--- apiVersion: v1 items: - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:04Z" involvedObject: kind: CertificateSigningRequest name: csr-64zxq kind: Event lastTimestamp: "2026-05-28T15:08:04Z" message: CSR "csr-64zxq" has been approved metadata: creationTimestamp: "2026-05-28T15:08:04Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: ovnkube-identity operation: Update time: "2026-05-28T15:08:04Z" name: csr-64zxq.18b3c32f1e4a474a namespace: default resourceVersion: "6437" uid: bfca1b85-5e7e-4387-9b5c-573e69a9fdb1 reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:12Z" involvedObject: kind: CertificateSigningRequest name: csr-662f8 kind: Event lastTimestamp: "2026-05-28T15:08:12Z" message: CSR "csr-662f8" has been approved metadata: creationTimestamp: "2026-05-28T15:08:12Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: ovnkube-identity operation: Update time: "2026-05-28T15:08:12Z" name: csr-662f8.18b3c330d4a6e491 namespace: default resourceVersion: "6680" uid: f018cc99-3275-4cb6-963c-d6c9985ac144 reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:06Z" involvedObject: kind: CertificateSigningRequest name: csr-7l7s9 kind: Event lastTimestamp: "2026-05-28T15:08:06Z" message: CSR "csr-7l7s9" has been approved metadata: creationTimestamp: "2026-05-28T15:08:06Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: ovnkube-identity operation: Update time: "2026-05-28T15:08:06Z" name: csr-7l7s9.18b3c32f7bd5db2a namespace: default resourceVersion: "6528" uid: 774d4322-bc07-48cc-9501-029594c20877 reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:17Z" involvedObject: kind: CertificateSigningRequest name: csr-7tw59 kind: Event lastTimestamp: "2026-05-28T15:08:17Z" message: CSR "csr-7tw59" has been approved metadata: creationTimestamp: "2026-05-28T15:08:17Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: ovnkube-identity operation: Update time: "2026-05-28T15:08:17Z" name: csr-7tw59.18b3c3320ab86e48 namespace: default resourceVersion: "6767" uid: 4e4da37b-9ec8-4ba1-90b0-7ade06174e43 reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:13Z" involvedObject: kind: CertificateSigningRequest name: csr-c22zj kind: Event lastTimestamp: "2026-05-28T15:08:13Z" message: CSR "csr-c22zj" has been approved metadata: creationTimestamp: "2026-05-28T15:08:13Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: ovnkube-identity operation: Update time: "2026-05-28T15:08:13Z" name: csr-c22zj.18b3c331064bfe31 namespace: default resourceVersion: "6693" uid: 70160ef0-674c-4329-932a-719259824f3a reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:58Z" involvedObject: kind: CertificateSigningRequest name: csr-vshfn kind: Event lastTimestamp: "2026-05-28T15:07:58Z" message: CSR "csr-vshfn" has been approved metadata: creationTimestamp: "2026-05-28T15:07:58Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: ovnkube-identity operation: Update time: "2026-05-28T15:07:58Z" name: csr-vshfn.18b3c32daa44a3d4 namespace: default resourceVersion: "6278" uid: da717ff8-0a82-4847-8899-2c65d97a1f4b reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 9 eventTime: null firstTimestamp: "2026-05-28T15:14:38Z" involvedObject: apiVersion: datasciencecluster.opendatahub.io/v2 kind: DataScienceCluster name: default-dsc resourceVersion: "14637" uid: 91183485-72f2-417f-b78d-ad93046ec8b2 kind: Event lastTimestamp: "2026-05-28T15:14:39Z" message: 'failure deploying resource {map[apiVersion:components.platform.opendatahub.io/v1alpha1 kind:Kserve metadata:map[annotations:map[component.opendatahub.io/management-state:Managed platform.opendatahub.io/instance.generation:1 platform.opendatahub.io/instance.name:default-dsc platform.opendatahub.io/instance.uid:91183485-72f2-417f-b78d-ad93046ec8b2 platform.opendatahub.io/type:Open Data Hub platform.opendatahub.io/version:3.4.0-ea.1] creationTimestamp: labels:map[platform.opendatahub.io/part-of:datasciencecluster] name:default-kserve ownerReferences:[map[apiVersion:datasciencecluster.opendatahub.io/v2 blockOwnerDeletion:%!s(bool=true) controller:%!s(bool=true) kind:DataScienceCluster name:default-dsc uid:91183485-72f2-417f-b78d-ad93046ec8b2]]] spec:map[modelsAsService:map[managementState:Removed] nim:map[managementState:Managed] rawDeploymentServiceConfig:Headed] status:map[]]}: apply failed components.platform.opendatahub.io/v1alpha1, Kind=Kserve: unable to patch components.platform.opendatahub.io/v1alpha1, Kind=Kserve default-kserve: kserves.components.platform.opendatahub.io "default-kserve" is forbidden: cannot set blockOwnerDeletion in this case because cannot find RESTMapping for APIVersion datasciencecluster.opendatahub.io/v2 Kind DataScienceCluster: no matches for kind "DataScienceCluster" in version "datasciencecluster.opendatahub.io/v2"' metadata: creationTimestamp: "2026-05-28T15:14:38Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: manager operation: Update time: "2026-05-28T15:14:39Z" name: default-dsc.18b3c38abeef444c namespace: default resourceVersion: "14705" uid: c3af7a0e-7ee2-4a88-b731-5bb72e135d6f reason: ProvisioningError reportingComponent: datasciencecluster reportingInstance: "" source: component: datasciencecluster type: Warning - apiVersion: v1 count: 9 eventTime: null firstTimestamp: "2026-05-28T15:14:38Z" involvedObject: apiVersion: dscinitialization.opendatahub.io/v2 kind: DSCInitialization name: default-dsci resourceVersion: "14466" uid: aca6e89a-0375-4827-9e14-40b8c68436c7 kind: Event lastTimestamp: "2026-05-28T15:14:39Z" message: 'failed to create operator resources for instance