Separate network faults from software drops and fix CPU temperature history

README.md

@@ -32,7 +32,7 @@ ssh root@192.168.0.10
 
 ```bash
 apt-get update
-apt-get install -y curl ca-certificates tar smartmontools iproute2 iputils-ping
+apt-get install -y curl ca-certificates tar smartmontools iproute2 iputils-ping ethtool
 
 cd /tmp
 curl -fL \
@@ -358,6 +358,17 @@ CPU и RAM с накопленным I/O, swap, PSI pressure, все посто
 Связи по PID и порту считаются подтверждёнными; совпадения только по названию
 помечаются как предположение.
 
+Для сложных reverse proxy и Docker-сетей в управлении сервисами можно сохранить
+ручную связь `сервис → агент/VMID → systemd/Docker/процесс → порт`. Она имеет
+приоритет над автоматическим определением и используется для группировки
+связанных уведомлений по первопричине.
+
+Dashboard хранит семь дней истории CPU, RAM, swap, PSI и файловых систем каждого
+агента. Из подробностей агента доступны только заранее разрешённые действия:
+перезапуск известной systemd-службы или Docker-контейнера, `reset-failed` и
+обновление списка пакетов. Агент не принимает произвольные shell-команды; каждое
+действие требует подтверждения в браузере и сохраняется в журнале управления.
+
 Откройте `Настройки → Агенты`, укажите адрес Dashboard, доступный из VM/LXC, и
 VMID. Кнопка создаст готовую команду установки. Одноразовый токен действует 15
 минут и после регистрации заменяется индивидуальным секретом агента.
@@ -390,3 +401,36 @@ curl -fsSL https://git.myown.center/maxim/ProxmoxDash/raw/branch/main/scripts/un
 go test ./...
 GOOS=linux GOARCH=amd64 CGO_ENABLED=0 go build -o proxmox-cpu-dashboard .
 ```
+
+## Сетевые ошибки и температура CPU (v0.19.3)
+
+RX/TX drops отображаются отдельно как информационные счётчики. Их рост сам по
+себе не вызывает аварийный алерт: в том числе LLDP на Linux bridge. Настройки
+Keenetic, LLDP и group_fwd_mask менять не требуется. Для VM учитываются tap,
+для LXC — veth; fwbr/fwpr/fwln остаются в группе интерфейсов хоста.
+
+Новые rx_errors/tx_errors, CRC/frame/FIFO/missed, carrier/link-down вызывают
+критический алерт. Sysfs позволяет отделить rx_missed_errors от RX drops,
+которые в /proc/net/dev объединены. Для Atlantic дополнительно читаются
+InErrors, InDroppedDma, AllocFails, SkbAllocFails и Restarts через ethtool -S.
+Установите `ethtool` на существующем хосте для этой дополнительной диагностики.
+При отсутствии утилиты остаются стандартные счётчики sysfs. Счётчики ошибок
+могут пересекаться: их сумма — прирост счётчиков, а не число уникальных пакетов.
+После перезапуска и сброса счётчиков старые значения не создают новые алерты.
+
+Карточка CPU и новые точки истории показывают максимум доступных датчиков CPU,
+а не среднее Tctl/Tdie/CCD или ядер. На AMD Tctl может включать управляющее
+смещение; подписи и значения всех датчиков доступны в подробностях CPU.
+История снимается раз в минуту, а на диапазоне 7 дней усредняется по 10 минутам,
+поэтому короткие пики между измерениями не гарантированно попадут на график.
+Старые точки до обновления остаются средними: исходные значения датчиков в них
+не сохранены. Масштаб графика расширяется для значений выше 100 °C.
+
+Релиз Linux amd64 собирается с номером версии и без CGO:
+
+```bash
+./scripts/build-release.sh v0.19.3
+```
+
+Скрипт запускает тесты и создаёт в dist бинарник, SHA-256 и установочный архив,
+совместимые со встроенным обновлением из Gitea Releases.

agent.go

@@ -13,6 +13,7 @@ import (
 	"io"
 	"net"
 	"net/http"
+	"net/url"
 	"os"
 	"os/exec"
 	"path/filepath"
@@ -40,16 +41,22 @@ type agentConfig struct {
 }
 
 type AgentContainer struct {
-	ID          string   `json:"id"`
+	ID               string   `json:"id"`
-	Name        string   `json:"name"`
+	Name             string   `json:"name"`
-	Image       string   `json:"image"`
+	Image            string   `json:"image"`
-	State       string   `json:"state"`
+	State            string   `json:"state"`
-	Status      string   `json:"status"`
+	Status           string   `json:"status"`
-	Health      string   `json:"health,omitempty"`
+	Health           string   `json:"health,omitempty"`
-	Restarts    int64    `json:"restarts"`
+	Restarts         int64    `json:"restarts"`
-	CPUPercent  float64  `json:"cpuPercent"`
+	CPUPercent       float64  `json:"cpuPercent"`
-	MemoryUsage uint64   `json:"memoryUsage"`
+	MemoryUsage      uint64   `json:"memoryUsage"`
-	Ports       []string `json:"ports,omitempty"`
+	Ports            []string `json:"ports,omitempty"`
+	Compose          bool     `json:"compose"`
+	UpdateAvailable  bool     `json:"updateAvailable"`
+	CurrentVersion   string   `json:"currentVersion,omitempty"`
+	CurrentDigest    string   `json:"currentDigest,omitempty"`
+	AvailableVersion string   `json:"availableVersion,omitempty"`
+	AvailableDigest  string   `json:"availableDigest,omitempty"`
 }
 
 type AgentInterface struct {
@@ -86,37 +93,39 @@ type AgentIssue struct {
 }
 
 type AgentReport struct {
-	Hostname         string            `json:"hostname"`
+	Hostname         string              `json:"hostname"`
-	MachineID        string            `json:"machineId"`
+	MachineID        string              `json:"machineId"`
-	Version          string            `json:"version"`
+	Version          string              `json:"version"`
-	OS               string            `json:"os"`
+	OS               string              `json:"os"`
-	Arch             string            `json:"arch"`
+	Arch             string              `json:"arch"`
-	OSName           string            `json:"osName"`
+	OSName           string              `json:"osName"`
-	Kernel           string            `json:"kernel"`
+	Kernel           string              `json:"kernel"`
-	UptimeSeconds    int64             `json:"uptimeSeconds"`
+	UptimeSeconds    int64               `json:"uptimeSeconds"`
-	Load1            float64           `json:"load1"`
+	Load1            float64             `json:"load1"`
-	CPUPercent       float64           `json:"cpuPercent"`
+	CPUPercent       float64             `json:"cpuPercent"`
-	MemoryTotal      uint64            `json:"memoryTotal"`
+	CPUCount         int                 `json:"cpuCount"`
-	MemoryUsed       uint64            `json:"memoryUsed"`
+	MemoryTotal      uint64              `json:"memoryTotal"`
-	SwapTotal        uint64            `json:"swapTotal"`
+	MemoryUsed       uint64              `json:"memoryUsed"`
-	SwapUsed         uint64            `json:"swapUsed"`
+	SwapTotal        uint64              `json:"swapTotal"`
-	RootTotal        uint64            `json:"rootTotal"`
+	SwapUsed         uint64              `json:"swapUsed"`
-	RootUsed         uint64            `json:"rootUsed"`
+	RootTotal        uint64              `json:"rootTotal"`
-	DockerAvailable  bool              `json:"dockerAvailable"`
+	RootUsed         uint64              `json:"rootUsed"`
-	DockerError      string            `json:"dockerError,omitempty"`
+	DockerAvailable  bool                `json:"dockerAvailable"`
-	Containers       []AgentContainer  `json:"containers"`
+	DockerError      string              `json:"dockerError,omitempty"`
-	Interfaces       []AgentInterface  `json:"interfaces"`
+	Containers       []AgentContainer    `json:"containers"`
-	Services         []AgentService    `json:"services"`
+	Interfaces       []AgentInterface    `json:"interfaces"`
-	Issues           []AgentIssue      `json:"issues"`
+	Services         []AgentService      `json:"services"`
-	Processes        []AgentProcess    `json:"processes"`
+	Issues           []AgentIssue        `json:"issues"`
-	Filesystems      []AgentFilesystem `json:"filesystems"`
+	Processes        []AgentProcess      `json:"processes"`
-	ListenPorts      []AgentListenPort `json:"listenPorts"`
+	Filesystems      []AgentFilesystem   `json:"filesystems"`
-	Pressure         AgentPressure     `json:"pressure"`
+	ListenPorts      []AgentListenPort   `json:"listenPorts"`
-	OOMKills         []AgentLog        `json:"oomKills"`
+	Pressure         AgentPressure       `json:"pressure"`
-	UpdatesAvailable int               `json:"updatesAvailable"`
+	OOMKills         []AgentLog          `json:"oomKills"`
-	RebootRequired   bool              `json:"rebootRequired"`
+	UpdatesAvailable int                 `json:"updatesAvailable"`
-	InventoryAt      int64             `json:"inventoryAt"`
+	RebootRequired   bool                `json:"rebootRequired"`
-	CollectedAt      int64             `json:"collectedAt"`
+	InventoryAt      int64               `json:"inventoryAt"`
+	CollectedAt      int64               `json:"collectedAt"`
+	ActionResults    []AgentActionResult `json:"actionResults,omitempty"`
 }
 
 type agentInventory struct {
@@ -137,6 +146,7 @@ type AgentUpdateManifest struct {
 type agentReportResponse struct {
 	Accepted bool                 `json:"accepted"`
 	Update   *AgentUpdateManifest `json:"update,omitempty"`
+	Commands []AgentCommand       `json:"commands,omitempty"`
 }
 
 var guestInventory struct {
@@ -150,6 +160,11 @@ var guestIssues struct {
 	collectedAt time.Time
 }
 
