Graham McIntire
1ec10bec1f
The single Era5MonthBatchWorker pinned an Oban slot for the full 30-45
min a CDS month-tile takes to assemble, and lost the work entirely on a
rolling deploy because the in-flight Task died with the pod. This splits
the flow into two tiny workers and persists the CDS job IDs so deploys
survive.
New pipeline:
1. Era5SubmitWorker (:era5_submit queue) — POSTs both CDS requests in
parallel, writes an `era5_cds_jobs` row with the returned job IDs,
and enqueues an Era5PollWorker scheduled +5 min. ~1s of real work.
Short-circuits when the month-tile is already cached or when a row
already exists (in-flight from a previous attempt).
2. Era5PollWorker (:era5_poll queue) — reads the row, calls
Era5Client.check_status/1 for both CDS job IDs, and:
- returns {:snooze, 300} if either job is still running (Oban
re-schedules without counting an attempt and releases the slot
immediately — a pod can keep dozens of tile-months in flight
without pinning workers)
- streams both GRIB files to disk via Req into: File.stream!,
decodes via Wgrib2.extract_grid_messages_from_file, bulk-inserts
via Era5BatchClient.decode_and_insert/6, deletes the row, and
DELETEs both completed jobs from CDS to free server-side quota
- if either leg CDS-reports failed, deletes the row + both CDS
jobs and returns {:error, reason}
Era5Client gains four testable building blocks:
submit_job/2 (bare POST → {:ok, job_id})
check_status/1 (GET → :running | {:done, src} | {:failed, reason})
download_source_to_file/3 (streams {:url, href} or writes {:body, bin})
delete_job/1 (DELETE /jobs/:id, treats 200/202/204/404 as :ok)
All Req calls now route through `era5_req_options` so tests can stub
CDS responses via Req.Test.stub(Era5Client, fn).
Era5MonthBatchWorker is retained as a thin forwarder to Era5SubmitWorker
so any jobs already in the :era5_batch queue on prod pods drain cleanly
on the next rolling deploy. Safe to delete in a follow-up.
Adds era5_cds_jobs table with a unique index on
(year, month, tile_lat, tile_lon) so duplicate submits collapse.
New queue config in runtime.exs:
era5_submit: local_limit 4, rate_limit 30/hour (burst protection)
era5_poll: local_limit 20 (polls are cheap GETs)
era5_batch: kept at 1 for legacy job drain, delete next cycle
96 lines
3 KiB
Elixir
96 lines
3 KiB
Elixir
defmodule Microwaveprop.Workers.Era5PollWorkerTest do
|
|
use Microwaveprop.DataCase, async: false
|
|
|
|
alias Microwaveprop.Weather.Era5CdsJob
|
|
alias Microwaveprop.Weather.Era5Client
|
|
alias Microwaveprop.Workers.Era5PollWorker
|
|
|
|
setup do
|
|
System.put_env("ERA5_CDS_API_KEY", "test-key")
|
|
on_exit(fn -> System.delete_env("ERA5_CDS_API_KEY") end)
|
|
:ok
|
|
end
|
|
|
|
defp insert_cds_job(overrides \\ %{}) do
|
|
attrs =
|
|
Map.merge(
|
|
%{
|
|
year: 2014,
|
|
month: 3,
|
|
tile_lat: 32,
|
|
tile_lon: -98,
|
|
single_job_id: "cds-single-123",
|
|
pressure_job_id: "cds-pressure-456",
|
|
submitted_at: ~U[2026-04-13 21:00:00Z]
|
|
},
|
|
overrides
|
|
)
|
|
|
|
{:ok, row} = %Era5CdsJob{} |> Era5CdsJob.changeset(attrs) |> Repo.insert()
|
|
row
|
|
end
|
|
|
|
describe "perform/1 — row lifecycle" do
|
|
test "returns :ok and does nothing when the era5_cds_jobs row no longer exists" do
|
|
# Row was already processed/deleted by a previous poll run; snooze is
|
|
# scheduled behind us in time; just no-op.
|
|
Req.Test.stub(Era5Client, fn _ -> raise "CDS should not be contacted" end)
|
|
|
|
missing_id = Ecto.UUID.generate()
|
|
|
|
assert :ok =
|
|
Era5PollWorker.perform(%Oban.Job{args: %{"era5_cds_job_id" => missing_id}})
|
|
end
|
|
end
|
|
|
|
describe "perform/1 — still running" do
|
|
test "returns {:snooze, seconds} and bumps poll_count when either CDS job is still running" do
|
|
row = insert_cds_job()
|
|
|
|
Req.Test.stub(Era5Client, fn conn ->
|
|
assert conn.method == "GET"
|
|
Req.Test.json(conn, %{"status" => "running"})
|
|
end)
|
|
|
|
assert {:snooze, snooze_s} =
|
|
Era5PollWorker.perform(%Oban.Job{args: %{"era5_cds_job_id" => row.id}})
|
|
|
|
assert snooze_s > 0
|
|
|
|
reloaded = Repo.get!(Era5CdsJob, row.id)
|
|
assert reloaded.poll_count == 1
|
|
assert reloaded.last_polled_at
|
|
end
|
|
end
|
|
|
|
describe "perform/1 — failure" do
|
|
test "returns {:error, _}, deletes the row, and deletes both CDS jobs when a leg fails" do
|
|
row = insert_cds_job()
|
|
test_pid = self()
|
|
|
|
Req.Test.stub(Era5Client, fn conn ->
|
|
cond do
|
|
conn.method == "GET" and String.contains?(conn.request_path, "cds-single-123") ->
|
|
Req.Test.json(conn, %{"status" => "failed", "message" => "bad input"})
|
|
|
|
conn.method == "GET" and String.contains?(conn.request_path, "cds-pressure-456") ->
|
|
Req.Test.json(conn, %{"status" => "running"})
|
|
|
|
conn.method == "DELETE" ->
|
|
send(test_pid, {:delete, conn.request_path})
|
|
Plug.Conn.resp(conn, 204, "")
|
|
end
|
|
end)
|
|
|
|
assert {:error, reason} =
|
|
Era5PollWorker.perform(%Oban.Job{args: %{"era5_cds_job_id" => row.id}})
|
|
|
|
assert reason =~ "bad input"
|
|
refute Repo.get(Era5CdsJob, row.id)
|
|
|
|
# Both CDS jobs are deleted to free server-side quota.
|
|
assert_received {:delete, "/api/retrieve/v1/jobs/cds-single-123"}
|
|
assert_received {:delete, "/api/retrieve/v1/jobs/cds-pressure-456"}
|
|
end
|
|
end
|
|
end
|