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.
39 lines
1.3 KiB
Elixir
39 lines
1.3 KiB
Elixir
defmodule Microwaveprop.Propagation.RunTiming do
|
|
@moduledoc """
|
|
One row per forecast hour of a `PropagationGridWorker` chain, recording
|
|
how long that hour's fetch + score + persist cycle took.
|
|
|
|
Rows are keyed by `(run_time, forecast_hour)`. `run_time` is the HRRR
|
|
model cycle and `forecast_hour` ∈ 0..18.
|
|
"""
|
|
use Ecto.Schema
|
|
|
|
import Ecto.Changeset
|
|
|
|
@primary_key {:id, :binary_id, autogenerate: true}
|
|
@foreign_key_type :binary_id
|
|
schema "propagation_run_timings" do
|
|
field :run_time, :utc_datetime
|
|
field :forecast_hour, :integer
|
|
field :valid_time, :utc_datetime
|
|
field :started_at, :utc_datetime_usec
|
|
field :finished_at, :utc_datetime_usec
|
|
field :duration_ms, :integer
|
|
field :status, Ecto.Enum, values: [:ok, :failed]
|
|
field :error, :string
|
|
|
|
timestamps(type: :utc_datetime, updated_at: false)
|
|
end
|
|
|
|
@required ~w(run_time forecast_hour valid_time started_at finished_at duration_ms status)a
|
|
@optional ~w(error)a
|
|
|
|
def changeset(row, attrs) do
|
|
row
|
|
|> cast(attrs, @required ++ @optional)
|
|
|> validate_required(@required)
|
|
|> validate_number(:forecast_hour, greater_than_or_equal_to: 0, less_than_or_equal_to: 18)
|
|
|> validate_number(:duration_ms, greater_than_or_equal_to: 0)
|
|
|> unique_constraint([:run_time, :forecast_hour])
|
|
end
|
|
end
|