DisaggregatedSet API

spec defines the desired state of DisaggregatedSet

status defines the observed state of DisaggregatedSet

Name is the unique identifier for this role.

SubRoles partitions one LWS into pools sharing its templates. Child targets sum to parent replicas; omit parent scaling. Parent spec.replicas is ignored.

Scaling configures how replicas are determined. Omit for inline Static scaling (default). When set to External, the DisaggregatedSet controller auto-creates a DisaggregatedSetRoleScaler and reads its spec.replicas.

LeaderWorkerSetTemplateSpec defines the LWS template for this role. Note: Spec.RolloutStrategy.Type must be RollingUpdate (or empty) and Spec.RolloutStrategy.RollingUpdateConfiguration.Partition must not be set. DisaggregatedSet handles rollouts across roles.

spec defines the desired state of DisaggregatedSetRoleScaler

status defines the observed state of DisaggregatedSetRoleScaler

Replicas is the desired replica count for the role. The controller seeds this at scaler creation — 1 for a fresh role (0 would deadlock vanilla HPA in ScalingDisabled), or the LWS's current replica count for a Static→External flip so the role does not silently drain to zero. External autoscalers overwrite it on their first tick.

Non-pointer with a default because kube-apiserver's CRD /scale handler extracts .spec.replicas at read time and errors ("the spec replicas field does not exist") when the JSONPath resolves to nothing. HPA reads /scale before its first write; a missing field would deadlock the loop.

Replicas is the observed replica count for this role — LWS groups (== leader pods), aggregated across all revisions currently present. Read by HPA as the "current" count for its ratio math.

Selector is a label selector (in string form) matching one pod per LWS group (the leader), across all revisions: disaggregatedset.x-k8s.io/name=,disaggregatedset.x-k8s.io/role=,leaderworkerset.sigs.k8s.io/worker-index=0 Leader-only so HPA's per-pod-metric averaging divides by group count (matching spec.replicas that HPA writes), keeping the ratio math consistent for leaderWorkerTemplate.size > 1. Aggregate across revisions so HPA observes the serving fleet during a rolling update.

ObservedGeneration is the .metadata.generation the status reflects.

Conditions expose scaler-level state (Ready).

ScaleDownDuringRollout controls demand-driven target replica reductions. Deferred waits until old revisions finish draining. Immediate considers reductions during the rollout, preferring safe old-revision drains. Both policies allow scale-up and old-revision drains within rollout bounds.

Roles defines the list of roles (at least 1 required). Each role has a unique name and its own configuration.

Slices is the number of independent copies of the whole role topology. Each slice is a complete set of all roles that rolls out independently. Changing Slices scales copies up or down and does not trigger a rollout.

ScalingPolicy controls scale-down during rolling updates. Omit it to preserve the default Deferred behavior.

PlacementPolicy controls how a slice's roles are co-located and how the DisaggregatedSet's slices are spread across topology domains. When set, the controller injects pod affinity and anti-affinity into the managed LeaderWorkerSet pod templates. Placement is applied when a LeaderWorkerSet is created, so changing it takes effect on the next rollout.

observedGeneration is the most recent generation observed for this DisaggregatedSet.

RoleStatuses lists current parent roles in spec order, with nested sub-role statuses. Parent counts include historical layouts and may exceed the visible child sum. Removed roles are omitted even while their groups drain.

conditions represent the current state of the DisaggregatedSet resource. Each condition has a unique type and reflects the status of a specific aspect of the resource.

Standard condition types include:

• "Available": the resource is fully functional
• "Progressing": the resource is being created or updated

The status of each condition is one of True, False, or Unknown.

Name is unique within the parent role.

Replicas counts groups (Static default: 1); omit it for External scaling.

Scaling selects this pool's replica source.

MaxSurge overrides the parent's rollout surge budget for this sub-role. Accepts a non-negative integer or a percentage up to 100%, rounded up against this sub-role's replica target. Omitted values inherit the parent; with no parent rollout configuration, the default is 0.

MaxUnavailable overrides the parent's rollout unavailability budget for this sub-role. Accepts a non-negative integer or a percentage up to 100%, rounded down against this sub-role's replica target. Omitted values inherit the parent; with no parent rollout configuration, the default is 1. Zero is explicit.

Type selects the placement guarantee. Defaults to None.

Topology is the node-label key that defines a domain, used as the affinity topologyKey. Required when Type is not None.

Mode controls the source of the replica count. Static (default) uses inline spec.replicas; External uses the auto-created scaler CR.

Name is the parent role name.

DesiredReplicas is the number of replicas the controller is driving this role toward, totalled across slices: its replicas, or the target of its DisaggregatedSetRoleScaler when its scaling mode is External. A partitioned role reports the sum of its sub-role targets. It is unset while any of those targets is unknown, for example before the scaler exists, so it is never mistaken for a requested zero. The Available condition is judged against it.

Replicas is the total number of replicas for this role.

ReadyReplicas is the number of ready replicas for this role. Sub-role readiness requires a coherent assignment across the whole group.

UpdatedReplicas is the number of replicas updated to the latest revision.

SubRoleStatuses lists the current sub-roles in spec order. Removed sub-roles are omitted, but their groups remain in the parent counts while draining. Do not add child counts to their parent aggregate.

Name is the sub-role name, without the parent prefix.

DesiredReplicas is the number of replica groups the controller is driving this sub-role toward, totalled across slices: its replicas, or the target of its DisaggregatedSetRoleScaler when its scaling mode is External. It is unset while that target is unknown.

Replicas is the number of replica groups assigned to this sub-role.

ReadyReplicas counts Ready groups with a coherent whole-group assignment.

UpdatedReplicas counts groups belonging to the latest revision.