+var guestActionResults struct {
+	sync.Mutex
+	value []AgentActionResult
+}
+
 var agentBinaryInfo struct {
 	sync.Once
 	manifest AgentUpdateManifest
@@ -258,6 +273,8 @@ func (s *Store) SaveAgentReport(id, secret, remote string, report AgentReport) e
 	if !s.AuthenticateAgent(id, secret) {
 		return errors.New("агент не авторизован")
 	}
+	s.CompleteAgentActions(id, report.ActionResults)
+	report.ActionResults = nil
 	data, _ := json.Marshal(report)
 	_, err := s.db.Exec(`UPDATE agents SET hostname=?,version=?,last_seen=?,report_json=?,remote_address=? WHERE id=?`, report.Hostname, report.Version, time.Now().Unix(), string(data), remote, id)
 	return err
@@ -325,6 +342,9 @@ func runGuestAgent(opts agentOptions) error {
 	client := &http.Client{Timeout: 12 * time.Second}
 	for {
 		report := collectAgentReport()
+		guestActionResults.Lock()
+		report.ActionResults = append([]AgentActionResult(nil), guestActionResults.value...)
+		guestActionResults.Unlock()
 		data, _ := json.Marshal(report)
 		req, _ := http.NewRequest(http.MethodPost, config.Server+"/api/agent/report", bytes.NewReader(data))
 		req.Header.Set("Content-Type", "application/json")
@@ -351,7 +371,23 @@ func runGuestAgent(opts agentOptions) error {
 			}
 			if response.StatusCode == http.StatusOK {
 				var result agentReportResponse
-				if json.Unmarshal(responseData, &result) == nil && result.Update != nil && newerAgentVersion(result.Update.Version, version) {
+				if json.Unmarshal(responseData, &result) == nil {
+					if len(report.ActionResults) > 0 {
+						guestActionResults.Lock()
+						guestActionResults.value = nil
+						guestActionResults.Unlock()
+					}
+					if len(result.Commands) > 0 {
+						executed := make([]AgentActionResult, 0, len(result.Commands))
+						for _, command := range result.Commands {
+							executed = append(executed, executeAgentCommand(command))
+						}
+						guestActionResults.Lock()
+						guestActionResults.value = append(guestActionResults.value, executed...)
+						guestActionResults.Unlock()
+					}
+				}
+				if result.Update != nil && newerAgentVersion(result.Update.Version, version) {
 					if updateErr := applyAgentUpdate(client, config, *result.Update); updateErr != nil {
 						requestErr = fmt.Errorf("автообновление: %v", updateErr)
 					} else {
@@ -363,7 +399,9 @@ func runGuestAgent(opts agentOptions) error {
 		if requestErr != nil {
 			fmt.Fprintf(os.Stderr, "agent: %v\n", requestErr)
 		}
-		time.Sleep(10 * time.Second)
+		// Короткий интервал нужен для интерактивных команд из панели. Тяжёлый
+		// системный инвентарь отдельно кэшируется и не запускается каждые 3 секунды.
+		time.Sleep(3 * time.Second)
 	}
 }
 
@@ -499,7 +537,7 @@ func saveAgentConfig(path string, c agentConfig) error {
 func collectAgentReport() AgentReport {
 	hostname, _ := os.Hostname()
 	machineID, _ := os.ReadFile("/etc/machine-id")
-	report := AgentReport{Hostname: hostname, MachineID: strings.TrimSpace(string(machineID)), Version: version, OS: runtime.GOOS, Arch: runtime.GOARCH, CollectedAt: time.Now().Unix()}
+	report := AgentReport{Hostname: hostname, MachineID: strings.TrimSpace(string(machineID)), Version: version, OS: runtime.GOOS, Arch: runtime.GOARCH, CPUCount: runtime.NumCPU(), CollectedAt: time.Now().Unix()}
 	if data, err := os.ReadFile("/proc/uptime"); err == nil {
 		fields := strings.Fields(string(data))
 		if len(fields) > 0 {
@@ -885,14 +923,23 @@ func collectDockerContainers() ([]AgentContainer, string) {
 		inspect, inspectErr := client.Get("http://docker/containers/" + v.ID + "/json")
 		if inspectErr == nil {
 			var detail struct {
+				Image        string
 				RestartCount int64
 				State        struct{ Health *struct{ Status string } }
+				Config       struct {
+					Labels map[string]string
+				}
 			}
 			if json.NewDecoder(inspect.Body).Decode(&detail) == nil {
 				item.Restarts = detail.RestartCount
 				if detail.State.Health != nil {
 					item.Health = detail.State.Health.Status
 				}
+				item.Compose = detail.Config.Labels["com.docker.compose.service"] != ""
+				item.CurrentVersion, item.CurrentDigest, _ = inspectDockerImage(client, detail.Image, v.Image)
+				var availableID string
+				item.AvailableVersion, item.AvailableDigest, availableID = inspectDockerImage(client, v.Image, v.Image)
+				item.UpdateAvailable = detail.Image != "" && availableID != "" && detail.Image != availableID
 			}
 			inspect.Body.Close()
 		}
@@ -943,6 +990,46 @@ func collectDockerContainers() ([]AgentContainer, string) {
 	}
 	return result, ""
 }
+
+func inspectDockerImage(client *http.Client, reference, fallback string) (string, string, string) {
+	if reference == "" {
+		return "", "", ""
+	}
+	response, err := client.Get("http://docker/images/" + url.PathEscape(reference) + "/json")
+	if err != nil {
+		return "", "", ""
+	}
+	defer response.Body.Close()
+	var detail struct {
+		ID          string
+		RepoTags    []string
+		RepoDigests []string
+		Config      struct{ Labels map[string]string }
+	}
+	if response.StatusCode != http.StatusOK || json.NewDecoder(response.Body).Decode(&detail) != nil {
+		return "", "", ""
+	}
+	version := firstNonEmpty(detail.Config.Labels["org.opencontainers.image.version"], detail.Config.Labels["version"], firstString(detail.RepoTags), fallback, shortDockerDigest(detail.ID))
+	digest := ""
+	if len(detail.RepoDigests) > 0 {
+		digest = detail.RepoDigests[0]
+		if _, value, found := strings.Cut(digest, "@"); found {
+			digest = value
+		}
+	}
+	if digest == "" {
+		digest = detail.ID
+	}
+	return version, shortDockerDigest(digest), detail.ID
+}
+
+func shortDockerDigest(value string) string {
+	value = strings.TrimPrefix(value, "sha256:")
+	if len(value) > 12 {
+		value = value[:12]
+	}
+	return value
+}
 func firstString(v []string) string {
 	if len(v) > 0 {
 		return v[0]

