feat(store): drift state, move candidates and service merge (#10)

Adds services.awaiting_inventory, Service.Drifted/RunsRef/RunningRef, AcceptRunning, MoveCandidates, MergeSources and MergeService, and maps a job for a deleted service to ErrNotFound.
2026-10-13 10:28:34 +02:00
parent 307e46e4c7
commit 061243f5da
11 changed files with 1036 additions and 14 deletions
@@ -0,0 +1,249 @@
+package store
+
+import (
+	"context"
+	"errors"
+	"fmt"
+
+	"github.com/jackc/pgx/v5"
+
+	"github.com/shcizo/package-updater/internal/master/model"
+	"github.com/shcizo/package-updater/internal/protocol"
+)
+
+// moveCandidatesSQL pairs a removed Compose service with a live one of the
+// same project and service name on another agent. A pair counts only when it
+// is the single one for both rows, and the live row is new (newer than the
+// removed one, never updated, no jobs) while the removed one has something
+// worth moving (a desired ref, auto mode or jobs).
+const moveCandidatesSQL = `
+WITH pairs AS (
+	SELECT f.id AS from_id, t.id AS to_id
+	FROM services f
+	JOIN services t ON t.kind = 'compose' AND t.removed_at IS NULL AND NOT t.self
+	 AND t.compose_project = f.compose_project AND t.compose_service = f.compose_service
+	 AND t.agent_id IS DISTINCT FROM f.agent_id
+	WHERE f.kind = 'compose' AND f.removed_at IS NOT NULL AND NOT f.self
+), uniq AS (
+	SELECT from_id, to_id FROM pairs p
+	WHERE (SELECT count(*) FROM pairs q WHERE q.from_id = p.from_id) = 1
+	  AND (SELECT count(*) FROM pairs q WHERE q.to_id   = p.to_id)   = 1
+)
+SELECT u.from_id, u.to_id, COALESCE(fa.name, ''), COALESCE(ta.name, '')
+FROM uniq u
+JOIN services f ON f.id = u.from_id
+JOIN services t ON t.id = u.to_id
+LEFT JOIN agents fa ON fa.id = f.agent_id
+LEFT JOIN agents ta ON ta.id = t.agent_id
+WHERE t.first_seen_at > f.first_seen_at
+  AND t.desired_ref = ''
+  AND NOT EXISTS (SELECT 1 FROM update_jobs j WHERE j.service_id = t.id)
+  AND (f.desired_ref <> '' OR f.update_mode = 'auto'
+       OR EXISTS (SELECT 1 FROM update_jobs j WHERE j.service_id = f.id))
+ORDER BY u.to_id`
+
+// MoveCandidates returns the removed Compose services that look like they
+// moved to another agent; see model.Move. It only suggests: nothing is merged.
+func (s *Store) MoveCandidates(ctx context.Context) ([]model.Move, error) {
+	rows, err := s.pool.Query(ctx, moveCandidatesSQL)
+	if err != nil {
+		return nil, fmt.Errorf("move candidates: %w", err)
+	}
+	defer rows.Close()
+	var out []model.Move
+	for rows.Next() {
+		var m model.Move
+		if err := rows.Scan(&m.FromID, &m.ToID, &m.FromAgent, &m.ToAgent); err != nil {
+			return nil, fmt.Errorf("scan move: %w", err)
+		}
+		out = append(out, m)
+	}
+	return out, rows.Err()
+}
+
+// MergeSources returns up to 50 removed services that could be merged into
+// the service toID: the same kind (Compose or Swarm), not the updater itself,
+// those with the same name first, then the most recently removed. Returns
+// model.ErrNotFound if toID does not exist.
