towerops/lib/towerops_web/live/site_live/show.ex
Graham McIntire d0946c3cd0
refactor: simplify job architecture from Oban coordinators to direct workers
Removes unnecessary two-layer architecture (Oban Coordinator → GenServer)
in favor of direct Oban workers that perform the actual work.

Changes:
- Replace DevicePollerCoordinator + PollerWorker with DevicePollerWorker
- Replace DeviceMonitorCoordinator + DeviceMonitor with DeviceMonitorWorker
- Simplify Monitoring.Supervisor (removed Registries, DynamicSupervisors)
- Remove all Exq dependencies (workers, supervisor, mix deps)
- Convert DiscoveryWorker from Exq to Oban pattern
- Update Devices context to auto-start/stop monitoring and polling
- Update all LiveView callers to use new Oban enqueue pattern
- Fix all tests to use Oban.Job struct instead of raw IDs

Benefits:
- Simpler codebase (~850 lines removed)
- Better reliability (Oban handles retries, failures)
- Lower memory (no persistent GenServers)
- Better observability (work visible in Oban dashboard)
- Cluster-wide coordination via PostgreSQL
- Extensive PubSub usage for real-time events

Files deleted:
- lib/towerops/workers/device_monitor_coordinator.ex
- lib/towerops/workers/device_poller_coordinator.ex
- lib/towerops/snmp/poller_worker.ex
- lib/towerops/monitoring/device_monitor.ex
- lib/towerops/workers/monitor_worker.ex
- lib/towerops/workers/poll_worker.ex
- lib/towerops/exq_supervisor.ex
- All related test files

Files created:
- lib/towerops/workers/device_poller_worker.ex
- lib/towerops/workers/device_monitor_worker.ex

All 3,686 tests passing.
2026-01-24 16:36:57 -06:00

101 lines
2.7 KiB
Elixir

defmodule ToweropsWeb.SiteLive.Show do
@moduledoc false
use ToweropsWeb, :live_view
alias Towerops.Devices
alias Towerops.Monitoring
alias Towerops.Sites
alias Towerops.Snmp
alias Towerops.Workers.DiscoveryWorker
@impl true
def mount(_params, _session, socket) do
{:ok, socket}
end
@impl true
def handle_params(%{"id" => id}, _, socket) do
organization = socket.assigns.current_organization
site = Sites.get_organization_site!(organization.id, id)
device = Devices.list_site_devices(site.id)
latency_chart_data = load_site_latency_chart_data(device)
{:noreply,
socket
|> assign(:page_title, site.name)
|> assign(:site, site)
|> assign(:device, device)
|> assign(:latency_chart_data, latency_chart_data)}
end
@impl true
def handle_event("force_rediscover_all", _params, socket) do
devices = socket.assigns.device
snmp_devices = Enum.filter(devices, & &1.snmp_enabled)
if Enum.empty?(snmp_devices) do
{:noreply, put_flash(socket, :error, "No SNMP-enabled devices at this site")}
else
# Enqueue discovery for all SNMP-enabled devices
Enum.each(snmp_devices, fn device ->
enqueue_discovery(device.id)
end)
count = length(snmp_devices)
{:noreply,
put_flash(
socket,
:info,
"Discovery started for #{count} device#{if count == 1, do: "", else: "s"}"
)}
end
end
defp load_site_latency_chart_data(devices) do
if Enum.empty?(devices) do
nil
else
twenty_four_hours_ago = DateTime.add(DateTime.utc_now(), -24, :hour)
datasets =
devices
|> Enum.map(fn device ->
checks =
device.id
|> Monitoring.get_latency_data(since: twenty_four_hours_ago, limit: 1000)
|> Enum.reverse()
%{
label: device.name,
data: Enum.map(checks, &latency_check_to_data_point/1)
}
end)
|> Enum.reject(fn dataset -> Enum.empty?(dataset.data) end)
if Enum.empty?(datasets) do
nil
else
Jason.encode!(%{datasets: datasets})
end
end
end
defp latency_check_to_data_point(check) do
%{
x: DateTime.to_unix(check.checked_at, :millisecond),
y: check.response_time_ms
}
end
# Enqueue discovery job - safe to call in test environment
defp enqueue_discovery(device_id) do
if Application.get_env(:towerops, :env) == :test do
# In test, run synchronously
_ = Task.start(fn -> Snmp.discover_device(Devices.get_device!(device_id)) end)
else
# In dev/prod, enqueue to Oban
DiscoveryWorker.enqueue(device_id)
end
end
end