surahman commented on issue #3724: URL: https://github.com/apache/incubator-heron/issues/3724#issuecomment-974547209
I think I have completed as much testing as I can to ensure this works. Here are the `StatefulSet`s for the Acking topology which consists of two `executor` Pods and one `manager` Pod. I can create a PR whenever but please keep in mind that this builds upon the [PVC PR](https://github.com/apache/incubator-heron/pull/3725). <details><summary>Manager</summary> ```yaml apiVersion: apps/v1 kind: StatefulSet metadata: creationTimestamp: "2021-11-19T23:43:09Z" generation: 1 name: acking-manager namespace: default resourceVersion: "794" uid: 81606d2d-f78e-41c5-9956-8225baa5cf27 spec: podManagementPolicy: Parallel replicas: 1 revisionHistoryLimit: 10 selector: matchLabels: app: heron topology: acking serviceName: acking template: metadata: annotations: prometheus.io/port: "8080" prometheus.io/scrape: "true" creationTimestamp: null labels: app: heron topology: acking spec: containers: - command: - sh - -c - './heron-core/bin/heron-downloader-config kubernetes && ./heron-core/bin/heron-downloader distributedlog://zookeeper:2181/heronbkdl/acking-saad-tag-0-7762179603298019532.tar.gz . && SHARD_ID=${POD_NAME##*-} && echo shardId=${SHARD_ID} && ./heron-core/bin/heron-executor --topology-name=acking --topology-id=acking39da483e-aed1-4701-af75-f80edeb12808 --topology-defn-file=acking.defn --state-manager-connection=zookeeper:2181 --state-manager-root=/heron --state-manager-config-file=./heron-conf/statemgr.yaml --tmanager-binary=./heron-core/bin/heron-tmanager --stmgr-binary=./heron-core/bin/heron-stmgr --metrics-manager-classpath=./heron-core/lib/metricsmgr/* --instance-jvm-opts="LVhYOitIZWFwRHVtcE9uT3V0T2ZNZW1vcnlFcnJvcg(61)(61)" --classpath=heron-api-examples.jar --heron-internals-config-file=./heron-conf/heron_internals.yaml --override-config-file=./heron-conf/override.yaml --component-ram-map=exclaim1:1073741824,word:1073741824 --component-jvm-opts="" --pkg-type=jar --topology-binary-file=heron-api-examples.jar --heron-java-home=$JAVA_HOME --heron-shell-binary=./heron-core/bin/heron-shell --cluster=kubernetes --role=saad --environment=default --instance-classpath=./heron-core/lib/instance/* --metrics-sinks-config-file=./heron-conf/metrics_sinks.yaml --scheduler-classpath=./heron-core/lib/scheduler/*:./heron-core/lib/packing/*:./heron-core/lib/statemgr/* --python-instance-binary=./heron-core/bin/heron-python-instance --cpp-instance-binary=./heron-core/bin/heron-cpp-instance --metricscache-manager-classpath=./heron-core/lib/metricscachemgr/* --metricscache-manager-mode=disabled --is-stateful=false --checkpoint-manager-classpath=./heron-core/lib/ckptmgr/*:./heron-core/lib/statefulstorage/*: --stateful-config-file=./heron-conf/stateful.yaml --checkpoint-manager-ram=1073741824 --health-manager-mode=disabled --health-manager-classpath=./heron-core/lib/healthmgr/* --shard=$SHARD_ID --server-port=6001 --tmanager-controller-port=6002 --tmanager-stats-port=6003 --shell-port=6004 --metrics-manager-port=6005 --scheduler-port=6006 --metricscache-manager-server-port=6007 --metricscache-manager-stats-port=6008 --checkpoint-manager-port=6009' env: - name: HOST valueFrom: fieldRef: apiVersion: v1 fieldPath: status.podIP - name: POD_NAME valueFrom: fieldRef: apiVersion: v1 fieldPath: metadata.name - name: var_one value: variable one - name: var_three value: variable three - name: var_two value: variable two image: apache/heron:testbuild imagePullPolicy: IfNotPresent name: manager ports: - containerPort: 5555 name: tcp-port-kept protocol: TCP - containerPort: 5556 name: udp-port-kept protocol: UDP - containerPort: 6001 name: server protocol: TCP - containerPort: 6002 name: tmanager-ctl protocol: TCP - containerPort: 6003 name: tmanager-stats protocol: TCP - containerPort: 6004 name: shell-port protocol: TCP - containerPort: 6005 name: metrics-mgr protocol: TCP - containerPort: 6006 name: scheduler protocol: TCP - containerPort: 6007 name: metrics-cache-m protocol: TCP - containerPort: 6008 name: metrics-cache-s protocol: TCP - containerPort: 6009 name: ckptmgr protocol: TCP resources: limits: cpu: "3" memory: 4Gi securityContext: allowPrivilegeEscalation: false terminationMessagePath: /dev/termination-log terminationMessagePolicy: File volumeMounts: - mountPath: /shared_volume name: shared-volume - image: alpine imagePullPolicy: Always name: sidecar-container resources: {} terminationMessagePath: /dev/termination-log terminationMessagePolicy: File volumeMounts: - mountPath: /shared_volume name: shared-volume dnsPolicy: ClusterFirst restartPolicy: Always schedulerName: default-scheduler securityContext: {} terminationGracePeriodSeconds: 0 tolerations: - effect: NoExecute key: node.kubernetes.io/not-ready operator: Exists tolerationSeconds: 10 - effect: NoExecute key: node.kubernetes.io/unreachable operator: Exists tolerationSeconds: 10 volumes: - emptyDir: {} name: shared-volume updateStrategy: rollingUpdate: partition: 0 type: RollingUpdate status: collisionCount: 0 