagerParameters taskManagerParameters = + ContaineredTaskManagerParameters.create(flinkConfig, taskExecutorProcessSpec); + final String dynamicProperties = BootstrapTools.getDynamicPropertiesAsString(flinkClientConfig, flinkConfig); - final KubernetesTaskManagerParameters kubernetesTaskManagerParameters = new KubernetesTaskManagerParameters( + return new KubernetesTaskManagerParameters( flinkConfig, podName, dynamicProperties, taskManagerParameters); - - final KubernetesPod taskManagerPod = - KubernetesTaskManagerFactory.createTaskManagerComponent(kubernetesTaskManagerParameters); - - log.info("TaskManager {} will be started with {}.", podName, taskExecutorProcessSpec); - kubeClient.createTaskManagerPod(taskManagerPod); } /** * Request new pod if pending pods cannot satisfy pending slot requests. */ - private void requestKubernetesPodIfRequired() { - final int requiredTaskManagers = getNumberRequiredTaskManagers(); + private void requestKubernetesPodIfRequired(WorkerResourceSpec workerResourceSpec) { + final int requiredTaskManagers = getPendingWorkerNums().get(workerResourceSpec); + final int pendingWorkerNum = pendingWorkerCounter.getNum(workerResourceSpec); - if (requiredTaskManagers > numPendingPodRequests) { - requestKubernetesPod(); + if (requiredTaskManagers > pendingWorkerNum) { + requestKubernetesPod(workerResourceSpec); } } private void removePodIfTerminated(KubernetesPod pod) { if (pod.isTerminated()) { kubeClient.stopPod(pod.getName()); - final KubernetesWorkerNode kubernetesWorkerNode = workerNodes.remove(new ResourceID(pod.getName())); - if (kubernetesWorkerNode != null) { - requestKubernetesPodIfRequired(); + final WorkerResourceSpec workerResourceSpec = removeWorkerNodeAndResourceSpec(new ResourceID(pod.getName())); + if (workerResourceSpec != null) { + requestKubernetesPodIfRequired(workerResourceSpec); } } } + private WorkerResourceSpec removeWorkerNodeAndResourceSpec(ResourceID resourceId) { Review comment: Nit: Changing the return type to `Optional<WorkerResourceSpec>` could make the contract of this method a bit more explicit. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services