Patch 1.20.1

VERSION

@@ -1 +1 @@
-1.20.0
+1.20.1

cmd/main.go

@@ -57,6 +57,7 @@ import (
 var scheme = runtime.NewScheme()
 
 func init() {
+
 	utilruntime.Must(clientgoscheme.AddToScheme(scheme))
 
 	// Check if OpenTelemetryCollector and PodMonitor CRD is installed before adding it to the scheme

config/manager/kustomization.yaml

@@ -3,4 +3,4 @@ resources:
 images:
   - name: controller
     newName: cr.eu-north1.nebius.cloud/soperator/slurm-operator
-    newTag: 1.20.0
+    newTag: 1.20.1

config/manager/manager.yaml

@@ -87,7 +87,7 @@ spec:
             value: "false"
           - name: SLURM_OPERATOR_WATCH_NAMESPACES
             value: "*"
-        image: controller:1.20.0
+        image: controller:1.20.1
         imagePullPolicy: Always
         name: manager
         securityContext:

config/soperatorchecks/kustomization.yaml

@@ -4,7 +4,7 @@ resources:
 images:
   - name: controller
     newName: cr.eu-north1.nebius.cloud/soperator/soperatorchecks
-    newTag: 1.20.0
+    newTag: 1.20.1
 patches:
   # Protect the /metrics endpoint by putting it behind auth.
   # If you want your controller-manager to expose the /metrics

fluxcd/base/soperator-fluxcd/resources.yaml

@@ -42,3 +42,7 @@ spec:
       name: soperator-fluxcd
       valuesKey: values.yaml
       optional: true
+    - kind: ConfigMap
+      name: backup-schedule
+      valuesKey: values.yaml
+      optional: true

fluxcd/environment/nebius-cloud/dev/bootstrap/flux-kustomization.yaml

@@ -11,7 +11,7 @@ spec:
     name: nebius-cloud
   postBuild:
     substitute:
-      soperator_version: 1.20.0
+      soperator_version: 1.20.1
   path: "./fluxcd/enviroment/nebius-cloud/dev"
   prune: true
   timeout: 1m

fluxcd/environment/nebius-cloud/prod/bootstrap/flux-kustomization.yaml

@@ -10,7 +10,7 @@ spec:
     name: nebius-cloud
   postBuild:
     substitute:
-      soperator_version: 1.20.0
+      soperator_version: 1.20.1
   path: "./fluxcd/enviroment/nebius-cloud/prod"
   prune: false
   timeout: 1m

helm/nodeconfigurator/Chart.yaml

@@ -13,9 +13,9 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 1.20.0
+version: 1.20.1
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "1.20.0"
+appVersion: "1.20.1"

helm/nodeconfigurator/values.yaml

@@ -22,7 +22,7 @@ rebooter:
   env: []
   image:
     repository: "cr.eu-north1.nebius.cloud/soperator/rebooter"
-    tag: "1.20.0"
+    tag: "1.20.1"
     pullPolicy: IfNotPresent
   nodeSelector: {}
   resources: {}

helm/slurm-cluster-storage/Chart.yaml

@@ -2,5 +2,5 @@ apiVersion: v2
 name: helm-slurm-cluster-storage
 description: A Helm chart for Kubernetes
 type: application
-version: "1.20.0"
-appVersion: "1.20.0"
+version: "1.20.1"
+appVersion: "1.20.1"

helm/slurm-cluster/Chart.yaml

@@ -2,6 +2,6 @@ apiVersion: v2
 name: helm-slurm-cluster
 description: A Helm chart for Kubernetes
 type: application
-version: "1.20.0"
-appVersion: "1.20.0"
+version: "1.20.1"
+appVersion: "1.20.1"
 kubeVersion: ">=1.29.0-0"

