mirror of
https://github.com/lukaszraczylo/claude-mnemonic.git
synced 2026-06-05 23:03:55 +00:00
fix: bound SQLite WAL growth and prevent worker hangs (#49)
The worker's SQLite WAL could grow unbounded (observed 19MB) and wedge the DB, hanging Claude Code on every prompt. No checkpoint ever truncated the WAL (only PASSIVE auto-checkpoint, which cannot reclaim the file), the connection-scoped pragmas were set via a single Exec so only one pooled connection received them (e.g. busy_timeout=0 on the rest), and the maintenance service that would optimize/checkpoint was never wired up. - Register a sqlite3 ConnectHook driver so all pragmas (busy_timeout, journal_mode, synchronous, cache_size, foreign_keys, journal_size_limit) apply to every pooled connection; enable safe connection recycling. - Add Store.Checkpoint (TRUNCATE), checkpoint-on-Close, and a periodic size-gated checkpoint loop with configurable interval/threshold. - Wire up the previously-dead maintenance service; make trigger_maintenance actually run DB maintenance instead of only recalculating scores. - Harden the user-prompt hook to honor its deadline and fail open so a slow worker can never stall a prompt. - Add regression tests for WAL truncation, checkpoint-on-close, and per-connection pragmas.
This commit is contained in:
+145
-38
@@ -5,18 +5,80 @@ import (
|
||||
"context"
|
||||
"database/sql"
|
||||
"fmt"
|
||||
"os"
|
||||
"slices"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
sqlite_vec "github.com/asg017/sqlite-vec-go-bindings/cgo"
|
||||
_ "github.com/mattn/go-sqlite3" // Import SQLite driver with FTS5 support
|
||||
sqlite3 "github.com/mattn/go-sqlite3" // SQLite driver with FTS5 support
|
||||
"github.com/rs/zerolog/log"
|
||||
"gorm.io/driver/sqlite"
|
||||
"gorm.io/gorm"
|
||||
"gorm.io/gorm/logger"
|
||||
)
|
||||
|
||||
// driverName is the name of the custom mattn/go-sqlite3 driver registered with a
|
||||
// ConnectHook that applies ALL connection pragmas (correctness + best-effort) to EVERY
|
||||
// pooled connection at open time. The stock "sqlite3" driver has no hook, so pragmas set
|
||||
// via a single post-open Exec only reach one arbitrary pooled connection (issue #49, F6).
|
||||
const driverName = "sqlite3_mnemonic"
|
||||
|
||||
// registerDriverOnce guards driver registration so it runs exactly once per process.
|
||||
// database/sql panics with "sql: Register called twice" on a duplicate name, and NewStore
|
||||
// may be called multiple times (e.g. after a config-change reinitialization).
|
||||
var registerDriverOnce sync.Once
|
||||
|
||||
// correctnessPragmas MUST succeed on every connection: getting any of them wrong changes
|
||||
// transactional/locking semantics, not just performance. A failure here aborts the open.
|
||||
var correctnessPragmas = []string{
|
||||
"PRAGMA foreign_keys=ON",
|
||||
"PRAGMA journal_mode=WAL",
|
||||
"PRAGMA synchronous=NORMAL",
|
||||
"PRAGMA busy_timeout=5000",
|
||||
"PRAGMA cache_size=-64000",
|
||||
}
|
||||
|
||||
// bestEffortPragmas are per-connection or database-wide optimizations. A failure is logged
|
||||
// and tolerated: the connection is still correct, just less tuned. (page_size only takes
|
||||
// effect on an empty database / next VACUUM, but applying it per-connection is harmless.)
