[PATCH ha-manager v4 14/28] usage: use add_service to add service usage to nodes

[Daniel Kral <d.kral@proxmox.com>]

The pve_static (and upcoming pve_dynamic) bindings expose the new
add_resource(...) method, which allow adding resources in a single call
with the additional running flag.

The running flag is needed to discriminate starting and started HA
resources from each other, which is needed to correctly account for HA
resources for the dynamic load usage implementation in the next patch.

This is because for the dynamic load usage, any HA resource, which is
scheduled to start by the HA Manager in the same round, will not be
accounted for in the next call to score_nodes_to_start_resource(...).
This is not a problem for the static load usage, because there the
current node usages are derived from the started resources on every
call already.

Passing only the HA resources' 'state' property is not enough since the
HA Manager will move any HA resource from the 'request_start' (or
through other transient states such as 'request_start_balance' and a
successful 'migrate'/'relocate') into the 'started' state.

This 'started' state is then picked up by the HA resource's LRM, which
will actually start the HA resource and if successful respond with a
'SUCCESS' LRM result. Only then will the HA Manager acknowledges this by
adding the running flag to the HA resource's state.

Signed-off-by: Daniel Kral <d.kral@proxmox.com>
Reviewed-by: Dominik Rusovac <d.rusovac@proxmox.com>
---
changes v3 -> v4:
- none

 src/PVE/HA/Usage.pm        | 13 ++++++++-----
 src/PVE/HA/Usage/Basic.pm  |  9 ++++++++-
 src/PVE/HA/Usage/Static.pm | 30 ++++++++++++++++++++++++------
 3 files changed, 40 insertions(+), 12 deletions(-)

diff --git a/src/PVE/HA/Usage.pm b/src/PVE/HA/Usage.pm
index be3e64d6..43feb041 100644
--- a/src/PVE/HA/Usage.pm
+++ b/src/PVE/HA/Usage.pm
@@ -33,9 +33,8 @@ sub contains_node {
     die "implement in subclass";
 }
 
-# Logs a warning to $haenv upon failure, but does not die.
-sub add_service_usage_to_node {
-    my ($self, $nodename, $sid) = @_;
+sub add_service {
+    my ($self, $sid, $current_node, $target_node, $running) = @_;
 
     die "implement in subclass";
 }
@@ -47,8 +46,12 @@ sub add_service_usage {
     my $online_nodes = { map { $_ => 1 } $self->list_nodes() };
     my ($current_node, $target_node) = get_used_service_nodes($online_nodes, $sd);
 
-    $self->add_service_usage_to_node($current_node, $sid) if $current_node;
-    $self->add_service_usage_to_node($target_node, $sid) if $target_node;
+    # some usage implementations need to discern whether a service is truly running;
+    # a service does only have the 'running' flag in 'started' state
+    my $running = ($sd->{state} eq 'started' && $sd->{running})
+        || ($sd->{state} ne 'started' && defined($current_node));
+
+    $self->add_service($sid, $current_node, $target_node, $running);
 }
 
 sub remove_service_usage {
diff --git a/src/PVE/HA/Usage/Basic.pm b/src/PVE/HA/Usage/Basic.pm
index 2584727b..5aa3ac05 100644
--- a/src/PVE/HA/Usage/Basic.pm
+++ b/src/PVE/HA/Usage/Basic.pm
@@ -38,7 +38,7 @@ sub contains_node {
     return defined($self->{nodes}->{$nodename});
 }
 
-sub add_service_usage_to_node {
+my sub add_service_usage_to_node {
     my ($self, $nodename, $sid) = @_;
 
     if ($self->contains_node($nodename)) {
@@ -51,6 +51,13 @@ sub add_service_usage_to_node {
     }
 }
 
+sub add_service {
+    my ($self, $sid, $current_node, $target_node, $running) = @_;
+
+    add_service_usage_to_node($self, $current_node, $sid) if defined($current_node);
+    add_service_usage_to_node($self, $target_node, $sid) if defined($target_node);
+}
+
 sub remove_service_usage {
     my ($self, $sid) = @_;
 
diff --git a/src/PVE/HA/Usage/Static.pm b/src/PVE/HA/Usage/Static.pm
index b60f5000..8c7a614b 100644
--- a/src/PVE/HA/Usage/Static.pm
+++ b/src/PVE/HA/Usage/Static.pm
@@ -71,17 +71,35 @@ my sub get_service_usage {
     return $service_stats;
 }
 
-sub add_service_usage_to_node {
-    my ($self, $nodename, $sid) = @_;
+sub add_service {
+    my ($self, $sid, $current_node, $target_node, $running) = @_;
 
-    $self->{'node-services'}->{$nodename}->{$sid} = 1;
+    # do not add service which do not put any usage on the nodes
+    return if !defined($current_node) && !defined($target_node);
+
+    # PVE::RS::ResourceScheduling::Static::add_service() expects $current_node
+    # to be set, so consider $target_node as $current_node for unset $current_node;
+    #
+    # currently, this happens for the request_start_balance service state and if
+    # node maintenance causes services to migrate to other nodes
+    if (!defined($current_node)) {
+        $current_node = $target_node;
+        undef $target_node;
+    }
 
     eval {
         my $service_usage = get_service_usage($self, $sid);
-        $self->{scheduler}->add_service_usage_to_node($nodename, $sid, $service_usage);
+
+        my $service = {
+            stats => $service_usage,
+            running => $running,
+            'current-node' => $current_node,
+            'target-node' => $target_node,
+        };
+
+        $self->{scheduler}->add_service($sid, $service);
     };
-    $self->{haenv}->log('warning', "unable to add service '$sid' usage to node '$nodename' - $@")
-        if $@;
+    $self->{haenv}->log('warning', "unable to add service '$sid' - $@") if $@;
 }
 
 sub remove_service_usage {
-- 
2.47.3