xintongsong commented on a change in pull request #11323: [FLINK-16439][k8s] Make KubernetesResourceManager starts workers using WorkerResourceSpec requested by SlotManager URL: https://github.com/apache/flink/pull/11323#discussion_r410838053
########## File path: flink-kubernetes/src/main/java/org/apache/flink/kubernetes/KubernetesResourceManager.java ########## @@ -237,57 +230,73 @@ private void recoverWorkerNodesFromPreviousAttempts() throws ResourceManagerExce ++currentMaxAttemptId); } - private void requestKubernetesPod() { - numPendingPodRequests++; + private void requestKubernetesPod(WorkerResourceSpec workerResourceSpec) { + final KubernetesTaskManagerParameters parameters = + createKubernetesTaskManagerParameters(workerResourceSpec); + + final KubernetesPod taskManagerPod = + KubernetesTaskManagerFactory.createTaskManagerComponent(parameters); + kubeClient.createTaskManagerPod(taskManagerPod); + + podWorkerResources.put(parameters.getPodName(), workerResourceSpec); + final int pendingWorkerNum = notifyNewWorkerRequested(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); + } + + private KubernetesTaskManagerParameters createKubernetesTaskManagerParameters(WorkerResourceSpec workerResourceSpec) { + 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 pendingWorkerNum = getNumPendingWorkersFor(workerResourceSpec); + int requiredTaskManagers = getRequiredResources().get(workerResourceSpec); - while (requiredTaskManagers > numPendingPodRequests) { - requestKubernetesPod(); + while (requiredTaskManagers-- > pendingWorkerNum) { + requestKubernetesPod(workerResourceSpec); } } private void removePodIfTerminated(KubernetesPod pod) { if (pod.isTerminated()) { kubeClient.stopPod(pod.getName()); Review comment: Thanks all for the feedbacks and good discussion. @zhengcanbin, I've added more checks to avoid relying on the order and non-duplication of received events. @tillrohrmann, I've also added more test cases verifying the pending worker counter with out-of-ordered and duplicated events. ---------------------------------------------------------------- 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