agent_actions.go

@@ -0,0 +1,346 @@
+package main
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"os/exec"
+	"path/filepath"
+	"regexp"
+	"strings"
+	"time"
+)
+
+type AgentCommand struct {
+	ID     int64  `json:"id"`
+	Action string `json:"action"`
+	Target string `json:"target,omitempty"`
+}
+
+type AgentActionResult struct {
+	ID      int64  `json:"id"`
+	Success bool   `json:"success"`
+	Message string `json:"message"`
+}
+
+type AgentAction struct {
+	ID          int64  `json:"id"`
+	AgentID     string `json:"agentId"`
+	AgentName   string `json:"agentName"`
+	Action      string `json:"action"`
+	Target      string `json:"target"`
+	RequestedAt int64  `json:"requestedAt"`
+	StartedAt   *int64 `json:"startedAt,omitempty"`
+	CompletedAt *int64 `json:"completedAt,omitempty"`
+	Status      string `json:"status"`
+	Result      string `json:"result"`
+}
+
+var safeUnitName = regexp.MustCompile(`^[A-Za-z0-9_.@:-]+\.service$`)
+var safeContainerName = regexp.MustCompile(`^[A-Za-z0-9_.-]{1,128}$`)
+
+func (s *Store) QueueAgentAction(agentID, action, target string) (AgentAction, error) {
+	action, target = strings.TrimSpace(action), strings.TrimSpace(target)
+	var raw, name string
+	if err := s.db.QueryRow(`SELECT report_json,name FROM agents WHERE id=?`, agentID).Scan(&raw, &name); err != nil {
+		return AgentAction{}, fmt.Errorf("агент не найден")
+	}
+	var report AgentReport
+	_ = json.Unmarshal([]byte(raw), &report)
+	valid := false
+	switch action {
+	case "systemd-restart", "systemd-reset-failed":
+		if safeUnitName.MatchString(target) {
+			for _, service := range report.Services {
+				if service.Name == target {
+					valid = true
+					break
+				}
+			}
+		}
+	case "docker-restart", "docker-check", "docker-update", "docker-remove":
+		if safeContainerName.MatchString(target) {
+			for _, container := range report.Containers {
+				if (container.ID == target || container.Name == target) && (action != "docker-remove" || container.State != "running") {
+					valid = true
+					break
+				}
+			}
+		}
+	case "updates-refresh", "system-update", "system-reboot":
+		valid = target == ""
+	}
+	if !valid {
+		return AgentAction{}, fmt.Errorf("действие или цель не входят в разрешённый список")
+	}
+	now := time.Now().Unix()
+	result, err := s.db.Exec(`INSERT INTO agent_actions(agent_id,action,target,requested_at,status) VALUES(?,?,?,?, 'queued')`, agentID, action, target, now)
+	if err != nil {
+		return AgentAction{}, err
+	}
+	id, _ := result.LastInsertId()
+	return AgentAction{ID: id, AgentID: agentID, AgentName: name, Action: action, Target: target, RequestedAt: now, Status: "queued"}, nil
+}
+
+func (s *Store) DispatchAgentActions(agentID string) ([]AgentCommand, error) {
+	tx, err := s.db.Begin()
+	if err != nil {
+		return nil, err
+	}
+	defer tx.Rollback()
+	// Обновление пакетов и Docker-образов может быть долгим. Не выдаём одну
+	// команду повторно, пока предыдущий запуск ещё имеет шанс завершиться.
+	_, _ = tx.Exec(`UPDATE agent_actions SET status='queued',started_at=NULL WHERE agent_id=? AND status='running' AND started_at<?`, agentID, time.Now().Add(-45*time.Minute).Unix())
+	rows, err := tx.Query(`SELECT id,action,target FROM agent_actions WHERE agent_id=? AND status='queued' ORDER BY id LIMIT 3`, agentID)
+	if err != nil {
+		return nil, err
+	}
+	var commands []AgentCommand
+	for rows.Next() {
+		var c AgentCommand
+		if err = rows.Scan(&c.ID, &c.Action, &c.Target); err != nil {
+			rows.Close()
+			return nil, err
+		}
+		commands = append(commands, c)
+	}
+	rows.Close()
+	now := time.Now().Unix()
+	for _, c := range commands {
+		if _, err = tx.Exec(`UPDATE agent_actions SET status='running',started_at=? WHERE id=?`, now, c.ID); err != nil {
+			return nil, err
+		}
+	}
+	return commands, tx.Commit()
+}
+
+func (s *Store) CompleteAgentActions(agentID string, results []AgentActionResult) {
+	now := time.Now().Unix()
+	for _, result := range results {
+		status := "failed"
+		if result.Success {
+			status = "completed"
+		}
+		message := result.Message
+		if len(message) > 4000 {
+			message = message[:4000]
+		}
+		_, _ = s.db.Exec(`UPDATE agent_actions SET status=?,result=?,completed_at=? WHERE id=? AND agent_id=? AND status='running'`, status, message, now, result.ID, agentID)
+	}
+}
+
+func (s *Store) AgentActions(limit int) ([]AgentAction, error) {
+	if limit < 1 || limit > 200 {
+		limit = 100
+	}
+	rows, err := s.db.Query(`SELECT a.id,a.agent_id,g.name,a.action,a.target,a.requested_at,a.started_at,a.completed_at,a.status,a.result FROM agent_actions a JOIN agents g ON g.id=a.agent_id ORDER BY a.id DESC LIMIT ?`, limit)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var out []AgentAction
+	for rows.Next() {
+		var v AgentAction
+		if err = rows.Scan(&v.ID, &v.AgentID, &v.AgentName, &v.Action, &v.Target, &v.RequestedAt, &v.StartedAt, &v.CompletedAt, &v.Status, &v.Result); err != nil {
+			return nil, err
+		}
+		out = append(out, v)
+	}
+	return out, rows.Err()
+}
+
+func executeAgentCommand(command AgentCommand) AgentActionResult {
+	result := AgentActionResult{ID: command.ID}
+	var output string
+	switch command.Action {
+	case "systemd-restart":
+		output = runAgentCombinedCommand(30*time.Second, "systemctl", "restart", command.Target)
+	case "systemd-reset-failed":
+		output = runAgentCombinedCommand(15*time.Second, "systemctl", "reset-failed", command.Target)
+	case "docker-restart":
+		output = restartAgentContainer(command.Target)
+	case "docker-update":
+		output = updateAgentContainer(command.Target, true)
+	case "docker-check":
+		output = updateAgentContainer(command.Target, false)
+	case "docker-remove":
+		output = removeAgentContainer(command.Target)
+	case "system-update":
+		output = updateAgentSystem()
+	case "system-reboot":
+		output = scheduleAgentReboot()
+	case "updates-refresh":
+		guestInventory.Lock()
+		guestInventory.value.CollectedAt = time.Time{}
+		guestInventory.Unlock()
+		result.Success = true
+		result.Message = "Проверка обновлений поставлена в очередь"
+		return result
+	default:
+		result.Message = "Команда не разрешена"
+		return result
+	}
+	result.Success = !strings.HasPrefix(output, "ERROR: ")
+	result.Message = strings.TrimSpace(output)
+	if result.Message == "" && result.Success {
+		result.Message = "Выполнено успешно"
+	}
+	return result
+}
+
+func removeAgentContainer(target string) string {
+	transport := &http.Transport{DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
+		return (&net.Dialer{}).DialContext(ctx, "unix", "/var/run/docker.sock")
+	}}
+	defer transport.CloseIdleConnections()
+	request, _ := http.NewRequest(http.MethodDelete, "http://docker/containers/"+target+"?v=false&force=false", nil)
+	response, err := (&http.Client{Transport: transport, Timeout: 20 * time.Second}).Do(request)
+	if err != nil {
+		return "ERROR: " + err.Error()
+	}
+	defer response.Body.Close()
+	if response.StatusCode != http.StatusNoContent {
+		message, _ := io.ReadAll(io.LimitReader(response.Body, 2048))
+		return fmt.Sprintf("ERROR: Docker вернул %s: %s", response.Status, strings.TrimSpace(string(message)))
+	}
+	return "Остановленный контейнер удалён; volumes сохранены"
+}
+
+func updateAgentSystem() string {
+	aptGet, err := exec.LookPath("apt-get")
+	if err != nil {
+		return "ERROR: apt-get не найден; обновление поддерживается для Debian/Ubuntu"
+	}
+	if output := runPrivilegedTransient(5*time.Minute, "update-lists", aptGet, "update"); strings.HasPrefix(output, "ERROR: ") {
+		return explainSystemUpdateError(output)
+	}
+	message := runPrivilegedTransient(30*time.Minute, "upgrade", aptGet, "-y", "upgrade")
+	if strings.HasPrefix(message, "ERROR: ") {
+		return explainSystemUpdateError(message)
+	}
+	guestInventory.Lock()
+	guestInventory.value.CollectedAt = time.Time{}
+	guestInventory.Unlock()
+	return "Обновления системы установлены; список пакетов будет обновлён в следующем отчёте агента"
+}
+
+func explainSystemUpdateError(message string) string {
+	if strings.Contains(strings.ToLower(message), "read-only file system") {
+		return "ERROR: файловая система агента доступна только для чтения. Обновите Dashboard и агент до v0.19.2 или новее, затем повторите операцию."
+	}
+	if len(message) > 1800 {
+		message = message[len(message)-1800:]
+	}
+	return message
+}
+
+func runPrivilegedTransient(timeout time.Duration, suffix, name string, args ...string) string {
+	systemdRun, err := exec.LookPath("systemd-run")
+	if err != nil {
+		return "ERROR: systemd-run не найден; невозможно безопасно выйти из read-only sandbox агента"
+	}
+	unit := fmt.Sprintf("proxmox-dashboard-%s-%d", suffix, time.Now().UnixNano())
+	commandArgs := []string{"--quiet", "--wait", "--collect", "--pipe", "--unit=" + unit, "--setenv=DEBIAN_FRONTEND=noninteractive", name}
+	commandArgs = append(commandArgs, args...)
+	return runAgentCombinedCommand(timeout, systemdRun, commandArgs...)
+}
+
+func scheduleAgentReboot() string {
+	systemdRun, err := exec.LookPath("systemd-run")
+	if err != nil {
+		return "ERROR: systemd-run не найден"
+	}
+	systemctl, err := exec.LookPath("systemctl")
+	if err != nil {
+		return "ERROR: systemctl не найден"
+	}
+	unit := fmt.Sprintf("proxmox-dashboard-reboot-%d", time.Now().UnixNano())
+	output := runAgentCombinedCommand(15*time.Second, systemdRun, "--quiet", "--collect", "--unit="+unit, "--on-active=20s", systemctl, "reboot")
+	if strings.HasPrefix(output, "ERROR: ") {
+		return output
+	}
+	return "Перезагрузка запланирована через 20 секунд; кратковременный offline агента ожидаем"
+}
+
+func updateAgentContainer(target string, recreate bool) string {
+	transport := &http.Transport{DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
+		return (&net.Dialer{}).DialContext(ctx, "unix", "/var/run/docker.sock")
+	}}
+	defer transport.CloseIdleConnections()
+	client := &http.Client{Transport: transport, Timeout: 10 * time.Second}
+	response, err := client.Get("http://docker/containers/" + target + "/json")
+	if err != nil {
+		return "ERROR: " + err.Error()
+	}
+	defer response.Body.Close()
+	var detail struct {
+		Config struct {
+			Labels map[string]string `json:"Labels"`
+		} `json:"Config"`
+	}
+	if response.StatusCode != http.StatusOK || json.NewDecoder(response.Body).Decode(&detail) != nil {
+		return "ERROR: не удалось получить Compose-конфигурацию контейнера"
+	}
+	labels := detail.Config.Labels
+	service := labels["com.docker.compose.service"]
+	workdir := labels["com.docker.compose.project.working_dir"]
+	files := strings.Split(labels["com.docker.compose.project.config_files"], ",")
+	if service == "" || workdir == "" || len(files) == 0 || !filepath.IsAbs(workdir) || !filepath.IsAbs(files[0]) {
+		return "ERROR: безопасное обновление доступно только для Docker Compose"
+	}
+	if _, err = exec.LookPath("docker"); err != nil {
+		return "ERROR: Docker CLI не найден"
+	}
+	commands := [][]string{{"compose", "-f", files[0], "pull", service}}
+	if recreate {
+		commands = append(commands, []string{"compose", "-f", files[0], "up", "-d", "--no-deps", service})
+	}
+	for _, args := range commands {
+		ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute)
+		command := exec.CommandContext(ctx, "docker", args...)
+		command.Dir = workdir
+		output, commandErr := command.CombinedOutput()
+		cancel()
+		if commandErr != nil {
+			return "ERROR: " + commandErr.Error() + ": " + strings.TrimSpace(string(output))
+		}
+	}
+	if recreate {
+		return "Образ загружен, Compose-контейнер пересоздан"
+	}
+	return "Проверка завершена: образ загружен; если digest изменился, карточка покажет доступное обновление"
+}
+
+func runAgentCombinedCommand(timeout time.Duration, name string, args ...string) string {
+	ctx, cancel := context.WithTimeout(context.Background(), timeout)
+	defer cancel()
+	output, err := exec.CommandContext(ctx, name, args...).CombinedOutput()
+	message := strings.TrimSpace(string(output))
+	if err != nil {
+		return "ERROR: " + err.Error() + ": " + message
+	}
+	return message
+}
+
+func restartAgentContainer(target string) string {
+	transport := &http.Transport{DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
+		return (&net.Dialer{}).DialContext(ctx, "unix", "/var/run/docker.sock")
+	}}
+	defer transport.CloseIdleConnections()
+	client := &http.Client{Transport: transport, Timeout: 35 * time.Second}
+	request, _ := http.NewRequest(http.MethodPost, "http://docker/containers/"+target+"/restart?t=10", bytes.NewReader(nil))
+	response, err := client.Do(request)
+	if err != nil {
+		return "ERROR: " + err.Error()
+	}
+	defer response.Body.Close()
+	body, _ := io.ReadAll(io.LimitReader(response.Body, 4096))
+	if response.StatusCode >= 300 {
+		return "ERROR: Docker вернул " + response.Status + ": " + strings.TrimSpace(string(body))
+	}
+	return "Контейнер перезапущен"
+}

