--- apiVersion: v1 items: - apiVersion: v1 count: 11 eventTime: null firstTimestamp: "2026-05-21T13:07:31Z" involvedObject: apiVersion: services.platform.opendatahub.io/v1alpha1 kind: Auth name: auth resourceVersion: "13666" uid: eeff1c2c-add3-435d-a0c4-fc30cc7614bd kind: Event lastTimestamp: "2026-05-21T13:07:37Z" message: 'failure deploying resource {map[apiVersion:rbac.authorization.k8s.io/v1 kind:Role metadata:map[annotations:map[platform.opendatahub.io/instance.generation:1 platform.opendatahub.io/instance.name:auth platform.opendatahub.io/instance.uid:eeff1c2c-add3-435d-a0c4-fc30cc7614bd platform.opendatahub.io/type:Open Data Hub platform.opendatahub.io/version:3.4.0-ea.1] labels:map[platform.opendatahub.io/part-of:auth] name:data-science-admingroup-role namespace:opendatahub ownerReferences:[map[apiVersion:services.platform.opendatahub.io/v1alpha1 blockOwnerDeletion:%!s(bool=true) controller:%!s(bool=true) kind:Auth name:auth uid:eeff1c2c-add3-435d-a0c4-fc30cc7614bd]]] rules:[map[apiGroups:[services.platform.opendatahub.io] resources:[auths] verbs:[get list watch patch update]] map[apiGroups:[services.opendatahub.io] resources:[auths/status] verbs:[get]] map[apiGroups:[infrastructure.opendatahub.io] resources:[hardwareprofiles] verbs:[create get list watch patch update delete]] map[apiGroups:[route.openshift.io] resources:[routes] verbs:[get list watch]] map[apiGroups:[batch] resources:[cronjobs] verbs:[get update watch]] map[apiGroups:[image.openshift.io] resources:[imagestreams] verbs:[create get list patch update delete watch]] map[apiGroups:[build.openshift.io] resources:[builds buildconfigs] verbs:[list get watch]] map[apiGroups:[apps] resources:[deployments] verbs:[patch update]] map[apiGroups:[opendatahub.io] resources:[odhdashboardconfigs] verbs:[get list watch create update patch]] map[apiGroups:[dashboard.opendatahub.io] resources:[odhapplications odhdocuments] verbs:[get list watch]] map[apiGroups:[console.openshift.io] resources:[odhquickstarts] verbs:[get list watch]] map[apiGroups:[template.openshift.io] resources:[templates] verbs:[get list watch create patch update delete]] map[apiGroups:[serving.kserve.io] resources:[servingruntimes] verbs:[create]] map[apiGroups:[nim.opendatahub.io] resources:[accounts] verbs:[watch update get list create patch delete]] map[apiGroups:[] resourceNames:[tier-to-group-mapping] resources:[configmaps] verbs:[get list watch patch update]]]]}: apply failed rbac.authorization.k8s.io/v1, Kind=Role: unable to patch rbac.authorization.k8s.io/v1, Kind=Role opendatahub/data-science-admingroup-role: roles.rbac.authorization.k8s.io "data-science-admingroup-role" is forbidden: cannot set blockOwnerDeletion in this case because cannot find RESTMapping for APIVersion services.platform.opendatahub.io/v1alpha1 Kind Auth: no matches for kind "Auth" in version "services.platform.opendatahub.io/v1alpha1"' metadata: creationTimestamp: "2026-05-21T13:07:31Z" 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: manager operation: Update time: "2026-05-21T13:07:37Z" name: auth.18b1968aed44ef16 namespace: default resourceVersion: "13945" uid: 479d4c0d-2974-49aa-b8f6-2473d2403780 reason: ProvisioningError reportingComponent: auth reportingInstance: "" source: component: auth type: Warning - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:59Z" involvedObject: kind: CertificateSigningRequest name: csr-gd2ws kind: Event lastTimestamp: "2026-05-21T13:02:59Z" message: CSR "csr-gd2ws" has been approved metadata: creationTimestamp: "2026-05-21T13:02:59Z" 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: "2026-05-21T13:02:59Z" name: csr-gd2ws.18b1964bbc111a6c namespace: default resourceVersion: "6348" uid: 0df3bade-10bf-41b2-8c63-87808a0589c4 reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:34Z" involvedObject: kind: CertificateSigningRequest name: csr-k9smn kind: Event lastTimestamp: "2026-05-21T13:03:34Z" message: CSR "csr-k9smn" has been approved metadata: creationTimestamp: "2026-05-21T13:03:34Z" 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: "2026-05-21T13:03:34Z" name: