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 8BD041FF133 for ; Mon, 11 May 2026 17:58:27 +0200 (CEST) Received: from firstgate.proxmox.com (localhost [127.0.0.1]) by firstgate.proxmox.com (Proxmox) with ESMTP id 55C7E1F524; Mon, 11 May 2026 17:58:24 +0200 (CEST) From: Dominik Rusovac To: pve-devel@lists.proxmox.com Subject: [PATCH pve-ha-manager 3/3] fix #7557: introduce 'auto-rebalance' property Date: Mon, 11 May 2026 17:57:34 +0200 Message-ID: <20260511155734.149101-4-d.rusovac@proxmox.com> X-Mailer: git-send-email 2.47.3 In-Reply-To: <20260511155734.149101-1-d.rusovac@proxmox.com> References: <20260511155734.149101-1-d.rusovac@proxmox.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Bm-Milter-Handled: 55990f41-d878-4baa-be0a-ee34c49e34d2 X-Bm-Transport-Timestamp: 1778514947797 X-SPAM-LEVEL: Spam detection results: 0 AWL 0.363 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 URIBL_BLOCKED 0.001 ADMINISTRATOR NOTICE: The query to URIBL was blocked. See http://wiki.apache.org/spamassassin/DnsBlocklists#dnsbl-block for more information. [resources.pm,status.pm,config.pm,hardware.pm,manager.pm,pvect.pm,pvevm.pm] Message-ID-Hash: NLPG3KAXAZVVPJF5L4VZLBVIQQP543Z4 X-Message-ID-Hash: NLPG3KAXAZVVPJF5L4VZLBVIQQP543Z4 X-MailFrom: d.rusovac@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: Add 'auto-rebalance' property to HA resources config, which gives users control over which HA resources may be moved by dynamic CRS during automatic rebalancing. The 'auto-rebalance' flag is set to true by default. Disabling 'auto-rebalance' for some HA resource, say vm:100, means that vm:100 will be disregarded as a migration candidate during auto-rebalancing. Any HA resource with a positive affinity for vm:100 will be disregarded too. Tests validate that an entire resource bundle will be disregarded if any resource belonging to the bundle has 'auto-rebalance' disabled. Signed-off-by: Dominik Rusovac --- src/PVE/API2/HA/Resources.pm | 7 ++ src/PVE/API2/HA/Status.pm | 9 +- src/PVE/HA/Config.pm | 2 + src/PVE/HA/Manager.pm | 12 ++- src/PVE/HA/Resources.pm | 6 ++ src/PVE/HA/Resources/PVECT.pm | 1 + src/PVE/HA/Resources/PVEVM.pm | 1 + src/PVE/HA/Sim/Hardware.pm | 1 + src/test/test_resource_bundles.pl | 134 +++++++++++++++++++++++++++++- 9 files changed, 166 insertions(+), 7 deletions(-) diff --git a/src/PVE/API2/HA/Resources.pm b/src/PVE/API2/HA/Resources.pm index e0690d5..181cdbb 100644 --- a/src/PVE/API2/HA/Resources.pm +++ b/src/PVE/API2/HA/Resources.pm @@ -142,6 +142,13 @@ __PACKAGE__->register_method({ optional => 1, default => 1, }, + 'auto-rebalance' => { + description => "HA resource may be migrated during" + . " automatic rebalancing.", + type => 'boolean', + optional => 1, + default => 1, + }, group => get_standard_option('pve-ha-group-id', { optional => 1 }), max_restart => { description => "Maximal number of tries to restart the service on" diff --git a/src/PVE/API2/HA/Status.pm b/src/PVE/API2/HA/Status.pm index 4894f3b..c352aa1 100644 --- a/src/PVE/API2/HA/Status.pm +++ b/src/PVE/API2/HA/Status.pm @@ -121,6 +121,13 @@ __PACKAGE__->register_method({ optional => 