agent_actions_test.go

@@ -0,0 +1,77 @@
+package main
+
+import (
+	"encoding/json"
+	"strings"
+	"testing"
+	"time"
+)
+
+func TestAgentActionAllowlistAndLifecycle(t *testing.T) {
+	store, err := openStore(":memory:")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer store.Close()
+	report, _ := json.Marshal(AgentReport{Services: []AgentService{{Name: "gitea.service"}}, Containers: []AgentContainer{{ID: "abc123", Name: "gitea", State: "running"}, {ID: "old123", Name: "old", State: "exited"}}})
+	_, err = store.db.Exec(`INSERT INTO agents(id,name,secret_hash,enrolled_at,last_seen,report_json) VALUES('a','agent','x',?,?,?)`, time.Now().Unix(), time.Now().Unix(), string(report))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if _, err = store.QueueAgentAction("a", "systemd-restart", "../../bad.service"); err == nil {
+		t.Fatal("unsafe unit accepted")
+	}
+	if _, err = store.QueueAgentAction("a", "docker-update", "gitea"); err != nil {
+		t.Fatalf("known Docker container rejected: %v", err)
+	}
+	if _, err = store.QueueAgentAction("a", "system-update", ""); err != nil {
+		t.Fatalf("system update rejected: %v", err)
+	}
+	if _, err = store.QueueAgentAction("a", "docker-remove", "gitea"); err == nil {
+		t.Fatal("running/unknown-state container accepted for removal")
+	}
+	action, err := store.QueueAgentAction("a", "docker-remove", "old")
+	if err != nil {
+		t.Fatalf("stopped container rejected for removal: %v", err)
+	}
+	commands, err := store.DispatchAgentActions("a")
+	if err != nil || len(commands) != 3 || commands[2].ID != action.ID {
+		t.Fatalf("commands=%#v err=%v", commands, err)
+	}
+	store.CompleteAgentActions("a", []AgentActionResult{{ID: action.ID, Success: true, Message: "ok"}})
+	items, err := store.AgentActions(10)
+	if err != nil || len(items) != 3 || items[0].Status != "completed" {
+		t.Fatalf("items=%#v err=%v", items, err)
+	}
+	if _, err = store.QueueAgentAction("a", "system-reboot", ""); err != nil {
+		t.Fatalf("system reboot rejected: %v", err)
+	}
+	if _, err = store.QueueAgentAction("a", "system-reboot", "now"); err == nil {
+		t.Fatal("system reboot with unexpected target accepted")
+	}
+}
+
+func TestManualServiceLinkGroupsOfflineAlerts(t *testing.T) {
+	metrics := dashboardMetrics{Agents: []ManagedAgent{{ID: "a", Name: "app", VMID: 105, Online: false}}, ServiceLinks: []ServiceLink{{ServiceID: 7, AgentID: "a", VMID: 105}}, Services: ServicesMetrics{Services: []ServiceStatus{{MonitoredService: MonitoredService{ID: 7, Name: "Gitea"}, Endpoints: []ServiceEndpointStatus{{Kind: "local", Up: false}}}}}}
+	alerts := []Alert{{ID: "agent-offline-a-105"}, {ID: "service-7-local"}, {ID: "other"}}
+	grouped := groupLinkedAlerts(metrics, alerts)
+	if len(grouped) != 2 {
+		t.Fatalf("grouped=%#v", grouped)
+	}
+	found := false
+	for _, alert := range grouped {
+		if alert.ID == "group-agent-offline-a-105" {
+			found = true
+		}
+	}
+	if !found {
+		t.Fatalf("group alert missing: %#v", grouped)
+	}
+}
+
+func TestExplainReadOnlySystemUpdateError(t *testing.T) {
+	message := explainSystemUpdateError("ERROR: apt failed: Read-only file system")
+	if !strings.Contains(message, "v0.19.2") {
+		t.Fatalf("read-only failure is not actionable: %s", message)
+	}
+}

agent_diagnostics.go

@@ -7,6 +7,7 @@ import (
 	"os"
 	"path/filepath"
 	"regexp"
+	"runtime"
 	"sort"
 	"strconv"
 	"strings"
@@ -25,6 +26,8 @@ type AgentProcess struct {
 	Name        string  `json:"name"`
 	State       string  `json:"state"`
 	CPUPercent  float64 `json:"cpuPercent"`
+	CPUCores    float64 `json:"cpuCores"`
+	HostPercent float64 `json:"hostPercent"`
 	MemoryBytes uint64  `json:"memoryBytes"`
 	ReadBytes   uint64  `json:"readBytes"`
 	WriteBytes  uint64  `json:"writeBytes"`
@@ -174,7 +177,11 @@ func collectAgentProcesses() []AgentProcess {
 			cpu, _ := strconv.ParseFloat(fields[3], 64)
 			rss, _ := strconv.ParseUint(fields[4], 10, 64)
 			elapsed, _ := strconv.ParseInt(fields[5], 10, 64)
-			item := AgentProcess{PID: pid, Name: fields[1], State: fields[2], CPUPercent: cpu, MemoryBytes: rss * 1024, Elapsed: elapsed, Command: strings.Join(fields[6:], " ")}
+			cpuCount := runtime.NumCPU()
+			if cpuCount < 1 {
+				cpuCount = 1
+			}
+			item := AgentProcess{PID: pid, Name: fields[1], State: fields[2], CPUPercent: cpu, CPUCores: cpu / 100, HostPercent: cpu / float64(cpuCount), MemoryBytes: rss * 1024, Elapsed: elapsed, Command: strings.Join(fields[6:], " ")}
 			item.ReadBytes, item.WriteBytes = readAgentProcessIO(pid)
 			result = append(result, item)
 			added++

agent_test.go

@@ -53,6 +53,12 @@ func TestAgentOnlyInstallsNewerVersion(t *testing.T) {
 	}
 }
 
+func TestShortDockerDigest(t *testing.T) {
+	if got := shortDockerDigest("sha256:1234567890abcdef"); got != "1234567890ab" {
+		t.Fatalf("unexpected short digest: %q", got)
+	}
+}
+
 func TestParseAgentIssues(t *testing.T) {
 	issues := parseAgentIssues(`{"MESSAGE":"disk error","_SYSTEMD_UNIT":"worker.service","__REALTIME_TIMESTAMP":"1722960000000000"}` + "\n" + `{"MESSAGE":"network error","__REALTIME_TIMESTAMP":"1722960001000000"}`)
 	if len(issues) != 2 || issues[0].Unit != "worker.service" || issues[1].Unit != "system" || issues[0].Time != 1722960000 {

alert_events.go

@@ -124,10 +124,22 @@ func (s *Store) AcknowledgeAlert(eventID int64) error {
 }
 
 func (s *Store) AlertHistory(limit int) ([]AlertEvent, error) {
+	return s.AlertHistoryBetween(limit, 0, 0)
+}
+
+func (s *Store) AlertHistoryBetween(limit int, from, to int64) ([]AlertEvent, error) {
 	if limit < 1 || limit > 500 {
 		limit = 200
 	}
-	rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message,first_seen,last_seen,resolved_at,acknowledged_at,planned,maintenance_reason FROM alert_events ORDER BY first_seen DESC LIMIT ?`, limit)
+	query := `SELECT id,alert_key,severity,source,title,message,first_seen,last_seen,resolved_at,acknowledged_at,planned,maintenance_reason FROM alert_events`
+	args := []any{}
+	if from > 0 && to > from {
+		query += ` WHERE first_seen>=? AND first_seen<?`
+		args = append(args, from, to)
+	}
+	query += ` ORDER BY first_seen DESC LIMIT ?`
+	args = append(args, limit)
+	rows, err := s.db.Query(query, args...)
 	if err != nil {
 		return nil, err
 	}

alerts.go

@@ -74,7 +74,10 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 		if disk.SMARTStatus == "Ошибка" {
 			add("disk-smart-"+disk.Name, "critical", "Диски", disk.Model+": ошибка SMART", joinReasons(disk.AttentionReasons, "SMART сообщает о неисправности диска."))
 		} else if disk.SMARTStatus == "Требует внимания" {
-			add("disk-smart-"+disk.Name, "warning", "Диски", disk.Model+": SMART требует внимания", joinReasons(disk.AttentionReasons, "Проверьте SMART-показатели диска."))
+			reasons := withoutReason(disk.AttentionReasons, "SMART self-test ещё ни разу не запускался")
+			if len(reasons) > 0 {
+				add("disk-smart-"+disk.Name, "warning", "Диски", disk.Model+": SMART требует внимания", joinReasons(reasons, "Проверьте SMART-показатели диска."))
+			}
 		}
 		if disk.Temperature != nil {
 			limit := thresholds.DiskTempWarning
@@ -260,10 +263,13 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 	}
 	var networkErrors uint64
 	for _, iface := range metrics.Network.Interfaces {
-		networkErrors += iface.ReceiveErrors + iface.TransmitErrors + iface.ReceiveDrops + iface.TransmitDrops
+		networkErrors += iface.NewErrors + iface.NewFaults
+		if iface.LinkDown {
+			add("network-link-"+iface.Name, "critical", "Сеть", iface.Name+": нет линка", "Используемый интерфейс потерял carrier или перешёл в down.")
+		}
 	}
 	if networkErrors > 0 {
-		add("network-errors", "warning", "Сеть", "Сетевые ошибки и потери пакетов", fmt.Sprintf("Суммарный счётчик интерфейсов: %d.", networkErrors))
+		add("network-errors", "critical", "Сеть", "Появились новые сетевые ошибки", fmt.Sprintf("Прирост счётчиков ошибок: %d (счётчики могут пересекаться). Software RX/TX drops показаны отдельно и не создают этот алерт.", networkErrors))
 	}
 	if !metrics.Network.Health.CheckedAt.IsZero() && !metrics.Network.Health.GatewayUp {
 		add("network-gateway", "critical", "Сеть", "Недоступен локальный шлюз", firstNonEmpty(metrics.Network.Health.Gateway, "Default gateway не определён."))
@@ -283,14 +289,7 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 	for _, name := range metrics.Network.Health.DisappearedInterfaces {
 		add("network-interface-missing-"+name, "warning", "Сеть", "Исчез сетевой интерфейс", name+" больше не присутствует в /proc/net/dev.")
 	}
-	for _, iface := range metrics.Network.Interfaces {
+
-		if iface.Kind == "Physical" && !iface.Carrier && (iface.Master != "" || iface.ReceiveBytes+iface.TransmitBytes > 0) {
-			add("network-link-"+iface.Name, "warning", "Сеть", iface.Name+": нет carrier", "Физический линк не поднят.")
-		}
-		if (iface.Kind == "Bridge" || iface.Kind == "Bond" || iface.Kind == "VLAN") && iface.State == "down" {
-			add("network-state-"+iface.Name, "warning", "Сеть", iface.Name+": интерфейс выключен", iface.Kind+" находится в состоянии down.")
-		}
-	}
 	if !metrics.Monitor.LastSuccessfulCollection.IsZero() && time.Since(metrics.Monitor.LastSuccessfulCollection) > 30*time.Second {
 		add("monitor-stale", "critical", "Dashboard", "Данные мониторинга устарели", "Последний успешный сбор был "+time.Since(metrics.Monitor.LastSuccessfulCollection).Round(time.Second).String()+" назад.")
 	}
@@ -386,3 +385,13 @@ func joinReasons(reasons []string, fallback string) string {
 	}
 	return strings.Join(reasons, " · ")
 }
+
+func withoutReason(reasons []string, excluded string) []string {
+	filtered := make([]string, 0, len(reasons))
+	for _, reason := range reasons {
+		if reason != excluded {
+			filtered = append(filtered, reason)
+		}
+	}
+	return filtered
+}

alerts_test.go

@@ -25,3 +25,17 @@ func TestSlowCollectionDoesNotCreateAlert(t *testing.T) {
 		}
 	}
 }
+
+func TestNeverRunSelfTestCreatesOneAlert(t *testing.T) {
+	metrics := dashboardMetrics{Disks: []DiskMetrics{{
+		Name:             "nvme0n1",
+		Model:            "Test NVMe",
+		SMARTStatus:      "Требует внимания",
+		SelfTestNeverRun: true,
+		AttentionReasons: []string{"SMART self-test ещё ни разу не запускался"},
+	}}}
+	alerts := evaluateAlerts(metrics, defaultThresholds())
+	if len(alerts) != 1 || alerts[0].ID != "disk-selftest-nvme0n1" {
+		t.Fatalf("ожидалось одно точное уведомление о self-test, получено: %+v", alerts)
+	}
+}

cpu.go

@@ -3,6 +3,7 @@ package main
 import (
 	"bufio"
 	"fmt"
+	"math"
 	"os"
 	"path/filepath"
 	"strconv"
@@ -33,14 +34,16 @@ type CPUStatic struct {
 
 type CPUMetrics struct {
 	CPUStatic
-	UsagePercent float64       `json:"usagePercent"`
+	UsagePercent       float64        `json:"usagePercent"`
-	FrequencyMHz float64       `json:"frequencyMhz"`
+	FrequencyMHz       float64        `json:"frequencyMhz"`
-	Load1        float64       `json:"load1"`
+	Load1              float64        `json:"load1"`
-	Load5        float64       `json:"load5"`
+	Load5              float64        `json:"load5"`
-	Load15       float64       `json:"load15"`
+	Load15             float64        `json:"load15"`
-	Uptime       uint64        `json:"uptimeSeconds"`
+	Uptime             uint64         `json:"uptimeSeconds"`
-	Temperatures []Temperature `json:"temperatures"`
+	TemperatureCelsius *float64       `json:"temperatureCelsius"`
-	CollectedAt  time.Time     `json:"collectedAt"`
+	Temperatures       []Temperature  `json:"temperatures"`
+	TopProcesses       []AgentProcess `json:"topProcesses"`
+	CollectedAt        time.Time      `json:"collectedAt"`
 }
 
 type Temperature struct {
@@ -89,10 +92,11 @@ func (c *cpuCollector) collect() (CPUMetrics, error) {
 	load1, load5, load15, _ := readLoadAverage()
 	uptime, _ := readUptime()
 
