From: Thomas Lamprecht <t.lamprecht@proxmox.com>
To: pve-devel@lists.proxmox.com
Subject: [PATCH ha-manager 05/15] env: pve2: delegate cluster stat gathering to scheduling library
Date: Wed, 18 Nov 2026 12:05:12 +0100 [thread overview]
Message-ID: <20261118110705.595989-6-t.lamprecht@proxmox.com> (raw)
In-Reply-To: <20261118110705.595989-1-t.lamprecht@proxmox.com>
The cluster node and guest stat gathering now lives in the
PVE::ResourceScheduling::Stats module of libpve-guest-common-perl.
Consume it here instead of keeping a second copy, so the HA manager
and the resource scheduling API share a single implementation and
cannot drift apart. The library's dynamic guest stats carry the host
memory accounting from fix #7974, and the stats the HA manager sees
stay the same.
The library has no dependency on the HA resource plugins, so build
the static per-guest-type usage resolvers from those plugins and pass
them in. As the library reports undecodable static node info as a
plain warning, log that at error level like before.
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
NOTE: the new libpve-guest-common-perl dependency needs a version
requirement for the first release with PVE::ResourceScheduling.
debian/control | 2 +
src/PVE/HA/Env/PVE2.pm | 155 ++++++++---------------------------------
2 files changed, 32 insertions(+), 125 deletions(-)
diff --git a/debian/control b/debian/control
index 107e367..2577d43 100644
--- a/debian/control
+++ b/debian/control
@@ -8,6 +8,7 @@ Build-Depends: debhelper-compat (= 13),
libpve-access-control,
libpve-cluster-perl,
libpve-common-perl,
+ libpve-guest-common-perl,
libpve-notify-perl,
libpve-rs-perl (>= 0.14.0),
libtest-mockmodule-perl <!nocheck>,
@@ -23,6 +24,7 @@ Architecture: any
Depends: libjson-perl,
libpve-cluster-perl (>= 9.1.5),
libpve-common-perl,
+ libpve-guest-common-perl,
libpve-notify-perl (>= 8.1.0),
libpve-rs-perl (>= 0.14.0),
pve-cluster (>= 3.0-17),
diff --git a/src/PVE/HA/Env/PVE2.pm b/src/PVE/HA/Env/PVE2.pm
index 5f195da..de56e20 100644
--- a/src/PVE/HA/Env/PVE2.pm
+++ b/src/PVE/HA/Env/PVE2.pm
@@ -14,6 +14,7 @@ use PVE::DataCenterConfig;
use PVE::INotify;
use PVE::RPCEnvironment;
use PVE::Notify;
+use PVE::ResourceScheduling::Stats;
use PVE::HA::Tools ':exit_codes';
use PVE::HA::Env;
@@ -36,30 +37,19 @@ PVE::HA::Rules::ResourceAffinity->register();
PVE::HA::Rules->init(property_isolation => 1);
+# The stats library has no dependency on the HA resource plugins, so build the per-guest-type static
+# usage resolvers from those plugins and pass them in.