default-dsci: unable to patch networking.k8s.io/v1, Kind=NetworkPolicy opendatahub/opendatahub: networkpolicies.networking.k8s.io "opendatahub" is forbidden: cannot set blockOwnerDeletion in this case because cannot find RESTMapping for APIVersion dscinitialization.opendatahub.io/v2 Kind DSCInitialization: no matches for kind "DSCInitialization" in version "dscinitialization.opendatahub.io/v2"' metadata: creationTimestamp: "2026-05-28T15:14:38Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: manager operation: Update time: "2026-05-28T15:14:39Z" name: default-dsci.18b3c38aaa78c7a7 namespace: default resourceVersion: "14703" uid: 6c0b908e-6acf-4841-9639-3153f3792034 reason: DSCInitializationReconcileError reportingComponent: dscinitialization-controller reportingInstance: "" source: component: dscinitialization-controller type: Warning - apiVersion: v1 count: 11 eventTime: null firstTimestamp: "2026-05-28T15:14:42Z" involvedObject: apiVersion: services.platform.opendatahub.io/v1alpha1 kind: GatewayConfig name: default-gateway resourceVersion: "14831" uid: e66ab365-f9a9-49b4-9b46-fccf8ab029cf kind: Event lastTimestamp: "2026-05-28T15:14:50Z" message: 'failed to lookup object openshift-ingress/data-science-tls-rule: no matches for kind "DestinationRule" in version "networking.istio.io/v1"' metadata: creationTimestamp: "2026-05-28T15:14:43Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: manager operation: Update time: "2026-05-28T15:14:50Z" name: default-gateway.18b3c38bd00555b9 namespace: default resourceVersion: "15053" uid: 34810920-fa93-4c4d-959f-ba5943b23759 reason: ProvisioningError reportingComponent: gatewayconfig reportingInstance: "" source: component: gatewayconfig type: Warning - apiVersion: v1 count: 13 eventTime: null firstTimestamp: "2026-05-28T15:14:50Z" involvedObject: apiVersion: components.platform.opendatahub.io/v1alpha1 kind: Kserve name: default-kserve resourceVersion: "15124" uid: 78862260-a6c9-41be-8e91-103040e48b7e kind: Event lastTimestamp: "2026-05-28T15:15:17Z" message: "failure deploying resource {map[apiVersion:serving.kserve.io/v1alpha1 kind:LLMInferenceServiceConfig metadata:map[annotations:map[internal.config.kubernetes.io/previousKinds:LLMInferenceServiceConfig internal.config.kubernetes.io/previousNames:kserve-config-llm-decode-template internal.config.kubernetes.io/previousNamespaces:opendatahub platform.opendatahub.io/instance.generation:1 platform.opendatahub.io/instance.name:default-kserve platform.opendatahub.io/instance.uid:78862260-a6c9-41be-8e91-103040e48b7e platform.opendatahub.io/type:Open Data Hub platform.opendatahub.io/version:3.4.0-ea.1 serving.kserve.io/well-known-config:true] labels:map[app.kubernetes.io/part-of:kserve app.opendatahub.io/kserve:true platform.opendatahub.io/part-of:kserve] name:v3-4-0-ea-1-kserve-config-llm-decode-template namespace:opendatahub ownerReferences:[map[apiVersion:components.platform.opendatahub.io/v1alpha1 blockOwnerDeletion:%!s(bool=true) controller:%!s(bool=true) kind:Kserve name:default-kserve uid:78862260-a6c9-41be-8e91-103040e48b7e]]] spec:map[template:map[containers:[map[args:[if [ \"$KSERVE_INFER_ROCE\" = \"true\" ]; then\n echo \"Trying to infer RoCE configs ... \"\n grep -H . /sys/class/infiniband/*/ports/*/gids/* 2>/dev/null\n grep -H . /sys/class/infiniband/*/ports/*/gid_attrs/types/* 2>/dev/null\n\n cat /proc/driver/nvidia/params\n\n \ KSERVE_INFER_IB_GID_INDEX_GREP=${KSERVE_INFER_IB_GID_INDEX_GREP:-\"RoCE v2\"}\n\n \ echo \"[Infer RoCE] Discovering active HCAs ...\"\n active_hcas=()\n # Loop through all mlx5 devices found in sysfs\n for hca_dir in /sys/class/infiniband/mlx5_*; do\n # Ensure it's a directory before proceeding\n if [ -d \"$hca_dir\" ]; then\n hca_name=$(basename \"$hca_dir\")\n port_state_file=\"$hca_dir/ports/1/state\" # Assume port 1\n type_file=\"$hca_dir/ports/1/gid_attrs/types/*\"\n\n \ echo \"[Infer RoCE] Check if the port state file ${port_state_file} exists and contains 'ACTIVE'\"\n if [ -f \"$port_state_file\" ] && grep -q \"ACTIVE\" \"$port_state_file\" && grep -q \"${KSERVE_INFER_IB_GID_INDEX_GREP}\" ${type_file} 2>/dev/null; then\n echo \"[Infer RoCE] Found active HCA: $hca_name\"\n active_hcas+=(\"$hca_name\")\n else\n \ echo \"[Infer RoCE] Skipping inactive or down HCA: $hca_name\"\n \ fi\n fi\n done\n\n ucx_hcas=()\n for hca in \"${active_hcas[@]}\"; do\n ucx_hcas+=(\"${hca}:1\")\n done\n\n # Check if we found any active HCAs\n \ if [ ${#active_hcas[@]} -gt 0 ]; then\n # Join the array elements with a comma\n hcas=$(IFS=,; echo \"${active_hcas[*]}\")\n echo \"[Infer RoCE] Setting active HCAs: ${hcas}\"\n export NCCL_IB_HCA=${NCCL_IB_HCA:-${hcas}}\n \ export NVSHMEM_HCA_LIST=${NVSHMEM_HCA_LIST:-${ucx_hcas}}\n export UCX_NET_DEVICES=${UCX_NET_DEVICES:-${ucx_hcas}}\n\n \ echo \"[Infer RoCE] NCCL_IB_HCA=${NCCL_IB_HCA}\"\n echo \"[Infer RoCE] NVSHMEM_HCA_LIST=${NVSHMEM_HCA_LIST}\"\n else\n echo \"[Infer RoCE] WARNING: No active RoCE HCAs found. NCCL_IB_HCA will not be set.\"\n fi\n\n if [ ${#active_hcas[@]} -gt 0 ]; then\n echo \"[Infer RoCE] Finding GID_INDEX for each active HCA (SR-IOV compatible)...