+func (s *Store) MergeSources(ctx context.Context, toID int64) ([]model.Service, error) {
+	to, err := s.GetService(ctx, toID)
+	if err != nil {
+		return nil, err
+	}
+	if to.Kind == protocol.KindContainer {
+		return nil, nil
+	}
+	rows, err := s.pool.Query(ctx, `
+		SELECT `+serviceColumns+`
+		FROM services s LEFT JOIN agents a ON a.id = s.agent_id
+		WHERE s.removed_at IS NOT NULL AND s.kind = $1 AND NOT s.self AND s.id <> $2
+		ORDER BY (s.compose_project, s.compose_service, s.swarm_service) = ($3, $4, $5) DESC,
+		         s.removed_at DESC, s.id DESC
+		LIMIT 50`,
+		string(to.Kind), toID, to.ComposeProject, to.ComposeService, to.SwarmService)
+	if err != nil {
+		return nil, fmt.Errorf("merge sources: %w", err)
+	}
+	defer rows.Close()
+	var out []model.Service
+	for rows.Next() {
+		m, err := scanService(rows)
+		if err != nil {
+			return nil, fmt.Errorf("scan service: %w", err)
+		}
+		out = append(out, m)
+	}
+	return out, rows.Err()
+}
+
+// mergeRow is what MergeService needs to know about one of the two rows.
+type mergeRow struct {
+	kind    string
+	agentID *int64
+	removed bool
+	self    bool
+}
+
+// MergeService moves the live service toID onto the removed service fromID:
+// the old row keeps its id, first_seen_at, update mode and desired ref, takes
+// the location and inventory of the live row (and its available suggestion),
+// becomes live, and the live row is deleted. The jobs of the live row move to
+// the old one. This is the only place a services row is deleted.
+//
+// It returns *model.MergeRefusedError when the pair cannot be merged,
+// model.ErrJobActive when either row has a queued or running job,
+// model.ErrRevoked when the live row's agent is revoked, model.ErrNotFound
+// when a row does not exist, and model.ErrConflict when the live row moved to
+// another agent while the merge started.
+//
+// Locks are taken in the order inventory writes use: the agent row first,
+// then the service rows by id. The live row is deleted before the old one is
+// updated because location_key is unique.
+func (s *Store) MergeService(ctx context.Context, fromID, toID int64) error {
+	if fromID == toID {
+		return &model.MergeRefusedError{Reason: model.ReasonMergeSame}
+	}
+	tx, err := s.pool.Begin(ctx)
+	if err != nil {
+		return fmt.Errorf("begin merge: %w", err)
+	}
+	defer func() { _ = tx.Rollback(ctx) }()
+
+	var toAgent *int64
+	err = tx.QueryRow(ctx, `SELECT agent_id FROM services WHERE id = $1`, toID).Scan(&toAgent)
+	if errors.Is(err, pgx.ErrNoRows) {
+		return model.ErrNotFound
+	}
+	if err != nil {
+		return fmt.Errorf("merge: find new service: %w", err)
+	}
+	if toAgent != nil {
+		if err := lockActiveAgent(ctx, tx, *toAgent); err != nil {
+			return err
+		}
+	}
+
+	rows, err := tx.Query(ctx, `
+		SELECT id, kind, agent_id, removed_at IS NOT NULL, self FROM services
+		WHERE id IN ($1, $2) ORDER BY id FOR UPDATE`, fromID, toID)
+	if err != nil {
+		return fmt.Errorf("merge: lock services: %w", err)
+	}
+	locked := map[int64]mergeRow{}
+	for rows.Next() {
+		var id int64
+		var r mergeRow
+		if err := rows.Scan(&id, &r.kind, &r.agentID, &r.removed, &r.self); err != nil {
+			rows.Close()
+			return fmt.Errorf("merge: scan service: %w", err)
+		}
+		locked[id] = r
+	}
+	rows.Close()
+	if err := rows.Err(); err != nil {
+		return fmt.Errorf("merge: lock services: %w", err)
+	}
+	from, okFrom := locked[fromID]
+	to, okTo := locked[toID]
+	if !okFrom || !okTo {
+		return model.ErrNotFound