+	temperatures := readTemperatures()
 	return CPUMetrics{
 		CPUStatic: c.static, UsagePercent: usage, FrequencyMHz: frequency,
 		Load1: load1, Load5: load5, Load15: load15, Uptime: uptime,
-		Temperatures: readTemperatures(), CollectedAt: time.Now(),
+		Temperatures: temperatures, TemperatureCelsius: cpuTemperature(temperatures), TopProcesses: collectAgentProcesses(), CollectedAt: time.Now(),
 	}, nil
 }
 
@@ -284,3 +288,19 @@ func isCPUTemperatureChip(name string) bool {
 		return false
 	}
 }
+
+// cpuTemperature is the hottest CPU sensor, shared by live and historical views.
+// Do not average Tctl/Tdie with cooler cores or CCDs.
+func cpuTemperature(temperatures []Temperature) *float64 {
+	var hottest *float64
+	for _, t := range temperatures {
+		if math.IsNaN(t.Celsius) || math.IsInf(t.Celsius, 0) || t.Celsius <= 0 {
+			continue
+		}
+		if hottest == nil || t.Celsius > *hottest {
+			value := t.Celsius
+			hottest = &value
+		}
+	}
+	return hottest
+}

cpu_temperature_test.go

@@ -0,0 +1,24 @@
+package main
+
+import (
+	"math"
+	"testing"
+)
+
+func TestCPUTemperatureSharedWithHistory(t *testing.T) {
+	temperatures := []Temperature{{Label: "k10temp · Tctl", Celsius: 62}, {Label: "k10temp · Tccd1", Celsius: 38}, {Label: "k10temp · Tccd2", Celsius: 41}}
+	live := cpuTemperature(temperatures)
+	point := historyPointFromMetrics(dashboardMetrics{CPU: CPUMetrics{Temperatures: temperatures}})
+	if live == nil || *live != 62 || point.CPUTemperature != *live {
+		t.Fatalf("live/history disagree: %v, %+v", live, point)
+	}
+}
+
+func TestCPUTemperatureInvalidSensors(t *testing.T) {
+	if cpuTemperature([]Temperature{{Celsius: math.NaN()}, {Celsius: math.Inf(1)}, {Celsius: 0}}) != nil {
+		t.Fatal("invalid temperature selected")
+	}
+	if cpuTemperature(nil) != nil {
+		t.Fatal("missing sensor should stay missing")
+	}
+}

disks.go

@@ -391,6 +391,17 @@ type smartctlJSON struct {
 			} `json:"table"`
 		} `json:"standard"`
 	} `json:"ata_smart_self_test_log"`
+	NVMeSelfTestLog struct {
+		Table []struct {
+			SelfTestCode struct {
+				String string `json:"string"`
+			} `json:"self_test_code"`
+			SelfTestResult struct {
+				String string `json:"string"`
+			} `json:"self_test_result"`
+			PowerOnHours uint64 `json:"power_on_hours"`
+		} `json:"table"`
+	} `json:"nvme_self_test_log"`
 	NVMeHealth *struct {
 		Temperature     float64 `json:"temperature"`
 		PercentageUsed  float64 `json:"percentage_used"`
@@ -410,6 +421,10 @@ func applySMART(disk *DiskMetrics) {
 	if len(output) == 0 {
 		return
 	}
+	applySMARTJSON(disk, output)
+}
+
+func applySMARTJSON(disk *DiskMetrics, output []byte) {
 	var smart smartctlJSON
 	if json.Unmarshal(output, &smart) != nil {
 		return
@@ -451,12 +466,20 @@ func applySMART(disk *DiskMetrics) {
 			disk.AttentionReasons = append(disk.AttentionReasons, "Ошибки целостности носителя: "+strconv.FormatUint(smart.NVMeHealth.MediaErrors, 10))
 		}
 	}
-	if len(smart.ATASelfTestLog.Standard.Table) > 0 {
+	if len(smart.NVMeSelfTestLog.Table) > 0 {
+		last := smart.NVMeSelfTestLog.Table[0]
+		description := strings.TrimSpace(last.SelfTestCode.String)
+		result := firstNonEmpty(strings.TrimSpace(last.SelfTestResult.String), "Результат неизвестен")
+		if description != "" {
+			disk.LastSelfTest = description + " · " + result
+		} else {
+			disk.LastSelfTest = result
+		}
+		setLastSelfTestAt(disk, last.PowerOnHours)
+	} else if len(smart.ATASelfTestLog.Standard.Table) > 0 {
 		last := smart.ATASelfTestLog.Standard.Table[0]
 		disk.LastSelfTest = firstNonEmpty(last.Status.String, "Результат неизвестен")
-		if disk.PowerOnHours != nil && *disk.PowerOnHours >= last.LifetimeHours {
+		setLastSelfTestAt(disk, last.LifetimeHours)
-			disk.LastSelfTestAt = time.Now().Add(-time.Duration(*disk.PowerOnHours-last.LifetimeHours) * time.Hour).Format(time.RFC3339)
-		}
 	} else {
 		disk.SelfTestNeverRun = true
 		disk.LastSelfTest = "Никогда не запускался"
@@ -469,6 +492,12 @@ func applySMART(disk *DiskMetrics) {
 	}
 }
 
+func setLastSelfTestAt(disk *DiskMetrics, testPowerOnHours uint64) {
+	if disk.PowerOnHours != nil && *disk.PowerOnHours >= testPowerOnHours {
+		disk.LastSelfTestAt = time.Now().Add(-time.Duration(*disk.PowerOnHours-testPowerOnHours) * time.Hour).Format(time.RFC3339)
+	}
+}
+
 func applyATAAttributes(disk *DiskMetrics, smart smartctlJSON) {
 	wearNames := map[string]bool{
 		"Percent_Lifetime_Remain": true, "SSD_Life_Left": true,

disks_test.go

@@ -6,8 +6,44 @@ import (
 	"path/filepath"
 	"strings"
 	"testing"
+	"time"
 )
 
+func TestApplySMARTJSONReadsNVMeSelfTestHistory(t *testing.T) {
+	disk := DiskMetrics{Path: "/dev/nvme0n1"}
+	output := []byte(`{
+		"model_name":"ADATA LEGEND 900",
+		"smart_status":{"passed":true},
+		"power_on_time":{"hours":960},
+		"nvme_self_test_log":{
+			"current_self_test_operation":{"value":0,"string":"No self-test in progress"},
+			"table":[{
+				"self_test_code":{"value":1,"string":"Short"},
+				"self_test_result":{"value":0,"string":"Completed without error"},
+				"power_on_hours":959
+			}]
+		}
+	}`)
+
+	before := time.Now().Add(-2 * time.Hour)
+	applySMARTJSON(&disk, output)
+	after := time.Now()
+
+	if disk.SelfTestNeverRun {
+		t.Fatal("завершённый NVMe self-test ошибочно отмечен как никогда не запускавшийся")
+	}
+	if disk.LastSelfTest != "Short · Completed without error" {
+		t.Fatalf("неожиданный результат self-test: %q", disk.LastSelfTest)
+	}
+	parsed, err := time.Parse(time.RFC3339, disk.LastSelfTestAt)
+	if err != nil || parsed.Before(before) || parsed.After(after) {
+		t.Fatalf("неверно вычислено время self-test: %q, err=%v", disk.LastSelfTestAt, err)
+	}
+	if len(disk.AttentionReasons) != 0 || disk.SMARTStatus != "Исправен" {
+		t.Fatalf("исправный NVMe требует внимания: %+v", disk)
+	}
+}
+
 func TestIsPhysicalDiskName(t *testing.T) {
 	tests := map[string]bool{
 		"sda": true, "sdb": true, "nvme0n1": true,

history.go

@@ -64,6 +64,30 @@ func (s *Store) AddEntityMetrics(metrics dashboardMetrics) {
 			s.AddEntityHistory("backup-duration", "VMID "+task.ID, ts, &duration, nil)
 		}
 	}
+	for _, agent := range metrics.Agents {
+		if !agent.Online {
+			continue
+		}
+		name := agent.ID + " · " + agent.Name
+		cpu := agent.Report.CPUPercent
+		memory := float64(0)
+		if agent.Report.MemoryTotal > 0 {
+			memory = float64(agent.Report.MemoryUsed) / float64(agent.Report.MemoryTotal) * 100
+		}
+		swap := float64(0)
+		if agent.Report.SwapTotal > 0 {
+			swap = float64(agent.Report.SwapUsed) / float64(agent.Report.SwapTotal) * 100
+		}
+		s.AddEntityHistory("agent-resource", name, ts, &cpu, &memory)
+		s.AddEntityHistory("agent-swap", name, ts, &swap, nil)
+		pressure := agent.Report.Pressure.IO.Avg10
+		s.AddEntityHistory("agent-pressure", name, ts, &pressure, nil)
+		for _, filesystem := range agent.Report.Filesystems {
+			used := filesystem.UsedPercent
+			inodes := filesystem.InodesPercent
+			s.AddEntityHistory("agent-filesystem", name+" · "+filesystem.Mountpoint, ts, &used, &inodes)
+		}
+	}
 	s.PruneEntityHistory()
 }
 
