Hyper.Cluster.Scheduler (Hyper v0.1.0)

Picks the node to run a VM on. The first pass reads the gossip-replicated Hyper.Node.Budget.NodeStates (Hyper.Cluster.Budget.all_states/0), drops nodes that cannot fit the spec, and ranks survivors by how many bytes of the VM's image layers they already have mounted (colo(N, VM) = sum of |L| over shared mounted layers). The result is an ordered candidate list; the chosen node confirms authoritatively via Hyper.Node.Budget.admit/2 (see place/3).

All filtering is best-effort on a possibly-stale snapshot: a node that no longer fits simply refuses at confirmation time.

Summary

Types

layer_sizes()

Functions

candidates(spec, layers \\ [])

Fitting nodes for spec, most colocated bytes first.

colocation_score(state, layers)

Bytes of layers already mounted on state's node.

place(spec, layers, attempt)

Place spec on the best confirming node.

run(spec, layers, start_fun, stop_fun)

Place and boot spec somewhere in the cluster.

Types

layer_sizes()

@type layer_sizes() :: [{Hyper.Layer.id(), Unit.Information.t()}]

Functions

candidates(spec, layers \\ [])

@spec candidates(Hyper.Vm.Instance.Spec.t(), layer_sizes()) :: [node()]

Fitting nodes for spec, most colocated bytes first.

colocation_score(state, layers)

@spec colocation_score(Hyper.Node.Budget.NodeState.t(), layer_sizes()) ::
  non_neg_integer()

Bytes of layers already mounted on state's node.

place(spec, layers, attempt)

@spec place(Hyper.Vm.Instance.Spec.t(), layer_sizes(), (node() ->
                                                    {:ok, term()}
                                                    | {:error, term()})) ::
  {:ok, {node(), term()}} | {:error, :no_capacity}

Place spec on the best confirming node.

Walks candidates/2 in rank order, calling attempt on each until one returns {:ok, result} (the authoritative confirmation, typically a node running Hyper.Node.try_run/3 over :erpc). {:error, :no_capacity} if all refuse.

run(spec, layers, start_fun, stop_fun)

@spec run(
  Hyper.Vm.Instance.Spec.t(),
  layer_sizes(),
  (-> {:ok, pid()} | {:error, term()}),
  (pid() ->
     :ok)
) ::
  {:ok, {node(), pid()}} | {:error, :no_capacity}

Place and boot spec somewhere in the cluster.

Confirms each candidate by RPC-ing Hyper.Node.try_run/3 on it; the first node to boot the VM and reserve its budget wins. start_fun/stop_fun describe how to boot/tear down the VM on the target node.