currentReplicas: 1 currentRevision: acking-manager-75dcc4c647 observedGeneration: 1 replicas: 1 updateRevision: acking-manager-75dcc4c647 updatedReplicas: 1 ``` </details> <details><summary>Executors</summary> ```yaml apiVersion: apps/v1 kind: StatefulSet metadata: creationTimestamp: "2021-11-19T23:43:09Z" generation: 1 name: acking-executors namespace: default resourceVersion: "789" uid: ee6bc457-6917-48a5-b31d-33b9b3e8cce0 spec: podManagementPolicy: Parallel replicas: 2 revisionHistoryLimit: 10 selector: matchLabels: app: heron topology: acking serviceName: acking template: metadata: annotations: prometheus.io/port: "8080" prometheus.io/scrape: "true" creationTimestamp: null labels: app: heron topology: acking spec: containers: - command: - sh - -c - './heron-core/bin/heron-downloader-config kubernetes && ./heron-core/bin/heron-downloader distributedlog://zookeeper:2181/heronbkdl/acking-saad-tag-0-7762179603298019532.tar.gz . && SHARD_ID=$((${POD_NAME##*-} + 1)) && echo shardId=${SHARD_ID} && ./heron-core/bin/heron-executor --topology-name=acking --topology-id=acking39da483e-aed1-4701-af75-f80edeb12808 --topology-defn-file=acking.defn --state-manager-connection=zookeeper:2181 --state-manager-root=/heron --state-manager-config-file=./heron-conf/statemgr.yaml --tmanager-binary=./heron-core/bin/heron-tmanager --stmgr-binary=./heron-core/bin/heron-stmgr --metrics-manager-classpath=./heron-core/lib/metricsmgr/* --instance-jvm-opts="LVhYOitIZWFwRHVtcE9uT3V0T2ZNZW1vcnlFcnJvcg(61)(61)" --classpath=heron-api-examples.jar --heron-internals-config-file=./heron-conf/heron_internals.yaml --override-config-file=./heron-conf/override.yaml --component-ram-map=exclaim1:1073741824,word:1073741824 --component-jvm-opts="" --pkg-type=jar --topology-binary-file=heron-api-examples.jar --heron-java-home=$JAVA_HOME --heron-shell-binary=./heron-core/bin/heron-shell --cluster=kubernetes --role=saad --environment=default --instance-classpath=./heron-core/lib/instance/* --metrics-sinks-config-file=./heron-conf/metrics_sinks.yaml --scheduler-classpath=./heron-core/lib/scheduler/*:./heron-core/lib/packing/*:./heron-core/lib/statemgr/* --python-instance-binary=./heron-core/bin/heron-python-instance --cpp-instance-binary=./heron-core/bin/heron-cpp-instance --metricscache-manager-classpath=./heron-core/lib/metricscachemgr/* --metricscache-manager-mode=disabled --is-stateful=false --checkpoint-manager-classpath=./heron-core/lib/ckptmgr/*:./heron-core/lib/statefulstorage/*: --stateful-config-file=./heron-conf/stateful.yaml --checkpoint-manager-ram=1073741824 --health-manager-mode=disabled --health-manager-classpath=./heron-core/lib/healthmgr/* --shard=$SHARD_ID --server-port=6001 --tmanager-controller-port=6002 --tmanager-stats-port=6003 --shell-port=6004 --metrics-manager-port=6005 --scheduler-port=6006 --metricscache-manager-server-port=6007 --metricscache-manager-stats-port=6008 --checkpoint-manager-port=6009' env: - name: HOST valueFrom: fieldRef: apiVersion: v1 fieldPath: status.podIP - name: POD_NAME valueFrom: fieldRef: apiVersion: v1 fieldPath: metadata.name - name: var_one value: variable one - name: var_three value: variable three - name: var_two value: variable two image: apache/heron:testbuild imagePullPolicy: IfNotPresent name: executor ports: - containerPort: 5555 name: tcp-port-kept protocol: TCP - containerPort: 5556 name: udp-port-kept protocol: UDP - containerPort: 6001 name: server protocol: TCP - containerPort: 6002 name: tmanager-ctl protocol: TCP - containerPort: 6003 name: tmanager-stats protocol: TCP - containerPort: 6004 name: shell-port protocol: TCP - containerPort: 6005 name: metrics-mgr protocol: TCP - containerPort: 6006 name: scheduler protocol: TCP - containerPort: 6007 name: metrics-cache-m protocol: TCP - containerPort: 6008 name: metrics-cache-s protocol: TCP - containerPort: 6009 name: ckptmgr protocol: TCP resources: limits: cpu: "3" memory: 4Gi requests: cpu: "3" memory: 4Gi securityContext: allowPrivilegeEscalation: false terminationMessagePath: /dev/termination-log terminationMessagePolicy: File volumeMounts: - mountPath: /shared_volume name: shared-volume - image: alpine imagePullPolicy: Always name: sidecar-container resources: {} terminationMessagePath: /dev/termination-log terminationMessagePolicy: File volumeMounts: - mountPath: /shared_volume name: shared-volume dnsPolicy: ClusterFirst restartPolicy: Always schedulerName: default-scheduler securityContext: {} terminationGracePeriodSeconds: 0 tolerations: - effect: NoExecute key: node.kubernetes.io/not-ready operator: Exists tolerationSeconds: 10 - effect: NoExecute key: node.kubernetes.io/unreachable operator: Exists tolerationSeconds: 10 volumes: - emptyDir: {} name: shared-volume updateStrategy: rollingUpdate: partition: 0 type: RollingUpdate status: collisionCount: 0 currentReplicas: 2 currentRevision: acking-executors-588597559c observedGeneration: 1 replicas: 2 updateRevision: acking-executors-588597559c updatedReplicas: 2 ``` </details> -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