csr-k9smn.18b19653c6a608ff namespace: default resourceVersion: "7526" uid: a4c6d6d2-c2d4-4f7b-9869-9dd1eb838056 reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:22Z" involvedObject: kind: CertificateSigningRequest name: csr-mv7wf kind: Event lastTimestamp: "2026-05-21T13:03:22Z" message: CSR "csr-mv7wf" has been approved metadata: creationTimestamp: "2026-05-21T13:03:22Z" 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: "2026-05-21T13:03:22Z" name: csr-mv7wf.18b19650e9a7084c namespace: default resourceVersion: "7030" uid: 509f92c5-e565-4d09-8f8e-de232324c15e reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:49Z" involvedObject: kind: CertificateSigningRequest name: csr-t7797 kind: Event lastTimestamp: "2026-05-21T13:02:49Z" message: CSR "csr-t7797" has been approved metadata: creationTimestamp: "2026-05-21T13:02:49Z" 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: "2026-05-21T13:02:49Z" name: csr-t7797.18b196494c5774ab namespace: default resourceVersion: "5920" uid: 293b3cb9-3ac4-4f94-a3c3-d4ac97267a76 reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:06Z" involvedObject: kind: CertificateSigningRequest name: csr-vpgcc kind: Event lastTimestamp: "2026-05-21T13:03:06Z" message: CSR "csr-vpgcc" has been approved metadata: creationTimestamp: "2026-05-21T13:03:06Z" 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: "2026-05-21T13:03:06Z" name: csr-vpgcc.18b1964d2d762e9d namespace: default resourceVersion: "6476" uid: 484d2bbb-cec8-49ae-a694-0e299994a2fe reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:44Z" involvedObject: kind: CertificateSigningRequest name: csr-wdpcz kind: Event lastTimestamp: "2026-05-21T13:02:44Z" message: CSR "csr-wdpcz" has been approved metadata: creationTimestamp: "2026-05-21T13:02:44Z" 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: ovnkube-identity operation: Update time: "2026-05-21T13:02:44Z" name: csr-wdpcz.18b196481f2994be namespace: default resourceVersion: "5823" uid: 19afa542-720b-4b8b-858a-e1187d83b5b7 reason: CSRApproved reportingComponent: ovnkube-csr-approver-controller reportingInstance: "" source: component: ovnkube-csr-approver-controller type: Normal - apiVersion: v1 count: 11 eventTime: null firstTimestamp: "2026-05-21T13:07:31Z" involvedObject: apiVersion: services.platform.opendatahub.io/v1alpha1 kind: GatewayConfig name: default-gateway resourceVersion: "13618" uid: 3ef4a297-854c-4a2e-80c2-dacc28dc6673 kind: Event lastTimestamp: "2026-05-21T13:07:37Z" message: 'failed to create auth proxy secret: secrets "kube-auth-proxy-creds" is forbidden: cannot set blockOwnerDeletion in this case because cannot find RESTMapping for APIVersion services.platform.opendatahub.io/v1alpha1 Kind GatewayConfig: no matches for kind "GatewayConfig" in version "services.platform.opendatahub.io/v1alpha1"' metadata: creationTimestamp: "2026-05-21T13:07:31Z" 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: manager operation: Update time: "2026-05-21T13:07:37Z" name: default-gateway.18b1968ae1170257 namespace: default resourceVersion: "13949" uid: d50d7a3b-97cd-4202-ab04-17c2d6483ce0 reason: ProvisioningError reportingComponent: gatewayconfig reportingInstance: "" source: component: gatewayconfig type: Warning - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:07:42Z" involvedObject: apiVersion: services.platform.opendatahub.io/v1alpha1 kind: GatewayConfig name: default-gateway resourceVersion: "14111" uid: 3ef4a297-854c-4a2e-80c2-dacc28dc6673 kind: Event lastTimestamp: "2026-05-21T13:07:42Z" message: 'failed to create OAuth client: failed to get auth proxy secret openshift-ingress/kube-auth-proxy-creds: Secret "kube-auth-proxy-creds" not found' metadata: creationTimestamp: "2026-05-21T13:07:42Z" 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: "2026-05-21T13:07:42Z" name: default-gateway.18b1968da0e42dac namespace: default resourceVersion: "14113" uid: 0fd3c6e5-7a0b-4d3c-a271-6597a77a6a8d reason: ProvisioningError reportingComponent: gatewayconfig reportingInstance: "" source: component: gatewayconfig type: Warning - apiVersion: v1 count: 4 eventTime: null firstTimestamp: "2026-05-21T13:07:43Z" involvedObject: apiVersion: services.platform.opendatahub.io/v1alpha1 kind: GatewayConfig name: default-gateway resourceVersion: "14169" uid: 3ef4a297-854c-4a2e-80c2-dacc28dc6673 kind: Event lastTimestamp: "2026-05-21T13:07:53Z" message: 'failed to lookup object openshift-ingress/data-science-tls-rule: no matches for kind "DestinationRule" in version "networking.istio.io/v1"' metadata: creationTimestamp: "2026-05-21T13:07:43Z" 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: "2026-05-21T13:07:53Z" name: default-gateway.18b1968db4b243d9 namespace: default resourceVersion: "14344" uid: 32e34df6-6be1-484a-8558-d2e7e799659c reason: ProvisioningError reportingComponent: gatewayconfig reportingInstance: "" source: component: gatewayconfig type: Warning - apiVersion: v1 count: 13 eventTime: null firstTimestamp: "2026-05-21T13:07:41Z" involvedObject: apiVersion: components.platform.opendatahub.io/v1alpha1 kind: Kserve name: default-kserve resourceVersion: "14092" uid: f595fd56-1bad-477e-ae75-8533723d1e2c kind: Event lastTimestamp: "2026-05-21T13:08:07Z" 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:f595fd56-1bad-477e-ae75-8533723d1e2c 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:f595fd56-1bad-477e-ae75-8533723d1e2c]]] 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: "2026-05-21T13:07:41Z" 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: manager operation: Update time: "2026-05-21T13:08:07Z" name: default-kserve.18b1968d60a8fcdd namespace: default resourceVersion: "15049" uid: a83cd2b2-f5fa-4ca8-81d3-efb999c37abd reason: ProvisioningError reportingComponent: kserve reportingInstance: "" source: component: kserve type: Warning - apiVersion: v1 count: 35 eventTime: null firstTimestamp: "2026-05-21T13:07:30Z" involvedObject: apiVersion: services.platform.opendatahub.io/v1alpha1 kind: Monitoring name: default-monitoring resourceVersion: "13584" uid: c26c764b-b6bf-4f5e-9bc5-b613f926ab67 kind: Event lastTimestamp: "2026-05-21T13:24:39Z" message: 'error fetching list of deployments: unable to list: opendatahub-monitoring because of unknown namespace for the cache' metadata: creationTimestamp: "2026-05-21T13:07:30Z" 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: manager operation: Update time: "2026-05-21T13:24:39Z" name: default-monitoring.18b1968adbe1a1d3 namespace: default resourceVersion: "35103" uid: 0a9cf2e4-f5c0-4a37-aa2a-504fab68c705 reason: ProvisioningError reportingComponent: monitoring reportingInstance: "" source: component: monitoring type: Warning - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-21T13:02:33Z" involvedObject: kind: Node name: ip-10-0-133-64.ec2.internal uid: ip-10-0-133-64.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:34Z" message: 'Node ip-10-0-133-64.ec2.internal status is now: NodeHasSufficientMemory' metadata: creationTimestamp: "2026-05-21T13:02:33Z" 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: "2026-05-21T13:02:34Z" name: ip-10-0-133-64.ec2.internal.18b19645b51986eb namespace: default resourceVersion: "5575" uid: cc849694-f0d6-4044-b343-5d7982cdeadf reason: NodeHasSufficientMemory reportingComponent: kubelet reportingInstance: ip-10-0-133-64.ec2.internal source: component: kubelet host: ip-10-0-133-64.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-21T13:02:33Z" involvedObject: kind: Node name: ip-10-0-133-64.ec2.internal uid: ip-10-0-133-64.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:34Z" message: 'Node ip-10-0-133-64.ec2.internal status is now: NodeHasNoDiskPressure' metadata: creationTimestamp: "2026-05-21T13:02:33Z" 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: "2026-05-21T13:02:34Z" name: ip-10-0-133-64.ec2.internal.18b19645b51a9662 namespace: default resourceVersion: "5576" uid: 284c523b-5ac2-4867-9e92-b7c8032acfbb reason: NodeHasNoDiskPressure reportingComponent: kubelet reportingInstance: ip-10-0-133-64.ec2.internal source: component: kubelet host: ip-10-0-133-64.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-21T13:02:33Z" involvedObject: kind: Node name: ip-10-0-133-64.ec2.internal uid: ip-10-0-133-64.