@@ -75,12 +99,10 @@ func historyPointFromMetrics(metrics dashboardMetrics) HistoryPoint {
 		NetworkTransmit: metrics.Network.TransmitPerSec, UPSCharge: metrics.UPS.ChargePercent,
 		UPSLoad: metrics.UPS.LoadPercent,
 	}
-	if len(metrics.CPU.Temperatures) > 0 {
+	if temperature := cpuTemperature(metrics.CPU.Temperatures); temperature != nil {
-		for _, temperature := range metrics.CPU.Temperatures {
+		point.CPUTemperature = *temperature
-			point.CPUTemperature += temperature.Celsius
-		}
-		point.CPUTemperature /= float64(len(metrics.CPU.Temperatures))
 	}
+
 	var zfsSize, zfsUsed uint64
 	for _, pool := range metrics.ZFS.Pools {
 		zfsSize += pool.SizeBytes

history_test.go

@@ -8,7 +8,7 @@ func TestHistoryPointFromMetrics(t *testing.T) {
 		Guests: GuestsMetrics{Guests: []GuestMetrics{{Status: "running", CPU: .5, MaxCPU: 4, MemoryBytes: 50, MaxMemory: 100}}},
 	}
 	point := historyPointFromMetrics(metrics)
-	if point.CPUTemperature != 50 || point.GuestsCPU != 50 || point.GuestsMemory != 50 {
+	if point.CPUTemperature != 60 || point.GuestsCPU != 50 || point.GuestsMemory != 50 {
 		t.Fatalf("неожиданная историческая точка: %+v", point)
 	}
 }

maintenance_window.go

@@ -17,6 +17,51 @@ type MaintenanceWindow struct {
 	AllAlerts  bool    `json:"allAlerts"`
 	ServiceIDs []int64 `json:"serviceIds"`
 	VMIDs      []int   `json:"vmids"`
+	Automatic  bool    `json:"automatic"`
+	Source     string  `json:"source,omitempty"`
+}
+
+func automaticBackupMaintenance(activity ProxmoxActivity, links []ServiceLink, now time.Time) MaintenanceWindow {
+	vmids := []int{}
+	backupRunning := false
+	for _, task := range activity.Tasks {
+		if task.Type != "vzdump" || task.EndTime > 0 || (task.Status != "" && !strings.EqualFold(task.Status, "running")) {
+			continue
+		}
+		backupRunning = true
+		if vmid := backupTaskVMID(task); vmid > 0 {
+			vmids = append(vmids, vmid)
+		}
+	}
+	vmids = uniqueInt(vmids)
+	if !backupRunning {
+		return MaintenanceWindow{}
+	}
+	selected := map[int]bool{}
+	for _, vmid := range vmids {
+		selected[vmid] = true
+	}
+	serviceIDs := []int64{}
+	for _, link := range links {
+		if selected[link.VMID] {
+			serviceIDs = append(serviceIDs, link.ServiceID)
+		}
+	}
+	return MaintenanceWindow{Enabled: true, Active: true, StartedAt: now.Unix(), EndsAt: now.Add(2 * time.Minute).Unix(), Reason: "Автоматически: выполняется backup VM/LXC", VMIDs: vmids, ServiceIDs: uniqueInt64(serviceIDs), AllAlerts: len(vmids) == 0, Automatic: true, Source: "backup"}
+}
+
+func backupTaskVMID(task ProxmoxTask) int {
+	if vmid, err := strconv.Atoi(strings.TrimSpace(task.ID)); err == nil && vmid > 0 {
+		return vmid
+	}
+	parts := strings.Split(task.UPID, ":")
+	for i, part := range parts {
+		if part == "vzdump" && i+1 < len(parts) {
+			vmid, _ := strconv.Atoi(parts[i+1])
+			return vmid
+		}
+	}
+	return 0
 }
 
 func (s *Store) MaintenanceWindow() MaintenanceWindow {

maintenance_window_test.go

@@ -38,6 +38,21 @@ func TestMaintenanceExpiresAutomatically(t *testing.T) {
 	}
 }
 
+func TestRunningBackupCreatesScopedAutomaticMaintenance(t *testing.T) {
+	now := time.Now()
+	window := automaticBackupMaintenance(ProxmoxActivity{Tasks: []ProxmoxTask{{Type: "vzdump", ID: "105"}, {Type: "vzdump", ID: "106", EndTime: now.Unix()}}}, []ServiceLink{{ServiceID: 7, VMID: 105}, {ServiceID: 8, VMID: 999}}, now)
+	if !window.Active || !window.Automatic || window.Source != "backup" || len(window.VMIDs) != 1 || window.VMIDs[0] != 105 || len(window.ServiceIDs) != 1 || window.ServiceIDs[0] != 7 {
+		t.Fatalf("неверное автоматическое окно: %+v", window)
+	}
+}
+
+func TestRunningBackupWithoutVMIDSuppressesAllAlerts(t *testing.T) {
+	window := automaticBackupMaintenance(ProxmoxActivity{Tasks: []ProxmoxTask{{Type: "vzdump", UPID: "unknown"}}}, nil, time.Now())
+	if !window.Active || !window.AllAlerts {
+		t.Fatalf("backup с неизвестной целью должен безопасно подавить алерты: %+v", window)
+	}
+}
+
 func TestPlannedAlertOnlyAppearsInHistory(t *testing.T) {
 	store, err := openStore(":memory:")
 	if err != nil {

network.go

@@ -3,6 +3,7 @@ package main
 import (
 	"bufio"
 	"context"
+	"fmt"
 	"io"
 	"net"
 	"net/http"
@@ -36,27 +37,37 @@ type NetworkHealth struct {
 	ExternalIPChanged     bool      `json:"externalIpChanged"`
 	DisappearedInterfaces []string  `json:"disappearedInterfaces"`
 	CheckedAt             time.Time `json:"checkedAt"`
+	Summary               string    `json:"summary"`
+	LikelyCause           string    `json:"likelyCause"`
+	RecommendedAction     string    `json:"recommendedAction"`
 }
 
 type NetworkInterface struct {
-	Name           string  `json:"name"`
+	Name             string            `json:"name"`
-	ReceiveBytes   uint64  `json:"receiveBytes"`
+	ReceiveBytes     uint64            `json:"receiveBytes"`
-	TransmitBytes  uint64  `json:"transmitBytes"`
+	TransmitBytes    uint64            `json:"transmitBytes"`
-	ReceiveErrors  uint64  `json:"receiveErrors"`
+	ReceiveErrors    uint64            `json:"receiveErrors"`
-	TransmitErrors uint64  `json:"transmitErrors"`
+	TransmitErrors   uint64            `json:"transmitErrors"`
-	ReceiveDrops   uint64  `json:"receiveDrops"`
+	ReceiveDrops     uint64            `json:"receiveDrops"`
-	TransmitDrops  uint64  `json:"transmitDrops"`
+	TransmitDrops    uint64            `json:"transmitDrops"`
-	ReceivePerSec  float64 `json:"receivePerSec"`
+	NewErrors        uint64            `json:"newErrors"`
-	TransmitPerSec float64 `json:"transmitPerSec"`
+	NewReceiveDrops  uint64            `json:"newReceiveDrops"`
-	VMID           int     `json:"vmid,omitempty"`
+	NewTransmitDrops uint64            `json:"newTransmitDrops"`
-	GuestName      string  `json:"guestName,omitempty"`
+	FaultCounters    map[string]uint64 `json:"faultCounters,omitempty"`
-	GuestType      string  `json:"guestType,omitempty"`
+	NewFaults        uint64            `json:"newFaults"`
-	Kind           string  `json:"kind"`
+	LinkDown         bool              `json:"linkDown"`
-	State          string  `json:"state"`
+	NewDrops         uint64            `json:"newDrops"`
-	Carrier        bool    `json:"carrier"`
+	ReceivePerSec    float64           `json:"receivePerSec"`
-	SpeedMbps      int     `json:"speedMbps,omitempty"`
+	TransmitPerSec   float64           `json:"transmitPerSec"`
-	Duplex         string  `json:"duplex,omitempty"`
+	VMID             int               `json:"vmid,omitempty"`
-	Master         string  `json:"master,omitempty"`
+	GuestName        string            `json:"guestName,omitempty"`
+	GuestType        string            `json:"guestType,omitempty"`
+	Kind             string            `json:"kind"`
+	State            string            `json:"state"`
+	Carrier          bool              `json:"carrier"`
+	SpeedMbps        int               `json:"speedMbps,omitempty"`
+	Duplex           string            `json:"duplex,omitempty"`
+	Master           string            `json:"master,omitempty"`
 }
 
 type networkSnapshot struct {
@@ -77,13 +88,14 @@ type networkCollector struct {
 }
 
 func newNetworkCollector(path string) (*networkCollector, error) {
-	snapshot, _, _, err := readNetworkSnapshot(path)
+	snapshot, _, details, err := readNetworkSnapshot(path)
 	if err != nil {
 		return nil, err
 	}
-	_, _, details, _ := readNetworkSnapshot(path)
 	previous := map[string]NetworkInterface{}
 	for _, v := range details {
+		decorateInterface(&v)
+		collectInterfaceFaults(&v)
 		previous[v.Name] = v
 	}
 	known := map[string]bool{}
@@ -110,10 +122,11 @@ func (c *networkCollector) collect() (NetworkMetrics, error) {
 	for i := range details {
 		v := &details[i]
 		decorateInterface(v)
-		if old, ok := c.previousInterfaces[v.Name]; ok && elapsed > 0 && v.ReceiveBytes >= old.ReceiveBytes && v.TransmitBytes >= old.TransmitBytes {
+		collectInterfaceFaults(v)
-			v.ReceivePerSec = float64(v.ReceiveBytes-old.ReceiveBytes) / elapsed
+		if old, ok := c.previousInterfaces[v.Name]; ok {
-			v.TransmitPerSec = float64(v.TransmitBytes-old.TransmitBytes) / elapsed
+			updateInterfaceDeltas(v, old, elapsed)
 		}
+		v.LinkDown = interfaceLinkDown(*v)
 	}
 	c.previousInterfaces = map[string]NetworkInterface{}
 	for _, v := range details {
@@ -138,12 +151,41 @@ func (c *networkCollector) collect() (NetworkMetrics, error) {
 		}
 	}
 	c.knownInterfaces = currentNames
+	explainNetworkHealth(&c.health, details)
 	return NetworkMetrics{
 		Interface: strings.Join(interfaceNames, ", "), Interfaces: details, ReceiveBytes: current.received,
 		TransmitBytes: current.sent, ReceivePerSec: receivedRate, TransmitPerSec: sentRate, Health: c.health,
 	}, nil
 }
 
