Release core 0.0.38 and bundles to 0.0.51

api/external/cinder/messages.go

@@ -50,14 +50,23 @@ func (r ExternalSchedulerRequest) GetTraceLogArgs() []slog.Attr {
 		slog.String("project", r.Context.ProjectID),
 	}
 }
-func (r ExternalSchedulerRequest) FilterHosts(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
+func (r ExternalSchedulerRequest) Filter(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
 	filteredHosts := make([]ExternalSchedulerHost, 0, len(includedHosts))
 	for _, host := range r.Hosts {
 		if _, exists := includedHosts[host.VolumeHost]; exists {
 			filteredHosts = append(filteredHosts, host)
 		}
 	}
 	r.Hosts = filteredHosts
+	// Also filter the weights map to only include the hosts that are still
+	// in the request, and update the weights accordingly.
+	filteredWeights := make(map[string]float64, len(includedHosts))
+	for host, weight := range includedHosts {
+		if _, exists := includedHosts[host]; exists {
+			filteredWeights[host] = weight
+		}
+	}
+	r.Weights = filteredWeights
 	return r
 }
 

api/external/ironcore/messages.go

@@ -32,7 +32,7 @@ func (r MachinePipelineRequest) GetWeights() map[string]float64 {
 func (r MachinePipelineRequest) GetTraceLogArgs() []slog.Attr {
 	return []slog.Attr{}
 }
-func (r MachinePipelineRequest) FilterHosts(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
+func (r MachinePipelineRequest) Filter(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
 	filteredPools := make([]ironcorev1alpha1.MachinePool, 0, len(includedHosts))
 	for _, pool := range r.Pools {
 		if _, exists := includedHosts[pool.Name]; exists {

api/external/manila/messages.go

@@ -50,14 +50,23 @@ func (r ExternalSchedulerRequest) GetTraceLogArgs() []slog.Attr {
 		slog.String("project", r.Context.ProjectID),
 	}
 }
-func (r ExternalSchedulerRequest) FilterHosts(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
+func (r ExternalSchedulerRequest) Filter(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
 	filteredHosts := make([]ExternalSchedulerHost, 0, len(includedHosts))
 	for _, host := range r.Hosts {
 		if _, exists := includedHosts[host.ShareHost]; exists {
 			filteredHosts = append(filteredHosts, host)
 		}
 	}
 	r.Hosts = filteredHosts
+	// Also filter the weights map to only include the hosts that are still
+	// in the request, and update the weights accordingly.
+	filteredWeights := make(map[string]float64, len(includedHosts))
+	for host, weight := range includedHosts {
+		if _, exists := includedHosts[host]; exists {
+			filteredWeights[host] = weight
+		}
+	}
+	r.Weights = filteredWeights
 	return r
 }
 

api/external/nova/messages.go

@@ -61,14 +61,23 @@ func (r ExternalSchedulerRequest) GetTraceLogArgs() []slog.Attr {
 		slog.String("project", r.Context.ProjectID),
 	}
 }
-func (r ExternalSchedulerRequest) FilterHosts(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
+func (r ExternalSchedulerRequest) Filter(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
 	filteredHosts := make([]ExternalSchedulerHost, 0, len(includedHosts))
 	for _, host := range r.Hosts {
 		if _, exists := includedHosts[host.ComputeHost]; exists {
 			filteredHosts = append(filteredHosts, host)
 		}
 	}
 	r.Hosts = filteredHosts
+	// Also filter the weights map to only include the hosts that are still
+	// in the request, and update the weights accordingly.
+	filteredWeights := make(map[string]float64, len(includedHosts))
+	for host, weight := range includedHosts {
+		if _, exists := includedHosts[host]; exists {
+			filteredWeights[host] = weight
+		}
+	}
+	r.Weights = filteredWeights
 	return r
 }
 

api/external/pods/messages.go

@@ -34,7 +34,7 @@ func (r PodPipelineRequest) GetWeights() map[string]float64 {
 func (r PodPipelineRequest) GetTraceLogArgs() []slog.Attr {
 	return []slog.Attr{}
 }
-func (r PodPipelineRequest) FilterHosts(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
+func (r PodPipelineRequest) Filter(includedHosts map[string]float64) lib.FilterWeigherPipelineRequest {
 	filteredNodes := make([]corev1.Node, 0, len(includedHosts))
 	for _, node := range r.Nodes {
 		if _, exists := includedHosts[node.Name]; exists {