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:34Z" message: 'Node ip-10-0-133-64.ec2.internal status is now: NodeHasSufficientPID' metadata: creationTimestamp: "2026-05-21T13:02:33Z" 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: "2026-05-21T13:02:34Z" name: ip-10-0-133-64.ec2.internal.18b19645b51acc71 namespace: default resourceVersion: "5577" uid: 291a2db4-3300-4d02-8e46-1712149440a0 reason: NodeHasSufficientPID reportingComponent: kubelet reportingInstance: ip-10-0-133-64.ec2.internal source: component: kubelet host: ip-10-0-133-64.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:33Z" involvedObject: kind: Node name: ip-10-0-133-64.ec2.internal uid: ip-10-0-133-64.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:33Z" message: Updated Node Allocatable limit across pods metadata: creationTimestamp: "2026-05-21T13:02:33Z" 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: "2026-05-21T13:02:33Z" name: ip-10-0-133-64.ec2.internal.18b19645b7bb31b6 namespace: default resourceVersion: "5487" uid: a57ccf5b-8653-4b2f-be22-d5352a14e4d1 reason: NodeAllocatableEnforced reportingComponent: kubelet reportingInstance: ip-10-0-133-64.ec2.internal source: component: kubelet host: ip-10-0-133-64.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:34Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-133-64.ec2.internal resourceVersion: "5489" uid: f3609f34-d37b-44c4-a023-20815cffafe7 kind: Event lastTimestamp: "2026-05-21T13:02:34Z" message: Node synced successfully metadata: creationTimestamp: "2026-05-21T13:02:34Z" 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: "2026-05-21T13:02:34Z" name: ip-10-0-133-64.ec2.internal.18b19645cdea839e namespace: default resourceVersion: "5583" uid: c09439ef-fd20-4e03-ac67-c8378409e9e2 reason: Synced reportingComponent: cloud-node-controller reportingInstance: "" source: component: cloud-node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:38Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-133-64.ec2.internal uid: f3609f34-d37b-44c4-a023-20815cffafe7 kind: Event lastTimestamp: "2026-05-21T13:02:38Z" message: 'Node ip-10-0-133-64.ec2.internal event: Registered Node ip-10-0-133-64.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-21T13:02:38Z" 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: kube-controller-manager operation: Update time: "2026-05-21T13:02:38Z" name: ip-10-0-133-64.ec2.internal.18b19646c240b270 namespace: default resourceVersion: "5710" uid: 8904bc40-5f29-486d-9014-003f5e366ebc reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:01Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-133-64.ec2.internal resourceVersion: "6371" uid: f3609f34-d37b-44c4-a023-20815cffafe7 kind: Event lastTimestamp: "2026-05-21T13:03:01Z" message: '[k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-133-64.ec2.internal, error getting gateway config for node ip-10-0-133-64.ec2.internal: k8s.ovn.org/l3-gateway-config annotation not found for node "ip-10-0-133-64.ec2.internal", failed to update chassis to local for local node ip-10-0-133-64.ec2.internal, error: failed to parse node chassis-id for node - ip-10-0-133-64.ec2.internal, error: k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-133-64.ec2.internal]' metadata: creationTimestamp: "2026-05-21T13:03:01Z" 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: ip-10-0-133-64 operation: Update time: "2026-05-21T13:03:01Z" name: ip-10-0-133-64.ec2.internal.18b1964c176e184a namespace: default resourceVersion: "6375" uid: b04a757e-b716-4076-a946-7c9ca0afc4a1 reason: ErrorAddingResource reportingComponent: ovnk-controlplane reportingInstance: "" source: component: ovnk-controlplane type: Warning - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:07Z" involvedObject: kind: Node name: ip-10-0-133-64.ec2.internal uid: ip-10-0-133-64.