+func explainNetworkHealth(health *NetworkHealth, interfaces []NetworkInterface) {
+	health.Summary, health.LikelyCause, health.RecommendedAction = "Сеть работает штатно", "Проблем не обнаружено", "Действий не требуется"
+	switch {
+	case health.Gateway == "":
+		health.Summary, health.LikelyCause, health.RecommendedAction = "Не найден маршрут в локальную сеть", "На хосте отсутствует default gateway", "Проверьте адрес шлюза и конфигурацию bridge/VLAN"
+	case !health.GatewayUp:
+		health.Summary, health.LikelyCause, health.RecommendedAction = "Хост не видит локальный шлюз", "Проблема между Proxmox и роутером: линк, bridge, bond или VLAN", "Проверьте кабель, carrier и настройки vmbr/bond/VLAN"
+	case health.PacketLoss > 0:
+		health.Summary = fmt.Sprintf("Нестабильная локальная сеть: потеряно %.1f%% пакетов", health.PacketLoss)
+		health.LikelyCause, health.RecommendedAction = "Перегрузка или ошибки линка между Proxmox и шлюзом", "Проверьте аппаратные ошибки, кабель, порт коммутатора и duplex"
+	case !health.DNSUp && health.InternetUp:
+		health.Summary, health.LikelyCause, health.RecommendedAction = "Интернет доступен, но DNS не отвечает", "Проблема DNS-сервера или /etc/resolv.conf", "Проверьте настроенные DNS и попробуйте разрешить домен вручную"
+	case health.DNSUp && !health.InternetUp:
+		health.Summary, health.LikelyCause, health.RecommendedAction = "Локальная сеть и DNS работают, но внешняя проверка недоступна", "Проблема выше роутера, блокировка HTTPS или недоступность провайдера", "Проверьте маршрут наружу, firewall и доступ к внешним адресам"
+	}
+	for _, v := range interfaces {
+		if v.LinkDown {
+			health.Summary, health.LikelyCause, health.RecommendedAction = v.Name+": линк не поднят", "Нет carrier либо интерфейс административно выключен", "Проверьте кабель, порт коммутатора и состояние интерфейса"
+			return
+		}
+		if v.NewErrors+v.NewFaults > 0 {
+			health.Summary = fmt.Sprintf("%s: за последний интервал появилось %d изменений счётчиков сетевых ошибок", v.Name, v.NewErrors+v.NewFaults)
+			health.LikelyCause, health.RecommendedAction = "Счётчики интерфейса сейчас растут из-за перегрузки, кабеля, MTU или duplex", "Проверьте скорость и duplex, кабель, порт коммутатора и MTU на обоих концах"
+			return
+		}
+	}
+}
+
 func decorateInterface(v *NetworkInterface) {
 	base := filepath.Join("/sys/class/net", v.Name)
 	v.State = readTrimmed(filepath.Join(base, "operstate"))
@@ -154,6 +196,10 @@ func decorateInterface(v *NetworkInterface) {
 		v.Master = filepath.Base(target)
 	}
 	switch {
+	case strings.HasPrefix(v.Name, "fwbr"):
+		v.Kind = "Firewall bridge"
+	case strings.HasPrefix(v.Name, "fwpr") || strings.HasPrefix(v.Name, "fwln"):
+		v.Kind = "Firewall link"
 	case strings.HasPrefix(v.Name, "vmbr"):
 		v.Kind = "Bridge"
 	case strings.HasPrefix(v.Name, "bond"):
@@ -232,7 +278,7 @@ func readNetworkSnapshot(path string) (networkSnapshot, []string, []NetworkInter
 			continue
 		}
 		fields := strings.Fields(values)
-		if len(fields) < 9 {
+		if len(fields) < 16 {
 			continue
 		}
 		rx, errRX := strconv.ParseUint(fields[0], 10, 64)

network_faults.go

@@ -0,0 +1,103 @@
+package main
+
+import (
+	"context"
+	"os/exec"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+)
+
+func counterDelta(current, previous uint64) uint64 {
+	if current < previous {
+		return 0
+	}
+	return current - previous
+}
+
+func updateInterfaceDeltas(v *NetworkInterface, old NetworkInterface, elapsed float64) {
+	if elapsed <= 0 {
+		return
+	}
+	v.ReceivePerSec = float64(counterDelta(v.ReceiveBytes, old.ReceiveBytes)) / elapsed
+	v.TransmitPerSec = float64(counterDelta(v.TransmitBytes, old.TransmitBytes)) / elapsed
+	v.NewErrors = counterDelta(v.ReceiveErrors, old.ReceiveErrors) + counterDelta(v.TransmitErrors, old.TransmitErrors)
+	v.NewReceiveDrops = counterDelta(v.ReceiveDrops, old.ReceiveDrops)
+	v.NewTransmitDrops = counterDelta(v.TransmitDrops, old.TransmitDrops)
+	v.NewDrops = v.NewReceiveDrops + v.NewTransmitDrops
+	for name, value := range v.FaultCounters {
+		if previous, ok := old.FaultCounters[name]; ok {
+			v.NewFaults += counterDelta(value, previous)
+		}
+	}
+	// A transition matters even if the interface has not carried traffic yet.
+	v.LinkDown = old.Carrier && !v.Carrier
+}
+
+func interfaceLinkDown(v NetworkInterface) bool {
+	if v.Kind == "Firewall bridge" || v.Kind == "Firewall link" {
+		return false
+	}
+	if v.LinkDown {
+		return true
+	}
+	used := v.Master != "" || v.ReceiveBytes+v.TransmitBytes > 0
+	if v.Kind == "Physical" {
+		return used && (!v.Carrier || v.State == "down")
+	}
+	return used && v.State == "down"
+}
+
+func collectInterfaceFaults(v *NetworkInterface) {
+	base := filepath.Join("/sys/class/net", v.Name)
+	// /proc/net/dev folds missed packets into RX drop. Sysfs keeps software
+	// drops separate from rx_missed_errors, which must still trigger an alert.
+	if n, err := strconv.ParseUint(readTrimmed(filepath.Join(base, "statistics/rx_dropped")), 10, 64); err == nil {
+		v.ReceiveDrops = n
+	}
+	v.FaultCounters = map[string]uint64{}
+	for _, name := range []string{"rx_crc_errors", "rx_frame_errors", "rx_fifo_errors", "rx_missed_errors", "tx_fifo_errors", "tx_carrier_errors", "carrier_down_count"} {
+		path := filepath.Join(base, "statistics", name)
+		if name == "carrier_down_count" {
+			path = filepath.Join(base, name)
+		}
+		if n, err := strconv.ParseUint(readTrimmed(path), 10, 64); err == nil {
+			v.FaultCounters[name] = n
+		}
+	}
+	// Only Atlantic exposes the driver-specific names below. No configuration
+	// changes, and a missing ethtool is not itself a network failure.
+	driver, err := filepath.EvalSymlinks(filepath.Join(base, "device/driver"))
+	if err != nil || filepath.Base(driver) != "atlantic" {
+		return
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second)
+	defer cancel()
+	if out, err := exec.CommandContext(ctx, "ethtool", "-S", v.Name).Output(); err == nil {
+		for k, n := range parseAtlanticFaults(string(out)) {
+			v.FaultCounters["atlantic:"+k] = n
+		}
+	}
+}
+
+func parseAtlanticFaults(output string) map[string]uint64 {
+	result := map[string]uint64{}
+	for _, line := range strings.Split(output, "\n") {
+		key, value, ok := strings.Cut(strings.TrimSpace(line), ":")
+		if !ok {
+			continue
+		}
+		fields := strings.Fields(key)
+		if len(fields) == 0 {
+			continue
+		}
+		switch fields[len(fields)-1] {
+		case "InErrors", "InDroppedDma", "AllocFails", "SkbAllocFails", "Restarts":
+			if n, err := strconv.ParseUint(strings.TrimSpace(value), 10, 64); err == nil {
+				result[key] = n
+			}
+		}
+	}
+	return result
+}

network_faults_test.go

@@ -0,0 +1,67 @@
+package main
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestNetworkDropsDoNotAlert(t *testing.T) {
+	for _, name := range []string{"enp6s0", "vmbr0", "fwbr100i0", "tap100i0"} {
+		v := NetworkInterface{Name: name, Carrier: true, State: "up", NewDrops: 15, NewReceiveDrops: 15}
+		metrics := dashboardMetrics{Network: NetworkMetrics{Interfaces: []NetworkInterface{v}}}
+		for _, a := range evaluateAlerts(metrics, AlertThresholds{}) {
+			if a.ID == "network-errors" {
+				t.Fatalf("%s: drops triggered alert", name)
+			}
+		}
+		v.NewErrors = 1
+		metrics.Network.Interfaces[0] = v
+		found := false
+		for _, a := range evaluateAlerts(metrics, AlertThresholds{}) {
+			if a.ID == "network-errors" {
+				found = a.Severity == "critical"
+			}
+		}
+		if !found {
+			t.Fatalf("%s: errors did not trigger critical alert", name)
+		}
+	}
+}
+
+func TestNetworkHardwareFaultAndLinkAlerts(t *testing.T) {
+	for _, v := range []NetworkInterface{{Name: "eth0", NewFaults: 1}, {Name: "eth0", LinkDown: true}} {
+		found := false
+		for _, a := range evaluateAlerts(dashboardMetrics{Network: NetworkMetrics{Interfaces: []NetworkInterface{v}}}, AlertThresholds{}) {
+			if strings.HasPrefix(a.ID, "network-") && a.Severity == "critical" {
+				found = true
+			}
+		}
+		if !found {
+			t.Fatalf("no critical alert for %+v", v)
+		}
+	}
+}
+
+func TestNetworkCounterResetsAndFaultBaselines(t *testing.T) {
+	old := NetworkInterface{ReceiveBytes: 100, ReceiveErrors: 20, TransmitErrors: 4, ReceiveDrops: 8, FaultCounters: map[string]uint64{"rx_missed_errors": 10, "atlantic:InErrors": 9}, Carrier: true}
+	next := NetworkInterface{ReceiveBytes: 1, ReceiveErrors: 1, TransmitErrors: 6, ReceiveDrops: 10, FaultCounters: map[string]uint64{"rx_missed_errors": 12, "atlantic:InErrors": 1, "new": 100}, Carrier: false}
+	updateInterfaceDeltas(&next, old, 2)
+	if next.NewErrors != 2 || next.NewFaults != 2 || next.NewReceiveDrops != 2 || next.ReceivePerSec != 0 || !next.LinkDown {
+		t.Fatalf("bad deltas: %+v", next)
+	}
+}
+
+func TestAtlanticFaults(t *testing.T) {
+	got := parseAtlanticFaults("NIC statistics:\n InErrors: 2\n InDroppedDma: 3\n Queue[0] AllocFails: 4\n Queue[1] SkbAllocFails: 5\n Queue[0] Restarts: 6\n Queue[0] InErrors: 7\n InPackets: 100\n Queue[0] XdpDrop: 50\n InErrorsBad: nope")
+	if len(got) != 6 || got["InDroppedDma"] != 3 || got["Queue[0] Restarts"] != 6 {
+		t.Fatalf("bad counters: %v", got)
+	}
+}
+
+func TestFirewallNotAttributedToGuest(t *testing.T) {
+	n := NetworkMetrics{Interfaces: []NetworkInterface{{Name: "fwbr100i0", ReceiveDrops: 100}, {Name: "tap100i0"}}}
+	decorateNetworkInterfaces(&n, GuestsMetrics{})
+	if n.Interfaces[0].VMID != 0 || n.Interfaces[1].VMID != 100 {
+		t.Fatalf("bad VM attribution: %+v", n)
+	}
+}

network_test.go

@@ -3,6 +3,7 @@ package main
 import (
 	"os"
 	"path/filepath"
+	"strings"
 	"testing"
 )
 