+	}
+	if (to.agentID == nil) != (toAgent == nil) || (toAgent != nil && *to.agentID != *toAgent) {
+		return model.ErrConflict
+	}
+	if reason := mergeRefusal(from, to); reason != "" {
+		return &model.MergeRefusedError{Reason: reason}
+	}
+
+	var active bool
+	if err := tx.QueryRow(ctx, `
+		SELECT EXISTS (SELECT 1 FROM update_jobs
+		               WHERE service_id IN ($1, $2) AND status IN ('queued', 'running'))`,
+		fromID, toID).Scan(&active); err != nil {
+		return fmt.Errorf("merge: check active jobs: %w", err)
+	}
+	if active {
+		return model.ErrJobActive
+	}
+
+	if _, err := tx.Exec(ctx, `UPDATE update_jobs SET service_id = $1 WHERE service_id = $2`, fromID, toID); err != nil {
+		return fmt.Errorf("merge: move jobs: %w", err)
+	}
+	var t model.Service
+	var lastTagDigest string
+	err = tx.QueryRow(ctx, `
+		SELECT agent_id, location_key, compose_project, compose_service, working_dir, config_files, built,
+		       swarm_cluster_id, swarm_service, container_name, image_repo, actual_ref, actual_digest, status, self,
+		       updated_at, available_ref, available_digest, available_source, available_at, last_poll_error,
+		       last_tag_digest
+		FROM services WHERE id = $1`, toID).Scan(
+		&t.AgentID, &t.LocationKey, &t.ComposeProject, &t.ComposeService, &t.WorkingDir, &t.ConfigFiles, &t.Built,
+		&t.SwarmClusterID, &t.SwarmService, &t.ContainerName, &t.ImageRepo, &t.ActualRef, &t.ActualDigest, &t.Status, &t.Self,
+		&t.UpdatedAt, &t.AvailableRef, &t.AvailableDigest, &t.AvailableSource, &t.AvailableAt, &t.LastPollError,
+		&lastTagDigest)
+	if err != nil {
+		return fmt.Errorf("merge: read new service: %w", err)
+	}
+	if _, err := tx.Exec(ctx, `DELETE FROM services WHERE id = $1`, toID); err != nil {
+		return fmt.Errorf("merge: delete new service: %w", err)
+	}
+	if _, err := tx.Exec(ctx, `
+		UPDATE services SET
+			agent_id = $2, location_key = $3, compose_project = $4, compose_service = $5, working_dir = $6,
+			config_files = $7, built = $8, swarm_cluster_id = $9, swarm_service = $10, container_name = $11,
+			image_repo = $12, actual_ref = $13, actual_digest = $14, status = $15, self = $16, updated_at = $17,
+			available_ref = $18, available_digest = $19, available_source = $20, available_at = $21,
+			last_poll_error = $22,
+			last_tag_digest = CASE WHEN last_tag_digest <> '' THEN last_tag_digest ELSE $23 END,
+			removed_at = NULL, awaiting_inventory = false
+		WHERE id = $1`,
+		fromID, t.AgentID, t.LocationKey, t.ComposeProject, t.ComposeService, t.WorkingDir,
+		t.ConfigFiles, t.Built, t.SwarmClusterID, t.SwarmService, t.ContainerName,
+		t.ImageRepo, t.ActualRef, t.ActualDigest, t.Status, t.Self, t.UpdatedAt,
+		t.AvailableRef, t.AvailableDigest, t.AvailableSource, t.AvailableAt,
+		t.LastPollError, lastTagDigest); err != nil {
+		return fmt.Errorf("merge: update old service: %w", err)
+	}
+	if err := tx.Commit(ctx); err != nil {
+		return fmt.Errorf("commit merge: %w", err)
+	}
+	return nil
+}
+
+// mergeRefusal returns why from (the old row) cannot be merged with to (the
+// live one), or "".
+func mergeRefusal(from, to mergeRow) string {
+	switch {
+	case !from.removed:
+		return model.ReasonMergeLiveOld
+	case to.removed:
+		return model.ReasonMergeGoneNew
+	case from.kind != to.kind:
+		return model.ReasonMergeKind
+	case from.kind == string(protocol.KindContainer):
+		return model.ReasonMergeContainer
+	case from.self || to.self:
+		return model.ReasonSelf
+	}
+	return ""
+}