|
||||
var bestEffortPragmas = []string{
|
||||
"PRAGMA temp_store=MEMORY", // Store temp tables in memory
|
||||
"PRAGMA mmap_size=268435456", // 256MB memory-mapped I/O
|
||||
"PRAGMA page_size=4096", // 4KB pages (optimal for most systems)
|
||||
"PRAGMA wal_autocheckpoint=1000", // Auto-checkpoint (PASSIVE) every 1000 WAL frames
|
||||
"PRAGMA journal_size_limit=8388608", // Backstop: cap -wal at 8MiB (issue #49)
|
||||
}
|
||||
|
||||
// connectHook applies all pragmas to a freshly opened connection. mattn/go-sqlite3 calls
|
||||
// it at the very end of Open, after DSN params and extensions, so it is authoritative.
|
||||
func connectHook(c *sqlite3.SQLiteConn) error {
|
||||
for _, pragma := range correctnessPragmas {
|
||||
if _, err := c.Exec(pragma, nil); err != nil {
|
||||
return fmt.Errorf("apply correctness pragma %q: %w", pragma, err)
|
||||
}
|
||||
}
|
||||
for _, pragma := range bestEffortPragmas {
|
||||
if _, err := c.Exec(pragma, nil); err != nil {
|
||||
log.Warn().Str("pragma", pragma).Err(err).Msg("Failed to set pragma (non-fatal)")
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// registerDriver registers the custom driver once. sqlite_vec.Auto() registers the vec
|
||||
// extension globally via sqlite3_auto_extension, which applies to connections from any
|
||||
// sqlite3-based driver, so the new driver still gets vec + FTS5.
|
||||
func registerDriver() {
|
||||
registerDriverOnce.Do(func() {
|
||||
sql.Register(driverName, &sqlite3.SQLiteDriver{
|
||||
ConnectHook: func(c *sqlite3.SQLiteConn) error {
|
||||
return connectHook(c)
|
||||
},
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
// Store represents the GORM database connection with sqlite-vec support.
|
||||
type Store struct {
|
||||
healthCacheTime time.Time
|
||||
@@ -24,6 +86,7 @@ type Store struct {
|
||||
sqlDB *sql.DB
|
||||
metrics *PoolMetrics
|
||||
cachedHealth *HealthInfo
|
||||
path string
|
||||
healthCacheTTL time.Duration
|
||||
healthCacheMu sync.RWMutex
|
||||
}
|
||||
@@ -36,22 +99,32 @@ type Config struct {
|
||||
}
|
||||
|
||||
// NewStore creates a new Store with WAL mode enabled and sqlite-vec registered.
|
||||
// CRITICAL: WAL mode and foreign keys are enabled via pragmas for concurrent reads.
|
||||
// CRITICAL: all connection pragmas (WAL, foreign_keys, busy_timeout, etc.) are applied to
|
||||
// EVERY pooled connection via a driver ConnectHook (see registerDriver), so the pool is
|
||||
// uniformly configured and connections may be recycled safely (issue #49, F6).
|
||||
func NewStore(cfg Config) (*Store, error) {
|
||||
// 1. Register sqlite-vec extension (must be done before opening database)
|
||||
// 1. Register sqlite-vec extension (must be done before opening database).
|
||||
// sqlite_vec.Auto() uses sqlite3_auto_extension, which is global to all sqlite3-based
|
||||
// drivers, so connections from our custom driver also get the vec virtual table.
|
||||
sqlite_vec.Auto()
|
||||
|
||||
// 2. Build connection string (foreign keys enabled in DSN)
|
||||
// Use sqlite3 driver (mattn/go-sqlite3) which has FTS5 support
|
||||
// 2. Register the custom driver whose ConnectHook applies ALL pragmas to EVERY pooled
|
||||
// connection (issue #49, F6). Without this, pragmas set via a single post-open
|
||||
// sqlDB.Exec reach only one arbitrary pooled connection. The hook is authoritative.
|
||||
registerDriver()
|
||||
|
||||
// 3. Build a minimal DSN. _foreign_keys is kept as belt-and-suspenders (the hook sets
|
||||
// it too); all other pragmas are applied per-connection by the ConnectHook, so they no
|
||||
// longer need to live in the DSN.