+my sub static_stats_resolvers {
+ return {
+ map {
+ my $plugin = PVE::HA::Resources->lookup($_);
+ ($_ => sub { $plugin->get_static_stats_from_config($_[0]) });
+ } qw(vm ct)
+ };
+}
+
my $lockdir = "/etc/pve/priv/lock";
-# rrd entry indices for VM and CT guests
-# taken from PVE::Service::pvestatd::update_{lxc,qemu}_status()
-use constant {
- RRD_VM_INDEX_STATUS => 2,
- RRD_VM_INDEX_MAXCPU => 5,
- RRD_VM_INDEX_CPU => 6,
- RRD_VM_INDEX_MAXMEM => 7,
- RRD_VM_INDEX_MEM => 8,
- RRD_VM_INDEX_MEMHOST => 15,
-};
-
-# rrd entry indices for PVE nodes
-# taken from PVE::Service::pvestatd::update_node_status()
-use constant {
- RRD_NODE_INDEX_MAXCPU => 4,
- RRD_NODE_INDEX_CPU => 5,
- RRD_NODE_INDEX_MAXMEM => 7,
- RRD_NODE_INDEX_MEM => 8,
-};
-
-my $HOSTNAME_RE = qr/(?:[a-zA-Z0-9](?:[a-zA-Z0-9\-]{,61}?[a-zA-Z0-9])?)/;
-
sub new {
my ($this, $nodename) = @_;
@@ -529,133 +519,48 @@ sub get_datacenter_settings {
};
}
-my sub get_cluster_service_stats {
- my $vmlist = PVE::Cluster::get_vmlist();
- my $idlist = $vmlist->{ids} // {};
-
- my $rrd = PVE::Cluster::rrd_dump();
-
- my $stats = {};
- for my $id (keys %$idlist) {
- my $type = eval { PVE::HA::Tools::get_ha_resource_type($idlist->{$id}->{type}) };
- next if $@; # silently ignore unknown pve types
-
- my $sid = "$type:$id";
- my $nodename = $idlist->{$id}->{node};
-
- my $rrdentry = $rrd->{"pve-vm-9.0/$id"} // [];
- # can be any QMP RunState, but 'running' is the only active VM state
- my $status = $rrdentry->[RRD_VM_INDEX_STATUS] // "stopped";
- my $state = $status eq "running" ? "started" : "stopped";
-
- $stats->{$sid} = {
- id => $id,
- node => $nodename,
- state => $state,
- running => $state eq 'started',
- type => $type,
- usage => {},
- };
- }
-
- return $stats;
-}
-
sub get_basic_service_stats {
my ($self) = @_;
- return get_cluster_service_stats();
+ return PVE::ResourceScheduling::Stats::get_cluster_guest_stats();
}
sub get_static_service_stats {
my ($self) = @_;
- my $properties = ['cores', 'cpulimit', 'memory', 'sockets', 'vcpus'];
- my $stats = get_cluster_service_stats();
- my $confs = PVE::Cluster::get_guest_config_properties($properties);
-
- for my $sid (keys %$stats) {
- my ($id, $type) = $stats->{$sid}->@{qw(id type)};
-
- my $conf = $confs->{$id} // {};
- my $plugin = PVE::HA::Resources->lookup($type);
-
- $stats->{$sid}->{usage} = $plugin->get_static_stats_from_config($conf);
- }
-
- return $stats;
+ return PVE::ResourceScheduling::Stats::get_static_guest_stats(static_stats_resolvers());
}
sub get_dynamic_service_stats {
my ($self) = @_;
- my $rrd = PVE::Cluster::rrd_dump();
-
- my $stats = get_cluster_service_stats();
- for my $sid (keys %$stats) {
- my $id = $stats->{$sid}->{id};
- my $rrdentry = $rrd->{"pve-vm-9.0/$id"} // [];
-
- # NOTE the guests' broadcasted vmstatus() caps maxcpu at the node's maxcpu
- my $maxcpu = ($rrdentry->[RRD_VM_INDEX_MAXCPU] || 0.0) + 0.0;
-
- # designated fallback for containers
- my $mem = $rrdentry->[RRD_VM_INDEX_MEMHOST] // $rrdentry->[RRD_VM_INDEX_MEM];
-
- $stats->{$sid}->{usage} = {
- maxcpu => $maxcpu,
- cpu => (($rrdentry->[RRD_VM_INDEX_CPU] || 0.0) + 0.0) * $maxcpu,
- maxmem => int($rrdentry->[RRD_VM_INDEX_MAXMEM] || 0),
- mem => int($mem || 0),
- };
- }
-
- return $stats;
+ return PVE::ResourceScheduling::Stats::get_dynamic_guest_stats();
}
sub get_static_node_stats {
my ($self) = @_;
- my $stats = PVE::Cluster::get_node_kv('static-info');
- for my $node (keys $stats->%*) {
- $stats->{$node} = eval {
- my $node_stats = decode_json($stats->{$node});
+ # The library reports undecodable static node info with warn(). Log that at 'err' level, as an
+ # online node without static info makes the CRM fall back to basic scheduling.
