Files
darroyo 84b185be39 Phase A-E: stability, security, observability, and test coverage
Phase A - Stability:
- Engine.Start(): recovers orphaned jobs (running/queued/waking_up) after crash
- Engine.Stop(): graceful shutdown - cancels all in-flight jobs and waits
- Queue keyed by jobID (not syncPairID): cancel now targets exact job
- Local rsync uses jobCtx (context.Background() replaced)
- Migrations wrapped in transactions; checksums stored

Phase B - Security:
- admin/admin default removed: SYNCSERVER_ADMIN_PASSWORD required on first run
- Path validation: rejects .., leading -, null bytes in sync pair paths
- Rsync flags allowlist: dangerous flags blocked (--rsync-path, -e, --files-from)
- Shell concat in RunRemote replaced with proper sh -c escaping
- knownhosts: replaced custom parser with golang.org/x/crypto/ssh/knownhosts
- RequireAdmin wired: machine CRUD, SSH key ops, settings require admin role
- deploy-keys: uses authorized_keys only (no private key upload)
- Hardcoded /var/lib/syncserver/ssh paths replaced with cfg.SSHDir()

Phase C - Operational:
- /readyz health check: DB query + SSH dir accessibility
- /metrics endpoint: Prometheus text format (jobs, queue, machines)
- Event struct JSON tags: job_id, machine_id, type (snake_case)
- EventBus broadcast: fanned out to all subscribers
- SQLite VACUUM INTO backup: scheduled before cleanup if BackupDir set
- Filesystem job log cleanup: removes .log files for purged jobs
- Backup retention: old backups auto-purged

Phase D - Frontend:
- Schedules page: REST API + full CRUD UI for cron schedules
- Dashboard: cancel button for running/queued jobs
- JobDetail: server-side log download via API
- Settings: displays data_dir from server
- 404 page: proper NotFound component

Phase E - Tests:
- auth_test.go: JWT, bcrypt, middleware, seed (18 tests)
- models_test.go: Job, Machine, SyncPair, Schedule repos (18 tests)
- go test -race: no data races found
2026-07-19 22:14:30 -04:00

98 lines
1.8 KiB
Go

package syncengine
import (
"errors"
"sync"
)
var ErrAlreadyRunning = errors.New("job already running for this sync pair")
type Queue struct {
mu sync.Mutex
runs map[int64]*RunInfo
}
type RunInfo struct {
JobID int64
SyncPairID int64
Cancel func()
CancelledBy bool
}
func NewQueue() *Queue {
return &Queue{runs: make(map[int64]*RunInfo)}
}
func (q *Queue) Enqueue(syncPairID, jobID int64, cancelFn func()) error {
q.mu.Lock()
defer q.mu.Unlock()
if _, exists := q.runs[jobID]; exists {
return ErrAlreadyRunning
}
for _, info := range q.runs {
if info.SyncPairID == syncPairID {
return ErrAlreadyRunning
}
}
q.runs[jobID] = &RunInfo{JobID: jobID, SyncPairID: syncPairID, Cancel: cancelFn}
return nil
}
func (q *Queue) Dequeue(jobID int64) {
q.mu.Lock()
defer q.mu.Unlock()
delete(q.runs, jobID)
}
func (q *Queue) IsRunning(jobID int64) bool {
q.mu.Lock()
defer q.mu.Unlock()
_, exists := q.runs[jobID]
return exists
}
func (q *Queue) GetByPair(syncPairID int64) (jobID int64, exists bool) {
q.mu.Lock()
defer q.mu.Unlock()
for _, info := range q.runs {
if info.SyncPairID == syncPairID {
return info.JobID, true
}
}
return 0, false
}
func (q *Queue) Cancel(jobID int64, byUser bool) bool {
q.mu.Lock()
defer q.mu.Unlock()
if info, exists := q.runs[jobID]; exists && info.Cancel != nil {
info.CancelledBy = byUser
info.Cancel()
return true
}
return false
}
func (q *Queue) IsCancelledByUser(jobID int64) bool {
q.mu.Lock()
defer q.mu.Unlock()
info, exists := q.runs[jobID]
return exists && info.CancelledBy
}
func (q *Queue) RunningJobs() []int64 {
q.mu.Lock()
defer q.mu.Unlock()
ids := make([]int64, 0, len(q.runs))
for id := range q.runs {
ids = append(ids, id)
}
return ids
}
func (q *Queue) Len() int {
q.mu.Lock()
defer q.mu.Unlock()
return len(q.runs)
}