terdut-server/internal/api/archiver.go

package api

import (
	"context"
	"database/sql"
	"log"
	"strings"
	"time"
)

const (
	// sweepInterval is how often the background sweeper runs.
	sweepInterval = 15 * time.Minute

	// expiryGrace absorbs clock skew and notification latency before an alert
	// whose ends_at watermark has passed is treated as stale.
	expiryGrace = 5 * time.Minute
)

// StartArchiver runs the alert sweeper until ctx is cancelled, starting with an
// immediate pass so a restart reconciles state right away.
func StartArchiver(ctx context.Context, db *sql.DB, archiveAfter, staleAfter time.Duration) {
	ticker := time.NewTicker(sweepInterval)
	defer ticker.Stop()

	Sweep(ctx, db, archiveAfter, staleAfter)
	for {
		select {
		case <-ticker.C:
			Sweep(ctx, db, archiveAfter, staleAfter)
		case <-ctx.Done():
			return
		}
	}
}

// Sweep runs a single pass, in dependency order: expire stale firing alerts,
// close the incidents that leaves with nothing firing, then archive whatever has
// been settled long enough. Running them in one pass means an alert can go stale
// and its incident can close and archive without waiting three ticks.
// Exported so tests can drive a pass without waiting on the ticker.
func Sweep(ctx context.Context, db *sql.DB, archiveAfter, staleAfter time.Duration) {
	expireStale(ctx, db, staleAfter)
	resolveSettledIncidents(ctx, db)
	archiveResolved(ctx, db, archiveAfter)
	archiveResolvedIncidents(ctx, db, archiveAfter)
}

// expireStale resolves firing alerts that Alertmanager has stopped refreshing.
//
// A resolved webhook is otherwise the only way out of the firing state, so a
// notification that is dropped, silenced, or lost to a restart would pin the
// alert as firing forever. Two independent signals mark an alert stale:
//
//   - ends_at, the "valid until" watermark Alertmanager sets on outgoing firing
//     notifications, has passed (plus expiryGrace for clock skew). Absent on
//     rows whose payload carried no ends_at, hence the second signal.
//   - received_at is older than staleAfter. Alertmanager re-sends firing
//     notifications every repeat_interval, making received_at a liveness
//     heartbeat — provided staleAfter exceeds that interval.
//
// The matching rows are collected before the update rather than updated in bulk,
// because each one owes its incident a timeline entry.
func expireStale(ctx context.Context, db *sql.DB, staleAfter time.Duration) {
	now := time.Now()

	ids, err := staleAlertIDs(ctx, db, now, staleAfter)
	if err != nil {
		log.Printf("sweeper: find stale: %v", err)
		return
	}
	if len(ids) == 0 {
		return
	}

	args := make([]any, 0, len(ids)+1)
	args = append(args, resolutionExpiry)
	for _, id := range ids {
		args = append(args, id)
	}
	if _, err := db.ExecContext(ctx, `
		UPDATE alerts
		   SET status            = 'resolved',
		       resolution_source = ?,
		       ends_at           = COALESCE(ends_at, unixepoch())
		 WHERE id IN (`+placeholders(len(ids))+`)`, args...); err != nil {
		log.Printf("sweeper: expire stale: %v", err)
		return
	}
	log.Printf("sweeper: expired %d stale firing alert(s)", len(ids))

	for _, id := range ids {
		incidentID, err := openIncidentForAlert(ctx, db, id)
		if err != nil {
			log.Printf("sweeper: incident for alert %d: %v", id, err)
			continue
		}
		if incidentID == 0 {
			continue
		}
		alertID := id
		if err := logEvent(ctx, db, incidentID, evAlertResolved, nil, &alertID, nil); err != nil {
			log.Printf("sweeper: log expiry event: %v", err)
		}
	}
}

