[PATCH pve-manager 10/10] pvescheduler: run cluster change hooks from a listener child

[Hannes Laimer <h.laimer@proxmox.com>]

On HUP the listener is stopped rather than handed over, so the reloaded
daemon runs the newly loaded hook modules. It is recorded under a
separate marker, which frees the hook slot for its replacement to start
immediately and still has the new daemon reap it, since reaping now
covers every recorded job type rather than a fixed list.

The listener keeps its position under /run, so the one started after a
reload resumes where the stopped one left off. Around a reload the
stopped listener may still be ending its runs while the new one starts,
and both may hold a connection and record a position for that moment,
which is safe since a recorded position only ever stands for completed
runs.

Signed-off-by: Hannes Laimer <h.laimer@proxmox.com>
---
 PVE/Service/pvescheduler.pm | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/PVE/Service/pvescheduler.pm b/PVE/Service/pvescheduler.pm
index f7271fc0..7c773829 100755
--- a/PVE/Service/pvescheduler.pm
+++ b/PVE/Service/pvescheduler.pm
@@ -5,6 +5,8 @@ use warnings;
 
 use POSIX qw(WNOHANG);
 
+use PVE::Cluster::Hooks;
+use PVE::HookRunner;
 use PVE::Jobs;
 use PVE::SafeSyslog;
 
@@ -17,8 +19,6 @@ my $cmdline = [$0, @ARGV];
 my %daemon_options = (stop_wait_time => 180, max_workers => 0);
 my $daemon = __PACKAGE__->new('pvescheduler', $cmdline, %daemon_options);
 
-my @JOB_TYPES = qw(replication jobs);
-
 my sub running_job_pids : prototype($) {
     my ($self) = @_;
     my $pids = [map { keys $_->%* } values $self->{jobs}->%*];
@@ -27,7 +27,7 @@ my sub running_job_pids : prototype($) {
 
 my sub finish_jobs : prototype($) {
     my ($self) = @_;
-    for my $type (@JOB_TYPES) {
+    for my $type (keys $self->{jobs}->%*) {
         for my $cpid (keys $self->{jobs}->{$type}->%*) {
             if (my $waitpid = waitpid($cpid, WNOHANG)) {
                 delete $self->{jobs}->{$type}->{$cpid} if $waitpid == $cpid || $waitpid == -1;
@@ -40,8 +40,14 @@ sub hup {
     my ($self) = @_;
 
     my $old_workers = "";
-    for my $type (@JOB_TYPES) {
+    for my $type (sort keys $self->{jobs}->%*) {
         my $worker = $self->{jobs}->{$type} // next;
+        # stopped rather than handed over, so the reload runs the new hook code
+        if ($type eq 'hooks') {
+            kill 'TERM', keys $worker->%*;
+            $old_workers .= "stopped:$_;" for keys $worker->%*;
+            next;
+        }
         $old_workers .= "$type:$_;" for keys $worker->%*;
     }
     $ENV{"PVE_DAEMON_WORKER_PIDS"} = $old_workers;
@@ -118,6 +124,18 @@ sub run {
             },
         );
 
+        # only run while a hook is registered, unlike the other job types
+        if (scalar(PVE::Cluster::Hooks->hooks()->@*)) {
+            $fork->(
+                'hooks',
+                sub {
+                    PVE::HookRunner->new(
+                        state => '/run/pvescheduler/hooks.seq',
+                    )->run();
+                },
+            );
+        }
+
         $first_run = 0;
     };
 
-- 
2.47.3