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:03:07Z" message: 'Node ip-10-0-133-64.ec2.internal status is now: NodeReady' metadata: creationTimestamp: "2026-05-21T13:03:07Z" 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: "2026-05-21T13:03:07Z" name: ip-10-0-133-64.ec2.internal.18b1964d7b5ddbe5 namespace: default resourceVersion: "6574" uid: 682c545d-065a-4f28-b569-228b5c0d88bb reason: NodeReady reportingComponent: kubelet reportingInstance: ip-10-0-133-64.ec2.internal source: component: kubelet host: ip-10-0-133-64.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:30Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-133-64.ec2.internal uid: f3609f34-d37b-44c4-a023-20815cffafe7 kind: Event lastTimestamp: "2026-05-21T13:03:30Z" message: 'Node ip-10-0-133-64.ec2.internal event: Registered Node ip-10-0-133-64.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-21T13:03:30Z" 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: kube-controller-manager operation: Update time: "2026-05-21T13:03:30Z" name: ip-10-0-133-64.ec2.internal.18b19652cbd58314 namespace: default resourceVersion: "7255" uid: b3662acb-6412-4e58-8e3b-9e8ca77bf4c1 reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-21T13:02:56Z" involvedObject: kind: Node name: ip-10-0-140-104.ec2.internal uid: ip-10-0-140-104.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:56Z" message: 'Node ip-10-0-140-104.ec2.internal status is now: NodeHasSufficientMemory' metadata: creationTimestamp: "2026-05-21T13:02:56Z" 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: "2026-05-21T13:02:57Z" name: ip-10-0-140-104.ec2.internal.18b1964b05a78fb8 namespace: default resourceVersion: "6194" uid: 1459e7be-192b-4f52-b3bf-5fd51749edca reason: NodeHasSufficientMemory reportingComponent: kubelet reportingInstance: ip-10-0-140-104.ec2.internal source: component: kubelet host: ip-10-0-140-104.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-21T13:02:56Z" involvedObject: kind: Node name: ip-10-0-140-104.ec2.internal uid: ip-10-0-140-104.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:56Z" message: 'Node ip-10-0-140-104.ec2.internal status is now: NodeHasNoDiskPressure' metadata: creationTimestamp: "2026-05-21T13:02:56Z" 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: "2026-05-21T13:02:57Z" name: ip-10-0-140-104.ec2.internal.18b1964b05a80f20 namespace: default resourceVersion: "6197" uid: 1c3e9185-5235-4a34-af3c-aa4a7ac407cd reason: NodeHasNoDiskPressure reportingComponent: kubelet reportingInstance: ip-10-0-140-104.ec2.internal source: component: kubelet host: ip-10-0-140-104.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-21T13:02:56Z" involvedObject: kind: Node name: ip-10-0-140-104.ec2.internal uid: ip-10-0-140-104.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:56Z" message: 'Node ip-10-0-140-104.ec2.internal status is now: NodeHasSufficientPID' metadata: creationTimestamp: "2026-05-21T13:02:56Z" 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: "2026-05-21T13:02:57Z" name: ip-10-0-140-104.ec2.internal.18b1964b05a85919 namespace: default resourceVersion: "6202" uid: 83e9ce61-dcbf-4c55-ad01-700ff6354696 reason: NodeHasSufficientPID reportingComponent: kubelet reportingInstance: ip-10-0-140-104.ec2.internal source: component: kubelet host: ip-10-0-140-104.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:56Z" involvedObject: kind: Node name: ip-10-0-140-104.ec2.internal uid: ip-10-0-140-104.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:56Z" message: Updated Node Allocatable limit across pods metadata: creationTimestamp: "2026-05-21T13:02:56Z" 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: "2026-05-21T13:02:56Z" name: ip-10-0-140-104.ec2.internal.18b1964b0876fe7f namespace: default resourceVersion: "6148" uid: f0175fa5-9a2b-4719-8a41-59313c5e855f reason: NodeAllocatableEnforced reportingComponent: kubelet reportingInstance: ip-10-0-140-104.ec2.internal source: component: kubelet host: ip-10-0-140-104.