- IemRateLimiter gains AIMD-style adaptive spacing. signal_429/0 widens the current gap (*= 1.5, capped at max_interval_ms default 10s); signal_success/0 narrows it back toward the configured base (*= 0.92, floored at interval_ms). Self-tunes to IEM's moving ceiling without needing the manual "safe for 4 pods" constant. - IemClient now routes every response through a central handle_response helper that fires the widen/narrow feedback signals, eliminating the four near-identical case blocks. - Mix.Tasks.Weather.RebatchAsos collapses any already-queued single- station "asos" jobs into the batched "asos_batch" shape the enqueuer now emits, so the pending backfill queue converts to the new per-request-efficient path instead of draining at the old rate. Idempotent; supports --dry-run. 2833 tests + credo green.
142 lines
4.5 KiB
Elixir
142 lines
4.5 KiB
Elixir
defmodule Microwaveprop.Weather.IemRateLimiter do
|
|
@moduledoc """
|
|
Per-pod serial gate for Iowa Environmental Mesonet HTTP calls with
|
|
AIMD-style adaptive spacing.
|
|
|
|
IEM rate-limits per source IP across all in-flight requests, not
|
|
per-concurrency. Simply lowering the `:weather` Oban queue to one
|
|
slot per pod still produced a steady stream of HTTP 429s because
|
|
workers were issuing back-to-back requests inside each job (ASOS
|
|
spanning multiple days, RAOB batches). This limiter enforces a
|
|
minimum gap between successive calls — callers block in `acquire/0`
|
|
until their reserved slot arrives.
|
|
|
|
**Adaptive gap.** The current gap lives between `interval_ms` (base,
|
|
floor) and `max_interval_ms` (ceiling). Each `signal_429/0` widens
|
|
the gap by `*= widen_factor`; each `signal_success/0` narrows it by
|
|
`*= narrow_factor`. Successes are the common case; 429s are the
|
|
feedback signal that IEM's moving ceiling has tightened. Over a
|
|
steady stream of calls the gap self-tunes to just under the IEM
|
|
429 threshold without requiring manual tuning.
|
|
|
|
Configured via:
|
|
* `:iem_rate_limiter_interval_ms` — base gap (default 1500)
|
|
* `:iem_rate_limiter_max_interval_ms` — ceiling (default 10_000)
|
|
|
|
In tests, pass `interval_ms: 0` to disable.
|
|
"""
|
|
|
|
use GenServer
|
|
|
|
@default_interval_ms 1500
|
|
@default_max_interval_ms 10_000
|
|
@widen_factor 1.5
|
|
@narrow_factor 0.92
|
|
|
|
@spec start_link(keyword()) :: GenServer.on_start()
|
|
def start_link(opts \\ []) do
|
|
GenServer.start_link(__MODULE__, opts, name: Keyword.get(opts, :name, __MODULE__))
|
|
end
|
|
|
|
@doc """
|
|
Reserve the next available slot and block until it arrives. Callers
|
|
MUST invoke this before every IEM HTTP request. Returns `:ok` once
|
|
the caller is allowed to proceed.
|
|
"""
|
|
@spec acquire(GenServer.server()) :: :ok
|
|
def acquire(server \\ __MODULE__) do
|
|
if registered?(server) do
|
|
reserved_ms = GenServer.call(server, :reserve, :infinity)
|
|
delay = reserved_ms - System.system_time(:millisecond)
|
|
if delay > 0, do: Process.sleep(delay)
|
|
:ok
|
|
else
|
|
# Limiter not started (e.g. dev Mix tasks running in isolation).
|
|
# Fail open rather than deadlock the caller.
|
|
:ok
|
|
end
|
|
end
|
|
|
|
@doc """
|
|
Widen the gap because we just got a 429. Cheap cast.
|
|
"""
|
|
@spec signal_429(GenServer.server()) :: :ok
|
|
def signal_429(server \\ __MODULE__) do
|
|
if registered?(server), do: GenServer.cast(server, :widen), else: :ok
|
|
:ok
|
|
end
|
|
|
|
@doc """
|
|
Narrow the gap toward base because we just got a 200 (or any non-429
|
|
success). Cheap cast.
|
|
"""
|
|
@spec signal_success(GenServer.server()) :: :ok
|
|
def signal_success(server \\ __MODULE__) do
|
|
if registered?(server), do: GenServer.cast(server, :narrow), else: :ok
|
|
:ok
|
|
end
|
|
|
|
@doc """
|
|
Read the current gap. Primarily for introspection + tests.
|
|
"""
|
|
@spec current_interval_ms(GenServer.server()) :: non_neg_integer()
|
|
def current_interval_ms(server \\ __MODULE__) do
|
|
if registered?(server), do: GenServer.call(server, :current_interval), else: 0
|
|
end
|
|
|
|
defp registered?(pid) when is_pid(pid), do: Process.alive?(pid)
|
|
defp registered?(name) when is_atom(name), do: Process.whereis(name) != nil
|
|
defp registered?(_), do: true
|
|
|
|
@impl true
|
|
def init(opts) do
|
|
base = Keyword.get(opts, :interval_ms, @default_interval_ms)
|
|
max_interval = Keyword.get(opts, :max_interval_ms, @default_max_interval_ms)
|
|
|
|
state = %{
|
|
base_ms: base,
|
|
max_ms: max_interval,
|
|
current_ms: base,
|
|
next_ms: System.system_time(:millisecond)
|
|
}
|
|
|
|
{:ok, state}
|
|
end
|
|
|
|
@impl true
|
|
def handle_call(:reserve, _from, %{base_ms: 0} = state) do
|
|
{:reply, System.system_time(:millisecond), state}
|
|
end
|
|
|
|
def handle_call(:reserve, _from, %{current_ms: gap, next_ms: next_ms} = state) do
|
|
now = System.system_time(:millisecond)
|
|
reserved = max(now, next_ms)
|
|
{:reply, reserved, %{state | next_ms: reserved + gap}}
|
|
end
|
|
|
|
def handle_call(:current_interval, _from, state), do: {:reply, state.current_ms, state}
|
|
|
|
@impl true
|
|
def handle_cast(:widen, %{base_ms: 0} = state), do: {:noreply, state}
|
|
|
|
def handle_cast(:widen, state) do
|
|
new_gap =
|
|
(state.current_ms * @widen_factor)
|
|
|> round()
|
|
|> min(state.max_ms)
|
|
|> max(state.base_ms)
|
|
|
|
{:noreply, %{state | current_ms: new_gap}}
|
|
end
|
|
|
|
def handle_cast(:narrow, %{base_ms: 0} = state), do: {:noreply, state}
|
|
|
|
def handle_cast(:narrow, state) do
|
|
new_gap =
|
|
(state.current_ms * @narrow_factor)
|
|
|> round()
|
|
|> max(state.base_ms)
|
|
|
|
{:noreply, %{state | current_ms: new_gap}}
|
|
end
|
|
end
|