|
=== RUN TestAdjacentAPI |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env using existing cluster |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env automatically acquiring client configuration |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env installing CRDs |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env reading CRDs from path {"path": "<REPRO_ROOT>/source/1.5.0/deploy/operator/config/crd/bases"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "nvidia.com_dynamocomponentdeployments.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "nvidia.com_dynamographdeploymentrequests.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "nvidia.com_dynamographdeployments.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "nvidia.com_dynamographdeploymentscalingadapters.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "nvidia.com_dynamomodels.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "nvidia.com_dynamoworkermetadatas.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env reading CRDs from path {"path": "<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/testing/prometheus"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "prometheusrule.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "servicemonitor.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env reading CRDs from path {"path": "<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/testing/inference.networking.k8s.io"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "inferencepools.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env reading CRDs from path {"path": "<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/testing/grove.io"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "clustertopologybindings.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "grove.io_clustertopologybindings.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "grove.io_podcliques.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "grove.io_podcliquescalinggroups.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "grove.io_podcliquesets.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "grove.io_podgangmaps.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "podcliques.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "podcliquescalinggroups.yaml"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env read CRDs from file {"file": "podcliquesets.yaml"} |
|
2026-10-17T10:33:26+08:00 INFO controller-runtime.test-env there are more than one CRD definitions with the same <Group, Version, Kind, Name> {"GVKN": {"GVK":{"Group":"apiextensions.k8s.io","Version":"v1","Kind":"CustomResourceDefinition"},"Name":"clustertopologybindings.grove.io"}} |
|
2026-10-17T10:33:26+08:00 INFO controller-runtime.test-env there are more than one CRD definitions with the same <Group, Version, Kind, Name> {"GVKN": {"GVK":{"Group":"apiextensions.k8s.io","Version":"v1","Kind":"CustomResourceDefinition"},"Name":"podcliques.grove.io"}} |
|
2026-10-17T10:33:26+08:00 INFO controller-runtime.test-env there are more than one CRD definitions with the same <Group, Version, Kind, Name> {"GVKN": {"GVK":{"Group":"apiextensions.k8s.io","Version":"v1","Kind":"CustomResourceDefinition"},"Name":"podcliquescalinggroups.grove.io"}} |
|
2026-10-17T10:33:26+08:00 INFO controller-runtime.test-env there are more than one CRD definitions with the same <Group, Version, Kind, Name> {"GVKN": {"GVK":{"Group":"apiextensions.k8s.io","Version":"v1","Kind":"CustomResourceDefinition"},"Name":"podcliquesets.grove.io"}} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "inferencepools.inference.networking.k8s.io"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "inferencepools.inference.networking.k8s.io"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "podcliques.grove.io"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "podcliques.grove.io"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "dynamocomponentdeployments.nvidia.com"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "dynamocomponentdeployments.nvidia.com"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "dynamographdeployments.nvidia.com"} |
|
2026-10-17T10:33:26+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "dynamographdeployments.nvidia.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "dynamoworkermetadatas.nvidia.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "dynamoworkermetadatas.nvidia.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "prometheusrules.monitoring.coreos.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "prometheusrules.monitoring.coreos.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "clustertopologybindings.grove.io"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "clustertopologybindings.grove.io"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "podcliquescalinggroups.grove.io"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "podcliquescalinggroups.grove.io"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "podcliquesets.grove.io"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "podcliquesets.grove.io"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "podgangmaps.grove.io"} |
|
2026-10-17T10:33:27+08:00 INFO unrecognized format "int32" |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "dynamographdeploymentrequests.nvidia.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "dynamographdeploymentrequests.nvidia.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "dynamographdeploymentscalingadapters.nvidia.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "dynamographdeploymentscalingadapters.nvidia.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "dynamomodels.nvidia.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "dynamomodels.nvidia.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing CRD {"crd": "servicemonitors.monitoring.coreos.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env CRD already exists, updating {"crd": "servicemonitors.monitoring.coreos.com"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "inference.networking.k8s.io/v1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "grove.io/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1beta1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1beta1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "monitoring.coreos.com/v1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "grove.io/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "grove.io/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "grove.io/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "grove.io/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1beta1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1beta1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "nvidia.com/v1alpha1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env adding API in waitlist {"GV": "monitoring.coreos.com/v1"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing webhooks |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing mutating webhook {"webhook": "operatorenv-dynamo-operator-mutating"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env Webhook configuration already exists, updating {"webhook": "operatorenv-dynamo-operator-mutating"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env installing validating webhook {"webhook": "operatorenv-dynamo-operator-validating"} |