|
||||
dsn := cfg.Path + "?_foreign_keys=ON"
|
||||
|
||||
// 3. Open raw database connection with mattn/go-sqlite3 (has FTS5 support)
|
||||
sqlDB, err := sql.Open("sqlite3", dsn)
|
||||
// 4. Open raw database connection with the custom driver (FTS5 + per-connection pragmas).
|
||||
sqlDB, err := sql.Open(driverName, dsn)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("open database: %w", err)
|
||||
}
|
||||
|
||||
// 4. Wrap with GORM using existing connection
|
||||
// 5. Wrap with GORM using existing connection
|
||||
db, err := gorm.Open(sqlite.Dialector{
|
||||
Conn: sqlDB,
|
||||
}, &gorm.Config{
|
||||
@@ -66,16 +139,25 @@ func NewStore(cfg Config) (*Store, error) {
|
||||
return nil, fmt.Errorf("open gorm: %w", err)
|
||||
}
|
||||
|
||||
// 5. Configure connection pool (same settings as current implementation)
|
||||
// 6. Configure connection pool.
|
||||
maxConns := cfg.MaxConns
|
||||
if maxConns <= 0 {
|
||||
maxConns = 4
|
||||
}
|
||||
sqlDB.SetMaxOpenConns(maxConns)
|
||||
sqlDB.SetMaxIdleConns(maxConns)
|
||||
sqlDB.SetConnMaxLifetime(0) // Never expire (SQLite connections are cheap)
|
||||
// Finite recycling (issue #49): previously SetConnMaxLifetime(0) meant connections
|
||||
// NEVER recycled, so a long-lived read connection could pin an old WAL read-mark for the
|
||||
// whole process lifetime and block TRUNCATE checkpoints from reclaiming the -wal file.
|
||||
// Recycling is safe now because the ConnectHook reapplies every correctness pragma on
|
||||
// each new connection — a recycled connection comes back fully configured, not with
|
||||
// defaults. 1h lifetime bounds read-mark staleness without churning the pool; 30m idle
|
||||
// time reclaims connections that sit unused (e.g. between sessions) so the pool shrinks
|
||||
// back to one warm connection during quiet periods, dropping their WAL read-marks.
|
||||
sqlDB.SetConnMaxLifetime(1 * time.Hour)
|
||||
sqlDB.SetConnMaxIdleTime(30 * time.Minute)
|
||||
|
||||
// 6. Verify connection
|
||||
// 7. Verify connection
|
||||
if err := sqlDB.Ping(); err != nil {
|
||||
return nil, fmt.Errorf("ping database: %w", err)
|
||||
}
|
||||
@@ -83,37 +165,18 @@ func NewStore(cfg Config) (*Store, error) {
|
||||
store := &Store{
|
||||
DB: db,
|
||||
sqlDB: sqlDB,
|
||||
path: cfg.Path,
|
||||
metrics: NewPoolMetrics(100), // Track last 100 latency samples
|
||||
healthCacheTTL: 5 * time.Second, // Cache health checks for 5 seconds
|
||||
}
|
||||
|
||||
// 7. Run migrations FIRST (before PRAGMA commands)
|
||||
// 8. Run migrations. All pragmas (correctness + best-effort) are applied per-connection
|
||||
// by the ConnectHook at open time, so there is no post-open pragma loop here anymore:
|
||||
// such a loop only ever reached one arbitrary pooled connection (issue #49, F6).