cmd/main.go

@@ -622,7 +622,8 @@ func main() {
 			"reconcileInterval", failoverConfig.ReconcileInterval,
 			"revalidationInterval", failoverConfig.RevalidationInterval,
 			"trustHypervisorLocation", failoverConfig.TrustHypervisorLocation,
-			"maxVMsToProcess", failoverConfig.MaxVMsToProcess)
+			"maxVMsToProcess", failoverConfig.MaxVMsToProcess,
+			"vmSelectionRotationInterval", failoverConfig.VMSelectionRotationInterval)
 	}
 
 	// +kubebuilder:scaffold:builder

helm/bundles/cortex-cinder/Chart.yaml

@@ -5,7 +5,7 @@ apiVersion: v2
 name: cortex-cinder
 description: A Helm chart deploying Cortex for Cinder.
 type: application
-version: 0.0.50
+version: 0.0.51
 appVersion: 0.1.0
 dependencies:
   # from: file://../../library/cortex-postgres
@@ -16,12 +16,12 @@ dependencies:
   # from: file://../../library/cortex
   - name: cortex
     repository: oci://ghcr.io/cobaltcore-dev/cortex/charts
-    version: 0.0.37
+    version: 0.0.38
     alias: cortex-knowledge-controllers
   # from: file://../../library/cortex
   - name: cortex
     repository: oci://ghcr.io/cobaltcore-dev/cortex/charts
-    version: 0.0.37
+    version: 0.0.38
     alias: cortex-scheduling-controllers
 
   # Owner info adds a configmap to the kubernetes cluster with information on

helm/bundles/cortex-crds/Chart.yaml

@@ -5,13 +5,13 @@ apiVersion: v2
 name: cortex-crds
 description: A Helm chart deploying Cortex CRDs.
 type: application
-version: 0.0.50
+version: 0.0.51
 appVersion: 0.1.0
 dependencies:
   # from: file://../../library/cortex
   - name: cortex
     repository: oci://ghcr.io/cobaltcore-dev/cortex/charts
-    version: 0.0.37
+    version: 0.0.38
 
   # Owner info adds a configmap to the kubernetes cluster with information on
   # the service owner. This makes it easier to find out who to contact in case

helm/bundles/cortex-ironcore/Chart.yaml

@@ -5,13 +5,13 @@ apiVersion: v2
 name: cortex-ironcore
 description: A Helm chart deploying Cortex for IronCore.
 type: application
-version: 0.0.50
+version: 0.0.51
 appVersion: 0.1.0
 dependencies:
   # from: file://../../library/cortex
   - name: cortex
     repository: oci://ghcr.io/cobaltcore-dev/cortex/charts
-    version: 0.0.37
+    version: 0.0.38
 
   # Owner info adds a configmap to the kubernetes cluster with information on
   # the service owner. This makes it easier to find out who to contact in case

helm/bundles/cortex-manila/Chart.yaml

@@ -5,7 +5,7 @@ apiVersion: v2
 name: cortex-manila
 description: A Helm chart deploying Cortex for Manila.
 type: application
-version: 0.0.50
+version: 0.0.51
 appVersion: 0.1.0
 dependencies:
   # from: file://../../library/cortex-postgres
@@ -16,12 +16,12 @@ dependencies:
   # from: file://../../library/cortex
   - name: cortex
     repository: oci://ghcr.io/cobaltcore-dev/cortex/charts
-    version: 0.0.37
+    version: 0.0.38
     alias: cortex-knowledge-controllers
   # from: file://../../library/cortex
   - name: cortex
     repository: oci://ghcr.io/cobaltcore-dev/cortex/charts
-    version: 0.0.37
+    version: 0.0.38
     alias: cortex-scheduling-controllers
 