\"\n\n # For SR-IOV environments, find the most common IPv4 RoCE v2 GID index across all HCAs\n declare -A gid_index_count\n declare -A hca_gid_index\n\n for hca_name in \"${active_hcas[@]}\"; do\n echo \"[Infer RoCE] Processing HCA: ${hca_name}\"\n\n # Find all RoCE v2 IPv4 GIDs for this HCA and count by index\n for tpath in /sys/class/infiniband/${hca_name}/ports/1/gid_attrs/types/*; do\n if grep -q \"${KSERVE_INFER_IB_GID_INDEX_GREP}\" \"$tpath\" 2>/dev/null; then\n idx=$(basename \"$tpath\")\n gid_file=\"/sys/class/infiniband/${hca_name}/ports/1/gids/${idx}\"\n \ # Check for IPv4 GID (contains ffff:)\n if [ -f \"$gid_file\" ] && grep -q \"ffff:\" \"$gid_file\"; then\n gid_value=$(cat \"$gid_file\" 2>/dev/null || echo \"\")\n echo \"[Infer RoCE] Found IPv4 RoCE v2 GID for ${hca_name}: index=${idx}, gid=${gid_value}\"\n hca_gid_index[\"${hca_name}\"]=\"${idx}\"\n \ gid_index_count[\"${idx}\"]=$((${gid_index_count[\"${idx}\"]} + 1))\n break # Use first found IPv4 GID per HCA\n fi\n \ fi\n done\n done\n\n # Find the most common GID index (most likely to be consistent across nodes)\n best_gid_index=\"\"\n \ max_count=0\n for idx in \"${!gid_index_count[@]}\"; do\n count=${gid_index_count[\"${idx}\"]}\n \ echo \"[Infer RoCE] GID_INDEX ${idx} found on ${count} HCAs\"\n if [ $count -gt $max_count ]; then\n max_count=$count\n best_gid_index=\"$idx\"\n \ fi\n done\n\n # Use deterministic fallback if counts are equal - prefer lower index number \n if [ ${#gid_index_count[@]} -gt 1 ]; then\n \ echo \"[Infer RoCE] Multiple GID indices found, selecting most common: ${best_gid_index}\"\n # If there's a tie, prefer index 3 as it's most common in SR-IOV setups\n if [ -n \"${gid_index_count['3']}\" ] && [ \"${gid_index_count['3']}\" -eq \"$max_count\" ]; then\n best_gid_index=\"3\"\n \ echo \"[Infer RoCE] Using deterministic fallback: GID_INDEX=3 (SR-IOV standard)\"\n fi\n fi\n\n # Check if GID_INDEX is already set via environment variables\n if [ -n \"${NCCL_IB_GID_INDEX}\" ]; then\n echo \"[Infer RoCE] Using pre-configured NCCL_IB_GID_INDEX=${NCCL_IB_GID_INDEX} from environment\"\n export NVSHMEM_IB_GID_INDEX=${NVSHMEM_IB_GID_INDEX:-$NCCL_IB_GID_INDEX}\n \ export UCX_IB_GID_INDEX=${UCX_IB_GID_INDEX:-$NCCL_IB_GID_INDEX}\n echo \"[Infer RoCE] Using hardcoded GID_INDEX=${NCCL_IB_GID_INDEX} for NCCL, NVSHMEM, and UCX\"\n elif [ -n \"$best_gid_index\" ]; then\n echo \"[Infer RoCE] Selected GID_INDEX: ${best_gid_index} (found on ${max_count} HCAs)\"\n\n \ export NCCL_IB_GID_INDEX=${NCCL_IB_GID_INDEX:-$best_gid_index}\n export NVSHMEM_IB_GID_INDEX=${NVSHMEM_IB_GID_INDEX:-$best_gid_index}\n export UCX_IB_GID_INDEX=${UCX_IB_GID_INDEX:-$best_gid_index}\n\n echo \"[Infer RoCE] Exported GID_INDEX=${best_gid_index} for NCCL, NVSHMEM, and UCX\"\n else\n \ echo \"[Infer RoCE] ERROR: No valid IPv4 ${KSERVE_INFER_IB_GID_INDEX_GREP} GID_INDEX found on any HCA.\"\n fi\n else\n echo \"[Infer RoCE] No active HCAs found, skipping GID_INDEX inference.\"\n fi\nfi\n\neval \"vllm serve /mnt/models \\\n --served-model-name \"{{ .Spec.Model.Name }}\" \\\n --port 8001 \\\n ${VLLM_ADDITIONAL_ARGS} \\\n --enable-ssl-refresh \\\n --ssl-certfile /var/run/kserve/tls/tls.crt \\\n --ssl-keyfile /var/run/kserve/tls/tls.key\"] command:[/bin/bash -c] env:[map[name:HOME value:/home] map[name:VLLM_LOGGING_LEVEL value:INFO] map[name:HF_HUB_CACHE value:/models]] image:registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:fc68d623d1bfc36c8cb2fe4a71f19c8578cfb420ce8ce07b20a02c1ee0be0cf3 imagePullPolicy:IfNotPresent livenessProbe:map[failureThreshold:%!s(int64=3) httpGet:map[path:/health port:%!s(int64=8001) scheme:HTTPS] initialDelaySeconds:%!s(int64=120) periodSeconds:%!s(int64=10) timeoutSeconds:%!s(int64=10)] name:main ports:[map[containerPort:%!s(int64=8001) protocol:TCP]] readinessProbe:map[failureThreshold:%!s(int64=60) httpGet:map[path:/health port:%!s(int64=8001) scheme:HTTPS] initialDelaySeconds:%!s(int64=10) periodSeconds:%!s(int64=10) timeoutSeconds:%!s(int64=5)] securityContext:map[allowPrivilegeEscalation:%!s(bool=false) capabilities:map[drop:[ALL]] readOnlyRootFilesystem:%!s(bool=false) runAsNonRoot:%!s(bool=true) seccompProfile:map[type:RuntimeDefault]] terminationMessagePath:/dev/termination-log terminationMessagePolicy:FallbackToLogsOnError volumeMounts:[map[mountPath:/home name:home] map[mountPath:/dev/shm name:dshm] map[mountPath:/models name:model-cache] map[mountPath:/var/run/kserve/tls name:tls-certs readOnly:%!s(bool=true)]]]] initContainers:[map[args:[--port=8000 --vllm-port=8001 --connector=nixlv2 --secure-proxy=true --cert-path=/var/run/kserve/tls --decoder-use-tls=true --prefiller-use-tls=true --enable-ssrf-protection=true --pool-group=inference.networking.x-k8s.io] env:[map[name:INFERENCE_POOL_NAMESPACE valueFrom:map[fieldRef:map[fieldPath:metadata.namespace]]] map[name:SSL_CERT_DIR value:/var/run/kserve/tls:/var/run/secrets/kubernetes.io/serviceaccount:/etc/pki/tls/certs]] image:quay.io/opendatahub/llm-d-routing-sidecar:release-v0.4 imagePullPolicy:IfNotPresent livenessProbe:map[failureThreshold:%!s(int64=3) httpGet:map[path:/health port:%!s(int64=8000) scheme:HTTPS] initialDelaySeconds:%!s(int64=10) periodSeconds:%!s(int64=10) timeoutSeconds:%!s(int64=10)] name:llm-d-routing-sidecar ports:[map[containerPort:%!s(int64=8000) protocol:TCP]] readinessProbe:map[failureThreshold:%!s(int64=10) httpGet:map[path:/health port:%!s(int64=8000) scheme:HTTPS] initialDelaySeconds:%!s(int64=10) periodSeconds:%!s(int64=10) timeoutSeconds:%!s(int64=5)] resources:map[] restartPolicy:Always securityContext:map[allowPrivilegeEscalation:%!s(bool=false) capabilities:map[drop:[ALL]] readOnlyRootFilesystem:%!s(bool=false) runAsNonRoot:%!s(bool=true)] terminationMessagePath:/dev/termination-log terminationMessagePolicy:FallbackToLogsOnError volumeMounts:[map[mountPath:/var/run/kserve/tls name:tls-certs readOnly:%!s(bool=true)]]]] terminationGracePeriodSeconds:%!s(int64=30) volumes:[map[emptyDir:map[] name:home] map[emptyDir:map[medium:Memory