mirror of
https://github.com/esphome/esphome.git
synced 2026-10-05 02:21:30 +00:00
[core] wake_loop_threadsafe() forces a component-phase iteration
After the Phase A / Phase B split in this PR, an external producer that
called wake_loop_threadsafe() (MQTT RX, USB RX, BLE event, espnow,
camera, mWW, speakers, USB host/CDC, lwip socket, enable_loop_soon_any_context)
only got Phase A — the component phase stayed gated by loop_interval_,
so the producer's component loop() could be delayed by up to
loop_interval_ ms before draining its queued work. That breaks the
long-standing semantic of wake_loop_threadsafe().
Add a wake_request flag set by every wake_loop_* entry point and
exchange-cleared at the gate in Application::loop(). When the flag is
set, force Phase B regardless of loop_interval_.
Storage is conditional on the threading model:
- ESPHOME_THREAD_MULTI_ATOMICS: std::atomic<uint8_t> (uint8_t, not
bool, because GCC on Xtensa generates an indirect call for
atomic<bool> ops — same workaround as scheduler.h)
- ESPHOME_THREAD_SINGLE / ESPHOME_THREAD_MULTI_NO_ATOMICS: volatile
uint8_t (8-bit aligned loads/stores are atomic on every supported
MCU; the platform signal that follows wake_request_set provides the
cross-thread/cross-core memory barrier)
Helpers (wake_request_set / wake_request_take) are always_inline so
IRAM_ATTR call sites stay in IRAM. Set BEFORE the platform signal so the
consumer is guaranteed to see the flag on its next gate check.
Adds an integration test that raises loop_interval_ to 2s, snapshots a
counting component's loop count, spawns a std::thread that calls
App.wake_loop_threadsafe() after 50ms, and asserts the count increments
inside a 500ms observation window. Without the fix the count would not
move for ~2s.
This commit is contained in:
@@ -0,0 +1,19 @@
|
||||
import esphome.codegen as cg
|
||||
import esphome.config_validation as cv
|
||||
from esphome.const import CONF_ID
|
||||
|
||||
CODEOWNERS = ["@esphome/tests"]
|
||||
|
||||
wake_test_component_ns = cg.esphome_ns.namespace("wake_test_component")
|
||||
WakeTestComponent = wake_test_component_ns.class_("WakeTestComponent", cg.Component)
|
||||
|
||||
CONFIG_SCHEMA = cv.Schema(
|
||||
{
|
||||
cv.GenerateID(): cv.declare_id(WakeTestComponent),
|
||||
}
|
||||
).extend(cv.COMPONENT_SCHEMA)
|
||||
|
||||
|
||||
async def to_code(config):
|
||||
var = cg.new_Pvariable(config[CONF_ID])
|
||||
await cg.register_component(var, config)
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
#include "wake_test_component.h"
|
||||
#include "esphome/core/application.h"
|
||||
#include "esphome/core/log.h"
|
||||
#include <chrono>
|
||||
#include <thread>
|
||||
|
||||
namespace esphome::wake_test_component {
|
||||
|
||||
static const char *const TAG = "wake_test_component";
|
||||
|
||||
void WakeTestComponent::start_async_wake() {
|
||||
ESP_LOGI(TAG, "Spawning async wake thread (50ms delay)");
|
||||
std::thread([] {
|
||||
std::this_thread::sleep_for(std::chrono::milliseconds(50));
|
||||
App.wake_loop_threadsafe();
|
||||
}).detach();
|
||||
}
|
||||
|
||||
} // namespace esphome::wake_test_component
|
||||
+27
@@ -0,0 +1,27 @@
|
||||
#pragma once
|
||||
|
||||
#include "esphome/core/component.h"
|
||||
#include <atomic>
|
||||
|
||||
namespace esphome::wake_test_component {
|
||||
|
||||
class WakeTestComponent : public Component {
|
||||
public:
|
||||
void setup() override {}
|
||||
void loop() override { this->loop_count_.fetch_add(1, std::memory_order_relaxed); }
|
||||
|
||||
int get_loop_count() const { return this->loop_count_.load(std::memory_order_relaxed); }
|
||||
|
||||
// Spawn a detached thread that sleeps briefly then calls
|
||||
// App.wake_loop_threadsafe(). Used by the integration test to verify a
|
||||
// cross-thread wake forces a component-phase iteration even when
|
||||
// loop_interval_ has been raised high enough to gate it off otherwise.
|
||||
void start_async_wake();
|
||||
|
||||
float get_setup_priority() const override { return setup_priority::DATA; }
|
||||
|
||||
protected:
|
||||
std::atomic<int> loop_count_{0};
|
||||
};
|
||||
|
||||
} // namespace esphome::wake_test_component
|
||||
@@ -0,0 +1,52 @@
|
||||
esphome:
|
||||
name: wake-loop-phase-b
|
||||
on_boot:
|
||||
priority: -100
|
||||
then:
|
||||
- lambda: |-
|
||||
// Raise loop_interval_ to 2000ms. Without the wake-request flag,
|
||||
// a wake_loop_threadsafe() call would only run Phase A (scheduler)
|
||||
// and leave the component phase gated for ~2s.