1, default => 1, }, + 'auto-rebalance' => { + description => "HA resource may be migrated during" + . " automatic rebalancing.", + type => 'boolean', + optional => 1, + default => 1, + }, max_relocate => { description => "For type 'service'.", type => "integer", @@ -333,7 +340,7 @@ __PACKAGE__->register_method({ # also return common resource attributes if (defined($sc)) { $data->{request_state} = $sc->{state}; - foreach my $key (qw(group max_restart max_relocate failback comment)) { + foreach my $key (qw(group max_restart max_relocate failback comment auto-rebalance)) { $data->{$key} = $sc->{$key} if defined($sc->{$key}); } } diff --git a/src/PVE/HA/Config.pm b/src/PVE/HA/Config.pm index a34a302..54a6503 100644 --- a/src/PVE/HA/Config.pm +++ b/src/PVE/HA/Config.pm @@ -118,8 +118,10 @@ sub read_and_check_resources_config { $d->{state} = 'started' if !defined($d->{state}); $d->{state} = 'started' if $d->{state} eq 'enabled'; # backward compatibility $d->{failback} = 1 if !defined($d->{failback}); + $d->{'auto-rebalance'} = 1 if !defined($d->{'auto-rebalance'}); $d->{max_restart} = 1 if !defined($d->{max_restart}); $d->{max_relocate} = 1 if !defined($d->{max_relocate}); + if (PVE::HA::Resources->lookup($d->{type})) { if (my $vmd = $vmlist->{ids}->{$name}) { $d->{node} = $vmd->{node}; diff --git a/src/PVE/HA/Manager.pm b/src/PVE/HA/Manager.pm index 2a4b31e..68e3cd6 100644 --- a/src/PVE/HA/Manager.pm +++ b/src/PVE/HA/Manager.pm @@ -136,12 +136,14 @@ sub update_crs_scheduler_mode { # HA resource in the resource bundle and also the key of each resource bundle # in the returned hash. sub get_active_stationary_resource_bundles { - my ($ss, $resource_affinity) = @_; + my ($ss, $sc, $resource_affinity) = @_; my $resource_bundles = {}; OUTER: for my $sid (sort keys %$ss) { # do not consider non-started resource as 'active' leading resource next if $ss->{$sid}->{state} ne 'started'; + # do not consider resource if it may not be moved + next if !$sc->{$sid}->{'auto-rebalance'}; my @resources = ($sid); my $nodes = { $ss->{$sid}->{node} => 1 }; @@ -156,6 +158,8 @@ OUTER: for my $sid (sort keys %$ss) { next OUTER if $state eq 'migrate' || $state eq 'relocate'; # do not add non-started resource to active bundle next if $state ne 'started'; + # do not consider stationary bundle if a dependent resource may not be moved + next OUTER if !$sc->{$csid}->{'auto-rebalance'}; $nodes->{$node} = 1; @@ -182,12 +186,12 @@ OUTER: for my $sid (sort keys %$ss) { sub get_resource_migration_candidates { my ($self) = @_; - my ($ss, $compiled_rules, $online_node_usage) = - $self->@{qw(ss compiled_rules online_node_usage)}; + my ($ss, $sc, $compiled_rules, $online_node_usage) = + $self->@{qw(ss sc compiled_rules online_node_usage)}; my ($node_affinity, $resource_affinity) = $compiled_rules->@{qw(node-affinity resource-affinity)}; - my $resource_bundles = get_active_stationary_resource_bundles($ss, $resource_affinity); + my $resource_bundles = get_active_stationary_resource_bundles($ss, $sc, $resource_affinity); my @compact_migration_candidates = (); for my $leader_sid (sort keys %$resource_bundles) { diff --git