   # Owner info adds a configmap to the kubernetes cluster with information on

helm/bundles/cortex-nova/Chart.yaml

@@ -5,7 +5,7 @@ apiVersion: v2
 name: cortex-nova
 description: A Helm chart deploying Cortex for Nova.
 type: application
-version: 0.0.50
+version: 0.0.51
 appVersion: 0.1.0
 dependencies:
   # from: file://../../library/cortex-postgres
@@ -16,12 +16,12 @@ dependencies:
   # from: file://../../library/cortex
   - name: cortex
     repository: oci://ghcr.io/cobaltcore-dev/cortex/charts
-    version: 0.0.37
+    version: 0.0.38
     alias: cortex-knowledge-controllers
   # from: file://../../library/cortex
   - name: cortex
     repository: oci://ghcr.io/cobaltcore-dev/cortex/charts
-    version: 0.0.37
+    version: 0.0.38
     alias: cortex-scheduling-controllers
 
   # Owner info adds a configmap to the kubernetes cluster with information on

helm/bundles/cortex-nova/alerts/nova.alerts.yaml

@@ -485,26 +485,6 @@ groups:
         CRD retrieval. Limes scrapes may time out, affecting capacity reporting.
 
   # Committed Resource Syncer Alerts
-  - alert: CortexNovaCommittedResourceSyncerNotRunning
-    expr: |
-      increase(cortex_committed_resource_syncer_runs_total{service="cortex-nova-metrics"}[2h]) == 0
-      or
-      absent(cortex_committed_resource_syncer_runs_total{service="cortex-nova-metrics"})
-    for: 5m
-    labels:
-      context: committed-resource-syncer
-      dashboard: cortex/cortex
-      service: cortex
-      severity: warning
-      support_group: workload-management
-    annotations:
-      summary: "Committed Resource syncer not running"
-      description: >
-        The committed resource syncer has not run in the last 2 hours or the metric is missing.
-        This indicates that the syncer may have stopped, is encountering errors, or the feature
-        is not enabled. Check the syncer logs for errors or verify the commitments-sync-task is
-        in the enabledTasks configuration.
-
   - alert: CortexNovaCommittedResourceSyncerErrorsHigh
     expr: increase(cortex_committed_resource_syncer_errors_total{service="cortex-nova-metrics"}[1h]) > 3
     for: 5m

helm/bundles/cortex-nova/values.yaml

@@ -218,11 +218,7 @@ cortex-knowledge-controllers:
       - datasource-controllers
       - knowledge-controllers
       - kpis-controller
-    # How often the commitments syncer reconciles Limes commitments to Reservation CRDs
-    # 1h = 3600000000000 nanoseconds
-    committedResourceSyncInterval: 3600000000000
-    enabledTasks:
-      - commitments-sync-task
+    enabledTasks: []
 
 # Custom configuration for the cortex postgres chart.
 cortex-postgres:

helm/bundles/cortex-pods/Chart.yaml

@@ -5,13 +5,13 @@ apiVersion: v2
 name: cortex-pods
 description: A Helm chart deploying Cortex for Pods.
 type: application
-version: 0.0.50
+version: 0.0.51
 appVersion: 0.1.0
 dependencies:
   # from: file://../../library/cortex
   - name: cortex
     repository: oci://ghcr.io/cobaltcore-dev/cortex/charts
-    version: 0.0.37
+    version: 0.0.38
 
   # Owner info adds a configmap to the kubernetes cluster with information on
   # the service owner. This makes it easier to find out who to contact in case

helm/library/cortex/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: cortex
 description: A Helm chart to distribute cortex.
 type: application
-version: 0.0.37
-appVersion: "sha-665d8dd0"
+version: 0.0.38
+appVersion: "sha-b3cf6dc8"
 icon: "https://example.com/icon.png"
 dependencies: []

internal/scheduling/lib/filter_weigher_pipeline.go

@@ -161,7 +161,7 @@ func (p *filterWeigherPipeline[RequestType]) runFilters(
 		})
 		// Mutate the request to only include the remaining hosts.
 		// Assume the resulting request type is the same as the input type.
-		filteredRequest = filteredRequest.FilterHosts(result.Activations).(RequestType)
+		filteredRequest = filteredRequest.Filter(result.Activations).(RequestType)
 	}
 	return filteredRequest, stepResults
 }

internal/scheduling/lib/filter_weigher_pipeline_request.go

@@ -12,7 +12,10 @@ type FilterWeigherPipelineRequest interface {
 	// of the request with only the given hosts remaining. This is helpful
 	// for steps that filter out hosts. Hosts not included in the map
 	// are considered as filtered out, and won't be reconsidered in later steps.
-	FilterHosts(includedHosts map[string]float64) FilterWeigherPipelineRequest
+	// This function should also update the weights of the remaining hosts
+	// accordingly, so that the weights map always corresponds to the hosts
+	// that are currently in the request.
+	Filter(includedHosts map[string]float64) FilterWeigherPipelineRequest
 	// Get the weights for the hosts.
 	GetWeights() map[string]float64
 	// Get logging args to be used in the step's trace log.