|
||||
if err := runMigrations(db, sqlDB); err != nil {
|
||||
return nil, fmt.Errorf("run migrations: %w", err)
|
||||
}
|
||||
|
||||
// 8. CRITICAL: Set WAL mode and other performance pragmas
|
||||
// Use raw sqlDB to avoid GORM transaction issues
|
||||
pragmas := []string{
|
||||
"PRAGMA journal_mode=WAL",
|
||||
"PRAGMA synchronous=NORMAL",
|
||||
"PRAGMA cache_size=-64000", // 64MB cache (negative = KB)
|
||||
"PRAGMA temp_store=MEMORY", // Store temp tables in memory
|
||||
"PRAGMA mmap_size=268435456", // 256MB memory-mapped I/O
|
||||
"PRAGMA page_size=4096", // 4KB pages (optimal for most systems)
|
||||
"PRAGMA wal_autocheckpoint=1000", // Explicit default; checkpoint every 1000 WAL frames
|
||||
}
|
||||
for _, pragma := range pragmas {
|
||||
if _, err := sqlDB.Exec(pragma); err != nil {
|
||||
log.Warn().Str("pragma", pragma).Err(err).Msg("Failed to set pragma (non-fatal)")
|
||||
}
|
||||
}
|
||||
// Set busy timeout to 5 seconds to handle concurrent writes
|
||||
// This allows SQLite to retry when database is locked instead of failing immediately
|
||||
if _, err := sqlDB.Exec("PRAGMA busy_timeout=5000"); err != nil {
|
||||
return nil, fmt.Errorf("set busy timeout: %w", err)
|
||||
}
|
||||
|
||||
// 9. Warm the connection pool
|
||||
store.WarmPool(maxConns)
|
||||
|
||||
@@ -148,11 +211,55 @@ func (s *Store) WarmPool(numConns int) {
|
||||
log.Debug().Int("connections", numConns).Msg("Connection pool warmed")
|
||||
}
|
||||
|
||||
// Close closes the database connection.
|
||||
// Close checkpoints the WAL (TRUNCATE) before closing the connection. Checkpointing on
|
||||
// shutdown prevents the WAL file from persisting in a large, dirty state across restarts
|
||||
// and config-change reinitializations, which otherwise leaves a multi-megabyte -wal file
|
||||
// on disk (issue #49). The checkpoint is best-effort: a failure is logged, not fatal.
|
||||
func (s *Store) Close() error {
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
|
||||
defer cancel()
|
||||
if err := s.Checkpoint(ctx); err != nil {
|
||||
log.Warn().Err(err).Msg("WAL checkpoint on close failed (non-fatal)")
|
||||
}
|
||||
return s.sqlDB.Close()
|
||||
}
|
||||
|
||||
// Checkpoint runs a TRUNCATE WAL checkpoint: it flushes WAL frames into the main
|
||||
// database file and shrinks the -wal file back to zero. Unlike a PASSIVE checkpoint
|
||||
// (which never truncates the file and is all SQLite's auto-checkpoint ever performs), a
|
||||
// TRUNCATE checkpoint reclaims disk and is the mechanism that bounds WAL growth.
|
||||
// It waits up to the connection busy_timeout for the write lock and returns an error
|
||||
// rather than blocking indefinitely.
|
||||
func (s *Store) Checkpoint(ctx context.Context) error {
|
||||
if _, err := s.sqlDB.ExecContext(ctx, "PRAGMA wal_checkpoint(TRUNCATE)"); err != nil {
|
||||
return fmt.Errorf("wal checkpoint (truncate): %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// WALSize returns the size in bytes of the SQLite WAL sidecar file (<db>-wal), or 0 if
|
||||
// it does not exist or cannot be stat'd. Used to decide when a checkpoint is worthwhile.
|
||||
func (s *Store) WALSize() int64 {
|
||||
if s.path == "" {
|
||||
return 0
|
||||
}
|
||||
info, err := os.Stat(s.path + "-wal")
|
||||
if err != nil {
|
||||
return 0
|
||||
}
|
||||
return info.Size()
|
||||
}
|
||||
|
||||
// CheckpointIfLarge performs a TRUNCATE checkpoint only when the WAL file has grown to or
|
||||
// beyond threshold bytes. Returns true if a checkpoint was performed. This keeps the
|
||||
// periodic checkpoint cheap: it does no work while the WAL is small.
|
||||
func (s *Store) CheckpointIfLarge(ctx context.Context, threshold int64) (bool, error) {
|
||||
if s.WALSize() < threshold {
|
||||
return false, nil
|
||||
}
|
||||
return true, s.Checkpoint(ctx)
|
||||
}
|
||||
|
||||
// Ping verifies the database connection is alive.
|
||||
func (s *Store) Ping() error {
|
||||
return s.sqlDB.Ping()
|
||||
@@ -193,8 +300,9 @@ func (s *Store) Optimize(ctx context.Context) error {
|
||||
log.Warn().Err(err).Msg("PRAGMA optimize failed (non-fatal)")
|
||||
}
|
||||
|
||||
// Passive WAL checkpoint — doesn't block readers/writers
|
||||
if _, err := s.sqlDB.ExecContext(ctx, "PRAGMA wal_checkpoint(PASSIVE)"); err != nil {
|
||||
// TRUNCATE WAL checkpoint — reclaims the -wal file during low-activity optimization.
|
||||
// (PASSIVE never shrinks the file, so it cannot bound WAL growth — see issue #49.)
|
||||
if err := s.Checkpoint(ctx); err != nil {
|
||||
log.Warn().Err(err).Msg("WAL checkpoint failed (non-fatal)")
|
||||
}
|
||||
|
||||
@@ -519,7 +627,6 @@ func (s *Store) ExecWithTimeout(ctx context.Context, timeout time.Duration, quer
|
||||
return nil
|
||||
}
|
||||
|
||||
|
||||
// TransactionWithTimeout wraps a transaction function with timeout handling.
|
||||
// The transaction is automatically rolled back if the context times out.
|
||||
func (s *Store) TransactionWithTimeout(ctx context.Context, timeout time.Duration, fn func(*gorm.DB) error) error {
|
||||
|
||||
@@ -5,9 +5,12 @@ package gorm
|
||||
|
||||
import (
|
||||
"context"
|
||||
"database/sql"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"gorm.io/gorm/logger"
|
||||
)
|
||||
@@ -239,3 +242,321 @@ func TestOptimize_RespectsContextCancellation(t *testing.T) {
|
||||
t.Error("expected error with cancelled context, got nil")
|
||||
}
|
||||
}
|
||||
|
||||
// growWAL inserts sizeable rows to push the SQLite WAL well past a few hundred KB so
|
||||
// checkpoint behaviour can be observed. Returns the WAL file size after the inserts.
|
||||
func growWAL(t *testing.T, store *Store, rows int) int64 {
|
||||
t.Helper()
|
||||
bigTitle := strings.Repeat("x", 2048)
|
||||
for i := 0; i < rows; i++ {
|
||||
_, err := store.GetRawDB().Exec(
|
||||
"INSERT INTO observations (sdk_session_id, title, scope, project, type, created_at, created_at_epoch) "+
|
||||
"VALUES (?, ?, 'project', '/tmp/test', 'decision', '2026-01-01T00:00:00Z', 1735689600)",
|
||||
"sess", bigTitle)
|
||||
if err != nil {
|
||||
t.Fatalf("insert row %d: %v", i, err)
|
||||
}
|
||||
}
|
||||
return store.WALSize()
|
||||
}
|
||||
|
||||
func countObservations(t *testing.T, store *Store) int64 {
|
||||
t.Helper()
|
||||
var n int64
|
||||
if err := store.GetRawDB().QueryRow("SELECT COUNT(*) FROM observations").Scan(&n); err != nil {
|
||||
t.Fatalf("count observations: %v", err)
|
||||
}
|
||||
return n
|
||||
}
|
||||
|
||||
// TestCheckpoint_TruncateShrinksWAL verifies Checkpoint() performs a TRUNCATE checkpoint
|
||||
// that actually reclaims the -wal file. This is the load-bearing fix for issue #49: a
|
||||
// PASSIVE checkpoint drains frames but never shrinks the file, so reverting Checkpoint to
|
||||
// PASSIVE would leave the WAL grown and fail this test.
