98 lines
3.3 KiB
Elixir
98 lines
3.3 KiB
Elixir
defmodule Microwaveprop.Workers.HrdpsGridWorker do
|
||
@moduledoc """
|
||
Cycle seed worker for the HRDPS Canadian propagation chain. Mirrors
|
||
`Microwaveprop.Workers.PropagationGridWorker` but seeds `grid_tasks`
|
||
rows with `source: "hrdps"` so the Rust worker routes them through
|
||
the HRDPS fetch path.
|
||
|
||
## Cadence
|
||
|
||
HRDPS runs 4×/day at 00/06/12/18Z and publishes f000 ~3-4h after each
|
||
cycle. This worker is intended to fire at HH+5 of each cycle hour
|
||
(05:35Z, 11:35Z, 17:35Z, 23:35Z) — see plan stage 6 for the cron entry.
|
||
|
||
## Activation
|
||
|
||
Active. The Rust prop-grid-rs worker handles `source: "hrdps"` rows via
|
||
`pipeline::run_chain_step_hrdps`, fetching from MSC Datamart, writing
|
||
scores to `<base>/<band>/<iso>.hrdps.prop` (sibling of the HRRR
|
||
`.prop` file for the same cycle). Cron entry lives in `runtime.exs`.
|
||
|
||
## Scope
|
||
|
||
Seeds exactly one forecast row per fire — the one whose valid_time
|
||
matches the current hour. The Canadian propagation/weather UI only
|
||
surfaces the present moment, so producing forecast hours per cycle
|
||
was wasted wgrib2 work (~20 min/chain step at production point
|
||
density). If forecast hours come back into scope later, swap the
|
||
enqueuer call back to `GridTaskEnqueuer.seed_with_analysis/2`.
|
||
"""
|
||
|
||
use Oban.Pro.Worker,
|
||
queue: :hrdps,
|
||
priority: 0,
|
||
max_attempts: 5,
|
||
# Deduplicate seed jobs in a 6-hour window matching the cycle cadence.
|
||
unique: [period: 6 * 3600, states: :incomplete]
|
||
|
||
alias Microwaveprop.Instrument
|
||
alias Microwaveprop.Propagation.GridTaskEnqueuer
|
||
alias Microwaveprop.Weather.HrdpsClient
|
||
|
||
require Logger
|
||
|
||
@impl Oban.Pro.Worker
|
||
def process(%Oban.Job{args: args}) when args == %{} do
|
||
Instrument.span([:hrdps, :grid_worker, :perform], %{}, fn ->
|
||
seed_chain()
|
||
end)
|
||
end
|
||
|
||
defp seed_chain do
|
||
# HRDPS shares grid_tasks with HRRR; the same reclaim sweep covers
|
||
# both because reclaim_stale_running/0 doesn't filter on source.
|
||
_ = GridTaskEnqueuer.reclaim_stale_running()
|
||
|
||
run_time = pick_run_time(DateTime.utc_now())
|
||
|
||
Logger.info("HrdpsGrid: seeding current-hour task run_time=#{run_time} source=hrdps")
|
||
|
||
case GridTaskEnqueuer.seed_current_hour(run_time, source: "hrdps") do
|
||
{:ok, count} ->
|
||
:telemetry.execute(
|
||
[:microwaveprop, :hrdps, :grid_worker, :seeded],
|
||
%{queued_tasks: count},
|
||
%{run_time: run_time}
|
||
)
|
||
|
||
:ok
|
||
|
||
{:error, reason} ->
|
||
:telemetry.execute(
|
||
[:microwaveprop, :hrdps, :grid_worker, :exception],
|
||
%{},
|
||
%{run_time: run_time, reason: inspect(reason)}
|
||
)
|
||
|
||
{:error, reason}
|
||
end
|
||
end
|
||
|
||
@doc """
|
||
Pick the freshest published HRDPS cycle. Probes `now-4h` (just past
|
||
typical publish latency) first; falls back to `now-10h` (one cycle
|
||
earlier) if the fresher cycle isn't yet on the datamart.
|
||
|
||
Public so tests can exercise selection logic without going through Oban.
|
||
"""
|
||
@spec pick_run_time(DateTime.t()) :: DateTime.t()
|
||
def pick_run_time(%DateTime{} = now) do
|
||
fresh = now |> DateTime.add(-4, :hour) |> HrdpsClient.nearest_hrdps_cycle() |> DateTime.truncate(:second)
|
||
|
||
if HrdpsClient.cycle_available?(fresh) do
|
||
fresh
|
||
else
|
||
now |> DateTime.add(-10, :hour) |> HrdpsClient.nearest_hrdps_cycle() |> DateTime.truncate(:second)
|
||
end
|
||
end
|
||
end
|