[pve-devel] [PATCH container 1/1] prestart-hook: detect cgroupv2 incompatible systemd version

[Stoiko Ivanov]

Some container OS (e.g. CentOS 7, Ubuntu 16.04) are booted with
systemd, in a version which is not able to run with a pure cgroupv2
(a.k.a unified hierarchy) environment.

Detect those in the lxc-pve-prestart-hook, because there we already
have all mount-points set up.

This approach only leaves syslog/journal as place for notifying the
user since starting a container eventually runs `systemctl start
pve-container at VMID.service`, where we lose the prints to stdout and
stderr (and the RPCEnvironment for warning in the tasklog).

The alternative of shortly mounting all container mounts just to
obtain the systemd-version, before starting the container seems
prohibitively expensive.

The heuristic of /sbin/init needing to be a link to something ending
in systemd is taken from the systemd documentation[0] and was verified
on a few of our container-templates (Ubuntu, Debian, SUSE, CentOS, Arch).

[0] https://www.freedesktop.org/software/systemd/man/systemd.html
Signed-off-by: Stoiko Ivanov <s.ivanov at proxmox.com>
---
 src/PVE/LXC/Setup.pm      |  8 ++++++++
 src/PVE/LXC/Setup/Base.pm | 36 ++++++++++++++++++++++++++++++++++++
 src/lxc-pve-prestart-hook |  7 +++++++
 3 files changed, 51 insertions(+)

diff --git a/src/PVE/LXC/Setup.pm b/src/PVE/LXC/Setup.pm
index cf72b03..9abdc85 100644
--- a/src/PVE/LXC/Setup.pm
+++ b/src/PVE/LXC/Setup.pm
@@ -421,4 +421,12 @@ sub get_ct_os_release {
     return &$parse_os_release($data);
 }
 
+sub unified_cgroupv2_support {
+    my ($self) = @_;
+
+    $self->protected_call(sub {
+	$self->{plugin}->unified_cgroupv2_support();
+    });
+}
+
 1;
diff --git a/src/PVE/LXC/Setup/Base.pm b/src/PVE/LXC/Setup/Base.pm
index 663df73..a5b77d3 100644
--- a/src/PVE/LXC/Setup/Base.pm
+++ b/src/PVE/LXC/Setup/Base.pm
@@ -503,6 +503,42 @@ sub clear_machine_id {
     }
 }
 
+# tries to guess the systemd version based on the existence of
+# (/usr)?/lib/systemd/libsystemd-shared<version>.so. It was introduced in v231.
+sub get_systemd_version {
+    my ($self) = @_;
+
+    my $sd_lib_dir = $self->ct_is_directory("/lib/systemd") ?
+	"/lib/systemd" : "/usr/lib/systemd";
+    my $libsd = PVE::Tools::dir_glob_regex($sd_lib_dir, "libsystemd-shared-.+\.so");
+    if (defined($libsd) && $libsd =~ /libsystemd-shared-(\d+)\.so/) {
+	return $1;
+    }
+
+    return undef;
+}
+
+sub unified_cgroupv2_support {
+    my ($self) = @_;
+
+    # https://www.freedesktop.org/software/systemd/man/systemd.html
+    # systemd is installed as symlink to /sbin/init
+    my $systemd = $self->ct_readlink('/sbin/init');
+
+    # assume non-systemd init will run with unified cgroupv2
+    if (!defined($systemd) || $systemd !~ m@/systemd$@) {
+	return 1;
+    }
+
+    # systemd version 232 (e.g. debian stretch) supports the unified hierarchy
+    my $sdver = $self->get_systemd_version();
+    if (!defined($sdver) || $sdver < 232) {
+	return 0;
+    }
+
+    return 1
+}
+
 sub pre_start_hook {
     my ($self, $conf) = @_;
 
diff --git a/src/lxc-pve-prestart-hook b/src/lxc-pve-prestart-hook
index 8d876a8..fac587e 100755
--- a/src/lxc-pve-prestart-hook
+++ b/src/lxc-pve-prestart-hook
@@ -15,6 +15,7 @@ use PVE::LXC::Config;
 use PVE::LXC::Setup;
 use PVE::LXC::Tools;
 use PVE::LXC;
+use PVE::SafeSyslog;
 use PVE::Storage;
 use PVE::Syscall qw(:fsmount);
 use PVE::Tools qw(AT_FDCWD O_PATH);
@@ -126,6 +127,12 @@ PVE::LXC::Tools::lxc_hook('pre-start', 'lxc', sub {
     my $lxc_setup = PVE::LXC::Setup->new($conf, $rootdir);
     $lxc_setup->pre_start_hook();
 
+    if (PVE::CGroup::cgroup_mode() == 2) {
+	if(!$lxc_setup->unified_cgroupv2_support()) {
+	    syslog('err', "CT $vmid does not support running in a pure cgroupv2 environment\n");
+	}
+    }
+
     if (@$devices) {
 	my $devlist = '';
 	foreach my $dev (@$devices) {
-- 
2.30.2