helm/slurm-cluster/values.yaml

@@ -485,14 +485,14 @@ telemetry: {}
 #   otelCollectorPort: 8429
 
 images:
-  slurmctld: "cr.eu-north1.nebius.cloud/soperator/controller_slurmctld:1.20.0-jammy-slurm24.05.7"
-  slurmrestd: "cr.eu-north1.nebius.cloud/soperator/slurmrestd:1.20.0-jammy-slurm24.05.7"
-  slurmd: "cr.eu-north1.nebius.cloud/soperator/worker_slurmd:1.20.0-jammy-slurm24.05.7"
-  sshd: "cr.eu-north1.nebius.cloud/soperator/login_sshd:1.20.0-jammy-slurm24.05.7"
-  munge: "cr.eu-north1.nebius.cloud/soperator/munge:1.20.0-jammy-slurm24.05.7"
-  populateJail: "cr.eu-north1.nebius.cloud/soperator/populate_jail:1.20.0-jammy-slurm24.05.7"
-  ncclBenchmark: "cr.eu-north1.nebius.cloud/soperator/nccl_benchmark:1.20.0-jammy-slurm24.05.7"
-  slurmdbd: "cr.eu-north1.nebius.cloud/soperator/controller_slurmdbd:1.20.0-jammy-slurm24.05.7"
-  exporter: "cr.eu-north1.nebius.cloud/soperator/exporter:1.20.0-jammy-slurm24.05.7"
-  sConfigController: cr.eu-north1.nebius.cloud/soperator/sconfigcontroller:1.20.0
+  slurmctld: "cr.eu-north1.nebius.cloud/soperator/controller_slurmctld:1.20.1-jammy-slurm24.05.7"
+  slurmrestd: "cr.eu-north1.nebius.cloud/soperator/slurmrestd:1.20.1-jammy-slurm24.05.7"
+  slurmd: "cr.eu-north1.nebius.cloud/soperator/worker_slurmd:1.20.1-jammy-slurm24.05.7"
+  sshd: "cr.eu-north1.nebius.cloud/soperator/login_sshd:1.20.1-jammy-slurm24.05.7"
+  munge: "cr.eu-north1.nebius.cloud/soperator/munge:1.20.1-jammy-slurm24.05.7"
+  populateJail: "cr.eu-north1.nebius.cloud/soperator/populate_jail:1.20.1-jammy-slurm24.05.7"
+  ncclBenchmark: "cr.eu-north1.nebius.cloud/soperator/nccl_benchmark:1.20.1-jammy-slurm24.05.7"
+  slurmdbd: "cr.eu-north1.nebius.cloud/soperator/controller_slurmdbd:1.20.1-jammy-slurm24.05.7"
+  exporter: "cr.eu-north1.nebius.cloud/soperator/exporter:1.20.1-jammy-slurm24.05.7"
+  sConfigController: cr.eu-north1.nebius.cloud/soperator/sconfigcontroller:1.20.1
   mariaDB: docker-registry1.mariadb.com/library/mariadb:11.4.3

helm/soperator-activechecks/Chart.yaml

@@ -2,5 +2,5 @@ apiVersion: v2
 name: helm-soperator-activechecks
 description: A Helm chart for Kubernetes
 type: application
-version: "1.20.0"
-appVersion: "1.20.0"
+version: "1.20.1"
+appVersion: "1.20.1"

helm/soperator-activechecks/values.yaml

@@ -36,6 +36,6 @@ activeCheck:
           persistentVolumeClaim:
             claimName: "jail-pvc"
 images:
-  slurmJob: "cr.eu-north1.nebius.cloud/soperator/slurm_check_job:1.20.0-jammy-slurm24.05.7"
+  slurmJob: "cr.eu-north1.nebius.cloud/soperator/slurm_check_job:1.20.1-jammy-slurm24.05.7"
   k8sJob: "ubuntu:jammy"
-  munge: "cr.eu-north1.nebius.cloud/soperator/munge:1.20.0-jammy-slurm24.05.7"
+  munge: "cr.eu-north1.nebius.cloud/soperator/munge:1.20.1-jammy-slurm24.05.7"

helm/soperator-crds/Chart.yaml

@@ -2,6 +2,6 @@ apiVersion: v2
 name: helm-soperator-crds
 description: A Helm chart for Kubernetes
 type: application
-version: 1.20.0
-appVersion: "1.20.0"
+version: 1.20.1
+appVersion: "1.20.1"
 kubeVersion: ">=1.29.0-0"

helm/soperator-dcgm-exporter/Chart.yaml

@@ -2,5 +2,5 @@ apiVersion: v2
 name: helm-soperator-dcgm-exporter
 description: A Helm chart for Nvidia DCGM Exporter
 type: application
-version: 1.20.0
-appVersion: "1.20.0"
+version: 1.20.1
+appVersion: "1.20.1"

helm/soperator-fluxcd/Chart.yaml

@@ -13,9 +13,9 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 1.20.0
+version: 1.20.1
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "1.20.0"
+appVersion: "1.20.1"

helm/soperator-fluxcd/templates/backup_schedule.yaml

@@ -24,7 +24,7 @@ spec:
   interval: {{ .Values.backup.schedule.interval }}
   timeout: {{ .Values.backup.schedule.timeout }}
   releaseName: {{ .Values.backup.schedule.releaseName }}
-  targetNamespace: {{ .Values.backup.schedule.namespace }}
+  targetNamespace: {{ .Values.slurmCluster.namespace }}
   upgrade:
     crds: Skip
   values:

helm/soperator-fluxcd/values.yaml

@@ -173,7 +173,7 @@ observability:
     enabled: true
     interval: 5m
     timeout: 5m
-    version: 1.20.0
+    version: 1.20.1
     namespace: soperator
     releaseName: soperator-dcgm-exporter
     values:
@@ -192,7 +192,7 @@ slurmCluster:
   enabled: true
   interval: 5m
   timeout: 5m
-  version: 1.20.0
+  version: 1.20.1
   namespace: soperator
   releaseName: soperator
   values: null
@@ -208,7 +208,7 @@ soperator:
   enabled: true
   interval: 5m
   timeout: 5m
-  version: 1.20.0
+  version: 1.20.1
   namespace: "soperator-system"
   releaseName: soperator-controller
   values:

helm/soperator/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: helm-soperator
 description: A Helm chart for Kubernetes
 type: application
-version: 1.20.0
-appVersion: "1.20.0"
+version: 1.20.1
+appVersion: "1.20.1"
 kubeVersion: ">=1.29.0-0"
 dependencies:
   - name: kruise

helm/soperator/values.yaml

@@ -37,7 +37,7 @@ controllerManager:
       slurmOperatorWatchNamespaces: '*'
     image:
       repository: cr.eu-north1.nebius.cloud/soperator/slurm-operator
-      tag: 1.20.0
+      tag: 1.20.1
     imagePullPolicy: Always
     resources:
       limits:

helm/soperatorchecks/Chart.yaml

@@ -13,9 +13,9 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 1.20.0
+version: 1.20.1
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "1.20.0"
+appVersion: "1.20.1"

helm/soperatorchecks/values.yaml

@@ -31,7 +31,7 @@ checks:
       slurmOperatorWatchNamespaces: '*'
     image:
       repository: cr.eu-north1.nebius.cloud/soperator/soperatorchecks
-      tag: 1.20.0
+      tag: 1.20.1
     imagePullPolicy: Always
     resources:
       limits:

internal/consts/version.go

@@ -2,5 +2,5 @@
 package consts
 
 const (
-	VersionCR = "1.20.0"
+	VersionCR = "1.20.1"
 )

internal/render/common/volume.go

@@ -6,6 +6,7 @@ import (
 	"path"
 
 	corev1 "k8s.io/api/core/v1"
+	"k8s.io/apimachinery/pkg/api/resource"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/utils/ptr"
 
@@ -419,12 +420,13 @@ func RenderVolumeMountSshdKeys() corev1.VolumeMount {
 // region InMemory
 
 // RenderVolumeInMemory renders [corev1.Volume] which content is stored in shared memory (tmpfs).
-func RenderVolumeInMemory() corev1.Volume {
+func RenderVolumeInMemory(sizeLimit *resource.Quantity) corev1.Volume {
 	return corev1.Volume{
 		Name: consts.VolumeNameInMemorySubmount,
 		VolumeSource: corev1.VolumeSource{
 			EmptyDir: &corev1.EmptyDirVolumeSource{
-				Medium: corev1.StorageMediumMemory,
+				Medium:    corev1.StorageMediumMemory,
+				SizeLimit: sizeLimit,
 			},
 		},
 	}

internal/render/login/volume.go

@@ -28,7 +28,7 @@ func renderVolumesAndClaimTemplateSpecs(
 		common.RenderVolumeSecurityLimits(clusterName, consts.ComponentTypeLogin),
 		common.RenderVolumeSshdKeys(secrets.SshdKeysName),
 		common.RenderVolumeSshdRootKeys(clusterName),
-		common.RenderVolumeInMemory(),
+		common.RenderVolumeInMemory(login.ContainerSshd.Resources.Memory()),
 		common.RenderVolumeTmpDisk(),
 		renderVolumeSshdConfigs(login.SSHDConfigMapName),
 	}

internal/render/worker/volume.go

@@ -32,7 +32,7 @@ func renderVolumesAndClaimTemplateSpecs(
 		common.RenderVolumeSecurityLimits(clusterName, consts.ComponentTypeWorker),
 		common.RenderVolumeSshdKeys(secrets.SshdKeysName),
 		common.RenderVolumeSshdRootKeys(clusterName),
-		common.RenderVolumeInMemory(),
+		common.RenderVolumeInMemory(worker.ContainerSlurmd.Resources.Memory()),
 		common.RenderVolumeTmpDisk(),
 		renderVolumeSshdConfigs(worker.SSHDConfigMapName),
 		renderVolumeNvidia(),