From 328a582ea850dacb4b59a49f7032f655f22fa8c8 Mon Sep 17 00:00:00 2001 From: Uday Bhaskar Date: Fri, 3 Apr 2026 00:07:29 +0530 Subject: [PATCH 1/2] GPUOP-618 fix helm upgrade issue with latest Argo CRDs (#1283) (cherry picked from commit fe9ec91bcb097f1c82d51e6646e85d32e96096a9) --- ...md-gpu-operator.clusterserviceversion.yaml | 4 +-- .../template-patch/pre-upgrade-hook.yaml | 26 +++++++++---------- helm-charts-k8s/Chart.lock | 2 +- .../templates/pre-upgrade-hook.yaml | 26 +++++++++---------- 4 files changed, 29 insertions(+), 29 deletions(-) diff --git a/bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml b/bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml index 13a41aaf..24531aca 100644 --- a/bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml +++ b/bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml @@ -35,8 +35,8 @@ metadata: ] capabilities: Seamless Upgrades categories: AI/Machine Learning,Monitoring - containerImage: docker.io/rocm/amd-gpu-operator:dev - createdAt: "2026-03-30T18:09:02Z" + containerImage: registry.test.pensando.io:5000/amd-gpu-operator:dev + createdAt: "2026-04-02T12:26:30Z" description: |- Operator responsible for deploying AMD GPU kernel drivers, device plugin, device test runner and device metrics exporter For more information, visit [documentation](https://instinct.docs.amd.com/projects/gpu-operator/en/latest/) diff --git a/hack/k8s-patch/template-patch/pre-upgrade-hook.yaml b/hack/k8s-patch/template-patch/pre-upgrade-hook.yaml index 40cf7c2d..026a4ab2 100644 --- a/hack/k8s-patch/template-patch/pre-upgrade-hook.yaml +++ b/hack/k8s-patch/template-patch/pre-upgrade-hook.yaml @@ -226,24 +226,24 @@ spec: - /bin/sh - -c - | - kubectl apply -f /opt/helm-charts-crds-k8s/deviceconfig-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/remediationworkflowstatus-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/deviceconfig-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/remediationworkflowstatus-crd.yaml {{- if index .Values "node-feature-discovery" "enabled" }} - kubectl apply -f /opt/helm-charts-crds-k8s/nfd-api-crds.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/nfd-api-crds.yaml {{- end }} {{- if .Values.kmm.enabled }} - kubectl apply -f /opt/helm-charts-crds-k8s/module-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/nodemodulesconfig-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/module-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/nodemodulesconfig-crd.yaml {{- end }} {{- if and .Values.remediation.enabled .Values.remediation.installCRDs }} - kubectl apply -f /opt/helm-charts-crds-k8s/clusterworkflowtemplate-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/cronworkflow-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflowartifactgctask-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflow-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workfloweventbinding-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflowtaskresult-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflowtaskset-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflowtemplate-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/clusterworkflowtemplate-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/cronworkflow-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflowartifactgctask-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflow-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workfloweventbinding-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflowtaskresult-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflowtaskset-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflowtemplate-crd.yaml {{- end }} restartPolicy: OnFailure {{- end }} diff --git a/helm-charts-k8s/Chart.lock b/helm-charts-k8s/Chart.lock index fa946e07..9fc17b6e 100644 --- a/helm-charts-k8s/Chart.lock +++ b/helm-charts-k8s/Chart.lock @@ -9,4 +9,4 @@ dependencies: repository: file://./charts/remediation-crds version: v1.0.0 digest: sha256:0806f6b6d7aa21be77bf1c91e720ae3238338a16f107df450a53b02ef940db1b -generated: "2026-03-27T12:42:32.543919608Z" +generated: "2026-04-02T12:26:25.920315689Z" diff --git a/helm-charts-k8s/templates/pre-upgrade-hook.yaml b/helm-charts-k8s/templates/pre-upgrade-hook.yaml index 40cf7c2d..026a4ab2 100644 --- a/helm-charts-k8s/templates/pre-upgrade-hook.yaml +++ b/helm-charts-k8s/templates/pre-upgrade-hook.yaml @@ -226,24 +226,24 @@ spec: - /bin/sh - -c - | - kubectl apply -f /opt/helm-charts-crds-k8s/deviceconfig-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/remediationworkflowstatus-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/deviceconfig-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/remediationworkflowstatus-crd.yaml {{- if index .Values "node-feature-discovery" "enabled" }} - kubectl apply -f /opt/helm-charts-crds-k8s/nfd-api-crds.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/nfd-api-crds.yaml {{- end }} {{- if .Values.kmm.enabled }} - kubectl apply -f /opt/helm-charts-crds-k8s/module-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/nodemodulesconfig-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/module-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/nodemodulesconfig-crd.yaml {{- end }} {{- if and .Values.remediation.enabled .Values.remediation.installCRDs }} - kubectl apply -f /opt/helm-charts-crds-k8s/clusterworkflowtemplate-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/cronworkflow-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflowartifactgctask-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflow-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workfloweventbinding-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflowtaskresult-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflowtaskset-crd.yaml - kubectl apply -f /opt/helm-charts-crds-k8s/workflowtemplate-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/clusterworkflowtemplate-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/cronworkflow-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflowartifactgctask-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflow-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workfloweventbinding-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflowtaskresult-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflowtaskset-crd.yaml + kubectl apply --server-side --force-conflicts -f /opt/helm-charts-crds-k8s/workflowtemplate-crd.yaml {{- end }} restartPolicy: OnFailure {{- end }} From 21e6ec5aae9e0c740a99df653dfe953f84a52895 Mon Sep 17 00:00:00 2001 From: Uday Bhaskar Date: Fri, 3 Apr 2026 10:28:00 +0530 Subject: [PATCH 2/2] Apply suggestion from @biluriuday --- bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml b/bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml index 24531aca..a627341a 100644 --- a/bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml +++ b/bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml @@ -35,7 +35,7 @@ metadata: ] capabilities: Seamless Upgrades categories: AI/Machine Learning,Monitoring - containerImage: registry.test.pensando.io:5000/amd-gpu-operator:dev + containerImage: docker.io/rocm/amd-gpu-operator:dev createdAt: "2026-04-02T12:26:30Z" description: |- Operator responsible for deploying AMD GPU kernel drivers, device plugin, device test runner and device metrics exporter