fix: commitments package refactoring/pipeline config

cmd/main.go

@@ -51,7 +51,6 @@ import (
 	"github.com/cobaltcore-dev/cortex/internal/scheduling/pods"
 	"github.com/cobaltcore-dev/cortex/internal/scheduling/reservations"
 	"github.com/cobaltcore-dev/cortex/internal/scheduling/reservations/commitments"
-	reservationscontroller "github.com/cobaltcore-dev/cortex/internal/scheduling/reservations/controller"
 	"github.com/cobaltcore-dev/cortex/internal/scheduling/reservations/failover"
 	"github.com/cobaltcore-dev/cortex/pkg/conf"
 	"github.com/cobaltcore-dev/cortex/pkg/monitoring"
@@ -489,16 +488,16 @@ func main() {
 	}
 	if slices.Contains(mainConfig.EnabledControllers, "reservations-controller") {
 		setupLog.Info("enabling controller", "controller", "reservations-controller")
-		monitor := reservationscontroller.NewControllerMonitor(multiclusterClient)
+		monitor := reservations.NewMonitor(multiclusterClient)
 		metrics.Registry.MustRegister(&monitor)
-		reservationsControllerConfig := conf.GetConfigOrDie[reservationscontroller.Config]()
+		commitmentsConfig := conf.GetConfigOrDie[commitments.Config]()
 
-		if err := (&reservationscontroller.ReservationReconciler{
+		if err := (&commitments.CommitmentReservationController{
 			Client: multiclusterClient,
 			Scheme: mgr.GetScheme(),
-			Conf:   reservationsControllerConfig,
+			Conf:   commitmentsConfig,
 		}).SetupWithManager(mgr, multiclusterClient); err != nil {
-			setupLog.Error(err, "unable to create controller", "controller", "Reservation")
+			setupLog.Error(err, "unable to create controller", "controller", "CommitmentReservation")
 			os.Exit(1)
 		}
 	}