a/src/PVE/HA/Resources.pm b/src/PVE/HA/Resources.pm index 4238d9b..df7c1ff 100644 --- a/src/PVE/HA/Resources.pm +++ b/src/PVE/HA/Resources.pm @@ -71,6 +71,12 @@ EODESC optional => 1, default => 1, }, + 'auto-rebalance' => { + description => "HA resource may be migrated during automatic rebalancing", + type => 'boolean', + optional => 1, + default => 1, + }, max_restart => { description => "Maximal number of tries to restart the resource on" . " a node after its start failed. When reached, the HA manager will try to" diff --git a/src/PVE/HA/Resources/PVECT.pm b/src/PVE/HA/Resources/PVECT.pm index 0943d5e..177b907 100644 --- a/src/PVE/HA/Resources/PVECT.pm +++ b/src/PVE/HA/Resources/PVECT.pm @@ -38,6 +38,7 @@ sub options { group => { optional => 1 }, comment => { optional => 1 }, failback => { optional => 1 }, + 'auto-rebalance' => { optional => 1 }, max_restart => { optional => 1 }, max_relocate => { optional => 1 }, }; diff --git a/src/PVE/HA/Resources/PVEVM.pm b/src/PVE/HA/Resources/PVEVM.pm index 1621c15..98ea7d6 100644 --- a/src/PVE/HA/Resources/PVEVM.pm +++ b/src/PVE/HA/Resources/PVEVM.pm @@ -38,6 +38,7 @@ sub options { group => { optional => 1 }, comment => { optional => 1 }, failback => { optional => 1 }, + 'auto-rebalance' => { optional => 1 }, max_restart => { optional => 1 }, max_relocate => { optional => 1 }, }; diff --git a/src/PVE/HA/Sim/Hardware.pm b/src/PVE/HA/Sim/Hardware.pm index 82f85c9..e247bfa 100644 --- a/src/PVE/HA/Sim/Hardware.pm +++ b/src/PVE/HA/Sim/Hardware.pm @@ -115,6 +115,7 @@ sub read_service_config { $d->{state} = 'disabled' if !$d->{state}; $d->{state} = 'started' if $d->{state} eq 'enabled'; # backward compatibility $d->{failback} = 1 if !defined($d->{failback}); + $d->{'auto-rebalance'} = 1 if !defined($d->{'auto-rebalance'}); $d->{max_restart} = 1 if !defined($d->{max_restart}); $d->{max_relocate} = 1 if !defined($d->{max_relocate}); } diff --git a/src/test/test_resource_bundles.pl b/src/test/test_resource_bundles.pl index d38dc51..7df96a9 100755 --- a/src/test/test_resource_bundles.pl +++ b/src/test/test_resource_bundles.pl @@ -21,6 +21,10 @@ my $get_active_stationary_resource_bundle_tests = [ node => 'node1', }, }, + service_config => { + 'vm:101' => { 'auto-rebalance' => 1 }, + 'vm:102' => { 'auto-rebalance' => 1 }, + }, resource_affinity => { positive => {}, negative => {}, @@ -46,6 +50,10 @@ my $get_active_stationary_resource_bundle_tests = [ node => 'node1', }, }, + service_config => { + 'vm:101' => { 'auto-rebalance' => 1 }, + 'vm:102' => { 'auto-rebalance' => 1 }, + }, resource_affinity => { positive => { 'vm:101' => { @@ -79,6 +87,11 @@ my $get_active_stationary_resource_bundle_tests = [ node => 'node1', }, }, + service_config => { + 'vm:101' => { 'auto-rebalance' => 1 }, + 'vm:102' => { 'auto-rebalance' => 1 }, + 'vm:103' => { 'auto-rebalance' => 1 }, + }, resource_affinity => { positive => { 'vm:101' => { @@ -118,6 +131,11 @@ my $get_active_stationary_resource_bundle_tests = [ node => 'node1', }, }, + service_config => { + 'vm:101' => { 'auto-rebalance' => 1 }, + 'vm:102' => { 'auto-rebalance' => 1 }, + 'vm:103' => { 'auto-rebalance' => 