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
Keep the metrics DB path override on the default org
rcourtmana9f102665685
diff --git a/docs/CONFIGURATION.md b/docs/CONFIGURATION.mdindex aa362722ce..7002eae391 100644--- a/docs/CONFIGURATION.md+++ b/docs/CONFIGURATION.md@@ -55,7 +55,8 @@ Path overrides:- `PULSE_DATA_DIR` sets the base directory for `system.json`, encrypted files, and the bootstrap token.- `PULSE_METRICS_DB_PATH` sets only the metrics SQLite database path. Use thisfor tmpfs-backed metrics history without moving secrets or config off the- persistent data directory.+ persistent data directory. It applies to the default org only; each+ non-default org keeps its own `metrics.db` in `/orgs/<org-id>/`.Multi-tenant layout:- Default org uses the root data directory for backward compatibility.diff --git a/docs/release-control/v6/internal/subsystems/monitoring.md b/docs/release-control/v6/internal/subsystems/monitoring.mdindex 7b5731b673..10c4eace7f 100644--- a/docs/release-control/v6/internal/subsystems/monitoring.md+++ b/docs/release-control/v6/internal/subsystems/monitoring.md@@ -624,6 +624,27 @@ These synthetic source controls reproduce a family matching #2382's secondoperator response, not that operator's cause, the original downgrade-resolvedregression, native appliance acceptance or release availability.+### Metrics database override stays on the default organization++`PULSE_METRICS_DB_PATH` names one SQLite file, so it applies only to the+default organization's monitor. `MultiTenantMonitor.GetMonitor` clears+`MetricsDBPath` on each non-default tenant's detached config copy after+setting its `DataPath`, and `monitoring.New` then opens that organization's+store at `<org data dir>/metrics.db`. Before this, the deep copy carried the+override into every tenant and all organizations wrote to and read from one+metrics database, so per-org charts, reports and Pulse Assistant summaries+could return another organization's series. Keeping tenant stores inside the+org directory also means `DeleteOrganization` removes that org's metrics with+the rest of its data. The trade-off is that tmpfs or RAM-disk placement+through the override covers the default org only; non-default org metrics+stay on the data volume. The default org's override path, rollup interval and+retention handling are unchanged. Regression coverage:+`internal/monitoring/multi_tenant_monitor_metrics_path_test.go` sets the+override, provisions two orgs, and proves each opens its own `metrics.db`+and cannot read series written by the default org or by the other org.+`TestMetricsStoreRuntimeOverridesStayOnMonitorBoundary` also requires the+clear to sit between the tenant `DataPath` assignment and `New`.+### Lightweight detached History readsGuest, node, disk and storage History readers allocate one exact-sized snapshot@@ -5186,7 +5207,9 @@ aggregation cadence: `internal/monitoring/monitor.go` may pass the resolveddata path, `PULSE_METRICS_DB_PATH`, and `PULSE_METRICS_ROLLUP_INTERVAL` throughto `pkg/metrics`, but the SQLite path normalization, rollup bounds, and writeamplification policy stay owned by the metrics store rather than by a-monitoring-local helper.+monitoring-local helper. The `PULSE_METRICS_DB_PATH` handoff reaches only the+default org's monitor; non-default tenants always resolve `metrics.db` from+their own data path.Install-wide telemetry counts are also monitoring-owned now. Any telemetry orreporting surface that claims installation totals must aggregate across theprovisioned tenant set through the reloadable multi-tenant monitor boundary,diff --git a/frontend-modern/public/docs/CONFIGURATION.md b/frontend-modern/public/docs/CONFIGURATION.mdindex aa362722ce..7002eae391 100644--- a/frontend-modern/public/docs/CONFIGURATION.md+++ b/frontend-modern/public/docs/CONFIGURATION.md@@ -55,7 +55,8 @@ Path overrides:- `PULSE_DATA_DIR` sets the base directory for `system.json`, encrypted files, and the bootstrap token.- `PULSE_METRICS_DB_PATH` sets only the metrics SQLite database path. Use thisfor tmpfs-backed metrics history without moving secrets or config off the- persistent data directory.+ persistent data directory. It applies to the default org only; each+ non-default org keeps its own `metrics.db` in `/orgs/<org-id>/`.Multi-tenant layout:- Default org uses the root data directory for backward compatibility.diff --git a/internal/monitoring/canonical_guardrails_test.go b/internal/monitoring/canonical_guardrails_test.goindex 87b9b9ae78..6ee5e04d3c 100644--- a/internal/monitoring/canonical_guardrails_test.go+++ b/internal/monitoring/canonical_guardrails_test.go@@ -681,6 +681,19 @@ func TestMetricsStoreRuntimeOverridesStayOnMonitorBoundary(t *testing.T) {t.Fatalf("monitor.go must contain %q", snippet)}}++ // The override names one file, so non-default tenants must not inherit it.