[pve-devel] [PATCH common] systemd: add helper to cleanup transient unit

[Fiona Ebner <f.ebner@proxmox.com>]

which combines the stop+wait logic previously present at the single
call site of wait_for_unit_removed() in QemuServer.pm. It also does a
reset-failed call first, to ensure a unit in a failed state is also
cleaned up properly.

Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
---
 src/PVE/Systemd.pm | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/src/PVE/Systemd.pm b/src/PVE/Systemd.pm
index 2517d31..327106f 100644
--- a/src/PVE/Systemd.pm
+++ b/src/PVE/Systemd.pm
@@ -7,7 +7,7 @@ use Net::DBus qw(dbus_uint32 dbus_uint64 dbus_boolean);
 use Net::DBus::Callback;
 use Net::DBus::Reactor;
 
-use PVE::Tools qw(file_set_contents file_get_contents trim);
+use PVE::Tools qw(file_set_contents file_get_contents run_command trim);
 
 sub escape_unit {
     my ($val, $is_path) = @_;
@@ -167,6 +167,20 @@ sub wait_for_unit_removed($;$) {
     }, $timeout);
 }
 
+sub cleanup_transient_unit($;$) {
+    my ($unit, $timeout) = @_;
+
+    eval {
+	my %param = ( outfunc => sub {}, errfunc => sub {} );
+	# If the unit is in a failed state (e.g. after being OOM-killed), stopping is not enough.
+	run_command(['/bin/systemctl', 'reset-failed', $unit], %param);
+	run_command(['/bin/systemctl', 'stop', $unit], %param);
+    };
+
+    # Issues with the above not being fully completed are rare, but not impossible, see bug #3733.
+    wait_for_unit_removed($unit, $timeout);
+}
+
 sub read_ini {
     my ($filename) = @_;
 
-- 
2.39.2