Hyper.Node.Budget.NodeState (Hyper v0.1.0)

The per-node resource snapshot published into Hyper.Cluster.Budget and read by Hyper.Cluster.Scheduler as the first pass of placement.

Approximate by design: hard headroom is exact at publish time but soft load is an EWMA that drifts and the record gossips with lag. The authoritative decision is always the owning node's Hyper.Node.Budget.admit/2. Each record carries the node's load and its ceilings, so a scheduler anywhere can evaluate fit without knowing the target's config or core count.

Summary

Types

t()

Functions

build()

Snapshot this node's current budget state.

fits?(state, spec)

Whether this snapshot's node can hold spec: hard memory/disk headroom plus the soft cpu/disk-bw/net-bw load ceilings. A pure predicate over the published snapshot; the authoritative check is still the owning node's Hyper.Node.Budget.admit/2.

Types

t()

@type t() :: %Hyper.Node.Budget.NodeState{
  cpu_capacity: pos_integer(),
  cpu_load: float(),
  cpu_max_load: float(),
  disk_bw_ceiling: Unit.Bandwidth.t(),
  disk_bw_load: Unit.Bandwidth.t(),
  disk_free: Unit.Information.t(),
  layers: [Hyper.Layer.id()],
  mem_free: Unit.Information.t(),
  net_bw_ceiling: Unit.Bandwidth.t(),
  net_bw_load: Unit.Bandwidth.t(),
  node: node()
}

Functions

build()

@spec build() :: t()

Snapshot this node's current budget state.

fits?(state, spec)

@spec fits?(t(), Hyper.Vm.Instance.Spec.t()) :: boolean()