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:57Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-140-104.ec2.internal resourceVersion: "6149" uid: 4cc497e0-d816-4432-9bf2-2428ec116211 kind: Event lastTimestamp: "2026-05-21T13:02:57Z" message: Node synced successfully metadata: creationTimestamp: "2026-05-21T13:02:57Z" 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: "2026-05-21T13:02:57Z" name: ip-10-0-140-104.ec2.internal.18b1964b1e0bcbae namespace: default resourceVersion: "6224" uid: 9183d9ce-ba76-4026-b9b5-7042f0f28323 reason: Synced reportingComponent: cloud-node-controller reportingInstance: "" source: component: cloud-node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:58Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-140-104.ec2.internal uid: 4cc497e0-d816-4432-9bf2-2428ec116211 kind: Event lastTimestamp: "2026-05-21T13:02:58Z" message: 'Node ip-10-0-140-104.ec2.internal event: Registered Node ip-10-0-140-104.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-21T13:02:58Z" 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: kube-controller-manager operation: Update time: "2026-05-21T13:02:58Z" name: ip-10-0-140-104.ec2.internal.18b1964b6a96098f namespace: default resourceVersion: "6320" uid: 7c69f850-2990-4670-a00b-296f03b2092a reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:30Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-140-104.ec2.internal uid: 4cc497e0-d816-4432-9bf2-2428ec116211 kind: Event lastTimestamp: "2026-05-21T13:03:30Z" message: 'Node ip-10-0-140-104.ec2.internal event: Registered Node ip-10-0-140-104.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-21T13:03:30Z" 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: kube-controller-manager operation: Update time: "2026-05-21T13:03:30Z" name: ip-10-0-140-104.ec2.internal.18b19652cbd23b87 namespace: default resourceVersion: "7226" uid: e532e904-4b27-46aa-9a3f-e079584eb70d reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:31Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-140-104.ec2.internal resourceVersion: "7487" uid: 4cc497e0-d816-4432-9bf2-2428ec116211 kind: Event lastTimestamp: "2026-05-21T13:03:31Z" message: '[k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-140-104.ec2.internal, error getting gateway config for node ip-10-0-140-104.ec2.internal: k8s.ovn.org/l3-gateway-config annotation not found for node "ip-10-0-140-104.ec2.internal", failed to update chassis to local for local node ip-10-0-140-104.ec2.internal, error: failed to parse node chassis-id for node - ip-10-0-140-104.ec2.internal, error: k8s.ovn.org/node-chassis-id annotation not found for node ip-10-0-140-104.ec2.internal]' metadata: creationTimestamp: "2026-05-21T13:03:31Z" 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: ip-10-0-140-104 operation: Update time: "2026-05-21T13:03:31Z" name: ip-10-0-140-104.ec2.internal.18b1965323ce61a5 namespace: default resourceVersion: "7488" uid: f8b14d3d-a213-4c5e-999a-710e34822d40 reason: ErrorAddingResource reportingComponent: ovnk-controlplane reportingInstance: "" source: component: ovnk-controlplane type: Warning - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:35Z" involvedObject: kind: Node name: ip-10-0-140-104.ec2.internal uid: ip-10-0-140-104.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:03:35Z" message: 'Node ip-10-0-140-104.ec2.internal status is now: NodeReady' metadata: creationTimestamp: "2026-05-21T13:03:35Z" 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: "2026-05-21T13:03:35Z" name: ip-10-0-140-104.ec2.internal.18b19654118b36c3 namespace: default resourceVersion: "7697" uid: 8675fec2-d4d2-402d-81b5-a43bfe1a4e77 reason: NodeReady reportingComponent: kubelet reportingInstance: ip-10-0-140-104.ec2.internal source: component: kubelet host: ip-10-0-140-104.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-21T13:02:17Z" involvedObject: kind: Node name: ip-10-0-143-142.ec2.internal uid: ip-10-0-143-142.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:17Z" message: 'Node ip-10-0-143-142.ec2.internal status is now: NodeHasSufficientMemory' metadata: creationTimestamp: "2026-05-21T13:02:17Z" 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: "2026-05-21T13:02:17Z" name: ip-10-0-143-142.ec2.internal.18b19641e6e01526 namespace: default resourceVersion: "5248" uid: 64ccac86-0e1b-4013-8356-fb83d0ecc899 reason: NodeHasSufficientMemory reportingComponent: kubelet reportingInstance: ip-10-0-143-142.ec2.internal source: component: kubelet host: ip-10-0-143-142.