fix: pin kubezero-lib chart dep, nvidia time-slicing support

2025-02-26 15:14:47 +00:00 · 2025-02-26 15:14:47 +00:00 · adaf4fd114
commit adaf4fd114
parent e8d3bebe0e
24 changed files with 51 additions and 28 deletions
--- a/charts/clamav/Chart.yaml
+++ b/charts/clamav/Chart.yaml
@ -14,6 +14,6 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
 kubeVersion: ">= 1.26.0"
--- a/charts/kubezero-addons/README.md
+++ b/charts/kubezero-addons/README.md
@ -14,7 +14,7 @@ KubeZero umbrella chart for various optional cluster addons

 ## Requirements

-Kubernetes: `>= 1.26.0`
+Kubernetes: `>= 1.30.0-0`

 | Repository | Name | Version |
 |------------|------|---------|
@ -94,9 +94,8 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
 | aws-node-termination-handler.managedTag | string | `"zdt:kubezero:nth:${ClusterName}"` | "zdt:kubezero:nth:${ClusterName}" |
 | aws-node-termination-handler.metadataTries | int | `0` |  |
 | aws-node-termination-handler.nodeSelector."node-role.kubernetes.io/control-plane" | string | `""` |  |
-| aws-node-termination-handler.podMonitor.create | bool | `false` |  |
 | aws-node-termination-handler.queueURL | string | `""` | https://sqs.${AWS::Region}.amazonaws.com/${AWS::AccountId}/${ClusterName}_Nth |
-| aws-node-termination-handler.rbac.pspEnabled | bool | `false` |  |
+| aws-node-termination-handler.serviceMonitor.create | bool | `false` |  |
 | aws-node-termination-handler.taintNode | bool | `true` |  |
 | aws-node-termination-handler.tolerations[0].effect | string | `"NoSchedule"` |  |
 | aws-node-termination-handler.tolerations[0].key | string | `"node-role.kubernetes.io/control-plane"` |  |
@ -110,7 +109,7 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
 | cluster-autoscaler.extraArgs.scan-interval | string | `"30s"` |  |
 | cluster-autoscaler.extraArgs.skip-nodes-with-local-storage | bool | `false` |  |
 | cluster-autoscaler.image.repository | string | `"registry.k8s.io/autoscaling/cluster-autoscaler"` |  |
-| cluster-autoscaler.image.tag | string | `"v1.30.2"` |  |
+| cluster-autoscaler.image.tag | string | `"v1.31.1"` |  |
 | cluster-autoscaler.nodeSelector."node-role.kubernetes.io/control-plane" | string | `""` |  |
 | cluster-autoscaler.podDisruptionBudget | bool | `false` |  |
 | cluster-autoscaler.prometheusRule.enabled | bool | `false` |  |
@ -159,6 +158,9 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
 | neuron-helm-chart.enabled | bool | `false` |  |
 | neuron-helm-chart.npd.enabled | bool | `false` |  |
 | nvidia-device-plugin.cdi.nvidiaHookPath | string | `"/usr/bin"` |  |
+| nvidia-device-plugin.config.default | string | `"default"` |  |
+| nvidia-device-plugin.config.map.default | string | `"version: v1\nflags:\n  migStrategy: none"` |  |
+| nvidia-device-plugin.config.map.time-slice-4x | string | `"version: v1\nflags:\n  migStrategy: none\nsharing:\n  timeSlicing:\n    resources:\n    - name: nvidia.com/gpu\n      replicas: 4"` |  |
 | nvidia-device-plugin.deviceDiscoveryStrategy | string | `"nvml"` |  |
 | nvidia-device-plugin.enabled | bool | `false` |  |
 | nvidia-device-plugin.runtimeClassName | string | `"nvidia"` |  |
--- a/charts/kubezero-addons/values.yaml
+++ b/charts/kubezero-addons/values.yaml
@ -185,6 +185,22 @@ neuron-helm-chart:
 nvidia-device-plugin:
  enabled: false

+  config:
+    default: "default"
+    map:
+      default: |-
+        version: v1
+        flags:
+          migStrategy: none
+      time-slice-4x: |-
+        version: v1
+        flags:
+          migStrategy: none
+        sharing:
+          timeSlicing:
+            resources:
+            - name: nvidia.com/gpu
+              replicas: 4
  cdi:
    nvidiaHookPath: /usr/bin
  deviceDiscoveryStrategy: nvml
--- a/charts/kubezero-argo/Chart.yaml
+++ b/charts/kubezero-argo/Chart.yaml
@ -15,7 +15,7 @@ maintainers:
 # Url: https://github.com/argoproj/argo-helm/tree/main/charts
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: argo-events
    version: 2.4.13
--- a/charts/kubezero-argo/values.yaml
+++ b/charts/kubezero-argo/values.yaml
@ -106,10 +106,12 @@ argo-cd:
      extraHosts: "git.zero-downtime.net ssh-rsa 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"

    params:
-      controller.status.processors: "10"
-      controller.operation.processors: "5"
+      controller.status.processors: 8
+      controller.operation.processors: 4
+      controller.kubectl.parallelism.limit: 8
+      controller.resource.health.persist: "false"
      controller.diff.server.side: "true"
-      controller.sync.timeout.seconds: "1800"
+      controller.sync.timeout.seconds: 1800

      server.insecure: true
      server.enable.gzip: true
@ -178,6 +180,9 @@ argo-cd:
      serviceMonitor:
        enabled: true

