[PATCH ha-manager v2 26/40] sim: hardware: add getters for dynamic {node,service} stats

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

From: Dominik Rusovac <d.rusovac@proxmox.com>

Aggregation of dynamic node stats is lazy.

Getters log on warning level in case of overcommitted stats.

Signed-off-by: Dominik Rusovac <d.rusovac@proxmox.com>
Signed-off-by: Daniel Kral <d.kral@proxmox.com>
---
changes v1 -> v2:
- new!

wrt v1:
- keep each commit functional on its own
- allow testing overcommitted scenarios

 src/PVE/HA/Sim/Env.pm      | 12 ++++++++
 src/PVE/HA/Sim/Hardware.pm | 59 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 71 insertions(+)

diff --git a/src/PVE/HA/Sim/Env.pm b/src/PVE/HA/Sim/Env.pm
index ad51245c..65d4efad 100644
--- a/src/PVE/HA/Sim/Env.pm
+++ b/src/PVE/HA/Sim/Env.pm
@@ -500,12 +500,24 @@ sub get_static_service_stats {
     return $self->{hardware}->get_static_service_stats();
 }
 
+sub get_dynamic_service_stats {
+    my ($self) = @_;
+
+    return $self->{hardware}->get_dynamic_service_stats();
+}
+
 sub get_static_node_stats {
     my ($self) = @_;
 
     return $self->{hardware}->get_static_node_stats();
 }
 
+sub get_dynamic_node_stats {
+    my ($self) = @_;
+
+    return $self->{hardware}->get_dynamic_node_stats();
+}
+
 sub get_node_version {
     my ($self, $node) = @_;
 
diff --git a/src/PVE/HA/Sim/Hardware.pm b/src/PVE/HA/Sim/Hardware.pm
index 89180ad7..c9362fd6 100644
--- a/src/PVE/HA/Sim/Hardware.pm
+++ b/src/PVE/HA/Sim/Hardware.pm
@@ -1196,6 +1196,27 @@ sub get_static_service_stats {
     return $stats;
 }
 
+sub get_dynamic_service_stats {
+    my ($self) = @_;
+
+    my $stats = get_cluster_service_stats($self);
+    my $static_stats = $self->read_static_service_stats();
+    my $dynamic_stats = $self->read_dynamic_service_stats();
+
+    for my $sid (keys %$stats) {
+        $stats->{$sid}->{usage} = {
+            $static_stats->{$sid}->%*, $dynamic_stats->{$sid}->%*,
+        };
+
+        $self->log('warning', "overcommitted cpu on '$sid'")
+            if $stats->{$sid}->{usage}->{cpu} > $stats->{$sid}->{usage}->{maxcpu};
+        $self->log('warning', "overcommitted mem on '$sid'")
+            if $stats->{$sid}->{usage}->{mem} > $stats->{$sid}->{usage}->{maxmem};
+    }
+
+    return $stats;
+}
+
 sub get_static_node_stats {
     my ($self) = @_;
 
@@ -1209,6 +1230,44 @@ sub get_static_node_stats {
     return $stats;
 }
 
+sub get_dynamic_node_stats {
+    my ($self) = @_;
+
+    my $stats = $self->get_static_node_stats();
+    for my $node (keys %$stats) {
+        $stats->{$node}->{maxcpu} = $stats->{$node}->{maxcpu} // $default_node_maxcpu;
+        $stats->{$node}->{cpu} = $stats->{$node}->{cpu} // 0.0;
+        $stats->{$node}->{maxmem} = $stats->{$node}->{maxmem} // $default_node_maxmem;
+        $stats->{$node}->{mem} = $stats->{$node}->{mem} // 0;
+    }
+
+    my $service_conf = $self->read_service_config();
+    my $dynamic_service_stats = $self->get_dynamic_service_stats();
+
+    my $cstatus = $self->read_hardware_status_nolock();
+    my $node_service_status = { map { $_ => $self->read_service_status($_) } keys %$cstatus };
+
+    for my $sid (keys %$service_conf) {
+        my $node = $service_conf->{$sid}->{node};
+
+        if ($node_service_status->{$node}->{$sid}) {
+            my ($cpu, $mem) = $dynamic_service_stats->{$sid}->{usage}->@{qw(cpu mem)};
+
+            die "unknown cpu load for '$sid'" if !defined($cpu);
+            $stats->{$node}->{cpu} += $cpu;
+            $self->log('warning', "overcommitted cpu on '$node'")
+                if $stats->{$node}->{cpu} > $stats->{$node}->{maxcpu};
+
+            die "unknown memory usage for '$sid'" if !defined($mem);
+            $stats->{$node}->{mem} += $mem;
+            $self->log('warning', "overcommitted mem on '$node'")
+                if $stats->{$node}->{mem} > $stats->{$node}->{maxmem};
+        }
+    }
+
+    return $stats;
+}
+
 sub get_node_version {
     my ($self, $node) = @_;
 
-- 
2.47.3