fix: prevent orphaned Chrome processes on daemon exit (#1137)
Three changes to ensure headless Chrome process trees are fully cleaned up when the daemon exits, whether gracefully or abnormally: 1. Spawn Chrome in its own process group (`setpgid(0,0)`) and kill the entire group (`kill(-pgid, SIGKILL)`) in `ChromeProcess::kill()`. This takes down all helper processes (GPU, renderer, utility, crashpad) instead of only the main Chrome PID. 2. On Linux, set `PR_SET_PDEATHSIG(SIGKILL)` on the Chrome process so the kernel automatically kills it when the daemon dies for any reason, including SIGKILL/OOM. No macOS equivalent exists. 3. Replace `process::exit(0)` in the daemon's close handler with a `Notify` signal back to the main loop, so Rust destructors (including `ChromeProcess::Drop`) actually run. Co-authored-by: ctate <366502+ctate@users.noreply.github.com>
This commit is contained in:
@@ -9,7 +9,7 @@ use std::time::Duration;
|
||||
|
||||
use tokio::io::{AsyncBufReadExt, AsyncWriteExt, BufReader};
|
||||
use tokio::signal;
|
||||
use tokio::sync::{mpsc, RwLock};
|
||||
use tokio::sync::{mpsc, Notify, RwLock};
|
||||
|
||||
use super::actions::{execute_command, DaemonState};
|
||||
use super::cdp::client::CdpClient;
|
||||
@@ -176,6 +176,11 @@ async fn run_socket_server(
|
||||
let (reset_tx, mut reset_rx) = mpsc::channel::<()>(64);
|
||||
let reset_tx = idle_timeout_ms.map(|_| Arc::new(reset_tx));
|
||||
|
||||
// Notifier used by handle_connection to signal the daemon loop to exit
|
||||
// after a "close" command, instead of calling process::exit() which skips
|
||||
// destructors and can leave Chrome processes orphaned (issue #1113).
|
||||
let close_notify = Arc::new(Notify::new());
|
||||
|
||||
let mut drain_interval = tokio::time::interval(Duration::from_millis(100));
|
||||
drain_interval.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Skip);
|
||||
|
||||
@@ -190,8 +195,9 @@ async fn run_socket_server(
|
||||
let state = state.clone();
|
||||
let reset_tx = reset_tx.clone();
|
||||
let sf = stream_file.clone();
|
||||
let cn = close_notify.clone();
|
||||
tokio::spawn(async move {
|
||||
handle_connection(stream, state, reset_tx, sf).await;
|
||||
handle_connection(stream, state, reset_tx, sf, cn).await;
|
||||
});
|
||||
}
|
||||
Err(e) => {
|
||||
@@ -229,6 +235,12 @@ async fn run_socket_server(
|
||||
.map(|ms| Box::pin(tokio::time::sleep(Duration::from_millis(ms))));
|
||||
continue;
|
||||
}
|
||||
_ = close_notify.notified() => {
|
||||
// "close" command was handled; browser already closed by
|
||||
// handle_close(). Break to run cleanup and exit gracefully
|
||||
// so destructors fire.
|
||||
break;
|
||||
}
|
||||
_ = shutdown_signal() => {
|
||||
let mut s = state.lock().await;
|
||||
if let Some(ref mut mgr) = s.browser {
|
||||
@@ -283,6 +295,8 @@ async fn run_socket_server(
|
||||
let (reset_tx, mut reset_rx) = mpsc::channel::<()>(64);
|
||||
let reset_tx = idle_timeout_ms.map(|_| Arc::new(reset_tx));
|
||||
|
||||
let close_notify = Arc::new(Notify::new());
|
||||
|
||||
let idle_sleep = idle_timeout_ms.map(|ms| tokio::time::sleep(Duration::from_millis(ms)));
|
||||
let mut idle_sleep_pin = idle_sleep.map(Box::pin);
|
||||
|
||||
@@ -294,8 +308,9 @@ async fn run_socket_server(
|
||||
let state = state.clone();
|
||||
let reset_tx = reset_tx.clone();
|
||||
let sf = stream_file.clone();
|
||||
let cn = close_notify.clone();
|
||||
tokio::spawn(async move {
|
||||
handle_connection(stream, state, reset_tx, sf).await;
|
||||
handle_connection(stream, state, reset_tx, sf, cn).await;
|
||||
});
|
||||
}
|
||||
Err(e) => {
|
||||
@@ -321,6 +336,10 @@ async fn run_socket_server(
|
||||
.map(|ms| Box::pin(tokio::time::sleep(Duration::from_millis(ms))));
|
||||
continue;
|
||||
}
|
||||
_ = close_notify.notified() => {
|
||||
let _ = fs::remove_file(&port_path);
|
||||
break;
|
||||
}
|
||||
_ = shutdown_signal() => {
|
||||
let mut s = state.lock().await;
|
||||
if let Some(ref mut mgr) = s.browser {
|
||||
@@ -340,6 +359,7 @@ async fn handle_connection<S>(
|
||||
state: std::sync::Arc<tokio::sync::Mutex<DaemonState>>,
|
||||
idle_reset_tx: Option<Arc<mpsc::Sender<()>>>,
|
||||
stream_file_cleanup: Option<PathBuf>,
|
||||
close_notify: Arc<Notify>,
|
||||
) where
|
||||
S: tokio::io::AsyncRead + tokio::io::AsyncWrite + Unpin,
|
||||
{
|
||||
@@ -396,8 +416,12 @@ async fn handle_connection<S>(
|
||||
if let Some(ref path) = stream_file_cleanup {
|
||||
let _ = fs::remove_file(path);
|
||||
}
|
||||
// Signal the daemon loop to exit gracefully instead of
|
||||
// calling process::exit(), which skips destructors and
|
||||
// can leave Chrome processes orphaned (issue #1113).
|
||||
tokio::time::sleep(tokio::time::Duration::from_millis(100)).await;
|
||||
process::exit(0);
|
||||
close_notify.notify_one();
|
||||
return;
|
||||
}
|
||||
}
|
||||
Err(_) => break,
|
||||
|
||||
Reference in New Issue
Block a user