+  redisSecretInit:
+    enabled: false
+
  # redis:
  # We might want to try to keep redis close to the controller
  #   affinity:
--- a/charts/kubezero-auth/Chart.yaml
+++ b/charts/kubezero-auth/Chart.yaml
@ -14,7 +14,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: keycloak
    repository: "oci://registry-1.docker.io/bitnamicharts"
--- a/charts/kubezero-cache/Chart.yaml
+++ b/charts/kubezero-cache/Chart.yaml
@ -14,7 +14,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.2.1"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: redis
    version: 20.0.3
--- a/charts/kubezero-cert-manager/Chart.yaml
+++ b/charts/kubezero-cert-manager/Chart.yaml
@ -13,7 +13,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: cert-manager
    version: v1.17.1
--- a/charts/kubezero-falco/Chart.yaml
+++ b/charts/kubezero-falco/Chart.yaml
@ -13,7 +13,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: falco
    version: 4.2.5
--- a/charts/kubezero-graph/Chart.yaml
+++ b/charts/kubezero-graph/Chart.yaml
@ -13,7 +13,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.2.1"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: neo4j
    version: 5.26.0
--- a/charts/kubezero-istio-gateway/Chart.yaml
+++ b/charts/kubezero-istio-gateway/Chart.yaml
@ -14,7 +14,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: gateway
    version: 1.24.2
--- a/charts/kubezero-istio/Chart.yaml
+++ b/charts/kubezero-istio/Chart.yaml
@ -13,7 +13,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: base
    version: 1.24.2
--- a/charts/kubezero-lib/Chart.yaml
+++ b/charts/kubezero-lib/Chart.yaml
@ -10,4 +10,4 @@ keywords:
 maintainers:
  - name: Stefan Reimer
    email: stefan@zero-downtime.net
-kubeVersion: ">= 1.30.0"
+kubeVersion: ">= 1.30.0-0"
--- a/charts/kubezero-logging/Chart.yaml
+++ b/charts/kubezero-logging/Chart.yaml
@ -17,7 +17,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: fluentd
    version: 0.5.2
--- a/charts/kubezero-metrics/Chart.yaml
+++ b/charts/kubezero-metrics/Chart.yaml
@ -16,7 +16,7 @@ maintainers:
 # https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: kube-prometheus-stack
    version: 69.2.3
--- a/charts/kubezero-mq/Chart.yaml
+++ b/charts/kubezero-mq/Chart.yaml
@ -14,7 +14,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: nats
    version: 1.2.2
--- a/charts/kubezero-network/Chart.yaml
+++ b/charts/kubezero-network/Chart.yaml
@ -16,7 +16,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: cilium
    version: 1.16.6
--- a/charts/kubezero-operators/Chart.yaml
+++ b/charts/kubezero-operators/Chart.yaml
@ -17,7 +17,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: opensearch-operator
    version: 2.7.0
--- a/charts/kubezero-sql/Chart.yaml
+++ b/charts/kubezero-sql/Chart.yaml
@ -14,7 +14,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: mariadb-galera
    version: 14.0.10
--- a/charts/kubezero-storage/Chart.yaml
+++ b/charts/kubezero-storage/Chart.yaml
@ -17,7 +17,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: lvm-localpv
    version: 1.6.2
--- a/charts/kubezero-telemetry/Chart.yaml
+++ b/charts/kubezero-telemetry/Chart.yaml
@ -16,7 +16,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.6"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
  - name: opentelemetry-collector
    version: 0.108.0
--- a/charts/kubezero/Chart.yaml
+++ b/charts/kubezero/Chart.yaml
@ -13,6 +13,6 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.2.1"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts
 kubeVersion: ">= 1.31.0-0"
--- a/charts/manticore/Chart.yaml
+++ b/charts/manticore/Chart.yaml
@ -14,7 +14,7 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.4"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts
  - name: manticoresearch
    version: "5.0.25"
--- a/charts/uptime-kuma/Chart.yaml
+++ b/charts/uptime-kuma/Chart.yaml
@ -14,6 +14,6 @@ maintainers:
    email: stefan@zero-downtime.net
 dependencies:
  - name: kubezero-lib
-    version: ">= 0.1.5"
+    version: 0.2.1
    repository: https://cdn.zero-downtime.net/charts/
 kubeVersion: ">= 1.20.0"