edgeguard-native/internal/handlers/cluster_rollingupdate.go

package handlers

import (
	"context"
	"encoding/json"
	"log/slog"
	"net/http"
	"os"
	"os/exec"
	"time"

	"github.com/gin-gonic/gin"

	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
)

const rollingUpdateStateFile = "/var/lib/edgeguard/rolling-update-state.json"

const (
	phaseIdle              = "idle"
	phaseUpdatingSecondary = "updating-secondary"
	phaseWaitingSecondary  = "waiting-secondary"
	phaseUpdatingPrimary   = "updating-primary"
	phaseDone              = "done"
	phaseFailed            = "failed"
)

// FinishRollingUpdateIfPending wird beim API-Start aufgerufen. Wenn die
// State-Datei "updating-primary" enthält, bedeutet das dass der Primary
// gerade erfolgreich neugestartet ist → Update abgeschlossen → "done" schreiben.
func FinishRollingUpdateIfPending() {
	st := readRollingUpdateState()
	if st.Phase == phaseUpdatingPrimary {
		writeRollingUpdateState(RollingUpdateState{
			Phase:         phaseDone,
			SecondaryID:   st.SecondaryID,
			SecondaryFQDN: st.SecondaryFQDN,
		})
	}
}

// RollingUpdateState hält den Fortschritt des Rolling-Updates.
// Persistiert in rollingUpdateStateFile damit der Status über
// einen kurzen API-Neustart hinaus lesbar bleibt.
type RollingUpdateState struct {
	Phase         string    `json:"phase"`
	SecondaryID   string    `json:"secondary_id,omitempty"`
	SecondaryFQDN string    `json:"secondary_fqdn,omitempty"`
	StartedAt     time.Time `json:"started_at,omitempty"`
	UpdatedAt     time.Time `json:"updated_at"`
	Error         string    `json:"error,omitempty"`
}

func readRollingUpdateState() RollingUpdateState {
	data, err := os.ReadFile(rollingUpdateStateFile)
	if err != nil {
		return RollingUpdateState{Phase: phaseIdle, UpdatedAt: time.Now()}
	}
	var s RollingUpdateState
	if err := json.Unmarshal(data, &s); err != nil {
		return RollingUpdateState{Phase: phaseIdle, UpdatedAt: time.Now()}
	}
	return s
}

func writeRollingUpdateState(s RollingUpdateState) {
	s.UpdatedAt = time.Now()
	data, err := json.Marshal(s)
	if err != nil {
		slog.Warn("rolling-update: failed to marshal state", "error", err)
		return
	}
	if err := os.WriteFile(rollingUpdateStateFile, data, 0o600); err != nil {
		slog.Warn("rolling-update: failed to write state file", "error", err)
	}
}

// RollingUpdate startet den Rolling-Update-Prozess:
// 1. Secondary aktualisieren (via mTLS /agent/cluster/trigger-update)
// 2. Warten bis Secondary neue Version meldet
// 3. Primary (dieser Node) aktualisieren (wie /system/upgrade)
//
// Kein Cluster vorhanden → 409 zurück damit der Client auf /system/upgrade
// ausweichen kann. Wenn bereits ein Rolling-Update läuft → aktuellen State.
func (h *ClusterHandler) RollingUpdate(c *gin.Context) {
	if h.Aggregator == nil || h.Store == nil {
		c.JSON(http.StatusConflict, gin.H{"error": "no cluster — use /system/upgrade"})
		return
	}

	st := readRollingUpdateState()
	if st.Phase != phaseIdle && st.Phase != phaseFailed && st.Phase != phaseDone {
		response.OK(c, st)
		return
	}

	nodes, err := h.Store.List(c.Request.Context())
	if err != nil {
		response.Internal(c, err)
		return
	}
	var secondary *models.HANode
	for i := range nodes {
		if nodes[i].ID != h.LocalID {
			secondary = &nodes[i]
			break
		}
	}
	if secondary == nil {
		c.JSON(http.StatusConflict, gin.H{"error": "no peer node — use /system/upgrade"})
		return
	}

	newState := RollingUpdateState{
		Phase:         phaseUpdatingSecondary,
		SecondaryID:   secondary.ID,
		SecondaryFQDN: secondary.FQDN,
		StartedAt:     time.Now(),
	}
	writeRollingUpdateState(newState)
	slog.Info("rolling-update: started", "secondary", secondary.FQDN)

	go h.runRollingUpdate(secondary)

	c.JSON(http.StatusAccepted, newState)
}

// RollingUpdateStatus gibt den aktuellen Rolling-Update-State zurück.
// Bei phase == "done" wird nach Auslieferung sofort auf idle zurückgesetzt
// damit der nächste Pageload keinen Stale-done vorfindet.
func (h *ClusterHandler) RollingUpdateStatus(c *gin.Context) {
	st := readRollingUpdateState()
	response.OK(c, st)
	if st.Phase == phaseDone {
		writeRollingUpdateState(RollingUpdateState{Phase: phaseIdle})
	}
}

func (h *ClusterHandler) runRollingUpdate(secondary *models.HANode) {
	ctx := context.Background()