|
||||
func TestCheckpoint_TruncateShrinksWAL(t *testing.T) {
|
||||
tmpDir, err := os.MkdirTemp("", "gorm_checkpoint_truncate_*")
|
||||
if err != nil {
|
||||
t.Fatalf("create temp dir: %v", err)
|
||||
}
|
||||
defer os.RemoveAll(tmpDir)
|
||||
|
||||
dbPath := filepath.Join(tmpDir, "test.db")
|
||||
store, err := NewStore(Config{Path: dbPath, MaxConns: 2, LogLevel: logger.Silent})
|
||||
if err != nil {
|
||||
t.Fatalf("NewStore failed: %v", err)
|
||||
}
|
||||
defer store.Close()
|
||||
|
||||
walBefore := growWAL(t, store, 1000)
|
||||
if walBefore < 64*1024 {
|
||||
t.Fatalf("expected WAL to grow above 64KiB, got %d bytes", walBefore)
|
||||
}
|
||||
|
||||
if err := store.Checkpoint(context.Background()); err != nil {
|
||||
t.Fatalf("Checkpoint failed: %v", err)
|
||||
}
|
||||
|
||||
walAfter := store.WALSize()
|
||||
if walAfter >= walBefore {
|
||||
t.Errorf("expected WAL to shrink after TRUNCATE checkpoint: before=%d after=%d", walBefore, walAfter)
|
||||
}
|
||||
if walAfter > 64*1024 {
|
||||
t.Errorf("expected WAL truncated to near-zero, got %d bytes", walAfter)
|
||||
}
|
||||
}
|
||||
|
||||
// TestCheckpointIfLarge_GatesOnThreshold verifies the size-gated periodic checkpoint used
|
||||
// by the worker's walCheckpointLoop: a no-op below the threshold, a truncating checkpoint
|
||||
// at/above it.
|
||||
func TestCheckpointIfLarge_GatesOnThreshold(t *testing.T) {
|
||||
tmpDir, err := os.MkdirTemp("", "gorm_checkpoint_gated_*")
|
||||
if err != nil {
|
||||
t.Fatalf("create temp dir: %v", err)
|
||||
}
|
||||
defer os.RemoveAll(tmpDir)
|
||||
|
||||
dbPath := filepath.Join(tmpDir, "test.db")
|
||||
store, err := NewStore(Config{Path: dbPath, MaxConns: 2, LogLevel: logger.Silent})
|
||||
if err != nil {
|
||||
t.Fatalf("NewStore failed: %v", err)
|
||||
}
|
||||
defer store.Close()
|
||||
|
||||
// Below an enormous threshold -> no checkpoint.
|
||||
done, err := store.CheckpointIfLarge(context.Background(), 1<<30) // 1 GiB
|
||||
if err != nil {
|
||||
t.Fatalf("CheckpointIfLarge (small) failed: %v", err)
|
||||
}
|
||||
if done {
|
||||
t.Errorf("expected no checkpoint below threshold, but one was performed")
|
||||
}
|
||||
|
||||
// Grow the WAL, then a low threshold triggers a truncating checkpoint.
|
||||
walBefore := growWAL(t, store, 1000)
|
||||
if walBefore < 64*1024 {
|
||||
t.Fatalf("expected WAL to grow above 64KiB, got %d bytes", walBefore)
|
||||
}
|
||||
|
||||
done, err = store.CheckpointIfLarge(context.Background(), 64*1024)
|
||||
if err != nil {
|
||||
t.Fatalf("CheckpointIfLarge (large) failed: %v", err)
|
||||
}
|
||||
if !done {
|
||||
t.Errorf("expected checkpoint above threshold, but none was performed")
|
||||
}
|
||||
if walAfter := store.WALSize(); walAfter >= walBefore {
|
||||
t.Errorf("expected WAL to shrink after gated checkpoint: before=%d after=%d", walBefore, walAfter)
|
||||
}
|
||||
}
|
||||
|
||||
// TestClose_CheckpointsWAL verifies Close() reclaims the WAL and leaves the data intact on
|
||||
// the next open (issue #49: shutdown must not leave a large dirty WAL on disk).
