[pve-devel] [PATCH manager] Jobs: fix scheduling when updating on unrelated nodes

[Dominik Csapak <d.csapak@proxmox.com>]

since the jobs are configured clusterwide in pmxcfs, a user can use any
node to update the config of them. for some configs (schedule/enabled)
we need to update the last runtime in the state file, but this
is sadly only node-local.

to also update the state file on the other nodes, we introduce
a new 'update_job_props' function that saves relevant properties from
the config to the statefile each round of the scheduler if they changed.

this way, we can detect changes in those and update the last runtime too.

the only situation where that would not be enough is when a user
changes schedules and back to the original one within a single minute
(so between scheduler runs). in that case, the other nodes won't
detect that change, but it seems to be a rather unlikely edge case
that we can ignore.

if we really want to solve that too, we'd have to save the 'updated'
timestamp in the config too, just to sync it to the job state file
later.

in 'synchronize_job_states_with_config' we switch from reading the
jobstate unconditionally to check the existing of the statefile
(which is the only condition where that can return undef anyway)
so that we don't read the file multiple times each round.

Signed-off-by: Dominik Csapak <d.csapak@proxmox.com>
---
 PVE/Jobs.pm | 62 ++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 57 insertions(+), 5 deletions(-)

diff --git a/PVE/Jobs.pm b/PVE/Jobs.pm
index 1091bc22..822f0454 100644
--- a/PVE/Jobs.pm
+++ b/PVE/Jobs.pm
@@ -25,6 +25,8 @@ my $default_state = {
     time => 0,
 };
 
+my $saved_props = [qw(enabled schedule)];
+
 # lockless, since we use file_get_contents, which is atomic
 sub read_job_state {
     my ($jobid, $type) = @_;
@@ -93,8 +95,15 @@ sub update_job_stopped {
 		upid => $state->{upid},
 	    };
 
-	    if ($state->{updated}) { # save updated time stamp
-		$new_state->{updated} = $state->{updated};
+	    # save some old props
+	    if (my $updated = $state->{updated}) {
+		$new_state->{updated} = $updated;
+	    }
+
+	    for my $prop (@$saved_props) {
+		if (defined($state->{$prop})) {
+		    $new_state->{$prop} = $state->{$prop};
+		}
 	    }
 
 	    my $path = $get_state_file->($jobid, $type);
@@ -105,7 +114,7 @@ sub update_job_stopped {
 
 # must be called when the job is first created
 sub create_job {
-    my ($jobid, $type) = @_;
+    my ($jobid, $type, $cfg) = @_;
 
     lock_job_state($jobid, $type, sub {
 	my $state = read_job_state($jobid, $type) // $default_state;
@@ -115,6 +124,11 @@ sub create_job {
 	}
 
 	$state->{time} = time();
+	for my $prop (@$saved_props) {
+	    if (defined($cfg->{$prop})) {
+		$state->{$prop} = $cfg->{$prop};
+	    }
+	}
 
 	my $path = $get_state_file->($jobid, $type);
 	PVE::Tools::file_set_contents($path, encode_json($state));
@@ -192,6 +206,39 @@ sub update_last_runtime {
     });
 }
 
+# saves some properties of the jobcfg into the jobstate so we can track
+# them on different nodes (where the update was not done)
+# and update the last runtime when they change
+sub update_job_props {
+    my ($jobid, $type, $cfg) = @_;
+
+    lock_job_state($jobid, $type, sub {
+	my $old_state = read_job_state($jobid, $type) // $default_state;
+
+	my $updated = 0;
+	for my $prop (@$saved_props) {
+	    my $old_prop = $old_state->{$prop} // '';
+	    my $new_prop = $cfg->{$prop} // '';
+	    next if "$old_prop" eq "$new_prop";
+
+	    if (defined($cfg->{$prop})) {
+		$old_state->{$prop} = $cfg->{$prop};
+	    } else {
+		delete $old_state->{$prop};
+	    }
+
+	    $updated = 1;
+	}
+
+	return if !$updated;
+	$old_state->{updated} = time();
+
+	my $path = $get_state_file->($jobid, $type);
+	PVE::Tools::file_set_contents($path, encode_json($old_state));
+    });
+}
+
+
 sub get_last_runtime {
     my ($jobid, $type) = @_;
 
@@ -265,8 +312,13 @@ sub synchronize_job_states_with_config {
 	for my $id (keys $data->{ids}->%*) {
 	    my $job = $data->{ids}->{$id};
 	    my $type = $job->{type};
-	    my $jobstate = read_job_state($id, $type);
-	    create_job($id, $type) if !defined($jobstate);
+
+	    my $path = $get_state_file->($id, $type);
+	    if (-e $path) {
+		update_job_props($id, $type, $job);
+	    } else {
+		create_job($id, $type, $job);
+	    }
 	}
 
 	PVE::Tools::dir_glob_foreach($state_dir, '(.*?)-(.*).json', sub {
-- 
2.30.2