From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from firstgate.proxmox.com (firstgate.proxmox.com [IPv6:2a01:7e0:0:424::9]) by lore.proxmox.com (Postfix) with ESMTPS id 38A4D1FF141 for ; Mon, 30 Mar 2026 16:44:04 +0200 (CEST) Received: from firstgate.proxmox.com (localhost [127.0.0.1]) by firstgate.proxmox.com (Proxmox) with ESMTP id 10199376DE; Mon, 30 Mar 2026 16:42:07 +0200 (CEST) From: Daniel Kral To: pve-devel@lists.proxmox.com Subject: [PATCH ha-manager v3 26/40] sim: hardware: add getters for dynamic {node,service} stats Date: Mon, 30 Mar 2026 16:30:35 +0200 Message-ID: <20260330144101.668747-27-d.kral@proxmox.com> X-Mailer: git-send-email 2.47.3 In-Reply-To: <20260330144101.668747-1-d.kral@proxmox.com> References: <20260330144101.668747-1-d.kral@proxmox.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Bm-Milter-Handled: 55990f41-d878-4baa-be0a-ee34c49e34d2 X-Bm-Transport-Timestamp: 1774881614549 X-SPAM-LEVEL: Spam detection results: 0 AWL 0.064 Adjusted score from AWL reputation of From: address BAYES_00 -1.9 Bayes spam probability is 0 to 1% DMARC_MISSING 0.1 Missing DMARC policy KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment SPF_HELO_NONE 0.001 SPF: HELO does not publish an SPF Record SPF_PASS -0.001 SPF: sender matches SPF record Message-ID-Hash: URKLZIFE5HHUHDSCSKK3472DWYZZPNNX X-Message-ID-Hash: URKLZIFE5HHUHDSCSKK3472DWYZZPNNX X-MailFrom: d.kral@proxmox.com X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; loop; banned-address; emergency; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header X-Mailman-Version: 3.3.10 Precedence: list List-Id: Proxmox VE development discussion List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: From: Dominik Rusovac Aggregation of dynamic node stats is lazy. Getters log on warning level in case of overcommitted stats. Signed-off-by: Dominik Rusovac Signed-off-by: Daniel Kral --- changes v2 -> v3: - add comment about get_dynamic_node_stats() excluding non-running resources from the summation src/PVE/HA/Sim/Env.pm | 12 ++++++++ src/PVE/HA/Sim/Hardware.pm | 61 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 73 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 b4000cfd..5693df0f 100644 --- a/src/PVE/HA/Sim/Hardware.pm +++ b/src/PVE/HA/Sim/Hardware.pm @@ -1232,6 +1232,27 @@ 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) = @_; @@ -1245,6 +1266,46 @@ 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}; + + # only add the dynamic load usage to node if service is actually marked + # as running by the node service status written by the LRM + 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