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-21T13:02:17Z" involvedObject: kind: Node name: ip-10-0-143-142.ec2.internal uid: ip-10-0-143-142.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:17Z" message: 'Node ip-10-0-143-142.ec2.internal status is now: NodeHasNoDiskPressure' metadata: creationTimestamp: "2026-05-21T13:02:17Z" 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: "2026-05-21T13:02:17Z" name: ip-10-0-143-142.ec2.internal.18b19641e6e1230e namespace: default resourceVersion: "5250" uid: a2001ff8-1463-45a0-b4a3-d59d33056259 reason: NodeHasNoDiskPressure reportingComponent: kubelet reportingInstance: ip-10-0-143-142.ec2.internal source: component: kubelet host: ip-10-0-143-142.ec2.internal type: Normal - apiVersion: v1 count: 6 eventTime: null firstTimestamp: "2026-05-21T13:02:17Z" involvedObject: kind: Node name: ip-10-0-143-142.ec2.internal uid: ip-10-0-143-142.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:17Z" message: 'Node ip-10-0-143-142.ec2.internal status is now: NodeHasSufficientPID' metadata: creationTimestamp: "2026-05-21T13:02:17Z" 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: "2026-05-21T13:02:17Z" name: ip-10-0-143-142.ec2.internal.18b19641e6e1802b namespace: default resourceVersion: "5254" uid: 5bc6714d-f755-4cba-a10d-f2ae2ed55ee2 reason: NodeHasSufficientPID reportingComponent: kubelet reportingInstance: ip-10-0-143-142.ec2.internal source: component: kubelet host: ip-10-0-143-142.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:17Z" involvedObject: kind: Node name: ip-10-0-143-142.ec2.internal uid: ip-10-0-143-142.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:17Z" message: Updated Node Allocatable limit across pods metadata: creationTimestamp: "2026-05-21T13:02:17Z" 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: "2026-05-21T13:02:17Z" name: ip-10-0-143-142.ec2.internal.18b19641ea3cddf3 namespace: default resourceVersion: "5199" uid: 5f09f019-c5aa-4c62-8503-9a237fc18236 reason: NodeAllocatableEnforced reportingComponent: kubelet reportingInstance: ip-10-0-143-142.ec2.internal source: component: kubelet host: ip-10-0-143-142.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:18Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-143-142.ec2.internal resourceVersion: "5201" uid: 215b94e7-aa7e-4736-afdf-d308c1967863 kind: Event lastTimestamp: "2026-05-21T13:02:18Z" message: Node synced successfully metadata: creationTimestamp: "2026-05-21T13:02:18Z" 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: "2026-05-21T13:02:18Z" name: ip-10-0-143-142.ec2.internal.18b1964205245f23 namespace: default resourceVersion: "5279" uid: 1757932b-03d9-4223-a078-94f02d159145 reason: Synced reportingComponent: cloud-node-controller reportingInstance: "" source: component: cloud-node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:18Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-143-142.ec2.internal uid: 215b94e7-aa7e-4736-afdf-d308c1967863 kind: Event lastTimestamp: "2026-05-21T13:02:18Z" message: 'Node ip-10-0-143-142.ec2.internal event: Registered Node ip-10-0-143-142.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-21T13:02:18Z" 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: "2026-05-21T13:02:18Z" name: ip-10-0-143-142.ec2.internal.18b1964219831b04 namespace: default resourceVersion: "5312" uid: 00e939b6-363b-4207-b60a-662676c8f8ed reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:02:50Z" involvedObject: kind: Node name: ip-10-0-143-142.ec2.internal uid: ip-10-0-143-142.ec2.internal kind: Event lastTimestamp: "2026-05-21T13:02:50Z" message: 'Node ip-10-0-143-142.ec2.internal status is now: NodeReady' metadata: creationTimestamp: "2026-05-21T13:02:50Z" 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: "2026-05-21T13:02:50Z" name: ip-10-0-143-142.ec2.internal.18b19649ab865af1 namespace: default resourceVersion: "5947" uid: bf64878e-f054-4376-8fda-cdafd2e46a34 reason: NodeReady reportingComponent: kubelet reportingInstance: ip-10-0-143-142.ec2.internal source: component: kubelet host: ip-10-0-143-142.ec2.internal type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T13:03:30Z" involvedObject: apiVersion: v1 kind: Node name: ip-10-0-143-142.ec2.internal uid: 215b94e7-aa7e-4736-afdf-d308c1967863 kind: Event lastTimestamp: "2026-05-21T13:03:30Z" message: 'Node ip-10-0-143-142.ec2.internal event: Registered Node ip-10-0-143-142.ec2.internal in Controller' metadata: creationTimestamp: "2026-05-21T13:03:30Z" 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: kube-controller-manager operation: Update time: "2026-05-21T13:03:30Z" name: ip-10-0-143-142.ec2.internal.18b19652cbd55c9a namespace: default resourceVersion: "7245" uid: 9555b409-82c3-422e-9bea-e33b87a97285 reason: RegisteredNode reportingComponent: node-controller reportingInstance: "" source: component: node-controller type: Normal - apiVersion: v1 count: 10 eventTime: null firstTimestamp: "2026-05-21T13:08:43Z" involvedObject: apiVersion: v1 kind: Namespace name: kuadrant-system resourceVersion: "15926" uid: aee75e85-c0df-4ba6-a15b-20229b84de96 kind: Event lastTimestamp: "2026-05-21T13:08:46Z" 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: "2026-05-21T13:08:43Z" 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: catalog operation: Update time: "2026-05-21T13:08:48Z" name: kuadrant-system.18b1969bc2b487e3 namespace: default resourceVersion: "16181" uid: c712ad74-33cf-4b1b-9fd5-fe464b771f8e 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: "2026-05-21T13:03:11Z" 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: "2026-05-21T13:03:11Z" name: kube-system.18b1964e79b252ea namespace: default resourceVersion: "6761" uid: 0430f7d2-6f25-4537-b174-145bbb4da3c6 reason: TerminationStart reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-6c8b4585b9-g82k8 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: "2026-05-21T13:03:26Z" 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: "2026-05-21T13:03:26Z" name: kube-system.18b19651f8129e8e namespace: default resourceVersion: "7159" uid: 296eae41-e90c-41e3-810b-98104f926cc7 reason: TerminationMinimalShutdownDurationFinished reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-6c8b4585b9-g82k8 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: "2026-05-21T13:03:26Z" 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: "2026-05-21T13:03:26Z" name: kube-system.18b19651f84fda2f namespace: default resourceVersion: "7160" uid: 3b0df76c-b6ca-46b8-8189-faa874a87e0b reason: TerminationStoppedServing reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-6c8b4585b9-g82k8 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: "2026-05-21T13:03:26Z" 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: "2026-05-21T13:03:26Z" name: kube-system.18b19651f8a0a0af namespace: default resourceVersion: "7161" uid: 5ab7cfc7-7c5a-4a84-986c-6d597f446fd3 reason: TerminationPreShutdownHooksFinished reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-6c8b4585b9-g82k8 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: "2026-05-21T13:04:26Z" 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: "2026-05-21T13:04:26Z" name: kube-system.18b1965ff0a8e92e namespace: default resourceVersion: "9754" uid: 787ed6f5-34f7-4a95-a752-c6d2ddbba8a4 reason: TerminationGracefulTerminationFinished reportingComponent: "" reportingInstance: "" source: component: apiserver host: openshift-apiserver-6c8b4585b9-g82k8 type: Normal - apiVersion: v1 count: 1 eventTime: null firstTimestamp: "2026-05-21T12:58:13Z" involvedObject: apiVersion: v1 kind: Namespace name: openshift-kube-apiserver namespace: default kind: Event lastTimestamp: "2026-05-21T12:58:13Z" message: readyz=true metadata: creationTimestamp: "2026-05-21T12:58:13Z" name: openshift-kube-apiserver.18b1960917c7300e namespace: default resourceVersion: "274" uid: 072560da-09ba-4d8d-8c2b-3d6becccfb8c reason: KubeAPIReadyz reportingComponent: "" reportingInstance: "" source: component: apiserver host: kube-apiserver-75dd8f78c4-wq92c type: Warning kind: EventList metadata: resourceVersion: "46885"