Graham McIntire
fc91f204fd
Add a propagation_run_timings table so the wall-clock duration of each (run_time, forecast_hour) step is queryable long after the run is over. Keyed by (run_time, forecast_hour) with a status column that captures whether the step succeeded or bailed out, and an error string on failure. PropagationGridWorker stamps every step (ok and failed) via Propagation.record_run_timing/1. Timing inserts are wrapped in rescue + changeset-error handling so the instrumentation can never brick the chain.
32 lines
1.2 KiB
Elixir
32 lines
1.2 KiB
Elixir
defmodule Microwaveprop.Repo.Migrations.CreatePropagationRunTimings do
|
|
use Ecto.Migration
|
|
|
|
def change do
|
|
create table(:propagation_run_timings, primary_key: false) do
|
|
add :id, :binary_id, primary_key: true
|
|
|
|
# `run_time` is the HRRR model cycle the chain is rolling through,
|
|
# `forecast_hour` ∈ 0..18 picks the step within that chain.
|
|
# (run_time, forecast_hour) is the natural key.
|
|
add :run_time, :utc_datetime, null: false
|
|
add :forecast_hour, :integer, null: false
|
|
add :valid_time, :utc_datetime, null: false
|
|
|
|
# Wall-clock window of this forecast hour's work, plus the total
|
|
# in ms so queries don't have to recompute it.
|
|
add :started_at, :utc_datetime_usec, null: false
|
|
add :finished_at, :utc_datetime_usec, null: false
|
|
add :duration_ms, :integer, null: false
|
|
|
|
# "ok" when replace_scores returned {:ok, _}, "failed" otherwise.
|
|
# `error` carries the inspected reason on failure, nil on success.
|
|
add :status, :string, null: false
|
|
add :error, :text
|
|
|
|
timestamps(type: :utc_datetime, updated_at: false)
|
|
end
|
|
|
|
create unique_index(:propagation_run_timings, [:run_time, :forecast_hour])
|
|
create index(:propagation_run_timings, [:started_at])
|
|
end
|
|
end
|