internal/scheduling/lib/filter_weigher_pipeline_request_test.go

@@ -19,11 +19,20 @@ func (m mockFilterWeigherPipelineRequest) GetHosts() []string             { retu
 func (m mockFilterWeigherPipelineRequest) GetWeights() map[string]float64 { return m.Weights }
 func (m mockFilterWeigherPipelineRequest) GetPipeline() string            { return m.Pipeline }
 
-func (m mockFilterWeigherPipelineRequest) FilterHosts(hosts map[string]float64) FilterWeigherPipelineRequest {
+func (m mockFilterWeigherPipelineRequest) Filter(hosts map[string]float64) FilterWeigherPipelineRequest {
 	filteredHosts := make([]string, 0, len(hosts))
 	for host := range hosts {
 		filteredHosts = append(filteredHosts, host)
 	}
 	m.Hosts = filteredHosts
+	// Also filter the weights map to only include the hosts that are still
+	// in the request, and update the weights accordingly.
+	filteredWeights := make(map[string]float64, len(hosts))
+	for host, weight := range hosts {
+		if _, exists := hosts[host]; exists {
+			filteredWeights[host] = weight
+		}
+	}
+	m.Weights = filteredWeights
 	return m
 }

internal/scheduling/reservations/commitments/api_change_commitments_test.go

@@ -84,6 +84,16 @@ func TestCommitmentChangeIntegration(t *testing.T) {
 			ExpectedReservations: []*TestReservation{},
 			ExpectedAPIResponse:  newAPIResponse("1 commitment(s) failed", "commitment long-long-long-long-long-long-long-long-long-long-long-long-long-: unexpected commitment format"),
 		},
+		{
+			Name:    "Planned CR is ignored in validation, no scheduling or capacity reservation",
+			VMs:     []*TestVM{},
+			Flavors: []*TestFlavor{m1Small},
+			CommitmentRequest: newCommitmentRequest("az-a", false, 1234,
+				createCommitment("hw_version_hana_1_ram", "project-A", "uuid-new", "planned", 200),
+			),
+			ExpectedReservations: []*TestReservation{},
+			ExpectedAPIResponse:  newAPIResponse(),
+		},
 		{
 			Name:                 "Invalid CR name - spaces",
 			VMs:                  []*TestVM{},

internal/scheduling/reservations/commitments/reservation_manager.go

@@ -284,7 +284,8 @@ func (m *ReservationManager) newReservation(
 	}
 
 	spec := v1alpha1.ReservationSpec{
-		Type: v1alpha1.ReservationTypeCommittedResource,
+		Type:             v1alpha1.ReservationTypeCommittedResource,
+		SchedulingDomain: v1alpha1.SchedulingDomainNova,
 		Resources: map[hv1.ResourceName]resource.Quantity{
 			hv1.ResourceMemory: *resource.NewQuantity(
 				memoryBytes,

internal/scheduling/reservations/failover/controller.go

@@ -6,6 +6,7 @@ package failover
 import (
 	"context"
 	"fmt"
+	"math/rand/v2"
 	"path/filepath"
 	"slices"
 	"sort"
@@ -518,7 +519,11 @@ func (c *FailoverReservationController) selectVMsToProcess(
 	offset := 0
 	rotationInterval := *c.Config.VMSelectionRotationInterval
 	if rotationInterval > 0 && c.reconcileCount%int64(rotationInterval) == 0 {
-		offset = int(c.reconcileCount) % len(vmsMissingFailover)
+		offset = rand.IntN(len(vmsMissingFailover)) //nolint:gosec // non-cryptographic randomness is fine for VM selection rotation
+		logger.Info("applying random rotation offset for VM selection",
+			"offset", offset,
+			"totalVMs", len(vmsMissingFailover),
+			"rotationInterval", rotationInterval)
 	}
 
 	selected = make([]vmFailoverNeed, 0, maxToProcess)