sizeLimit:1Gi] name:dshm] map[emptyDir:map[] name:model-cache] map[name:tls-certs secret:map[secretName:{{ ChildName .ObjectMeta.Name `-kserve-self-signed-certs` }}]]]]]]}: apply failed serving.kserve.io/v1alpha1, Kind=LLMInferenceServiceConfig: unable to patch serving.kserve.io/v1alpha1, Kind=LLMInferenceServiceConfig opendatahub/v3-4-0-ea-1-kserve-config-llm-decode-template: Internal error occurred: failed calling webhook \"llminferenceserviceconfig.kserve-webhook-server.validator\": failed to call webhook: Post \"https://kserve-webhook-server-service.opendatahub.svc:443/validate-serving-kserve-io-v1alpha1-llminferenceserviceconfig?timeout=10s\": no endpoints available for service \"kserve-webhook-server-service\"" metadata: creationTimestamp: "2026-05-28T15:14:50Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: manager operation: Update time: "2026-05-28T15:15:17Z" name: default-kserve.18b3c38d947770f2 namespace: default resourceVersion: "16564" uid: b4234dfc-7ba4-4d28-98b2-5ad4ab2aa937 reason: ProvisioningError reportingComponent: kserve reportingInstance: "" source: component: kserve type: Warning - apiVersion: v1 count: 32 eventTime: null firstTimestamp: "2026-05-28T15:14:41Z" involvedObject: apiVersion: services.platform.opendatahub.io/v1alpha1 kind: Monitoring name: default-monitoring resourceVersion: "14714" uid: 296669b5-eb86-4ba0-8849-5efc70a9a8db kind: Event lastTimestamp: "2026-05-28T15:31:49Z" message: 'error fetching list of deployments: unable to list: opendatahub-monitoring because of unknown namespace for the cache' metadata: creationTimestamp: "2026-05-28T15:14:41Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: manager operation: Update time: "2026-05-28T15:31:49Z" name: default-monitoring.18b3c38b58f8b576 namespace: default resourceVersion: "35996" uid: 900f9821-90b0-4001-9bb5-6d95d3c5cc7b reason: ProvisioningError reportingComponent: monitoring reportingInstance: "" source: component: monitoring type: Warning - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-28T15:07:43Z" involvedObject: kind: Node name: ip-10-0-135-61.ec2.internal uid: ip-10-0-135-61.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:43Z" message: 'Node ip-10-0-135-61.ec2.internal status is now: NodeHasSufficientMemory' metadata: creationTimestamp: "2026-05-28T15:07:43Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:43Z" name: ip-10-0-135-61.ec2.internal.18b3c32a300ca880 namespace: default resourceVersion: "5993" uid: 774907ce-8bd6-4b5c-b244-035c10e4db1f reason: NodeHasSufficientMemory reportingComponent: kubelet reportingInstance: ip-10-0-135-61.ec2.internal source: component: kubelet host: ip-10-0-135-61.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-28T15:07:43Z" involvedObject: kind: Node name: ip-10-0-135-61.ec2.internal uid: ip-10-0-135-61.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:43Z" message: 'Node ip-10-0-135-61.ec2.internal status is now: NodeHasNoDiskPressure' metadata: creationTimestamp: "2026-05-28T15:07:43Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:43Z" name: ip-10-0-135-61.ec2.internal.18b3c32a300cf5f8 namespace: default resourceVersion: "5997" uid: c077f52b-4109-4eff-85e2-2cf39e0cebd0 reason: NodeHasNoDiskPressure reportingComponent: kubelet reportingInstance: ip-10-0-135-61.ec2.internal source: component: kubelet host: ip-10-0-135-61.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-28T15:07:43Z" involvedObject: kind: Node name: ip-10-0-135-61.ec2.internal uid: ip-10-0-135-61.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:43Z" message: 'Node ip-10-0-135-61.ec2.internal status is now: NodeHasSufficientPID' metadata: creationTimestamp: "2026-05-28T15:07:43Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:44Z" name: ip-10-0-135-61.ec2.internal.18b3c32a300d2d33 namespace: default resourceVersion: "6003" uid: eaaed2aa-b73a-43e9-bce2-658ab17f6a74 reason: NodeHasSufficientPID reportingComponent: kubelet reportingInstance: ip-10-0-135-61.ec2.internal source: component: kubelet host: ip-10-0-135-61.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:43Z" involvedObject: kind: Node name: ip-10-0-135-61.ec2.internal uid: ip-10-0-135-61.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:43Z" message: Updated Node Allocatable limit across pods metadata: creationTimestamp: "2026-05-28T15:07:43Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:43Z" name: ip-10-0-135-61.ec2.internal.18b3c32a326a52e9 namespace: default resourceVersion: "5906" uid: 00b2a872-179f-483e-976f-3d3a92ec9207 reason: NodeAllocatableEnforced reportingComponent: kubelet reportingInstance: ip-10-0-135-61.ec2.internal source: component: kubelet host: ip-10-0-135-61.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:44Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-135-61.ec2.internal resourceVersion: "5910" uid: 59ad1414-b01b-4199-b581-0120e3729e7b kind: Event lastTimestamp: "2026-05-28T15:07:44Z" message: Node synced successfully metadata: creationTimestamp: "2026-05-28T15:07:44Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: aws-cloud-controller-manager operation: Update time: "2026-05-28T15:07:44Z" name: ip-10-0-135-61.ec2.internal.18b3c32a482fe842 namespace: default resourceVersion: "6013" uid: ef786bda-8917-4ce6-a612-8fb0fbc6df02 reason: Synced reportingComponent: cloud-node-controller reportingInstance: "" source: component: cloud-node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:46Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-135-61.ec2.internal uid: 59ad1414-b01b-4199-b581-0120e3729e7b kind: Event lastTimestamp: "2026-05-28T15:07:46Z" message: 'Node ip-10-0-135-61.ec2.internal event: Registered Node ip-10-0-135-61.