github/esphome
2
0
Fork 0
mirror of https://github.com/esphome/esphome.git synced 2026-10-06 10:56:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

[core] Remove pre-sleep socket scan from fast select path

Browse Source 
The pre-sleep scan in Application::yield_with_select_() walks
monitored_sockets_ on every loop iteration, issuing a volatile
cross-thread read on each socket's lwip_sock::rcvevent to preserve
select() semantics when the FreeRTOS task notification counter had
been consumed but a socket still had unread data.

That scenario only existed because of a Socket::ready() contract
violation: callers could stop reading with rcvevent > 0, leaving
data behind with no pending notification. That contract is now
documented and enforced (#15590), and #15589 (the first failure
that reverted the earlier removal attempt #14475) has been fixed.

With the contract honoured, every rcvevent > 0 is paired with a
pending xTaskNotifyGive from the lwip event_callback wrapper (see
lwip_fast_select.c). ulTaskNotifyTake either returns immediately
(counter non-zero) or wakes the moment the notify lands — the scan
has nothing left to rescue.

Evidence: https://github.com/esphome/esphome/pull/15638 — an
instrumentation PR ran across 5 devices (ESP32 rev1/rev3.1/C3 on
Ethernet and WiFi, plus LibreTiny RTL8720CF) through Home Assistant
disconnect/reconnect cycles, multi-client API logger bursts, and
BLE GATT connect storms. Across ~275,000 scans and 4 observed
load-bearing candidates, every hit was in the 2–14µs range — the
instruction-level window between the lwip callback writing
rcvevent and calling xTaskNotifyGive a few instructions later.
Zero hits exceeded 100µs. No hit came anywhere near loop_interval
(16ms), which is the latency scale the scan was added to prevent.

In addition to being unused, the scan is actively harmful on the
hot path: N volatile 16-bit loads against cache-cold cross-thread
lwip_sock structures on every main-loop iteration, just to
reproduce a microsecond-scale ordering artifact the notification
path is already handling authoritatively.

This also removes the now-unused monitored_sockets_ vector and
Application::{register,unregister}_socket() on the fast-select
path. Socket implementations now call esphome_lwip_hook_socket()
directly to install the netconn event callback wrapper.
This commit is contained in:
J. Nick Koston
2026-04-10 20:50:47 -10:00
parent 5460ee7edd
commit 7ce49089a0
4 changed files with 27 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files
esphome/components/socket/bsd_sockets_impl.cpp
+9 -7
View File
@@ -14,9 +14,13 @@ BSDSocketImpl::BSDSocketImpl(int fd, bool monitor_loop) {
if (!monitor_loop || this->fd_ < 0)
return;
#ifdef USE_LWIP_FAST_SELECT
// Cache lwip_sock pointer and register for monitoring (hooks callback internally)
// Cache lwip_sock pointer (used by ready() for direct rcvevent reads) and hook the
// netconn event callback so the main loop is notified via FreeRTOS task notifications.
this->cached_sock_ = esphome_lwip_get_sock(this->fd_);
this->loop_monitored_ = App.register_socket(this->cached_sock_);
if (this->cached_sock_ != nullptr) {
esphome_lwip_hook_socket(this->cached_sock_);
this->loop_monitored_ = true;
}
#else
this->loop_monitored_ = App.register_socket_fd(this->fd_);
#endif
@@ -30,12 +34,10 @@ BSDSocketImpl::~BSDSocketImpl() {
int BSDSocketImpl::close() {
if (!this->closed_) {
// Unregister before closing to avoid dangling pointer in monitored set
#ifdef USE_LWIP_FAST_SELECT
if (this->loop_monitored_) {
App.unregister_socket(this->cached_sock_);
this->cached_sock_ = nullptr;
}
// All LwIP sockets share the same static event_callback, so there is no per-socket
// unhook needed — just drop the cached pointer before the socket is destroyed.
this->cached_sock_ = nullptr;
#else
if (this->loop_monitored_) {
App.unregister_socket_fd(this->fd_);