|
||||
func TestClose_CheckpointsWAL(t *testing.T) {
|
||||
tmpDir, err := os.MkdirTemp("", "gorm_close_checkpoint_*")
|
||||
if err != nil {
|
||||
t.Fatalf("create temp dir: %v", err)
|
||||
}
|
||||
defer os.RemoveAll(tmpDir)
|
||||
|
||||
dbPath := filepath.Join(tmpDir, "test.db")
|
||||
store, err := NewStore(Config{Path: dbPath, MaxConns: 2, LogLevel: logger.Silent})
|
||||
if err != nil {
|
||||
t.Fatalf("NewStore failed: %v", err)
|
||||
}
|
||||
|
||||
if walBefore := growWAL(t, store, 800); walBefore == 0 {
|
||||
t.Fatalf("expected WAL to grow before close, got 0")
|
||||
}
|
||||
count := countObservations(t, store)
|
||||
if count < 800 {
|
||||
t.Fatalf("expected >=800 observations before close, got %d", count)
|
||||
}
|
||||
|
||||
if err := store.Close(); err != nil {
|
||||
t.Fatalf("Close failed: %v", err)
|
||||
}
|
||||
|
||||
// The -wal file must not persist large on disk after a clean shutdown.
|
||||
if info, statErr := os.Stat(dbPath + "-wal"); statErr == nil && info.Size() > 64*1024 {
|
||||
t.Errorf("expected WAL reclaimed on close, -wal still %d bytes", info.Size())
|
||||
}
|
||||
|
||||
// Reopen and verify data survived the checkpoint.
|
||||
store2, err := NewStore(Config{Path: dbPath, MaxConns: 2, LogLevel: logger.Silent})
|
||||
if err != nil {
|
||||
t.Fatalf("reopen NewStore failed: %v", err)
|
||||
}
|
||||
defer store2.Close()
|
||||
|
||||
if count2 := countObservations(t, store2); count2 != count {
|
||||
t.Errorf("expected %d observations after reopen, got %d", count, count2)
|
||||
}
|
||||
}
|
||||
|
||||
// TestBusyTimeoutAppliedToAllConnections verifies the issue #49 DSN fix: busy_timeout is
|
||||
// applied to EVERY pooled connection (not just one arbitrary connection as happened when
|
||||
// it was set via a single post-open sqlDB.Exec).
|
||||
func TestBusyTimeoutAppliedToAllConnections(t *testing.T) {
|
||||
tmpDir, err := os.MkdirTemp("", "gorm_busy_timeout_*")
|
||||
if err != nil {
|
||||
t.Fatalf("create temp dir: %v", err)
|
||||
}
|
||||
defer os.RemoveAll(tmpDir)
|
||||
|
||||
dbPath := filepath.Join(tmpDir, "test.db")
|
||||
const maxConns = 4
|
||||
store, err := NewStore(Config{Path: dbPath, MaxConns: maxConns, LogLevel: logger.Silent})
|
||||
if err != nil {
|
||||
t.Fatalf("NewStore failed: %v", err)
|
||||
}
|
||||
defer store.Close()
|
||||
|
||||
// Pin all connections concurrently so each distinct connection is inspected, then
|
||||
// assert every one reports busy_timeout=5000.
|
||||
raw := store.GetRawDB()
|
||||
conns := make([]*sql.Conn, 0, maxConns)
|
||||
defer func() {
|
||||
for _, c := range conns {
|
||||
_ = c.Close()
|
||||
}
|
||||
}()
|
||||
for i := 0; i < maxConns; i++ {
|
||||
c, err := raw.Conn(context.Background())
|
||||
if err != nil {
|
||||
t.Fatalf("acquire conn %d: %v", i, err)
|
||||
}
|
||||
conns = append(conns, c)
|
||||
}
|
||||
for i, c := range conns {
|
||||
var timeout int
|
||||
if err := c.QueryRowContext(context.Background(), "PRAGMA busy_timeout").Scan(&timeout); err != nil {
|
||||
t.Fatalf("query busy_timeout on conn %d: %v", i, err)
|
||||
}
|
||||
if timeout != 5000 {
|
||||
t.Errorf("conn %d: expected busy_timeout=5000, got %d", i, timeout)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestAllPragmasAppliedToAllConnections verifies the issue #49 (F6) ConnectHook fix: not
|
||||
// just busy_timeout but the full pragma set — including the best-effort pragmas that used
|
||||
// to be set via a single post-open sqlDB.Exec (journal_size_limit, temp_store,
|
||||
// wal_autocheckpoint) — is applied to EVERY pooled connection. It pins all connections so
|
||||
// each distinct connection is inspected, then asserts each reports the expected value.