+ data, err = os.ReadFile("multi_tenant_monitor.go")+ if err != nil {+ t.Fatalf("failed to read multi_tenant_monitor.go: %v", err)+ }+ tenantSource := string(data)+ dataPathIdx := strings.Index(tenantSource, "tenantConfig.DataPath = tenantPersistence.GetConfigDir()")+ clearIdx := strings.Index(tenantSource, "tenantConfig.MetricsDBPath = \"\"")+ newIdx := strings.Index(tenantSource, "monitor, err = New(tenantConfig)")+ if dataPathIdx < 0 || clearIdx < 0 || newIdx < 0 || !(dataPathIdx < clearIdx && clearIdx < newIdx) {+ t.Fatal("multi_tenant_monitor.go must clear MetricsDBPath for non-default tenants after setting DataPath and before New")+ }}func TestEscalationDeliveryDefersToCanonicalAlertSuppression(t *testing.T) {diff --git a/internal/monitoring/multi_tenant_monitor.go b/internal/monitoring/multi_tenant_monitor.goindex a11950ad1f..430a391ab0 100644--- a/internal/monitoring/multi_tenant_monitor.go+++ b/internal/monitoring/multi_tenant_monitor.go@@ -220,6 +220,14 @@ func (mtm *MultiTenantMonitor) GetMonitor(orgID string) (*Monitor, error) {return nil, fmt.Errorf("failed to get persistence for org %s: %w", orgID, err)}tenantConfig.DataPath = tenantPersistence.GetConfigDir()+ if orgID != "default" {+ // PULSE_METRICS_DB_PATH names one database file. Inherited by every+ // tenant it would put all organizations' series in the same store, so+ // the override applies to the default org only. Other orgs keep+ // metrics.db under their own data directory, where org deletion also+ // removes it.+ tenantConfig.MetricsDBPath = ""+ }// Load tenant-specific nodes from <orgDir>/nodes.encnodesConfig, err := tenantPersistence.LoadNodesConfig()diff --git a/internal/monitoring/multi_tenant_monitor_metrics_path_test.go b/internal/monitoring/multi_tenant_monitor_metrics_path_test.gonew file mode 100644index 0000000000..8a5028e126--- /dev/null+++ b/internal/monitoring/multi_tenant_monitor_metrics_path_test.go@@ -0,0 +1,99 @@+package monitoring++import (+ "os"+ "path/filepath"+ "testing"+ "time"++ "github.com/rcourtman/pulse-go-rewrite/internal/config"+ "github.com/rcourtman/pulse-go-rewrite/internal/models"+ "github.com/rcourtman/pulse-go-rewrite/pkg/metrics"+)++// PULSE_METRICS_DB_PATH names a single database file. Only the default org may+// use it; every other org must keep its own metrics.db under its data+// directory so organizations never read each other's series.+func TestMultiTenantMonitorMetricsDBPathOverrideStaysOnDefaultOrg(t *testing.T) {+ mtp, defaultPersistence := newTestTenantPersistence(t)+ overridePath := filepath.Join(t.TempDir(), "metrics-tmpfs", "metrics.db")+ baseCfg := &config.Config{+ DataPath: defaultPersistence.GetConfigDir(),+ MetricsDBPath: overridePath,+ }+ mtm := NewMultiTenantMonitor(baseCfg, mtp, nil)+ t.Cleanup(mtm.Stop)++ orgIDs := []string{"org-a", "org-b"}+ for _, orgID := range orgIDs {+ if err := mtp.SaveOrganization(&models.Organization{ID: orgID, DisplayName: orgID}); err != nil {+ t.Fatalf("SaveOrganization(%s) error = %v", orgID, err)+ }+ }++ stores := make(map[string]*metrics.Store)+ for _, orgID := range append([]string{"default"}, orgIDs...) {+ monitor, err := mtm.GetMonitor(orgID)+ if err != nil {+ t.Fatalf("GetMonitor(%s) error = %v", orgID, err)+ }+ store := monitor.GetMetricsStore()+ if store == nil {+ t.Fatalf("GetMonitor(%s) has no metrics store", orgID)+ }+ stores[orgID] = store+ }++ if baseCfg.MetricsDBPath != overridePath {+ t.Fatalf("base config MetricsDBPath = %q, want %q", baseCfg.MetricsDBPath, overridePath)+ }+ if _, err := os.Stat(overridePath); err != nil {+ t.Fatalf("default org should open the override path %q: %v", overridePath, err)+ }+ for _, orgID := range orgIDs {+ orgPersistence, err := mtp.GetPersistence(orgID)+ if err != nil {+ t.Fatalf("GetPersistence(%s) error = %v", orgID, err)+ }+ orgDBPath := filepath.Join(orgPersistence.GetConfigDir(), "metrics.db")+ if _, err := os.Stat(orgDBPath); err != nil {+ t.Fatalf("%s should open its own metrics database at %q: %v", orgID, orgDBPath, err)+ }+ }+ if stores["org-a"] == stores["org-b"] || stores["org-a"] == stores["default"] {+ t.Fatal("expected a distinct metrics store per organization")+ }++ now := time.Now().Truncate(time.Second)+ for _, orgID := range []string{"default", "org-a"} {+ stores[orgID].WriteBatchSync([]metrics.WriteMetric{{+ ResourceType: "vm",+ ResourceID: "vm-" + orgID,+ MetricType: "cpu",+ Value: 42,+ Timestamp: now,+ Tier: metrics.TierRaw,+ }})+ }++ for _, tc := range []struct {+ orgID string+ resourceID string+ wantPoints bool+ }{+ {orgID: "default", resourceID: "vm-default", wantPoints: true},+ {orgID: "default", resourceID: "vm-org-a", wantPoints: false},+ {orgID: "org-a", resourceID: "vm-org-a", wantPoints: true},+ {orgID: "org-a", resourceID: "vm-default", wantPoints: false},+ {orgID: "org-b", resourceID: "vm-org-a", wantPoints: false},+ {orgID: "org-b", resourceID: "vm-default", wantPoints: false},+ } {+ points, err := stores[tc.orgID].Query("vm", tc.resourceID, "cpu", now.Add(-time.Minute), now.Add(time.Minute), 0)+ if err != nil {+ t.Fatalf("%s Query(%s) error = %v", tc.orgID, tc.resourceID, err)+ }+ if got := len(points) > 0; got != tc.wantPoints {+ t.Fatalf("%s store points for %s = %d, want present=%v", tc.orgID, tc.resourceID, len(points), tc.wantPoints)+ }+ }+}