+ my $previous = $SIG{__WARN__};
+ local $SIG{__WARN__} = sub {
+ my ($msg) = @_;
+ if ($msg =~ m/^unable to decode static node info /) {
+ $self->log('err', $msg);
+ } elsif (ref($previous) eq 'CODE') {
+ $previous->($msg);
+ } else {
+ warn $msg;
+ }
+ };
- return {
- maxcpu => $node_stats->{cpus},
- maxmem => $node_stats->{memory},
- };
- };
- $self->log('err', "unable to decode static node info for '$node' - $@") if $@;
- }
-
- return $stats;
+ return PVE::ResourceScheduling::Stats::get_static_node_stats();
}
sub get_dynamic_node_stats {
my ($self) = @_;
- my $rrd = PVE::Cluster::rrd_dump();
-
- my $stats = {};
- for my $key (keys %$rrd) {
- my ($nodename) = $key =~ m/^pve-node-9.0\/($HOSTNAME_RE)$/;
-
- next if !$nodename;
-
- my $rrdentry = $rrd->{$key} // [];
-
- my $maxcpu = int($rrdentry->[RRD_NODE_INDEX_MAXCPU] || 0);
-
- $stats->{$nodename} = {
- maxcpu => $maxcpu,
- cpu => (($rrdentry->[RRD_NODE_INDEX_CPU] || 0.0) + 0.0) * $maxcpu,
- maxmem => int($rrdentry->[RRD_NODE_INDEX_MAXMEM] || 0),
- mem => int($rrdentry->[RRD_NODE_INDEX_MEM] || 0),
- };
- }
-
- return $stats;
+ return PVE::ResourceScheduling::Stats::get_dynamic_node_stats();
}
sub get_node_version {
--
2.47.3
next prev parent reply other threads:[~2026-11-18 11:08 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-18 11:05 [PATCH guest-common,ha-manager,manager,docs 0/15] cluster resource scheduling for all guests Thomas Lamprecht
2026-11-18 11:05 ` [PATCH guest-common 01/15] scheduling: add cluster resource scheduling library Thomas Lamprecht
2026-11-18 11:05 ` [PATCH ha-manager 02/15] helpers: block both locations of a migrating negative affinity partner Thomas Lamprecht
2026-11-18 11:05 ` [PATCH ha-manager 03/15] usage: static: count services per node again for scoring fallback Thomas Lamprecht
2026-11-18 11:05 ` [PATCH ha-manager 04/15] config: allow getting motion info of many resources at once Thomas Lamprecht
2026-11-18 11:05 ` Thomas Lamprecht [this message]
2026-11-18 11:05 ` [PATCH ha-manager 06/15] usage: share one scheduler base between static and dynamic Thomas Lamprecht
2026-11-18 11:05 ` [PATCH manager 07/15] ui: bulk action: translate error title and CT restart warning Thomas Lamprecht
2026-11-18 11:05 ` [PATCH manager 08/15] ui: bulk migrate: show CT restart warning for cluster-wide migration Thomas Lamprecht
2026-11-18 11:05 ` [PATCH manager 09/15] ui: migrate: recheck preconditions if the target changed meanwhile Thomas Lamprecht
2026-11-18 11:05 ` [PATCH manager 10/15] api: cluster: add resource scheduling endpoints Thomas Lamprecht
2026-11-18 11:05 ` [PATCH manager 11/15] ui: migrate: sort target nodes by scheduler recommendation Thomas Lamprecht
2026-11-18 11:05 ` [PATCH manager 12/15] api: bulk migrate: allow a per-guest target node mapping Thomas Lamprecht
2026-11-18 11:05 ` [PATCH manager 13/15] ui: bulk migrate: support per-guest target nodes Thomas Lamprecht
2026-11-18 11:05 ` [PATCH manager 14/15] ui: dc: add a Rebalance Guests bulk action Thomas Lamprecht
2026-11-18 11:05 ` [PATCH docs 15/15] pvecm: document balancing the cluster load with migrations Thomas Lamprecht
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261118110705.595989-6-t.lamprecht@proxmox.com \
--to=t.lamprecht@proxmox.com \
--cc=pve-devel@lists.proxmox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox