[pve-devel] [PATCH guest-common 2/2] replication: don't sync to offline targets on error states

[Wolfgang Bumiller]

There's no point in trying to replicate to a target node
which is offline. Note that if we're not already in an
error state we do still give it a try in order for this to
get logged as an error at least once.
---
 PVE/ReplicationState.pm | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/PVE/ReplicationState.pm b/PVE/ReplicationState.pm
index 2ef31b5..e064545 100644
--- a/PVE/ReplicationState.pm
+++ b/PVE/ReplicationState.pm
@@ -233,9 +233,10 @@ sub job_status {
 	# only consider guest on local node
 	next if $vms->{ids}->{$vmid}->{node} ne $local_node;
 
+	my $target = $jobcfg->{target};
 	if (!$jobcfg->{remove_job}) {
 	    # never sync to local node
-	    next if $jobcfg->{target} eq $local_node;
+	    next if $target eq $local_node;
 
 	    next if $jobcfg->{disable};
 	}
@@ -252,7 +253,10 @@ sub job_status {
 	    # todo: consider fail_count? How many retries?
 	} else  {
 	    if (my $fail_count = $state->{fail_count}) {
-		$next_sync = $state->{last_try} + 60*($fail_count < 3 ? 5*$fail_count : 30);
+		my $members = PVE::Cluster::get_members();
+		if (!$fail_count || ($members->{$target} && $members->{$target}->{online})) {
+		    $next_sync = $state->{last_try} + 60*($fail_count < 3 ? 5*$fail_count : 30);
+		}
 	    } else {
 		my $schedule =  $jobcfg->{schedule} || '*/15';
 		my $calspec = PVE::CalendarEvent::parse_calendar_event($schedule);
-- 
2.11.0