helm/bundles/cortex-nova/templates/pipelines_kvm.yaml

@@ -664,4 +664,257 @@ spec:
         requested by the nova flavor extra specs, like `{"arch": "x86_64",
         "maxphysaddr:bits": 46, ...}`.
   weighers: []
+---
+apiVersion: cortex.cloud/v1alpha1
+kind: Pipeline
+metadata:
+  name: kvm-committed-resource-reservation-general-purpose
+spec:
+  schedulingDomain: nova
+  description: |
+    This pipeline is used for placing committed resource (CR) reservations
+    for general purpose workloads. It uses the same filtering
+    as regular VM scheduling to ensure proper placement, considering all
+    existing VMs, capacity constraints, traits, and other requirements.
+
+    Key difference from regular VM scheduling: reserved capacity is kept
+    locked (lockReserved: true) to prevent CR reservations from overlapping
+    with each other, even for the same project.
+
+    This is the pipeline used for KVM hypervisors (qemu and cloud-hypervisor).
+    Specifically, this pipeline uses load balancing for general purpose workloads.
+  type: filter-weigher
+  createDecisions: true
+  # Fetch all placement candidates, ignoring nova's preselection.
+  ignorePreselection: true
+  filters:
+    - name: filter_host_instructions
+      description: |
+        This step will consider the `ignore_hosts` and `force_hosts` instructions
+        from the nova scheduler request spec to filter out or exclusively allow
+        certain hosts.
+    - name: filter_has_enough_capacity
+      description: |
+        This step will filter out hosts that do not have enough available capacity
+        to host the requested flavor. Reserved space is kept locked to avoid
+        CR reservations overlapping.
+      params:
+        - {key: lockReserved, boolValue: true}
+    - name: filter_has_requested_traits
+      description: |
+        This step filters hosts that do not have the requested traits given by the
+        nova flavor extra spec: "trait:<trait>": "forbidden" means the host must
+        not have the specified trait. "trait:<trait>": "required" means the host
+        must have the specified trait.
+    - name: filter_has_accelerators
+      description: |
+        This step will filter out hosts without the trait `COMPUTE_ACCELERATORS` if
+        the nova flavor extra specs request accelerators via "accel:device_profile".
+    - name: filter_correct_az
+      description: |
+        This step will filter out hosts whose aggregate information indicates they
+        are not placed in the requested availability zone.
+    - name: filter_status_conditions
+      description: |
+        This step will filter out hosts for which the hypervisor status conditions
+        do not meet the expected values, for example, that the hypervisor is ready
+        and not disabled.
+    - name: filter_external_customer
+      description: |
+        This step prefix-matches the domain name for external customer domains and
+        filters out hosts that are not intended for external customers. It considers
+        the `CUSTOM_EXTERNAL_CUSTOMER_SUPPORTED` trait on hosts as well as the
+        `domain_name` scheduler hint from the nova request spec.
+      params:
+        - {key: domainNamePrefixes, stringListValue: ["iaas-"]}
+    - name: filter_allowed_projects
+      description: |
+        This step filters hosts based on allowed projects defined in the
+        hypervisor resource. Note that hosts allowing all projects are still
+        accessible and will not be filtered out. In this way some hypervisors
+        are made accessible to some projects only.
+    - name: filter_capabilities
+      description: |
+        This step will filter out hosts that do not meet the compute capabilities
+        requested by the nova flavor extra specs, like `{"arch": "x86_64",
+        "maxphysaddr:bits": 46, ...}`.
+
+        Note: currently, advanced boolean/numeric operators for the capabilities
+        like `>`, `!`, ... are not supported because they are not used by any of our
+        flavors in production.
+    - name: filter_instance_group_affinity
+      description: |
+        This step selects hosts in the instance group specified in the nova
+        scheduler request spec.
+    - name: filter_instance_group_anti_affinity
+      description: |
+        This step selects hosts not in the instance group specified in the nova
+        scheduler request spec, but only until the max_server_per_host limit is
+        reached (default = 1).
+    - name: filter_live_migratable
+      description: |
+        This step ensures that the target host of a live migration can accept
+        the migrating VM, by checking cpu architecture, cpu features, emulated
+        devices, and cpu modes.
+    - name: filter_requested_destination
+      params: {{ .Values.kvm.filterRequestedDestinationParams | toYaml | nindent 8 }}
+      description: |
+        This step filters hosts based on the `requested_destination` instruction
+        from the nova scheduler request spec. It supports filtering by host and
+        by aggregates.
+  weighers:
+    - name: kvm_prefer_smaller_hosts
+      params:
+        - {key: resourceWeights, floatMapValue: {"memory": 1.0}}
+      description: |
+        This step pulls virtual machines onto smaller hosts (by capacity). This
+        ensures that larger hosts are not overly fragmented with small VMs,
+        and can still accommodate larger VMs when they need to be scheduled.
+    - name: kvm_instance_group_soft_affinity
+      description: |
+        This weigher implements the "soft affinity" and "soft anti-affinity" policy
+        for instance groups in nova.
+
+        It assigns a weight to each host based on how many instances of the same
+        instance group are already running on that host. The more instances of the
+        same group on a host, the lower (for soft-anti-affinity) or higher
+        (for soft-affinity) the weight, which makes it less likely or more likely,
+        respectively, for the scheduler to choose that host for new instances of
+        the same group.
+    - name: kvm_binpack
+      multiplier: -1.0 # inverted = balancing
+      params:
+        - {key: resourceWeights, floatMapValue: {"memory": 1.0}}
+      description: |
+        This step implements a balancing weigher for workloads on kvm hypervisors,
+        which is the opposite of binpacking. Instead of pulling the requested vm
+        into the smallest gaps possible, it spreads the load to ensure
+        workloads are balanced across hosts. In this pipeline, the balancing will
+        focus on general purpose virtual machines.
+---
+apiVersion: cortex.cloud/v1alpha1
+kind: Pipeline
+metadata:
+  name: kvm-committed-resource-reservation-hana
+spec:
+  schedulingDomain: nova
+  description: |
+    This pipeline is used for placing committed resource (CR) reservations
+    for HANA workloads. It uses the same comprehensive filtering as regular
+    VM scheduling to ensure proper placement, considering all existing VMs,
+    capacity constraints, traits, and other requirements.
+
+    Key difference from regular VM scheduling: reserved capacity is kept
+    locked (lockReserved: true) to prevent CR reservations from overlapping
+    with each other, even for the same project.
+
+    This is the pipeline used for KVM hypervisors (qemu and cloud-hypervisor).
+    Specifically, this pipeline uses bin-packing for HANA workloads to consolidate
+    them on fewer hosts, leaving larger hosts available for future large VMs.
+  type: filter-weigher
+  createDecisions: true
+  # Fetch all placement candidates, ignoring nova's preselection.
+  ignorePreselection: true
+  filters:
+    - name: filter_host_instructions
+      description: |
+        This step will consider the `ignore_hosts` and `force_hosts` instructions
+        from the nova scheduler request spec to filter out or exclusively allow
+        certain hosts.
+    - name: filter_has_enough_capacity
+      description: |
+        This step will filter out hosts that do not have enough available capacity
+        to host the requested flavor. Reserved space is kept locked to avoid
+        CR reservations overlapping.
+      params:
+        - {key: lockReserved, boolValue: true}
+    - name: filter_has_requested_traits
+      description: |
+        This step filters hosts that do not have the requested traits given by the
+        nova flavor extra spec: "trait:<trait>": "forbidden" means the host must
+        not have the specified trait. "trait:<trait>": "required" means the host
+        must have the specified trait.
+    - name: filter_has_accelerators
+      description: |
+        This step will filter out hosts without the trait `COMPUTE_ACCELERATORS` if
+        the nova flavor extra specs request accelerators via "accel:device_profile".
+    - name: filter_correct_az
+      description: |
+        This step will filter out hosts whose aggregate information indicates they
+        are not placed in the requested availability zone.
+    - name: filter_status_conditions
+      description: |
+        This step will filter out hosts for which the hypervisor status conditions
+        do not meet the expected values, for example, that the hypervisor is ready
+        and not disabled.
+    - name: filter_external_customer
+      description: |
+        This step prefix-matches the domain name for external customer domains and
+        filters out hosts that are not intended for external customers. It considers
+        the `CUSTOM_EXTERNAL_CUSTOMER_SUPPORTED` trait on hosts as well as the
+        `domain_name` scheduler hint from the nova request spec.
+      params:
+        - {key: domainNamePrefixes, stringListValue: ["iaas-"]}
+    - name: filter_allowed_projects
+      description: |
+        This step filters hosts based on allowed projects defined in the
+        hypervisor resource. Note that hosts allowing all projects are still
+        accessible and will not be filtered out. In this way some hypervisors
+        are made accessible to some projects only.
+    - name: filter_capabilities
+      description: |
+        This step will filter out hosts that do not meet the compute capabilities
+        requested by the nova flavor extra specs, like `{"arch": "x86_64",
+        "maxphysaddr:bits": 46, ...}`.
+
+        Note: currently, advanced boolean/numeric operators for the capabilities
+        like `>`, `!`, ... are not supported because they are not used by any of our
+        flavors in production.
+    - name: filter_instance_group_affinity
+      description: |
+        This step selects hosts in the instance group specified in the nova
+        scheduler request spec.
+    - name: filter_instance_group_anti_affinity
+      description: |
+        This step selects hosts not in the instance group specified in the nova
+        scheduler request spec, but only until the max_server_per_host limit is
+        reached (default = 1).
+    - name: filter_live_migratable
+      description: |
+        This step ensures that the target host of a live migration can accept
+        the migrating VM, by checking cpu architecture, cpu features, emulated
+        devices, and cpu modes.
+    - name: filter_requested_destination
+      params: {{ .Values.kvm.filterRequestedDestinationParams | toYaml | nindent 8 }}
+      description: |
+        This step filters hosts based on the `requested_destination` instruction
+        from the nova scheduler request spec. It supports filtering by host and
+        by aggregates.
+  weighers:
+    - name: kvm_prefer_smaller_hosts
+      params:
+        - {key: resourceWeights, floatMapValue: {"memory": 1.0}}
+      description: |
+        This step pulls virtual machines onto smaller hosts (by capacity). This
+        ensures that larger hosts are not overly fragmented with small VMs,
+        and can still accommodate larger VMs when they need to be scheduled.
+    - name: kvm_instance_group_soft_affinity
+      description: |
+        This weigher implements the "soft affinity" and "soft anti-affinity" policy
+        for instance groups in nova.
+
+        It assigns a weight to each host based on how many instances of the same
+        instance group are already running on that host. The more instances of the
+        same group on a host, the lower (for soft-anti-affinity) or higher
+        (for soft-affinity) the weight, which makes it less likely or more likely,
+        respectively, for the scheduler to choose that host for new instances of
+        the same group.
+    - name: kvm_binpack
+      params:
+        - {key: resourceWeights, floatMapValue: {"memory": 1.0}}
+      description: |
+        This step implements a binpacking weigher for workloads on kvm hypervisors.
+        It pulls the requested vm into the smallest gaps possible, to ensure
+        other hosts with less allocation stay free for bigger vms.
+        In this pipeline, the binpacking will focus on hana virtual machines.
 {{- end }}

helm/bundles/cortex-nova/values.yaml

@@ -138,9 +138,14 @@ cortex-scheduling-controllers:
       - reservations-controller
     enabledTasks:
       - nova-decisions-cleanup-task
-    # Endpoints configuration for reservations controller
-    endpoints:
-      novaExternalScheduler: "http://localhost:8080/scheduler/nova/external"
+    # NovaExternalScheduler is the URL of the nova external scheduler API for CR reservations
+    novaExternalScheduler: "http://localhost:8080/scheduler/nova/external"
+    # FlavorGroupPipelines maps flavor group IDs to pipeline names for CR reservations
+    # This allows different scheduling strategies per flavor group (e.g., HANA vs GP)
+    flavorGroupPipelines:
+      "2152": "kvm-committed-resource-reservation-hana"  # HANA flavor group
+      "2101": "kvm-committed-resource-reservation-general-purpose"    # General Purpose flavor group
+      "*": "kvm-committed-resource-reservation-general-purpose"  # Catch-all fallback
     # OvercommitMappings is a list of mappings that map hypervisor traits to
     # overcommit ratios. Note that this list is applied in order, so if there
     # are multiple mappings applying to the same hypervisors, the last mapping