Real-time monitoring dashboard for Proxmox VE, PBS, Docker, Kubernetes, TrueNAS and vSphere. Self-hosted, with alerts for failed backups, full disks, unhealthy containers and offline nodes.
Go aialertsdashboarddockerdocker-monitoringgohomelabinfrastructure-monitoringkubernetesmonitoringmspproxmoxproxmox-backup-serverproxmox-mail-gatewayproxmox-veself-hostedtruenastypescriptvspherewebhooks
Drop pending temperature context with explicit clears and removal
pulse-triage[bot]4a8a5104d873
diff --git a/internal/alerts/active_cleanup.go b/internal/alerts/active_cleanup.goindex ea78202cf7..106ade74f5 100644--- a/internal/alerts/active_cleanup.go+++ b/internal/alerts/active_cleanup.go@@ -336,7 +336,7 @@ func (m *Manager) CleanupAlertsForNodes(existingNodes map[string]bool) {// ClearActiveAlerts removes all active and pending alerts, resetting the manager state.func (m *Manager) ClearActiveAlerts() {m.mu.Lock()- if len(m.activeAlerts) == 0 && len(m.intentPending) == 0 && len(m.smartCounterSnapshots) == 0 {+ if len(m.activeAlerts) == 0 && len(m.intentPending) == 0 && len(m.smartCounterSnapshots) == 0 && len(m.hostDiskTempPendingContexts) == 0 {m.mu.Unlock()return}@@ -344,6 +344,7 @@ func (m *Manager) ClearActiveAlerts() {m.restoredBackupNotifications = nilm.activeAlertAlias = make(map[string]string)m.core.Reset()+ m.hostDiskTempPendingContexts = nilm.intentPending = make(map[string]IntentPendingState)m.intentRuntimeTicks = make(map[string]time.Duration)m.recentAlerts = make(map[string]*Alert)diff --git a/internal/alerts/host_disk_temperature.go b/internal/alerts/host_disk_temperature.goindex 80d9a397ff..4f7dec14ab 100644--- a/internal/alerts/host_disk_temperature.go+++ b/internal/alerts/host_disk_temperature.go@@ -48,6 +48,9 @@ func (m *Manager) rememberHostDiskTemperaturePending(host models.Host, disk modefunc (m *Manager) hostDiskTemperatureTrackedResourcesNoLock() map[string]struct{} {resources := make(map[string]struct{})+ for resourceID := range m.hostDiskTempPendingContexts {+ resources[resourceID] = struct{}{}+ }for _, state := range m.mirrorStatesNoLock() {for _, resourceID := range state.PendingResourceIDs() {resources[resourceID] = struct{}{}diff --git a/internal/alerts/host_unraid_lifecycle_test.go b/internal/alerts/host_unraid_lifecycle_test.goindex 2fccbd0662..c2a5d962b3 100644--- a/internal/alerts/host_unraid_lifecycle_test.go+++ b/internal/alerts/host_unraid_lifecycle_test.go@@ -1038,3 +1038,32 @@ func TestDiskTemperatureCurrentCollectionAndOverrideControls(t *testing.T) {}})}++func TestDiskTemperaturePendingContextCleanup(t *testing.T) {+ for _, removal := range []bool{false, true} {+ t.Run(fmt.Sprintf("removed=%v", removal), func(t *testing.T) {+ m, _ := continuityManager(t, false)+ m.mu.Lock()+ m.shadow = nil+ m.mu.Unlock()+ host := hostWithSMARTDiskTemp("pending-cleanup", "custom", 85)+ m.CheckHost(host)+ m.mu.RLock()+ tracked := len(m.hostDiskTempPendingContexts)+ m.mu.RUnlock()+ if tracked != 1 || len(m.GetActiveAlerts()) != 0 {+ t.Fatal("control must have pending context and no active alert")+ }+ if removal {+ m.HandleHostRemoved(host)+ } else {+ m.ClearActiveAlerts()+ }+ m.mu.RLock()+ defer m.mu.RUnlock()+ if len(m.hostDiskTempPendingContexts) != 0 || m.hostDiskTemperaturePendingNoLock(hostDiskTemperatureResourceID(host.ID, host.Sensors.SMART[0].Device)) {+ t.Fatal("pending context/state outlived its host or explicit clear")+ }+ })+ }+}