|
2026-10-17T10:33:27+08:00 DEBUG controller-runtime.test-env Webhook configuration already exists, updating {"webhook": "operatorenv-dynamo-operator-validating"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/validate/nvidia.com/v1beta1/dynamocomponentdeployments"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/validate-nvidia-com-v1alpha1-dynamocomponentdeployment"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/validate/nvidia.com/v1beta1/dynamographdeployments"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/validate-nvidia-com-v1alpha1-dynamomodel"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/validate-nvidia-com-v1beta1-dynamographdeploymentrequest"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/convert"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.builder Conversion webhook enabled {"GVK": "nvidia.com/v1beta1, Kind=DynamoGraphDeploymentRequest"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.builder Conversion webhook enabled {"GVK": "nvidia.com/v1beta1, Kind=DynamoGraphDeployment"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.builder Conversion webhook enabled {"GVK": "nvidia.com/v1beta1, Kind=DynamoComponentDeployment"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.builder Conversion webhook enabled {"GVK": "nvidia.com/v1beta1, Kind=DynamoGraphDeploymentScalingAdapter"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/mutate-nvidia-com-v1beta1-dynamocomponentdeployment"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/mutate/nvidia.com/v1beta1/dynamographdeployments"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/mutate-nvidia-com-v1beta1-dynamographdeploymentrequest"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Registering webhook {"path": "/mutate-core-v1-pod-checkpoint-restore"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Starting webhook server |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.certwatcher Updated current TLS certificate {"cert": "<TMP_PATH>", "key": "<TMP_PATH>"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.webhook Serving webhook server {"host": "127.0.0.1", "port": 64682} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.certwatcher Starting certificate poll+watcher {"cert": "<TMP_PATH>", "key": "<TMP_PATH>", "interval": "10s"} |
|
zz_adjacent_api_test.go:95: Candidate uses the SAME API server and existing objects; no historical state is recreated |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoComponentDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoComponentDeployment", "source": "kind source: *v2.HorizontalPodAutoscaler"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoComponentDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoComponentDeployment", "source": "kind source: *v1beta1.DynamoComponentDeployment"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "source": "kind source: *v1beta1.DynamoGraphDeployment"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoComponentDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoComponentDeployment", "source": "kind source: *v1.Deployment"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "source": "kind source: *v1alpha1.DynamoGraphDeploymentScalingAdapter"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoComponentDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoComponentDeployment", "source": "kind source: *v1.Service"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoComponentDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoComponentDeployment", "source": "kind source: *v1.Ingress"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "source": "kind source: *v1beta1.DynamoComponentDeployment"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "source": "kind source: *v1.Pod"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "source": "kind source: *v1alpha1.PodCliqueSet"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "source": "kind source: *v1.PersistentVolumeClaim"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "source": "kind source: *v1alpha1.PodClique"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "source": "kind source: *v1.Service"} |
|
2026-10-17T10:33:27+08:00 INFO Starting EventSource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "source": "kind source: *v1alpha1.PodCliqueScalingGroup"} |
|
2026-10-17T10:33:27+08:00 INFO controller-runtime.cache Warning: nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter |
|
2026-10-17T10:33:28+08:00 INFO Starting Controller {"controller": "DynamoComponentDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoComponentDeployment"} |
|
2026-10-17T10:33:28+08:00 INFO Starting workers {"controller": "DynamoComponentDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoComponentDeployment", "worker count": 1} |
|
2026-10-17T10:33:28+08:00 INFO Starting Controller {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment"} |
|
2026-10-17T10:33:28+08:00 INFO Starting workers {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "worker count": 1} |
|
2026-10-17T10:33:28+08:00 INFO admission.dynamographdeployment-validating-webhook validate update {"object": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "resource": {"group":"nvidia.com","version":"v1beta1","resource":"dynamographdeployments"}, "user": "admin", "requestID": "72280b3a-b5fc-4ac7-a1c1-25daca691502", "name": "adjacent-custom-1-5", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciling Grove resources {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "hasMultinode": false} |
|
2026-10-17T10:33:28+08:00 INFO K8s discovery is enabled {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-k8s-service-discovery","namespace":"operatorenv-zkk2r5v9"}, "kind": "ServiceAccount", "apiVersion": "v1", "type": "Normal", "reason": "UpdateServiceAccount", "action": "Update", "note": "Skipping update ServiceAccount operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Role found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 INFO Role spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-k8s-service-discovery-role","namespace":"operatorenv-zkk2r5v9"}, "kind": "Role", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRole", "action": "Update", "note": "Skipping update Role operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG No EPP service defined, skipping EPP resource reconciliation {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-k8s-service-discovery-binding","namespace":"operatorenv-zkk2r5v9"}, "kind": "RoleBinding", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRoleBinding", "action": "Update", "note": "Skipping update RoleBinding operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Unstructured spec changes detected {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5", "resourceType": "Unstructured", "diff": " map[string]any{\n \t\"replicas\": int64(1),\n \t\"template\": map[string]any{\n \t\t\"cliqueStartupType\": string(\"CliqueStartupTypeAnyOrder\"),\n \t\t\"cliques\": []any{\n \t\t\tmap[string]any{\n \t\t\t\t\"annotations\": map[string]any{\"nvidia.com/dynamo-discovery-backend\": string(\"kubernetes\"), \"nvidia.com/dynamo-operator-origin-version\": string(\"1.4.0\")},\n \t\t\t\t\"labels\": map[string]any{\n \t\t\t\t\t... // 5 identical entries\n \t\t\t\t\t\"nvidia.com/dynamo-namespace\": string(\"operatorenv-zkk2r5v9-adjacent-custom-1-5\"),\n \t\t\t\t\t\"nvidia.com/dynamo-sub-component-type\": string(\"prefill\"),\n+ \t\t\t\t\t\"nvidia.com/dynamo-worker-hash\": string(\"39ae5e0c\"),\n \t\t\t\t\t\"nvidia.com/metrics-enabled\": string(\"true\"),\n \t\t\t\t\t\"nvidia.com/selector\": string(\"adjacent-custom-1-5-sglangprefill\"),\n \t\t\t\t},\n \t\t\t\t\"name\": string(\"sglangprefill\"),\n \t\t\t\t\"spec\": map[string]any{\n \t\t\t\t\t\"minAvailable\": int64(1),\n \t\t\t\t\t\"podSpec\": map[string]any{\n \t\t\t\t\t\t\"containers\": []any{\n \t\t\t\t\t\t\tmap[string]any{\n \t\t\t\t\t\t\t\t\"args\": []any{string(\"--model-path\"), string(\"Qwen/Qwen3-0.6B\"), string(\"--disaggregation-mode\"), string(\"prefill\")},\n \t\t\t\t\t\t\t\t\"command\": []any{string(\"python3\"), string(\"-m\"), string(\"dynamo.sglang\")},\n \t\t\t\t\t\t\t\t\"env\": []any{\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_COMPONENT\"), \"value\": string(\"prefill\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_DISCOVERY_BACKEND\"), \"value\": string(\"kubernetes\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_FORWARDPASS_METRIC_PORT\"), \"value\": string(\"20380\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\n \t\t\t\t\t\t\t\t\t\t\"name\": string(\"DYN_HEALTH_CHECK_ENABLED\"),\n- \t\t\t\t\t\t\t\t\t\t\"value\": string(\"false\"),\n+ \t\t\t\t\t\t\t\t\t\t\"value\": string(\"true\"),\n \t\t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_NAMESPACE\"), \"value\": string(\"operatorenv-zkk2r5v9-adjacent-custom-1-5\")},\n+ \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_NAMESPACE_WORKER_SUFFIX\"), \"value\": string(\"39ae5e0c\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_PARENT_DGD_K8S_NAME\"), \"value\": string(\"adjacent-custom-1-5\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_PARENT_DGD_K8S_NAMESPACE\"), \"value\": string(\"operatorenv-zkk2r5v9\")},\n \t\t\t\t\t\t\t\t\t... // 9 identical elements\n \t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\"image\": string(\"registry.example.com/dynamo/sglang-runtime:v1.5.0-9aa3-repro\"),\n \t\t\t\t\t\t\t\t\"livenessProbe\": map[string]any{\n- \t\t\t\t\t\t\t\t\t\"failureThreshold\": int64(1),\n+ \t\t\t\t\t\t\t\t\t\"failureThreshold\": int64(3),\n \t\t\t\t\t\t\t\t\t\"httpGet\": map[string]any{\"path\": string(\"/live\"), \"port\": string(\"system\")},\n \t\t\t\t\t\t\t\t\t\"periodSeconds\": int64(5),\n \t\t\t\t\t\t\t\t\t\"timeoutSeconds\": int64(4),\n \t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\"name\": string(\"main\"),\n \t\t\t\t\t\t\t\t\"ports\": []any{map[string]any{\"containerPort\": int64(9090), \"name\": string(\"system\"), \"protocol\": string(\"TCP\")}, map[string]any{\"containerPort\": int64(19090), \"name\": string(\"nixl\"), \"protocol\": string(\"TCP\")}},\n \t\t\t\t\t\t\t\t... // 4 identical entries\n \t\t\t\t\t\t\t},\n \t\t\t\t\t\t},\n \t\t\t\t\t\t\"restartPolicy\": string(\"Always\"),\n \t\t\t\t\t\t\"securityContext\": map[string]any{\"fsGroup\": int64(1000)},\n \t\t\t\t\t\t... // 3 identical entries\n \t\t\t\t\t},\n \t\t\t\t\t\"replicas\": int64(2),\n \t\t\t\t\t\"roleName\": string(\"sglangprefill\"),\n \t\t\t\t},\n \t\t\t},\n \t\t\tmap[string]any{\n \t\t\t\t\"annotations\": map[string]any{\"nvidia.com/dynamo-discovery-backend\": string(\"kubernetes\"), \"nvidia.com/dynamo-operator-origin-version\": string(\"1.4.0\")},\n \t\t\t\t\"labels\": map[string]any{\n \t\t\t\t\t... // 5 identical entries\n \t\t\t\t\t\"nvidia.com/dynamo-namespace\": string(\"operatorenv-zkk2r5v9-adjacent-custom-1-5\"),\n \t\t\t\t\t\"nvidia.com/dynamo-sub-component-type\": string(\"decode\"),\n+ \t\t\t\t\t\"nvidia.com/dynamo-worker-hash\": string(\"39ae5e0c\"),\n \t\t\t\t\t\"nvidia.com/metrics-enabled\": string(\"true\"),\n \t\t\t\t\t\"nvidia.com/selector\": string(\"adjacent-custom-1-5-sglangdecode\"),\n \t\t\t\t},\n \t\t\t\t\"name\": string(\"sglangdecode\"),\n \t\t\t\t\"spec\": map[string]any{\n \t\t\t\t\t\"minAvailable\": int64(1),\n \t\t\t\t\t\"podSpec\": map[string]any{\n \t\t\t\t\t\t\"containers\": []any{\n \t\t\t\t\t\t\tmap[string]any{\n \t\t\t\t\t\t\t\t\"args\": []any{string(\"--model-path\"), string(\"Qwen/Qwen3-0.6B\"), string(\"--disaggregation-mode\"), string(\"decode\")},\n \t\t\t\t\t\t\t\t\"command\": []any{string(\"python3\"), string(\"-m\"), string(\"dynamo.sglang\")},\n \t\t\t\t\t\t\t\t\"env\": []any{\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_COMPONENT\"), \"value\": string(\"decode\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_DISCOVERY_BACKEND\"), \"value\": string(\"kubernetes\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_FORWARDPASS_METRIC_PORT\"), \"value\": string(\"20380\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\n \t\t\t\t\t\t\t\t\t\t\"name\": string(\"DYN_HEALTH_CHECK_ENABLED\"),\n- \t\t\t\t\t\t\t\t\t\t\"value\": string(\"false\"),\n+ \t\t\t\t\t\t\t\t\t\t\"value\": string(\"true\"),\n \t\t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_NAMESPACE\"), \"value\": string(\"operatorenv-zkk2r5v9-adjacent-custom-1-5\")},\n+ \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_NAMESPACE_WORKER_SUFFIX\"), \"value\": string(\"39ae5e0c\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_PARENT_DGD_K8S_NAME\"), \"value\": string(\"adjacent-custom-1-5\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_PARENT_DGD_K8S_NAMESPACE\"), \"value\": string(\"operatorenv-zkk2r5v9\")},\n \t\t\t\t\t\t\t\t\t... // 9 identical elements\n \t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\"image\": string(\"registry.example.com/dynamo/sglang-runtime:v1.5.0-9aa3-repro\"),\n \t\t\t\t\t\t\t\t\"livenessProbe\": map[string]any{\n- \t\t\t\t\t\t\t\t\t\"failureThreshold\": int64(1),\n+ \t\t\t\t\t\t\t\t\t\"failureThreshold\": int64(3),\n \t\t\t\t\t\t\t\t\t\"httpGet\": map[string]any{\"path\": string(\"/live\"), \"port\": string(\"system\")},\n \t\t\t\t\t\t\t\t\t\"periodSeconds\": int64(5),\n \t\t\t\t\t\t\t\t\t\"timeoutSeconds\": int64(4),\n \t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\"name\": string(\"main\"),\n \t\t\t\t\t\t\t\t\"ports\": []any{map[string]any{\"containerPort\": int64(9090), \"name\": string(\"system\"), \"protocol\": string(\"TCP\")}, map[string]any{\"containerPort\": int64(19090), \"name\": string(\"nixl\"), \"protocol\": string(\"TCP\")}},\n \t\t\t\t\t\t\t\t... // 4 identical entries\n \t\t\t\t\t\t\t},\n \t\t\t\t\t\t},\n \t\t\t\t\t\t\"restartPolicy\": string(\"Always\"),\n \t\t\t\t\t\t\"securityContext\": map[string]any{\"fsGroup\": int64(1000)},\n \t\t\t\t\t\t... // 3 identical entries\n \t\t\t\t\t},\n \t\t\t\t\t\"replicas\": int64(2),\n \t\t\t\t\t\"roleName\": string(\"sglangdecode\"),\n \t\t\t\t},\n \t\t\t},\n \t\t},\n \t\t\"headlessServiceConfig\": map[string]any{\"publishNotReadyAddresses\": bool(true)},\n \t\t\"terminationDelay\": string(\"15m0s\"),\n \t},\n }\n"} |
|
2026-10-17T10:33:28+08:00 INFO Unstructured updated. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5", "resourceType": "Unstructured"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "kind": "PodCliqueSet", "apiVersion": "grove.io/v1alpha1", "type": "Normal", "reason": "UpdateUnstructured", "action": "Update", "note": "Updated Unstructured operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 DEBUG Reconciling Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-custom-1-5-0-sglangprefill\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-custom-1-5-0-sglangdecode\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 DEBUG Successfully reconciled Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-sglangprefill","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-sglangdecode","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciliation done {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "65f2dd94-0559-46c1-8f81-fe1aee136cc2"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciling Grove resources {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "hasMultinode": false} |
|
2026-10-17T10:33:28+08:00 INFO K8s discovery is enabled {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO Role found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-k8s-service-discovery","namespace":"operatorenv-zkk2r5v9"}, "kind": "ServiceAccount", "apiVersion": "v1", "type": "Normal", "reason": "UpdateServiceAccount", "action": "Update", "note": "Skipping update ServiceAccount operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Role spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-k8s-service-discovery-role","namespace":"operatorenv-zkk2r5v9"}, "kind": "Role", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRole", "action": "Update", "note": "Skipping update Role operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG No EPP service defined, skipping EPP resource reconciliation {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-k8s-service-discovery-binding","namespace":"operatorenv-zkk2r5v9"}, "kind": "RoleBinding", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRoleBinding", "action": "Update", "note": "Skipping update RoleBinding operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Unstructured spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5", "resourceType": "Unstructured"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "kind": "PodCliqueSet", "apiVersion": "grove.io/v1alpha1", "type": "Normal", "reason": "UpdateUnstructured", "action": "Update", "note": "Skipping update Unstructured operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 ERROR unable to persist workload program status {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "error": "update DynamoGraphDeployment status: Operation cannot be fulfilled on dynamographdeployments.nvidia.com \"adjacent-custom-1-5\": the object has been modified; please apply your changes to the latest version and try again"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:197 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 ERROR Reconciler error {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "7a64af10-4084-4e2c-8ff7-83e12a794037", "error": "update DynamoGraphDeployment status: Operation cannot be fulfilled on dynamographdeployments.nvidia.com \"adjacent-custom-1-5\": the object has been modified; please apply your changes to the latest version and try again"} |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:494 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 INFO admission.dynamographdeployment-validating-webhook validate update {"object": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "resource": {"group":"nvidia.com","version":"v1beta1","resource":"dynamographdeployments"}, "user": "admin", "requestID": "2a1eec3d-fb6a-4ed6-a1c4-45be1311de1e", "name": "adjacent-official-1-4", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciling Grove resources {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "hasMultinode": false} |
|
2026-10-17T10:33:28+08:00 INFO K8s discovery is enabled {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO Role found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-4-k8s-service-discovery","namespace":"operatorenv-zkk2r5v9"}, "kind": "ServiceAccount", "apiVersion": "v1", "type": "Normal", "reason": "UpdateServiceAccount", "action": "Update", "note": "Skipping update ServiceAccount operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Role spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-4-k8s-service-discovery-role","namespace":"operatorenv-zkk2r5v9"}, "kind": "Role", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRole", "action": "Update", "note": "Skipping update Role operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG No EPP service defined, skipping EPP resource reconciliation {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-4-k8s-service-discovery-binding","namespace":"operatorenv-zkk2r5v9"}, "kind": "RoleBinding", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRoleBinding", "action": "Update", "note": "Skipping update RoleBinding operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Unstructured spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4", "resourceType": "Unstructured"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "kind": "PodCliqueSet", "apiVersion": "grove.io/v1alpha1", "type": "Normal", "reason": "UpdateUnstructured", "action": "Update", "note": "Skipping update Unstructured operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 DEBUG Reconciling Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-4-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-4-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-official-1-4-0-sglangprefill\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-4-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-4-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-4-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-official-1-4-0-sglangdecode\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-4-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 DEBUG Successfully reconciled Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-4-sglangprefill","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-4-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-4-sglangdecode","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciliation done {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-4","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-4", "reconcileID": "ada19f58-cb9d-47b0-b639-156ac7f6aea4"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciling Grove resources {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "hasMultinode": false} |
|
2026-10-17T10:33:28+08:00 INFO K8s discovery is enabled {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO Role found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-k8s-service-discovery","namespace":"operatorenv-zkk2r5v9"}, "kind": "ServiceAccount", "apiVersion": "v1", "type": "Normal", "reason": "UpdateServiceAccount", "action": "Update", "note": "Skipping update ServiceAccount operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Role spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-k8s-service-discovery-role","namespace":"operatorenv-zkk2r5v9"}, "kind": "Role", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRole", "action": "Update", "note": "Skipping update Role operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG No EPP service defined, skipping EPP resource reconciliation {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-k8s-service-discovery-binding","namespace":"operatorenv-zkk2r5v9"}, "kind": "RoleBinding", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRoleBinding", "action": "Update", "note": "Skipping update RoleBinding operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Unstructured spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5", "resourceType": "Unstructured"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "kind": "PodCliqueSet", "apiVersion": "grove.io/v1alpha1", "type": "Normal", "reason": "UpdateUnstructured", "action": "Update", "note": "Skipping update Unstructured operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO admission.dynamographdeployment-validating-webhook validate update {"object": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "resource": {"group":"nvidia.com","version":"v1beta1","resource":"dynamographdeployments"}, "user": "admin", "requestID": "728c17a8-c598-440c-8deb-2173fef180fc", "name": "adjacent-custom-1-5", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Worker spec change detected but rolling update not supported for this pathway {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "isGrove": true, "hasMultinode": false} |
|
2026-10-17T10:33:28+08:00 DEBUG Reconciling Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "kind": "DynamoGraphDeployment", "apiVersion": "nvidia.com/v1beta1", "type": "Warning", "reason": "RollingUpdateNotSupported", "action": "Update", "note": "Worker spec changed but custom rolling updates are not supported for Grove/multinode deployments"} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-custom-1-5-0-sglangprefill\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-custom-1-5-0-sglangdecode\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-custom-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 DEBUG Successfully reconciled Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-sglangprefill","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-custom-1-5-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-custom-1-5-sglangdecode","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciliation done {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-custom-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-custom-1-5", "reconcileID": "d3712613-4ca7-42dc-9b04-15138c77dc05"} |
|
2026-10-17T10:33:28+08:00 INFO admission.dynamographdeployment-validating-webhook validate update {"object": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "resource": {"group":"nvidia.com","version":"v1beta1","resource":"dynamographdeployments"}, "user": "admin", "requestID": "1ac066c0-a080-4afb-93fa-8b02faa50204", "name": "adjacent-official-1-5", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciling Grove resources {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "hasMultinode": false} |
|
2026-10-17T10:33:28+08:00 INFO K8s discovery is enabled {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO Role found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-k8s-service-discovery","namespace":"operatorenv-zkk2r5v9"}, "kind": "ServiceAccount", "apiVersion": "v1", "type": "Normal", "reason": "UpdateServiceAccount", "action": "Update", "note": "Skipping update ServiceAccount operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Role spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-k8s-service-discovery-role","namespace":"operatorenv-zkk2r5v9"}, "kind": "Role", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRole", "action": "Update", "note": "Skipping update Role operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG No EPP service defined, skipping EPP resource reconciliation {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-k8s-service-discovery-binding","namespace":"operatorenv-zkk2r5v9"}, "kind": "RoleBinding", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRoleBinding", "action": "Update", "note": "Skipping update RoleBinding operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Unstructured spec changes detected {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5", "resourceType": "Unstructured", "diff": " map[string]any{\n \t\"replicas\": int64(1),\n \t\"template\": map[string]any{\n \t\t\"cliqueStartupType\": string(\"CliqueStartupTypeAnyOrder\"),\n \t\t\"cliques\": []any{\n \t\t\tmap[string]any{\n \t\t\t\t\"annotations\": map[string]any{\"nvidia.com/dynamo-discovery-backend\": string(\"kubernetes\"), \"nvidia.com/dynamo-operator-origin-version\": string(\"1.4.0\")},\n \t\t\t\t\"labels\": map[string]any{\n \t\t\t\t\t... // 5 identical entries\n \t\t\t\t\t\"nvidia.com/dynamo-namespace\": string(\"operatorenv-zkk2r5v9-adjacent-official-1-5\"),\n \t\t\t\t\t\"nvidia.com/dynamo-sub-component-type\": string(\"prefill\"),\n+ \t\t\t\t\t\"nvidia.com/dynamo-worker-hash\": string(\"37070ad2\"),\n \t\t\t\t\t\"nvidia.com/metrics-enabled\": string(\"true\"),\n \t\t\t\t\t\"nvidia.com/selector\": string(\"adjacent-official-1-5-sglangprefill\"),\n \t\t\t\t},\n \t\t\t\t\"name\": string(\"sglangprefill\"),\n \t\t\t\t\"spec\": map[string]any{\n \t\t\t\t\t\"minAvailable\": int64(1),\n \t\t\t\t\t\"podSpec\": map[string]any{\n \t\t\t\t\t\t\"containers\": []any{\n \t\t\t\t\t\t\tmap[string]any{\n \t\t\t\t\t\t\t\t\"args\": []any{string(\"--model-path\"), string(\"Qwen/Qwen3-0.6B\"), string(\"--disaggregation-mode\"), string(\"prefill\")},\n \t\t\t\t\t\t\t\t\"command\": []any{string(\"python3\"), string(\"-m\"), string(\"dynamo.sglang\")},\n \t\t\t\t\t\t\t\t\"env\": []any{\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_COMPONENT\"), \"value\": string(\"prefill\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_DISCOVERY_BACKEND\"), \"value\": string(\"kubernetes\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_FORWARDPASS_METRIC_PORT\"), \"value\": string(\"20380\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\n \t\t\t\t\t\t\t\t\t\t\"name\": string(\"DYN_HEALTH_CHECK_ENABLED\"),\n- \t\t\t\t\t\t\t\t\t\t\"value\": string(\"false\"),\n+ \t\t\t\t\t\t\t\t\t\t\"value\": string(\"true\"),\n \t\t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_NAMESPACE\"), \"value\": string(\"operatorenv-zkk2r5v9-adjacent-official-1-5\")},\n+ \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_NAMESPACE_WORKER_SUFFIX\"), \"value\": string(\"37070ad2\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_PARENT_DGD_K8S_NAME\"), \"value\": string(\"adjacent-official-1-5\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_PARENT_DGD_K8S_NAMESPACE\"), \"value\": string(\"operatorenv-zkk2r5v9\")},\n \t\t\t\t\t\t\t\t\t... // 9 identical elements\n \t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\"image\": string(\"nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.5.0\"),\n \t\t\t\t\t\t\t\t\"livenessProbe\": map[string]any{\n- \t\t\t\t\t\t\t\t\t\"failureThreshold\": int64(1),\n+ \t\t\t\t\t\t\t\t\t\"failureThreshold\": int64(3),\n \t\t\t\t\t\t\t\t\t\"httpGet\": map[string]any{\"path\": string(\"/live\"), \"port\": string(\"system\")},\n \t\t\t\t\t\t\t\t\t\"periodSeconds\": int64(5),\n \t\t\t\t\t\t\t\t\t\"timeoutSeconds\": int64(4),\n \t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\"name\": string(\"main\"),\n \t\t\t\t\t\t\t\t\"ports\": []any{map[string]any{\"containerPort\": int64(9090), \"name\": string(\"system\"), \"protocol\": string(\"TCP\")}, map[string]any{\"containerPort\": int64(19090), \"name\": string(\"nixl\"), \"protocol\": string(\"TCP\")}},\n \t\t\t\t\t\t\t\t... // 4 identical entries\n \t\t\t\t\t\t\t},\n \t\t\t\t\t\t},\n \t\t\t\t\t\t\"restartPolicy\": string(\"Always\"),\n \t\t\t\t\t\t\"securityContext\": map[string]any{\"fsGroup\": int64(1000)},\n \t\t\t\t\t\t... // 3 identical entries\n \t\t\t\t\t},\n \t\t\t\t\t\"replicas\": int64(2),\n \t\t\t\t\t\"roleName\": string(\"sglangprefill\"),\n \t\t\t\t},\n \t\t\t},\n \t\t\tmap[string]any{\n \t\t\t\t\"annotations\": map[string]any{\"nvidia.com/dynamo-discovery-backend\": string(\"kubernetes\"), \"nvidia.com/dynamo-operator-origin-version\": string(\"1.4.0\")},\n \t\t\t\t\"labels\": map[string]any{\n \t\t\t\t\t... // 5 identical entries\n \t\t\t\t\t\"nvidia.com/dynamo-namespace\": string(\"operatorenv-zkk2r5v9-adjacent-official-1-5\"),\n \t\t\t\t\t\"nvidia.com/dynamo-sub-component-type\": string(\"decode\"),\n+ \t\t\t\t\t\"nvidia.com/dynamo-worker-hash\": string(\"37070ad2\"),\n \t\t\t\t\t\"nvidia.com/metrics-enabled\": string(\"true\"),\n \t\t\t\t\t\"nvidia.com/selector\": string(\"adjacent-official-1-5-sglangdecode\"),\n \t\t\t\t},\n \t\t\t\t\"name\": string(\"sglangdecode\"),\n \t\t\t\t\"spec\": map[string]any{\n \t\t\t\t\t\"minAvailable\": int64(1),\n \t\t\t\t\t\"podSpec\": map[string]any{\n \t\t\t\t\t\t\"containers\": []any{\n \t\t\t\t\t\t\tmap[string]any{\n \t\t\t\t\t\t\t\t\"args\": []any{string(\"--model-path\"), string(\"Qwen/Qwen3-0.6B\"), string(\"--disaggregation-mode\"), string(\"decode\")},\n \t\t\t\t\t\t\t\t\"command\": []any{string(\"python3\"), string(\"-m\"), string(\"dynamo.sglang\")},\n \t\t\t\t\t\t\t\t\"env\": []any{\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_COMPONENT\"), \"value\": string(\"decode\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_DISCOVERY_BACKEND\"), \"value\": string(\"kubernetes\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_FORWARDPASS_METRIC_PORT\"), \"value\": string(\"20380\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\n \t\t\t\t\t\t\t\t\t\t\"name\": string(\"DYN_HEALTH_CHECK_ENABLED\"),\n- \t\t\t\t\t\t\t\t\t\t\"value\": string(\"false\"),\n+ \t\t\t\t\t\t\t\t\t\t\"value\": string(\"true\"),\n \t\t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_NAMESPACE\"), \"value\": string(\"operatorenv-zkk2r5v9-adjacent-official-1-5\")},\n+ \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_NAMESPACE_WORKER_SUFFIX\"), \"value\": string(\"37070ad2\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_PARENT_DGD_K8S_NAME\"), \"value\": string(\"adjacent-official-1-5\")},\n \t\t\t\t\t\t\t\t\tmap[string]any{\"name\": string(\"DYN_PARENT_DGD_K8S_NAMESPACE\"), \"value\": string(\"operatorenv-zkk2r5v9\")},\n \t\t\t\t\t\t\t\t\t... // 9 identical elements\n \t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\"image\": string(\"nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.5.0\"),\n \t\t\t\t\t\t\t\t\"livenessProbe\": map[string]any{\n- \t\t\t\t\t\t\t\t\t\"failureThreshold\": int64(1),\n+ \t\t\t\t\t\t\t\t\t\"failureThreshold\": int64(3),\n \t\t\t\t\t\t\t\t\t\"httpGet\": map[string]any{\"path\": string(\"/live\"), \"port\": string(\"system\")},\n \t\t\t\t\t\t\t\t\t\"periodSeconds\": int64(5),\n \t\t\t\t\t\t\t\t\t\"timeoutSeconds\": int64(4),\n \t\t\t\t\t\t\t\t},\n \t\t\t\t\t\t\t\t\"name\": string(\"main\"),\n \t\t\t\t\t\t\t\t\"ports\": []any{map[string]any{\"containerPort\": int64(9090), \"name\": string(\"system\"), \"protocol\": string(\"TCP\")}, map[string]any{\"containerPort\": int64(19090), \"name\": string(\"nixl\"), \"protocol\": string(\"TCP\")}},\n \t\t\t\t\t\t\t\t... // 4 identical entries\n \t\t\t\t\t\t\t},\n \t\t\t\t\t\t},\n \t\t\t\t\t\t\"restartPolicy\": string(\"Always\"),\n \t\t\t\t\t\t\"securityContext\": map[string]any{\"fsGroup\": int64(1000)},\n \t\t\t\t\t\t... // 3 identical entries\n \t\t\t\t\t},\n \t\t\t\t\t\"replicas\": int64(2),\n \t\t\t\t\t\"roleName\": string(\"sglangdecode\"),\n \t\t\t\t},\n \t\t\t},\n \t\t},\n \t\t\"headlessServiceConfig\": map[string]any{\"publishNotReadyAddresses\": bool(true)},\n \t\t\"terminationDelay\": string(\"15m0s\"),\n \t},\n }\n"} |
|
2026-10-17T10:33:28+08:00 INFO Unstructured updated. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5", "resourceType": "Unstructured"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "kind": "PodCliqueSet", "apiVersion": "grove.io/v1alpha1", "type": "Normal", "reason": "UpdateUnstructured", "action": "Update", "note": "Updated Unstructured operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 DEBUG Reconciling Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-official-1-5-0-sglangprefill\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-official-1-5-0-sglangdecode\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 DEBUG Successfully reconciled Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-sglangprefill","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-sglangdecode","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciliation done {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "ca4ac8d0-ed98-4cff-bceb-954007f031fe"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciling Grove resources {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "hasMultinode": false} |
|
2026-10-17T10:33:28+08:00 INFO K8s discovery is enabled {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO Role found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-k8s-service-discovery","namespace":"operatorenv-zkk2r5v9"}, "kind": "ServiceAccount", "apiVersion": "v1", "type": "Normal", "reason": "UpdateServiceAccount", "action": "Update", "note": "Skipping update ServiceAccount operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Role spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-k8s-service-discovery-role","namespace":"operatorenv-zkk2r5v9"}, "kind": "Role", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRole", "action": "Update", "note": "Skipping update Role operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG No EPP service defined, skipping EPP resource reconciliation {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-k8s-service-discovery-binding","namespace":"operatorenv-zkk2r5v9"}, "kind": "RoleBinding", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRoleBinding", "action": "Update", "note": "Skipping update RoleBinding operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Unstructured spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5", "resourceType": "Unstructured"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "kind": "PodCliqueSet", "apiVersion": "grove.io/v1alpha1", "type": "Normal", "reason": "UpdateUnstructured", "action": "Update", "note": "Skipping update Unstructured operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 ERROR unable to persist workload program status {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "error": "update DynamoGraphDeployment status: Operation cannot be fulfilled on dynamographdeployments.nvidia.com \"adjacent-official-1-5\": the object has been modified; please apply your changes to the latest version and try again"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:197 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 ERROR Reconciler error {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "522c96df-f5e1-4a4a-9e0f-3293efa93a82", "error": "update DynamoGraphDeployment status: Operation cannot be fulfilled on dynamographdeployments.nvidia.com \"adjacent-official-1-5\": the object has been modified; please apply your changes to the latest version and try again"} |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:494 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
zz_adjacent_api_test.go:170: release=1.5.0 case=custom-1.5 persistedHash=39ae5e0c PCS-generation=2 |
|
2026-10-17T10:33:28+08:00 INFO Reconciling Grove resources {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "hasMultinode": false} |
|
2026-10-17T10:33:28+08:00 INFO K8s discovery is enabled {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO ServiceAccount spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery", "resourceType": "ServiceAccount"} |
|
2026-10-17T10:33:28+08:00 INFO Role found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-k8s-service-discovery","namespace":"operatorenv-zkk2r5v9"}, "kind": "ServiceAccount", "apiVersion": "v1", "type": "Normal", "reason": "UpdateServiceAccount", "action": "Update", "note": "Skipping update ServiceAccount operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Role spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-role", "resourceType": "Role"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-k8s-service-discovery-role","namespace":"operatorenv-zkk2r5v9"}, "kind": "Role", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRole", "action": "Update", "note": "Skipping update Role operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO RoleBinding spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-k8s-service-discovery-binding", "resourceType": "RoleBinding"} |
|
2026-10-17T10:33:28+08:00 DEBUG No EPP service defined, skipping EPP resource reconciliation {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-k8s-service-discovery-binding","namespace":"operatorenv-zkk2r5v9"}, "kind": "RoleBinding", "apiVersion": "rbac.authorization.k8s.io/v1", "type": "Normal", "reason": "UpdateRoleBinding", "action": "Update", "note": "Skipping update RoleBinding operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Unstructured spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5", "resourceType": "Unstructured"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "kind": "PodCliqueSet", "apiVersion": "grove.io/v1alpha1", "type": "Normal", "reason": "UpdateUnstructured", "action": "Update", "note": "Skipping update Unstructured operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO admission.dynamographdeployment-validating-webhook validate update {"object": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "resource": {"group":"nvidia.com","version":"v1beta1","resource":"dynamographdeployments"}, "user": "admin", "requestID": "7680e89a-976f-4300-a0ea-fdb518a7e2c5", "name": "adjacent-official-1-5", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Worker spec change detected but rolling update not supported for this pathway {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "isGrove": true, "hasMultinode": false} |
|
2026-10-17T10:33:28+08:00 DEBUG Reconciling Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "kind": "DynamoGraphDeployment", "apiVersion": "nvidia.com/v1beta1", "type": "Warning", "reason": "RollingUpdateNotSupported", "action": "Update", "note": "Worker spec changed but custom rolling updates are not supported for Grove/multinode deployments"} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-official-1-5-0-sglangprefill\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangprefill", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Scaling resource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "replicas": 2} |
|
2026-10-17T10:33:28+08:00 ERROR Failed to get current scale - resource may not support scale subresource {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9", "groupResource": "podcliques.grove.io", "error": "podcliques.grove.io \"adjacent-official-1-5-0-sglangdecode\" not found"} |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller_common.ScaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller_common/scale.go:54 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).scaleResource |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:111 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveScaler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_scaler.go:81 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveWorkloadsReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_workloads_reconciler.go:123 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*groveProgram).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dgd_grove_program.go:129 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/controller.(*DynamoGraphDeploymentReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/controller/dynamographdeployment_controller.go:192 |
|
github.com/ai-dynamo/dynamo/deploy/operator/internal/observability.(*ObservedReconciler).Reconcile |
|
<REPRO_ROOT>/source/1.5.0/deploy/operator/internal/observability/reconciler_wrapper.go:46 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Reconcile |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:221 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).reconcileHandler |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:478 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).processNextWorkItem |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:437 |
|
sigs.k8s.io/controller-runtime/pkg/internal/controller.(*Controller[...]).Start.func1.1 |
|
<GOMODCACHE>/sigs.k8s.io/controller-runtime@v0.24.1/pkg/internal/controller/controller.go:312 |
|
2026-10-17T10:33:28+08:00 DEBUG Grove resource not found yet, skipping scaling for now {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "gvr": "grove.io/v1alpha1, Resource=podcliques", "name": "adjacent-official-1-5-0-sglangdecode", "namespace": "operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 DEBUG Successfully reconciled Grove scaling operations {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-sglangprefill", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-sglangprefill","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO Service found. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 INFO Service spec is the same. Skipping update. {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183", "namespace": "operatorenv-zkk2r5v9", "resourceName": "adjacent-official-1-5-sglangdecode", "resourceType": "Service"} |
|
2026-10-17T10:33:28+08:00 DEBUG events Event occurred {"object": {"name":"adjacent-official-1-5-sglangdecode","namespace":"operatorenv-zkk2r5v9"}, "kind": "Service", "apiVersion": "v1", "type": "Normal", "reason": "UpdateService", "action": "Update", "note": "Skipping update Service operatorenv-zkk2r5v9"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183"} |
|
2026-10-17T10:33:28+08:00 INFO nvidia.com/v1alpha1 DynamoGraphDeploymentScalingAdapter is deprecated; use nvidia.com/v1beta1 DynamoGraphDeploymentScalingAdapter {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183"} |
|
2026-10-17T10:33:28+08:00 INFO Reconciliation done {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment", "DynamoGraphDeployment": {"name":"adjacent-official-1-5","namespace":"operatorenv-zkk2r5v9"}, "namespace": "operatorenv-zkk2r5v9", "name": "adjacent-official-1-5", "reconcileID": "281e155e-db63-4a00-84fc-2cec5af29183"} |
|
zz_adjacent_api_test.go:170: release=1.5.0 case=official-1.5 persistedHash=37070ad2 PCS-generation=2 |
|
zz_adjacent_api_test.go:170: release=1.5.0 case=official-1.4 persistedHash=3cf136a2 PCS-generation=1 |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for warmup runnables |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for non leader election runnables |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for leader election runnables |
|
2026-10-17T10:33:29+08:00 INFO Shutdown signal received, waiting for all workers to finish {"controller": "DynamoComponentDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoComponentDeployment"} |
|
2026-10-17T10:33:29+08:00 INFO All workers finished {"controller": "DynamoComponentDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoComponentDeployment"} |
|
2026-10-17T10:33:29+08:00 INFO Shutdown signal received, waiting for all workers to finish {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment"} |
|
2026-10-17T10:33:29+08:00 INFO All workers finished {"controller": "DynamoGraphDeployment", "controllerGroup": "nvidia.com", "controllerKind": "DynamoGraphDeployment"} |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for caches |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for webhooks |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for HTTP servers |
|
2026-10-17T10:33:29+08:00 INFO Wait completed, proceeding to shutdown the manager |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for non leader election runnables |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for leader election runnables |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for caches |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for warmup runnables |
|
2026-10-17T10:33:29+08:00 INFO Stopping and waiting for webhooks |
|
2026-10-17T10:33:29+08:00 INFO controller-runtime.webhook Shutting down webhook server with timeout of 1 minute |
|
2026-10-17T10:33:30+08:00 INFO Stopping and waiting for HTTP servers |
|
2026-10-17T10:33:30+08:00 INFO Wait completed, proceeding to shutdown the manager |
|
--- PASS: TestAdjacentAPI (3.80s) |
|
PASS |
|
ok github.com/ai-dynamo/dynamo/deploy/operator/internal/controller 4.553s |