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-28T15:07:46Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: kube-controller-manager operation: Update time: "2026-05-28T15:07:46Z" name: ip-10-0-135-61.ec2.internal.18b3c32acd142f63 namespace: default resourceVersion: "6070" uid: 1b291a4f-a18f-4eeb-b92e-237268452dcb reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:14Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-135-61.ec2.internal resourceVersion: "6711" uid: 59ad1414-b01b-4199-b581-0120e3729e7b kind: Event lastTimestamp: "2026-05-28T15:08:14Z" message: '[k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-135-61.ec2.internal, error getting gateway config for node ip-10-0-135-61.ec2.internal: k8s.ovn.org/l3-gateway-config annotation not found for node "ip-10-0-135-61.ec2.internal", failed to update chassis to local for local node ip-10-0-135-61.ec2.internal, error: failed to parse node chassis-id for node - ip-10-0-135-61.ec2.internal, error: k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-135-61.ec2.internal]' metadata: creationTimestamp: "2026-05-28T15:08:14Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: ip-10-0-135-61 operation: Update time: "2026-05-28T15:08:14Z" name: ip-10-0-135-61.ec2.internal.18b3c3314f398cda namespace: default resourceVersion: "6715" uid: 23d23cb9-9c91-48c0-9e8c-7c8a8f421287 reason: ErrorAddingResource reportingComponent: ovnk-controlplane reportingInstance: "" source: component: ovnk-controlplane type: Warning - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:19Z" involvedObject: kind: Node name: ip-10-0-135-61.ec2.internal uid: ip-10-0-135-61.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:08:19Z" message: 'Node ip-10-0-135-61.ec2.internal status is now: NodeReady' metadata: creationTimestamp: "2026-05-28T15:08:19Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:08:19Z" name: ip-10-0-135-61.ec2.internal.18b3c3326ab626fc namespace: default resourceVersion: "6798" uid: d86cde2d-ed88-49ff-b327-d4f28f19301a reason: NodeReady reportingComponent: kubelet reportingInstance: ip-10-0-135-61.ec2.internal source: component: kubelet host: ip-10-0-135-61.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:10:01Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-135-61.ec2.internal uid: 59ad1414-b01b-4199-b581-0120e3729e7b kind: Event lastTimestamp: "2026-05-28T15:10:01Z" message: 'Node ip-10-0-135-61.ec2.internal event: Registered Node ip-10-0-135-61.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-28T15:10:01Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: kube-controller-manager operation: Update time: "2026-05-28T15:10:01Z" name: ip-10-0-135-61.ec2.internal.18b3c34a55a12723 namespace: default resourceVersion: "8071" uid: ef610d5e-809d-41a9-94a5-01156947e83e reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:40Z" involvedObject: kind: Node name: ip-10-0-137-0.ec2.internal uid: ip-10-0-137-0.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:40Z" message: Starting kubelet. metadata: creationTimestamp: "2026-05-28T15:07:40Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:40Z" name: ip-10-0-137-0.ec2.internal.18b3c32975263f96 namespace: default resourceVersion: "5689" uid: 8327cd7c-2af4-419e-b77c-10384ad42f49 reason: Starting reportingComponent: kubelet reportingInstance: ip-10-0-137-0.ec2.internal source: component: kubelet host: ip-10-0-137-0.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-28T15:07:40Z" involvedObject: kind: Node name: ip-10-0-137-0.ec2.internal uid: ip-10-0-137-0.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:40Z" message: 'Node ip-10-0-137-0.ec2.internal status is now: NodeHasSufficientMemory' metadata: creationTimestamp: "2026-05-28T15:07:40Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:40Z" name: ip-10-0-137-0.ec2.internal.18b3c32977035e30 namespace: default resourceVersion: "5782" uid: 6e9a0dd6-3ae7-4342-b81d-56c4162c815b reason: NodeHasSufficientMemory reportingComponent: kubelet reportingInstance: ip-10-0-137-0.ec2.internal source: component: kubelet host: ip-10-0-137-0.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-28T15:07:40Z" involvedObject: kind: Node name: ip-10-0-137-0.ec2.internal uid: ip-10-0-137-0.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:40Z" message: 'Node ip-10-0-137-0.ec2.internal status is now: NodeHasNoDiskPressure' metadata: creationTimestamp: "2026-05-28T15:07:40Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:40Z" name: ip-10-0-137-0.ec2.internal.18b3c3297703b809 namespace: default resourceVersion: "5784" uid: 85aac248-f2ae-4e57-9cbc-725b217c4a46 reason: NodeHasNoDiskPressure reportingComponent: kubelet reportingInstance: ip-10-0-137-0.ec2.internal source: component: kubelet host: ip-10-0-137-0.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-28T15:07:40Z" involvedObject: kind: Node name: ip-10-0-137-0.ec2.internal uid: ip-10-0-137-0.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:40Z" message: 'Node ip-10-0-137-0.ec2.internal status is now: NodeHasSufficientPID' metadata: creationTimestamp: "2026-05-28T15:07:40Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:40Z" name: ip-10-0-137-0.ec2.internal.18b3c3297703f1a1 namespace: default resourceVersion: "5785" uid: 2fb27175-b202-48dc-bfc1-b84c1f96f830 reason: NodeHasSufficientPID reportingComponent: kubelet reportingInstance: ip-10-0-137-0.ec2.internal source: component: kubelet host: ip-10-0-137-0.