feat(server): pure Status.compute/2 for ok/warning/critical/offline

This commit is contained in:
Carsten 2026-04-21 22:49:15 +02:00
parent 9c457c1f68
commit f3e7fab4d2
2 changed files with 102 additions and 0 deletions

View file

@ -0,0 +1,41 @@
defmodule Server.Status do
@moduledoc """
Derive a status level for a host from its latest fast sample.
:offline host has no active agent connection
:critical pool DEGRADED/FAULTED or capacity > 90
:warning capacity 80..90 or pending OS updates
:ok everything nominal
"""
@bad_pool_states ~w(DEGRADED FAULTED SUSPENDED UNAVAIL)
@spec compute(String.t(), map() | nil) :: :offline | :critical | :warning | :ok
def compute(host_status, _payload) when host_status in ~w(offline never_connected),
do: :offline
def compute(_host_status, nil), do: :ok
def compute(_host_status, %{} = payload) do
pools = get_in(payload, ["zfs_pools", "pools"]) || []
pending = get_in(payload, ["system_info", "pending_updates"]) || 0
cond do
Enum.any?(pools, &critical_pool?/1) -> :critical
Enum.any?(pools, &warning_pool?/1) -> :warning
pending > 0 -> :warning
true -> :ok
end
end
defp critical_pool?(pool) do
health = pool["health"]
cap = pool["capacity_percent"] || 0
health in @bad_pool_states or cap > 90
end
defp warning_pool?(pool) do
cap = pool["capacity_percent"] || 0
cap >= 80 and cap <= 90
end
end