// staleAlertIDs reads the ids in one go and closes the cursor before the caller
// writes: the pool is limited to a single connection, so an open read would
// block the update behind it.
func staleAlertIDs(ctx context.Context, db *sql.DB, now time.Time, staleAfter time.Duration) ([]int64, error) {
	rows, err := db.QueryContext(ctx, `
		SELECT id FROM alerts
		 WHERE status = 'firing'
		   AND archived_at IS NULL
		   AND ((ends_at IS NOT NULL AND ends_at < ?) OR received_at < ?)`,
		now.Add(-expiryGrace).Unix(), now.Add(-staleAfter).Unix())
	if err != nil {
		return nil, err
	}
	defer rows.Close()

	var ids []int64
	for rows.Next() {
		var id int64
		if err := rows.Scan(&id); err != nil {
			return nil, err
		}
		ids = append(ids, id)
	}
	return ids, rows.Err()
}

// resolveSettledIncidents closes incidents whose alerts have all stopped firing.
// This is the cascade from alerts up to the work item, and it is what turns an
// expiry into a closed incident rather than one that sits open forever.
func resolveSettledIncidents(ctx context.Context, db *sql.DB) {
	ids, err := settledIncidentIDs(ctx, db)
	if err != nil {
		log.Printf("sweeper: find settled incidents: %v", err)
		return
	}

	resolved := 0
	for _, id := range ids {
		ok, err := resolveIfSettled(ctx, db, id)
		if err != nil {
			log.Printf("sweeper: resolve incident %d: %v", id, err)
			continue
		}
		if ok {
			resolved++
		}
	}
	if resolved > 0 {
		log.Printf("sweeper: resolved %d settled incident(s)", resolved)
	}
}

func settledIncidentIDs(ctx context.Context, db *sql.DB) ([]int64, error) {
	rows, err := db.QueryContext(ctx, `
		SELECT i.id
		FROM   incidents i
		WHERE  i.resolved_at IS NULL
		  AND  EXISTS (SELECT 1 FROM incident_alerts ia WHERE ia.incident_id = i.id)
		  AND  NOT EXISTS (SELECT 1
		                     FROM incident_alerts ia
		                     JOIN alerts a ON a.id = ia.alert_id
		                    WHERE ia.incident_id = i.id
		                      AND a.status = 'firing')`)
	if err != nil {
		return nil, err
	}
	defer rows.Close()

	var ids []int64
	for rows.Next() {
		var id int64
		if err := rows.Scan(&id); err != nil {
			return nil, err
		}
		ids = append(ids, id)
	}
	return ids, rows.Err()
}

// archiveResolved hides resolved alerts that have been settled for archiveAfter.
func archiveResolved(ctx context.Context, db *sql.DB, archiveAfter time.Duration) {
	cutoff := time.Now().Add(-archiveAfter).Unix()
	res, err := db.ExecContext(ctx,
		`UPDATE alerts SET archived_at = unixepoch()
		 WHERE status = 'resolved'
		   AND archived_at IS NULL
		   AND COALESCE(ends_at, received_at) < ?`, cutoff)
	if err != nil {
		log.Printf("archiver: %v", err)
		return
	}
	if n, _ := res.RowsAffected(); n > 0 {
		log.Printf("archiver: archived %d resolved alert(s)", n)
	}
}

// archiveResolvedIncidents does the same for the work items, on the same clock.
func archiveResolvedIncidents(ctx context.Context, db *sql.DB, archiveAfter time.Duration) {
	cutoff := time.Now().Add(-archiveAfter).Unix()
	res, err := db.ExecContext(ctx,
		`UPDATE incidents SET archived_at = unixepoch()
		 WHERE resolved_at IS NOT NULL
		   AND archived_at IS NULL
		   AND resolved_at < ?`, cutoff)
	if err != nil {
		log.Printf("archiver: incidents: %v", err)
		return
	}
	if n, _ := res.RowsAffected(); n > 0 {
		log.Printf("archiver: archived %d resolved incident(s)", n)
	}
}

// placeholders builds "?, ?, …" for an IN clause of n values.
func placeholders(n int) string {
	return strings.TrimSuffix(strings.Repeat("?, ", n), ", ")
}