	// 1. Secondary triggern
	slog.Info("rolling-update: posting trigger-update to secondary", "fqdn", secondary.FQDN)
	result := h.Aggregator.PostPeer(ctx, *secondary, "/agent/cluster/trigger-update")
	if !result.OK {
		writeRollingUpdateState(RollingUpdateState{
			Phase:         phaseFailed,
			SecondaryID:   secondary.ID,
			SecondaryFQDN: secondary.FQDN,
			Error:         "trigger-update failed: " + result.Err,
		})
		slog.Warn("rolling-update: secondary trigger failed", "error", result.Err)
		return
	}

	// 2. Secondary-Version pollen — der Secondary restartet nach dem
	//    Upgrade, danach zeigt /agent/cluster/version eine neue Version.
	writeRollingUpdateState(RollingUpdateState{
		Phase:         phaseWaitingSecondary,
		SecondaryID:   secondary.ID,
		SecondaryFQDN: secondary.FQDN,
	})
	slog.Info("rolling-update: waiting for secondary version flip")

	// Kurze Wartezeit damit apt auf dem Secondary erst losläuft
	time.Sleep(20 * time.Second)

	deadline := time.Now().Add(10 * time.Minute)
	versionFlipped := false
	for time.Now().Before(deadline) {
		results := h.Aggregator.FanOut(ctx, []models.HANode{*secondary}, "/agent/cluster/version", h.LocalID)
		if len(results) > 0 && results[0].OK {
			var ver struct {
				Version string `json:"version"`
			}
			if err := json.Unmarshal(results[0].Data, &ver); err == nil {
				slog.Info("rolling-update: secondary version", "version", ver.Version, "primary", h.Version)
				if ver.Version != h.Version {
					versionFlipped = true
					break
				}
			}
		}
		time.Sleep(10 * time.Second)
	}

	if !versionFlipped {
		writeRollingUpdateState(RollingUpdateState{
			Phase:         phaseFailed,
			SecondaryID:   secondary.ID,
			SecondaryFQDN: secondary.FQDN,
			Error:         "timeout (10 min) waiting for secondary version flip",
		})
		slog.Warn("rolling-update: secondary version flip timeout")
		return
	}

	// 3. Primary (uns selbst) aktualisieren — identisch zu /system/upgrade
	writeRollingUpdateState(RollingUpdateState{
		Phase:         phaseUpdatingPrimary,
		SecondaryID:   secondary.ID,
		SecondaryFQDN: secondary.FQDN,
	})
	slog.Info("rolling-update: triggering primary self-upgrade")

	const scriptPath = "/var/lib/edgeguard/upgrade.sh"
	const script = `#!/bin/bash
set -e
sleep 2
export DEBIAN_FRONTEND=noninteractive
dpkg --configure -a || true
retry_apt() {
    local attempt=0 max=3 wait_for=15
    while [ $attempt -lt $max ]; do
        attempt=$((attempt + 1))
        apt-get update -qq || true
        if apt-get install -y -qq -o Dpkg::Options::=--force-confold \
            edgeguard-api edgeguard-ui edgeguard; then return 0; fi
        [ $attempt -lt $max ] && sleep $wait_for && wait_for=$((wait_for * 2))
    done
    return 1
}
retry_apt
echo "[upgrade] complete"
rm -f /var/lib/edgeguard/upgrade.sh
`
	if err := os.WriteFile(scriptPath, []byte(script), 0o755); err != nil {
		writeRollingUpdateState(RollingUpdateState{
			Phase:         phaseFailed,
			SecondaryID:   secondary.ID,
			SecondaryFQDN: secondary.FQDN,
			Error:         "write upgrade script: " + err.Error(),
		})
		return
	}

	const unitName = "edgeguard-upgrade.service"
	_ = exec.Command("sudo", "-n", "/usr/bin/systemctl", "reset-failed", unitName).Run()
	cmd := exec.Command("sudo", "-n", "/usr/bin/systemd-run",
		"--unit="+unitName,
		"--description=EdgeGuard self-upgrade",
		"--collect",
		"bash", scriptPath)
	if err := cmd.Run(); err != nil {
		writeRollingUpdateState(RollingUpdateState{
			Phase:         phaseFailed,
			SecondaryID:   secondary.ID,
			SecondaryFQDN: secondary.FQDN,
			Error:         "systemd-run failed: " + err.Error(),
		})
		slog.Warn("rolling-update: primary systemd-run failed", "error", err)
		return
	}
	// State bleibt "updating-primary" — der Primary restartet gleich.
	// UI erkennt Version-Flip via /system/health und schließt den Flow.
	slog.Info("rolling-update: primary upgrade dispatched, process will restart")
}