1 }, + }, resource_affinity => { positive => { 'vm:101' => { @@ -159,6 +177,11 @@ my $get_active_stationary_resource_bundle_tests = [ target => 'node1', }, }, + service_config => { + 'vm:101' => { 'auto-rebalance' => 1 }, + 'vm:102' => { 'auto-rebalance' => 1 }, + 'vm:103' => { 'auto-rebalance' => 1 }, + }, resource_affinity => { positive => { 'vm:101' => { @@ -196,6 +219,11 @@ my $get_active_stationary_resource_bundle_tests = [ node => 'node3', }, }, + service_config => { + 'vm:101' => { 'auto-rebalance' => 1 }, + 'vm:102' => { 'auto-rebalance' => 1 }, + 'vm:103' => { 'auto-rebalance' => 1 }, + }, resource_affinity => { positive => { 'vm:101' => { @@ -215,6 +243,108 @@ my $get_active_stationary_resource_bundle_tests = [ }, resource_bundles => {}, }, + { + description => "singleton resource bundle with disabled auto-rebalance", + services => { + 'vm:101' => { + state => 'started', + node => 'node1', + }, + 'vm:102' => { + state => 'started', + node => 'node1', + }, + }, + service_config => { + 'vm:101' => { 'auto-rebalance' => 0 }, + 'vm:102' => { 'auto-rebalance' => 1 }, + }, + resource_affinity => { + positive => {}, + negative => {}, + }, + resource_bundles => { + 'vm:102' => [ + 'vm:102', + ], + }, + }, + { + description => "resource bundle leader with disabled auto-rebalance", + services => { + 'vm:101' => { + state => 'started', + node => 'node1', + }, + 'vm:102' => { + state => 'started', + node => 'node1', + }, + 'ct:103' => { + state => 'started', + node => 'node2', + }, + }, + service_config => { + 'vm:101' => { 'auto-rebalance' => 0 }, + 'vm:102' => { 'auto-rebalance' => 1 }, + 'ct:103' => { 'auto-rebalance' => 1 }, + }, + resource_affinity => { + positive => { + 'vm:101' => { + 'vm:102' => 1, + }, + 'vm:102' => { + 'vm:101' => 1, + }, + }, + negative => {}, + }, + resource_bundles => { + 'ct:103' => [ + 'ct:103', + ], + }, + }, + { + description => "some member of resource bundle with disabled auto-rebalance", + services => { + 'vm:101' => { + state => 'started', + node => 'node1', + }, + 'vm:102' => { + state => 'started', + node => 'node1', + }, + 'ct:103' => { + state => 'started', + node => 'node2', + }, + }, + service_config => { + 'vm:101' => { 'auto-rebalance' => 1 }, + 'vm:102' => { 'auto-rebalance' => 0 }, + 'ct:103' => { 'auto-rebalance' => 1 }, + }, + resource_affinity => { + positive => { + 'vm:101' => { + 'vm:102' => 1, + }, + 'vm:102' => { + 'vm:101' => 1, + }, + }, + negative => {}, + }, + resource_bundles => { + 'ct:103' => [ + 'ct:103', + ], + }, + }, ]; my $tests = [ @@ -224,9 +354,9 @@ my $tests = [ plan(tests => scalar($tests->@*)); for my $case ($get_active_stationary_resource_bundle_tests->@*) { - my ($ss, $resource_affinity) = $case->@{qw(services resource_affinity)}; + my ($ss, $sc, $resource_affinity) = $case->@{qw(services service_config resource_affinity)}; - my $result = PVE::HA::Manager::get_active_stationary_resource_bundles($ss, $resource_affinity); + my $result = PVE::HA::Manager::get_active_stationary_resource_bundles($ss, $sc, $resource_affinity); is_deeply($result, $case->{resource_bundles}, $case->{description}); } -- 2.47.3