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:40Z" involvedObject: kind: Node name: ip-10-0-137-0.ec2.internal uid: ip-10-0-137-0.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:40Z" message: Updated Node Allocatable limit across pods metadata: creationTimestamp: "2026-05-28T15:07:40Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:40Z" name: ip-10-0-137-0.ec2.internal.18b3c3297a4c7d76 namespace: default resourceVersion: "5693" uid: 687a8713-4b93-4f85-8693-aaaf63efc200 reason: NodeAllocatableEnforced reportingComponent: kubelet reportingInstance: ip-10-0-137-0.ec2.internal source: component: kubelet host: ip-10-0-137-0.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:40Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-137-0.ec2.internal resourceVersion: "5694" uid: 9818da2c-1375-47af-a519-ddd8b9378581 kind: Event lastTimestamp: "2026-05-28T15:07:40Z" message: Node synced successfully metadata: creationTimestamp: "2026-05-28T15:07:40Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: aws-cloud-controller-manager operation: Update time: "2026-05-28T15:07:40Z" name: ip-10-0-137-0.ec2.internal.18b3c3298df3ff32 namespace: default resourceVersion: "5789" uid: 13273b4f-bbc0-443f-915b-e9577a8353c2 reason: Synced reportingComponent: cloud-node-controller reportingInstance: "" source: component: cloud-node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:41Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-137-0.ec2.internal uid: 9818da2c-1375-47af-a519-ddd8b9378581 kind: Event lastTimestamp: "2026-05-28T15:07:41Z" message: 'Node ip-10-0-137-0.ec2.internal event: Registered Node ip-10-0-137-0.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-28T15:07:41Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: kube-controller-manager operation: Update time: "2026-05-28T15:07:41Z" name: ip-10-0-137-0.ec2.internal.18b3c329a2ff1351 namespace: default resourceVersion: "5797" uid: 949a8848-7fa6-4324-a067-3c6f1dc568f9 reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:08Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-137-0.ec2.internal resourceVersion: "6591" uid: 9818da2c-1375-47af-a519-ddd8b9378581 kind: Event lastTimestamp: "2026-05-28T15:08:08Z" message: '[k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-137-0.ec2.internal, error getting gateway config for node ip-10-0-137-0.ec2.internal: k8s.ovn.org/l3-gateway-config annotation not found for node "ip-10-0-137-0.ec2.internal", failed to update chassis to local for local node ip-10-0-137-0.ec2.internal, error: failed to parse node chassis-id for node - ip-10-0-137-0.ec2.internal, error: k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-137-0.ec2.internal]' metadata: creationTimestamp: "2026-05-28T15:08:08Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: ip-10-0-137-0 operation: Update time: "2026-05-28T15:08:08Z" name: ip-10-0-137-0.ec2.internal.18b3c32fd9a76f4f namespace: default resourceVersion: "6604" uid: faa23ebd-cb33-4c10-a25c-e5971f985d82 reason: ErrorAddingResource reportingComponent: ovnk-controlplane reportingInstance: "" source: component: ovnk-controlplane type: Warning - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:14Z" involvedObject: kind: Node name: ip-10-0-137-0.ec2.internal uid: ip-10-0-137-0.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:08:14Z" message: 'Node ip-10-0-137-0.ec2.internal status is now: NodeReady' metadata: creationTimestamp: "2026-05-28T15:08:14Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:08:14Z" name: ip-10-0-137-0.ec2.internal.18b3c33154c4ba5f namespace: default resourceVersion: "6718" uid: 37157935-b006-4049-9959-e66c95421ec7 reason: NodeReady reportingComponent: kubelet reportingInstance: ip-10-0-137-0.ec2.internal source: component: kubelet host: ip-10-0-137-0.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:10:01Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-137-0.ec2.internal uid: 9818da2c-1375-47af-a519-ddd8b9378581 kind: Event lastTimestamp: "2026-05-28T15:10:01Z" message: 'Node ip-10-0-137-0.ec2.internal event: Registered Node ip-10-0-137-0.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-28T15:10:01Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: kube-controller-manager operation: Update time: "2026-05-28T15:10:01Z" name: ip-10-0-137-0.ec2.internal.18b3c34a55a2a310 namespace: default resourceVersion: "8072" uid: ce5a53c2-a566-4c6e-9a4d-d48e80855d31 reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-28T15:07:29Z" involvedObject: kind: Node name: ip-10-0-140-141.ec2.internal uid: ip-10-0-140-141.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:29Z" message: 'Node ip-10-0-140-141.ec2.internal status is now: NodeHasSufficientMemory' metadata: creationTimestamp: "2026-05-28T15:07:29Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:29Z" name: ip-10-0-140-141.ec2.internal.18b3c326e6e6ce7d namespace: default resourceVersion: "5508" uid: 5783fdeb-10e2-4627-a60b-55fbd88a5ae8 reason: NodeHasSufficientMemory reportingComponent: kubelet reportingInstance: ip-10-0-140-141.ec2.internal source: component: kubelet host: ip-10-0-140-141.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-28T15:07:29Z" involvedObject: kind: Node name: ip-10-0-140-141.ec2.internal uid: ip-10-0-140-141.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:29Z" message: 'Node ip-10-0-140-141.ec2.internal status is now: NodeHasNoDiskPressure' metadata: creationTimestamp: "2026-05-28T15:07:29Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:29Z" name: ip-10-0-140-141.ec2.internal.18b3c326e6e715df namespace: default resourceVersion: "5509" uid: 5f435c25-b48b-4be4-8e1c-d4f31c12d50c reason: NodeHasNoDiskPressure reportingComponent: kubelet reportingInstance: ip-10-0-140-141.ec2.internal source: component: kubelet host: ip-10-0-140-141.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-28T15:07:29Z" involvedObject: kind: Node name: ip-10-0-140-141.ec2.internal uid: ip-10-0-140-141.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:29Z" message: 'Node ip-10-0-140-141.ec2.internal status is now: NodeHasSufficientPID' metadata: creationTimestamp: "2026-05-28T15:07:29Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:29Z" name: ip-10-0-140-141.ec2.internal.18b3c326e6e73eb0 namespace: default resourceVersion: "5511" uid: d33bd11b-4f0e-4ba3-821a-a05f534ec555 reason: NodeHasSufficientPID reportingComponent: kubelet reportingInstance: ip-10-0-140-141.ec2.internal source: component: kubelet host: ip-10-0-140-141.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:29Z" involvedObject: kind: Node name: ip-10-0-140-141.ec2.internal uid: ip-10-0-140-141.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:07:29Z" message: Updated Node Allocatable limit across pods metadata: creationTimestamp: "2026-05-28T15:07:29Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:07:29Z" name: ip-10-0-140-141.ec2.internal.18b3c326e9543d1e namespace: default resourceVersion: "5448" uid: 29f6d0d2-8071-4710-b2f2-09bad1c94cc0 reason: NodeAllocatableEnforced reportingComponent: kubelet reportingInstance: ip-10-0-140-141.ec2.internal source: component: kubelet host: ip-10-0-140-141.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:30Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-140-141.ec2.internal resourceVersion: "5449" uid: a20462f6-d5d4-415b-b74a-b2903e5cc5a6 kind: Event lastTimestamp: "2026-05-28T15:07:30Z" message: Node synced successfully metadata: creationTimestamp: "2026-05-28T15:07:30Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: aws-cloud-controller-manager operation: Update time: "2026-05-28T15:07:30Z" name: ip-10-0-140-141.ec2.internal.18b3c327002f4e86 namespace: default resourceVersion: "5528" uid: a9d5d1c8-55e6-4311-9a15-9ac0cc8aa034 reason: Synced reportingComponent: cloud-node-controller reportingInstance: "" source: component: cloud-node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:07:31Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-140-141.ec2.internal uid: a20462f6-d5d4-415b-b74a-b2903e5cc5a6 kind: Event lastTimestamp: "2026-05-28T15:07:31Z" message: 'Node ip-10-0-140-141.ec2.internal event: Registered Node ip-10-0-140-141.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-28T15:07:31Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: kube-controller-manager operation: Update time: "2026-05-28T15:07:31Z" name: ip-10-0-140-141.ec2.internal.18b3c3274ed15742 namespace: default resourceVersion: "5589" uid: 929af333-78c7-4426-a1c3-0af027a6f29e reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:00Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-140-141.ec2.internal resourceVersion: "6297" uid: a20462f6-d5d4-415b-b74a-b2903e5cc5a6 kind: Event lastTimestamp: "2026-05-28T15:08:00Z" message: '[k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-140-141.ec2.internal, error getting gateway config for node ip-10-0-140-141.ec2.internal: k8s.ovn.org/l3-gateway-config annotation not found for node "ip-10-0-140-141.ec2.internal", failed to update chassis to local for local node ip-10-0-140-141.ec2.internal, error: failed to parse node chassis-id for node - ip-10-0-140-141.ec2.internal, error: k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-140-141.ec2.internal]' metadata: creationTimestamp: "2026-05-28T15:08:00Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: ip-10-0-140-141 operation: Update time: "2026-05-28T15:08:00Z" name: ip-10-0-140-141.ec2.internal.18b3c32e06a952f7 namespace: default resourceVersion: "6299" uid: b7570867-b4c5-45f7-ab7f-a23b0606a4e3 reason: ErrorAddingResource reportingComponent: ovnk-controlplane reportingInstance: "" source: component: ovnk-controlplane type: Warning - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:08:06Z" involvedObject: kind: Node name: ip-10-0-140-141.ec2.internal uid: ip-10-0-140-141.ec2.internal kind: Event lastTimestamp: "2026-05-28T15:08:06Z" message: 'Node ip-10-0-140-141.ec2.internal status is now: NodeReady' metadata: creationTimestamp: "2026-05-28T15:08:06Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:reportingInstance: {} f:source: f:component: {} f:host: {} f:type: {} manager: kubelet operation: Update time: "2026-05-28T15:08:06Z" name: ip-10-0-140-141.ec2.internal.18b3c32f79aefa25 namespace: default resourceVersion: "6518" uid: 4bb261d4-07b9-4806-8624-024da57cbf33 reason: NodeReady reportingComponent: kubelet reportingInstance: ip-10-0-140-141.ec2.internal source: component: kubelet host: ip-10-0-140-141.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:10:01Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-140-141.ec2.internal uid: a20462f6-d5d4-415b-b74a-b2903e5cc5a6 kind: Event lastTimestamp: "2026-05-28T15:10:01Z" message: 'Node ip-10-0-140-141.ec2.internal event: Registered Node ip-10-0-140-141.