lerko
8b39d4c1a1
Every check spawned `go e.db.Save*(...)` with the error discarded: a fire-and-forget goroutine per log line, check, state change, and alert health update. SaveLog ran a full-table prune DELETE on every insert and SaveCheck a COUNT + conditional prune on every check, so the hot path amplified each write into several statements. Nothing tracked these goroutines, so at shutdown they raced the store's Close() — writes to a closing DB, silently swallowed. Introduce a single writer goroutine that drains a buffered channel of typed dbWrite values (log/check/state-change/alert-health). Writes are enqueued non-blocking; a saturated queue drops and notes it in the in-memory log rather than blocking the check loop. Write errors are now logged instead of discarded. Retention moves off the hot path: SaveLog and SaveCheck become plain INSERTs, and PruneLogs/PruneCheckHistory/ PruneStateChanges run on a 10-minute timer inside the writer (single keep-newest-N-per-site pass via a window function). state_changes was previously never pruned — now bounded. Add Engine.Stop(): cancels the engine's context, then waits for the writer to drain every buffered write before returning. main wires it in before the deferred store Close() so no write races a closed DB. SQLite gains busy_timeout=5000 and synchronous=NORMAL, applied via the DSN so every pooled connection inherits them (a post-open PRAGMA only touches one connection); WAL moves to the DSN too. :memory: test DBs are left as-is. Tests: writer drains on Stop, Stop is idempotent, and the prune queries keep newest-N per site / N logs on real SQLite. Full suite green under -race.
86 lines
2.6 KiB
Go
86 lines
2.6 KiB
Go
package store
|
|
|
|
import (
|
|
"time"
|
|
|
|
"gitea.lerkolabs.com/lerkolabs/uptop/internal/models"
|
|
)
|
|
|
|
type Store interface {
|
|
Init() error
|
|
|
|
// Sites
|
|
GetSites() ([]models.Site, error)
|
|
AddSite(site models.Site) error
|
|
UpdateSite(site models.Site) error
|
|
UpdateSitePaused(id int, paused bool) error
|
|
DeleteSite(id int) error
|
|
|
|
// Alerts
|
|
GetAllAlerts() ([]models.AlertConfig, error)
|
|
GetAlert(id int) (models.AlertConfig, error)
|
|
AddAlert(name, aType string, settings map[string]string) error
|
|
UpdateAlert(id int, name, aType string, settings map[string]string) error
|
|
DeleteAlert(id int) error
|
|
|
|
// Declarative config support
|
|
GetSiteByName(name string) (models.Site, error)
|
|
GetAlertByName(name string) (models.AlertConfig, error)
|
|
AddSiteReturningID(site models.Site) (int, error)
|
|
AddAlertReturningID(name, aType string, settings map[string]string) (int, error)
|
|
|
|
// Users
|
|
GetAllUsers() ([]models.User, error)
|
|
AddUser(username, publicKey, role string) error
|
|
UpdateUser(id int, username, publicKey, role string) error
|
|
DeleteUser(id int) error
|
|
|
|
// History
|
|
SaveCheck(siteID int, latencyNs int64, isUp bool) error
|
|
SaveCheckFromNode(siteID int, nodeID string, latencyNs int64, isUp bool) error
|
|
LoadAllHistory(limit int) (map[int][]models.CheckRecord, error)
|
|
PruneCheckHistory() error
|
|
|
|
// State Changes
|
|
SaveStateChange(siteID int, fromStatus, toStatus, errorReason string) error
|
|
GetStateChanges(siteID int, limit int) ([]models.StateChange, error)
|
|
GetStateChangesSince(siteID int, since time.Time) ([]models.StateChange, error)
|
|
PruneStateChanges() error
|
|
|
|
// Nodes
|
|
RegisterNode(node models.ProbeNode) error
|
|
GetNode(id string) (models.ProbeNode, error)
|
|
GetAllNodes() ([]models.ProbeNode, error)
|
|
UpdateNodeLastSeen(id string) error
|
|
DeleteNode(id string) error
|
|
|
|
// Alert Health
|
|
LoadAlertHealth() (map[int]models.AlertHealthRecord, error)
|
|
SaveAlertHealth(h models.AlertHealthRecord) error
|
|
|
|
// Logs
|
|
SaveLog(message string) error
|
|
LoadLogs(limit int) ([]string, error)
|
|
PruneLogs() error
|
|
|
|
// Maintenance Windows
|
|
GetActiveMaintenanceWindows() ([]models.MaintenanceWindow, error)
|
|
GetAllMaintenanceWindows(limit int) ([]models.MaintenanceWindow, error)
|
|
AddMaintenanceWindow(mw models.MaintenanceWindow) error
|
|
EndMaintenanceWindow(id int) error
|
|
DeleteMaintenanceWindow(id int) error
|
|
PruneExpiredMaintenanceWindows(retention time.Duration) (int64, error)
|
|
IsMonitorInMaintenance(monitorID int) (bool, error)
|
|
|
|
// Preferences
|
|
GetPreference(key string) (string, error)
|
|
SetPreference(key, value string) error
|
|
|
|
// Backup & Restore
|
|
ExportData() (models.Backup, error)
|
|
ImportData(data models.Backup) error
|
|
|
|
// Lifecycle
|
|
Close() error
|
|
}
|