From d2b0c78e2356eb66f38da1d499a66709befa7d2b Mon Sep 17 00:00:00 2001
From: Dominik Csapak <d.csapak@proxmox.com>
Date: Wed, 29 Jul 2020 13:50:27 +0200
Subject: [PATCH] api2/node/termproxy: fix zombies on worker abort

tokios kill_on_drop sometimes leaves zombies around, especially
when there is not another tokio::process::Command spawned after

so instead of relying on the 'kill_on_drop' feature, we explicitly
kill the child on a worker abort. to be able to do this
we have to use 'tokio::select' instead of 'futures::select' since
the latter requires the future to be fused, which consumes the
child handle, leaving us no possibility to kill it after fusing.
(tokio::select does not need the futures to be fused, so we
can reuse the child future after the select again)

Signed-off-by: Dominik Csapak <d.csapak@proxmox.com>
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
---
 src/api2/node.rs | 36 ++++++++++++++++++++++++++----------
 1 file changed, 26 insertions(+), 10 deletions(-)

diff --git a/src/api2/node.rs b/src/api2/node.rs
index f7a86968..af3e8432 100644
--- a/src/api2/node.rs
+++ b/src/api2/node.rs
@@ -2,10 +2,7 @@ use std::net::TcpListener;
 use std::os::unix::io::AsRawFd;
 
 use anyhow::{bail, format_err, Error};
-use futures::{
-    future::{FutureExt, TryFutureExt},
-    select,
-};
+use futures::future::{FutureExt, TryFutureExt};
 use hyper::body::Body;
 use hyper::http::request::Parts;
 use hyper::upgrade::Upgraded;
@@ -172,7 +169,6 @@ async fn termproxy(
             let mut cmd = tokio::process::Command::new("/usr/bin/termproxy");
 
             cmd.args(&arguments)
-                .kill_on_drop(true)
                 .stdout(std::process::Stdio::piped())
                 .stderr(std::process::Stdio::piped());
 
@@ -199,8 +195,9 @@ async fn termproxy(
                 Ok::<(), Error>(())
             };
 
-            select!{
-                res = child.fuse() => {
+            let mut needs_kill = false;
+            let res = tokio::select!{
+                res = &mut child => {
                     let exit_code = res?;
                     if !exit_code.success() {
                         match exit_code.code() {
@@ -210,10 +207,29 @@ async fn termproxy(
                     }
                     Ok(())
                 },
-                res = stdout_fut.fuse() => res,
-                res = stderr_fut.fuse() => res,
-                res = worker.abort_future().fuse() => res.map_err(Error::from),
+                res = stdout_fut => res,
+                res = stderr_fut => res,
+                res = worker.abort_future() => {
+                    needs_kill = true;
+                    res.map_err(Error::from)
+                }
+            };
+
+            if needs_kill {
+                if res.is_ok() {
+                    child.kill()?;
+                    child.await?;
+                    return Ok(());
+                }
+
+                if let Err(err) = child.kill() {
+                    worker.warn(format!("error killing termproxy: {}", err));
+                } else if let Err(err) = child.await {
+                    worker.warn(format!("error awaiting termproxy: {}", err));
+                }
             }
+
+            res
         },
     )?;