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-28T15:10:01Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: kube-controller-manager operation: Update time: "2026-05-28T15:10:01Z" name: ip-10-0-140-141.ec2.internal.18b3c34a55a2c445 namespace: default resourceVersion: "8078" uid: b3c89e2f-101e-4fa6-a9e3-a0107830cc33 reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 10 eventTime: null firstTimestamp: "2026-05-28T15:15:50Z" involvedObject: apiVersion: v1 kind: Namespace name: kuadrant-system resourceVersion: "16832" uid: eb452a14-2af6-4f2f-a709-9003ac61e73e kind: Event lastTimestamp: "2026-05-28T15:15:53Z" message: 'error using catalogsource kuadrant-system/kuadrant-operator-catalog: failed to list bundles: rpc error: code = Unavailable desc = connection error: desc = "error reading server preface: http2: frame too large"' metadata: creationTimestamp: "2026-05-28T15:15:51Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:count: {} f:firstTimestamp: {} f:involvedObject: {} f:lastTimestamp: {} f:message: {} f:reason: {} f:reportingComponent: {} f:source: f:component: {} f:type: {} manager: catalog operation: Update time: "2026-05-28T15:15:56Z" name: kuadrant-system.18b3c39b8d2df400 namespace: default resourceVersion: "17162" uid: f94fb849-b825-445a-a588-8bc197979697 reason: ResolutionFailed reportingComponent: operator-lifecycle-manager reportingInstance: "" source: component: operator-lifecycle-manager type: Warning - apiVersion: v1 eventTime: null firstTimestamp: null involvedObject: apiVersion: v1 kind: Namespace name: kube-system namespace: default kind: Event lastTimestamp: null message: Received signal to terminate, becoming unready, but keeping serving metadata: creationTimestamp: "2026-05-28T15:09:42Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:involvedObject: {} f:message: {} f:reason: {} f:source: f:component: {} f:host: {} f:type: {} manager: openshift-apiserver operation: Update time: "2026-05-28T15:09:42Z" name: kube-system.18b3c345d7d36627 namespace: default resourceVersion: "7722" uid: 5c42ca58-8abc-4ff6-aebf-0c8a4b50fe1d reason: TerminationStart reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-767647d49c-k9xrs type: Normal - apiVersion: v1 eventTime: null firstTimestamp: null involvedObject: apiVersion: v1 kind: Namespace name: kube-system namespace: default kind: Event lastTimestamp: null message: The minimal shutdown duration of 15s finished metadata: creationTimestamp: "2026-05-28T15:09:57Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:involvedObject: {} f:message: {} f:reason: {} f:source: f:component: {} f:host: {} f:type: {} manager: openshift-apiserver operation: Update time: "2026-05-28T15:09:57Z" name: kube-system.18b3c349562eb619 namespace: default resourceVersion: "7986" uid: 31393f49-a862-4a74-89e1-ce8523a7419e reason: TerminationMinimalShutdownDurationFinished reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-767647d49c-k9xrs type: Normal - apiVersion: v1 eventTime: null firstTimestamp: null involvedObject: apiVersion: v1 kind: Namespace name: kube-system namespace: default kind: Event lastTimestamp: null message: Server has stopped listening metadata: creationTimestamp: "2026-05-28T15:09:57Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:involvedObject: {} f:message: {} f:reason: {} f:source: f:component: {} f:host: {} f:type: {} manager: openshift-apiserver operation: Update time: "2026-05-28T15:09:57Z" name: kube-system.18b3c3495667f7c2 namespace: default resourceVersion: "7987" uid: 6dff5e3b-a4e5-4f7e-bc8e-f1d42c510d72 reason: TerminationStoppedServing reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-767647d49c-k9xrs type: Normal - apiVersion: v1 eventTime: null firstTimestamp: null involvedObject: apiVersion: v1 kind: Namespace name: kube-system namespace: default kind: Event lastTimestamp: null message: All pre-shutdown hooks have been finished metadata: creationTimestamp: "2026-05-28T15:09:57Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:involvedObject: {} f:message: {} f:reason: {} f:source: f:component: {} f:host: {} f:type: {} manager: openshift-apiserver operation: Update time: "2026-05-28T15:09:57Z" name: kube-system.18b3c34956bb0f7c namespace: default resourceVersion: "7988" uid: e96a3f00-89cb-483e-ac96-5ee7acd9eaa1 reason: TerminationPreShutdownHooksFinished reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-767647d49c-k9xrs type: Normal - apiVersion: v1 eventTime: null firstTimestamp: null involvedObject: apiVersion: v1 kind: Namespace name: kube-system namespace: default kind: Event lastTimestamp: null message: All pending requests processed metadata: creationTimestamp: "2026-05-28T15:10:57Z" managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:involvedObject: {} f:message: {} f:reason: {} f:source: f:component: {} f:host: {} f:type: {} manager: openshift-apiserver operation: Update time: "2026-05-28T15:10:57Z" name: kube-system.18b3c3574eb96a43 namespace: default resourceVersion: "9874" uid: e9fce55d-ec2f-480f-b6a4-5d271440ee29 reason: TerminationGracefulTerminationFinished reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-767647d49c-k9xrs type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-28T15:02:43Z" involvedObject: apiVersion: v1 kind: Namespace name: openshift-kube-apiserver namespace: default kind: Event lastTimestamp: "2026-05-28T15:02:43Z" message: readyz=true metadata: creationTimestamp: "2026-05-28T15:02:43Z" name: openshift-kube-apiserver.18b3c2e431552976 namespace: default resourceVersion: "274" uid: 114ec1b2-d2cc-4079-869e-88c203f40731 reason: KubeAPIReadyz reportingComponent: "" reportingInstance: "" source: component: apiserver host: kube-apiserver-659dc8775b-rzkgw type: Warning kind: EventList metadata: resourceVersion: "47002"