|
||||
App.set_loop_interval(2000);
|
||||
# Let boot transients settle.
|
||||
- delay: 1000ms
|
||||
- lambda: |-
|
||||
// Snapshot the loop counter, then ask the component to spawn a
|
||||
// background thread that calls App.wake_loop_threadsafe() after
|
||||
// ~50ms. With the fix, that wake forces Phase B on the next tick
|
||||
// and the counter increments well within the 500ms observation
|
||||
// window below.
|
||||
id(count_at_start) = id(wake_counter)->get_loop_count();
|
||||
id(start_time) = millis();
|
||||
id(wake_counter)->start_async_wake();
|
||||
ESP_LOGI("test", "WAKE_STARTED count=%d", id(count_at_start));
|
||||
# Observation window must be much shorter than loop_interval_ (2000ms)
|
||||
# so a "false pass" isn't possible by simply waiting out the gate.
|
||||
- delay: 500ms
|
||||
- lambda: |-
|
||||
int count_now = id(wake_counter)->get_loop_count();
|
||||
int delta = count_now - id(count_at_start);
|
||||
uint32_t elapsed = millis() - id(start_time);
|
||||
ESP_LOGI("test", "WAKE_RESULT delta=%d elapsed=%u", delta, elapsed);
|
||||
|
||||
host:
|
||||
api:
|
||||
logger:
|
||||
level: INFO
|
||||
|
||||
external_components:
|
||||
- source:
|
||||
type: local
|
||||
path: EXTERNAL_COMPONENT_PATH
|
||||
components: [wake_test_component]
|
||||
|
||||
globals:
|
||||
- id: count_at_start
|
||||
type: int
|
||||
initial_value: "0"
|
||||
- id: start_time
|
||||
type: uint32_t
|
||||
initial_value: "0"
|
||||
|
||||
wake_test_component:
|
||||
id: wake_counter
|
||||
@@ -0,0 +1,76 @@
|
||||
"""Test that wake_loop_threadsafe() forces a component-phase iteration.
|
||||
|
||||
Regression test for the wake-request flag added to Application::loop()'s
|
||||
Phase A / Phase B gate. Background producers (MQTT RX, USB RX, BLE event,
|
||||
etc.) call App.wake_loop_threadsafe() expecting their component's loop()
|
||||
to drain queued work; if the component phase stays gated by loop_interval_,
|
||||
the work waits up to loop_interval_ ms instead of running on the next tick.
|
||||
|
||||
Setup:
|
||||
- App.set_loop_interval(2000) — a wide gate that would clearly mask the bug.
|
||||
- A test component spawns a detached std::thread that sleeps 50 ms and then
|
||||
calls App.wake_loop_threadsafe() from a non-main thread.
|
||||
- The on_boot block snapshots the component's loop counter before/after a
|
||||
500 ms observation window.
|
||||
|
||||
Without the fix, delta=0 (the gate holds Phase B for ~2 s).
|
||||
With the fix, delta>=1 (the wake forces Phase B within one tick of the wake).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
from pathlib import Path
|
||||
import re
|
||||
|
||||
import pytest
|
||||
|
||||
from .types import APIClientConnectedFactory, RunCompiledFunction
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_wake_loop_forces_phase_b(
|
||||
yaml_config: str,
|
||||
run_compiled: RunCompiledFunction,
|
||||
api_client_connected: APIClientConnectedFactory,
|
||||
) -> None:
|
||||
"""A wake_loop_threadsafe() call from a background thread must trigger the
|
||||
component phase within the next tick, even when loop_interval_ is raised
|
||||
well above the observation window."""
|
||||
external_components_path = str(
|
||||
Path(__file__).parent / "fixtures" / "external_components"
|
||||
)
|
||||
yaml_config = yaml_config.replace(
|
||||
"EXTERNAL_COMPONENT_PATH", external_components_path
|
||||
)
|
||||
|
||||
loop = asyncio.get_running_loop()
|
||||
result: asyncio.Future[tuple[int, int]] = loop.create_future()
|
||||
|
||||
def on_log_line(line: str) -> None:
|
||||
match = re.search(r"WAKE_RESULT delta=(\d+) elapsed=(\d+)", line)
|
||||
if match and not result.done():
|
||||
result.set_result((int(match.group(1)), int(match.group(2))))
|
||||
|
||||
async with (
|
||||
run_compiled(yaml_config, line_callback=on_log_line),
|
||||
api_client_connected() as client,
|
||||
):
|
||||
device_info = await client.device_info()
|
||||
assert device_info is not None
|
||||
assert device_info.name == "wake-loop-phase-b"
|
||||
|
||||
try:
|
||||
delta, elapsed = await asyncio.wait_for(result, timeout=15.0)
|
||||
except TimeoutError:
|
||||
pytest.fail("WAKE_RESULT marker never appeared")
|
||||
|
||||
# Without the fix, delta would be 0 — loop_interval_=2000ms held
|
||||
# Phase B off for the full 500ms observation window. With the fix
|
||||
# the wake from the background thread (~50ms after start) forces
|
||||
# Phase B on the next tick, so the counter increments at least once.
|
||||
assert delta >= 1, (
|
||||
f"wake_loop_threadsafe() from a background thread should force "
|
||||
f"Phase B within the next tick; observed delta={delta} after "
|
||||
f"{elapsed}ms with loop_interval_=2000ms"
|
||||
)
|
||||
Reference in New Issue
Block a user