@@ -33,8 +34,28 @@ func TestReadNetworkSnapshot(t *testing.T) {
 	}
 }
 
+func TestExplainNetworkHealthDistinguishesDNSFailure(t *testing.T) {
+	health := NetworkHealth{Gateway: "192.168.0.1", GatewayUp: true, InternetUp: true, DNSUp: false}
+	explainNetworkHealth(&health, nil)
+	if !strings.Contains(health.Summary, "DNS") || health.RecommendedAction == "" {
+		t.Fatalf("непонятная диагностика: %+v", health)
+	}
+}
+
+func TestExplainNetworkHealthIgnoresOldInterfaceCounters(t *testing.T) {
+	health := NetworkHealth{Gateway: "192.168.0.1", GatewayUp: true, InternetUp: true, DNSUp: true}
+	explainNetworkHealth(&health, []NetworkInterface{{Name: "eno1", Carrier: true, State: "up", ReceiveDrops: 42}})
+	if health.Summary != "Сеть работает штатно" {
+		t.Fatalf("старый накопленный счётчик вызвал текущую тревогу: %+v", health)
+	}
+	explainNetworkHealth(&health, []NetworkInterface{{Name: "eno1", Carrier: true, State: "up", ReceiveDrops: 43, NewDrops: 1}})
+	if health.Summary != "Сеть работает штатно" {
+		t.Fatalf("software drops вызвали тревогу: %+v", health)
+	}
+}
+
 func TestInterfaceVMID(t *testing.T) {
-	for name, want := range map[string]int{"tap100i0": 100, "veth108i0": 108, "fwbr113i0": 113, "vmbr0": 0, "enp6s0": 0} {
+	for name, want := range map[string]int{"tap100i0": 100, "veth108i0": 108, "fwbr113i0": 0, "vmbr0": 0, "enp6s0": 0} {
 		if got := interfaceVMID(name); got != want {
 			t.Fatalf("%s: got %d want %d", name, got, want)
 		}

scripts/build-release.sh

@@ -0,0 +1,16 @@
+#!/bin/sh
+set -eu
+version=${1:?Usage: build-release.sh vX.Y.Z}
+cd "$(dirname "$0")/.."
+go test ./...
+mkdir -p dist
+GOOS=linux GOARCH=amd64 CGO_ENABLED=0 go build -trimpath -ldflags "-s -w -X main.version=$version" -o dist/proxmox-dashboard-linux-amd64 .
+(cd dist && shasum -a 256 proxmox-dashboard-linux-amd64 > proxmox-dashboard-linux-amd64.sha256)
+stage=$(mktemp -d)
+trap 'rm -rf "$stage"' EXIT INT TERM
+package="$stage/proxmox-dashboard-install"
+mkdir -p "$package/dist" "$package/scripts"
+cp dist/proxmox-dashboard-linux-amd64 dist/proxmox-dashboard-linux-amd64.sha256 "$package/dist/"
+cp scripts/install.sh scripts/install-agent.sh scripts/uninstall-agent.sh scripts/proxmox-dashboard-update "$package/scripts/"
+cp ./*.service ./*.timer ./*.path README.md "$package/"
+tar -czf dist/proxmox-dashboard-install-amd64.tar.gz -C "$stage" proxmox-dashboard-install

service_links.go

@@ -0,0 +1,110 @@
+package main
+
+import (
+	"fmt"
+	"sort"
+	"strings"
+)
+
+type ServiceLink struct {
+	ServiceID     int64  `json:"serviceId"`
+	AgentID       string `json:"agentId"`
+	VMID          int    `json:"vmid"`
+	ComponentType string `json:"componentType"`
+	ComponentName string `json:"componentName"`
+	Port          int    `json:"port"`
+}
+
+func (s *Store) ServiceLinks() ([]ServiceLink, error) {
+	rows, err := s.db.Query(`SELECT service_id,agent_id,vmid,component_type,component_name,port FROM service_links ORDER BY service_id`)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var out []ServiceLink
+	for rows.Next() {
+		var v ServiceLink
+		if err = rows.Scan(&v.ServiceID, &v.AgentID, &v.VMID, &v.ComponentType, &v.ComponentName, &v.Port); err != nil {
+			return nil, err
+		}
+		out = append(out, v)
+	}
+	return out, rows.Err()
+}
+
+func (s *Store) SaveServiceLink(v ServiceLink) (ServiceLink, error) {
+	v.AgentID = strings.TrimSpace(v.AgentID)
+	v.ComponentType = strings.TrimSpace(v.ComponentType)
+	v.ComponentName = strings.TrimSpace(v.ComponentName)
+	if v.ServiceID <= 0 {
+		return v, fmt.Errorf("выберите сервис")
+	}
+	if v.AgentID == "" && v.VMID <= 0 {
+		return v, fmt.Errorf("выберите агент или VMID")
+	}
+	if v.ComponentType != "" && v.ComponentType != "systemd" && v.ComponentType != "docker" && v.ComponentType != "process" {
+		return v, fmt.Errorf("неизвестный тип компонента")
+	}
+	if v.Port < 0 || v.Port > 65535 {
+		return v, fmt.Errorf("некорректный порт")
+	}
+	_, err := s.db.Exec(`INSERT INTO service_links(service_id,agent_id,vmid,component_type,component_name,port) VALUES(?,?,?,?,?,?) ON CONFLICT(service_id) DO UPDATE SET agent_id=excluded.agent_id,vmid=excluded.vmid,component_type=excluded.component_type,component_name=excluded.component_name,port=excluded.port`, v.ServiceID, v.AgentID, v.VMID, v.ComponentType, v.ComponentName, v.Port)
+	return v, err
+}
+func (s *Store) DeleteServiceLink(serviceID int64) error {
+	_, err := s.db.Exec(`DELETE FROM service_links WHERE service_id=?`, serviceID)
+	return err
+}
+
+func groupLinkedAlerts(metrics dashboardMetrics, alerts []Alert) []Alert {
+	if len(metrics.ServiceLinks) == 0 {
+		return alerts
+	}
+	agentOffline := map[string]ManagedAgent{}
+	for _, agent := range metrics.Agents {
+		if !agent.Online {
+			agentOffline[agent.ID] = agent
+		}
+	}
+	affected := map[string][]string{}
+	remove := map[string]bool{}
+	for _, link := range metrics.ServiceLinks {
+		agent, offline := agentOffline[link.AgentID]
+		if !offline {
+			continue
+		}
+		for _, service := range metrics.Services.Services {
+			if service.ID != link.ServiceID {
+				continue
+			}
+			for _, endpoint := range service.Endpoints {
+				if !endpoint.Up {
+					key := fmt.Sprintf("service-%d-%s", service.ID, endpoint.Kind)
+					remove[key] = true
+					affected[agent.ID] = append(affected[agent.ID], service.Name)
+				}
+			}
+		}
+	}
+	if len(affected) == 0 {
+		return alerts
+	}
+	out := make([]Alert, 0, len(alerts))
+	for _, alert := range alerts {
+		skip := remove[alert.ID]
+		for agentID := range affected {
+			if alert.ID == "agent-offline-"+agentID+fmt.Sprintf("-%d", agentOffline[agentID].VMID) {
+				skip = true
+			}
+		}
+		if !skip {
+			out = append(out, alert)
+		}
+	}
+	for agentID, names := range affected {
+		sort.Strings(names)
+		agent := agentOffline[agentID]
+		out = append(out, Alert{ID: "group-agent-offline-" + agentID + fmt.Sprintf("-%d", agent.VMID), Severity: "critical", Source: "Корреляция", Title: agent.Name + ": агент недоступен, связанные сервисы не отвечают", Message: fmt.Sprintf("VMID %d. Затронуто сервисов: %d — %s. Вероятная первопричина: недоступна гостевая система или агент.", agent.VMID, len(names), strings.Join(names, ", "))})
+	}
+	return out
+}

store.go

@@ -140,6 +140,9 @@ func openStore(path string) (*Store, error) {
 		`CREATE INDEX IF NOT EXISTS entity_history_kind_ts_idx ON entity_history(kind,ts)`,
 		`CREATE TABLE IF NOT EXISTS agent_enrollment_tokens (token_hash TEXT PRIMARY KEY, created_at INTEGER NOT NULL, expires_at INTEGER NOT NULL, used_at INTEGER)`,
 		`CREATE TABLE IF NOT EXISTS agents (id TEXT PRIMARY KEY, name TEXT NOT NULL, vmid INTEGER NOT NULL DEFAULT 0, hostname TEXT NOT NULL DEFAULT '', machine_id TEXT NOT NULL DEFAULT '', secret_hash TEXT NOT NULL, enrolled_at INTEGER NOT NULL, last_seen INTEGER NOT NULL, version TEXT NOT NULL DEFAULT '', report_json TEXT NOT NULL DEFAULT '{}', remote_address TEXT NOT NULL DEFAULT '')`,
+		`CREATE TABLE IF NOT EXISTS agent_actions (id INTEGER PRIMARY KEY AUTOINCREMENT, agent_id TEXT NOT NULL, action TEXT NOT NULL, target TEXT NOT NULL DEFAULT '', requested_at INTEGER NOT NULL, started_at INTEGER, completed_at INTEGER, status TEXT NOT NULL DEFAULT 'queued', result TEXT NOT NULL DEFAULT '', FOREIGN KEY(agent_id) REFERENCES agents(id) ON DELETE CASCADE)`,
+		`CREATE INDEX IF NOT EXISTS agent_actions_agent_status_idx ON agent_actions(agent_id,status)`,
+		`CREATE TABLE IF NOT EXISTS service_links (service_id INTEGER PRIMARY KEY, agent_id TEXT NOT NULL DEFAULT '', vmid INTEGER NOT NULL DEFAULT 0, component_type TEXT NOT NULL DEFAULT '', component_name TEXT NOT NULL DEFAULT '', port INTEGER NOT NULL DEFAULT 0, FOREIGN KEY(service_id) REFERENCES services(id) ON DELETE CASCADE)`,
 	}
 	for _, statement := range statements {
 		if _, err := db.Exec(statement); err != nil {