Graham McIntire
a61abd836c
- create MonitoringCheck schema for the monitoring_checks table, fixing silent data loss where ping results were dropped by the wrong schema - update agent channel and device monitor worker to use new schema - fix Stats queries to use MonitoringCheck instead of Check schema - add list_online_cloud_pollers and list_cloud_polled_devices queries - add CloudLatencyProbeWorker to dispatch cross-agent latency probes every 8 hours via PubSub to all online cloud pollers - scope AgentLatencyEvaluator to cloud pollers only with cloud_only filter, lower min_checks (5), wider time window (48h), and device-level assignments to avoid changing site/org defaults - update cron schedule: probes at 0/8/16h, evaluation at 0:30/8:30/16:30 - refactor monitoring.ex and http_executor.ex to fix credo complexity
47 lines
1.3 KiB
Elixir
47 lines
1.3 KiB
Elixir
defmodule Towerops.Workers.CloudLatencyProbeWorker do
|
|
@moduledoc """
|
|
Oban cron worker that dispatches latency probes from all online cloud agents
|
|
to all cloud-polled devices.
|
|
|
|
Runs every 8 hours to collect cross-agent latency data used by
|
|
AgentLatencyEvaluator for automatic device reassignment.
|
|
|
|
Each cloud agent receives a list of devices to ping (5 pings per device).
|
|
Results flow back through the existing MonitoringCheck pipeline.
|
|
"""
|
|
use Oban.Worker, queue: :maintenance
|
|
|
|
alias Towerops.Agents
|
|
|
|
require Logger
|
|
|
|
@impl Oban.Worker
|
|
def perform(%Oban.Job{}) do
|
|
cloud_pollers = Agents.list_online_cloud_pollers()
|
|
devices = Agents.list_cloud_polled_devices()
|
|
|
|
if cloud_pollers == [] or devices == [] do
|
|
Logger.info("Cloud latency probe: no work (#{length(cloud_pollers)} pollers, #{length(devices)} devices)")
|
|
:ok
|
|
else
|
|
dispatch_probes(cloud_pollers, devices)
|
|
end
|
|
end
|
|
|
|
defp dispatch_probes(cloud_pollers, devices) do
|
|
Logger.info(
|
|
"Cloud latency probe: dispatching to #{length(cloud_pollers)} poller(s) " <>
|
|
"for #{length(devices)} device(s)"
|
|
)
|
|
|
|
for poller <- cloud_pollers do
|
|
Phoenix.PubSub.broadcast(
|
|
Towerops.PubSub,
|
|
"agent:#{poller.id}:latency_probe",
|
|
{:latency_probe_jobs, devices}
|
|
)
|
|
end
|
|
|
|
:ok
|
|
end
|
|
end
|