|
||||
func TestAllPragmasAppliedToAllConnections(t *testing.T) {
|
||||
tmpDir, err := os.MkdirTemp("", "gorm_all_pragmas_*")
|
||||
if err != nil {
|
||||
t.Fatalf("create temp dir: %v", err)
|
||||
}
|
||||
defer os.RemoveAll(tmpDir)
|
||||
|
||||
dbPath := filepath.Join(tmpDir, "test.db")
|
||||
const maxConns = 4
|
||||
store, err := NewStore(Config{Path: dbPath, MaxConns: maxConns, LogLevel: logger.Silent})
|
||||
if err != nil {
|
||||
t.Fatalf("NewStore failed: %v", err)
|
||||
}
|
||||
defer store.Close()
|
||||
|
||||
// Expected per-connection pragma values. temp_store=MEMORY reports as 2; the others are
|
||||
// numeric. foreign_keys/journal_mode/synchronous are covered by TestNewStore and the
|
||||
// busy_timeout test; here we focus on the previously single-connection pragmas.
|
||||
checks := []struct {
|
||||
name string
|
||||
want int64
|
||||
}{
|
||||
{"busy_timeout", 5000},
|
||||
{"journal_size_limit", 8388608},
|
||||
{"temp_store", 2}, // 2 == MEMORY
|
||||
{"wal_autocheckpoint", 1000},
|
||||
{"foreign_keys", 1},
|
||||
}
|
||||
|
||||
raw := store.GetRawDB()
|
||||
conns := make([]*sql.Conn, 0, maxConns)
|
||||
defer func() {
|
||||
for _, c := range conns {
|
||||
_ = c.Close()
|
||||
}
|
||||
}()
|
||||
for i := 0; i < maxConns; i++ {
|
||||
c, err := raw.Conn(context.Background())
|
||||
if err != nil {
|
||||
t.Fatalf("acquire conn %d: %v", i, err)
|
||||
}
|
||||
conns = append(conns, c)
|
||||
}
|
||||
|
||||
for i, c := range conns {
|
||||
for _, chk := range checks {
|
||||
var got int64
|
||||
query := "PRAGMA " + chk.name
|
||||
if err := c.QueryRowContext(context.Background(), query).Scan(&got); err != nil {
|
||||
t.Fatalf("conn %d: query %q: %v", i, chk.name, err)
|
||||
}
|
||||
if got != chk.want {
|
||||
t.Errorf("conn %d: %s = %d, want %d", i, chk.name, got, chk.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestRecycledConnectionRetainsPragmas verifies that recycling a connection (which now
|
||||
// happens because SetConnMaxLifetime is finite, not 0) does NOT drop the correctness
|
||||
// pragmas: the ConnectHook reapplies them on every new connection. We force recycling by
|
||||
// setting a near-zero max lifetime so the next acquisition opens a fresh connection, then
|
||||
// assert the new connection still reports the safe values rather than SQLite defaults
|
||||
// (busy_timeout would default to 0 and journal_mode to "delete" without the hook).
|
||||
func TestRecycledConnectionRetainsPragmas(t *testing.T) {
|
||||
tmpDir, err := os.MkdirTemp("", "gorm_recycle_pragmas_*")
|
||||
if err != nil {
|
||||
t.Fatalf("create temp dir: %v", err)
|
||||
}
|
||||
defer os.RemoveAll(tmpDir)
|
||||
|
||||
dbPath := filepath.Join(tmpDir, "test.db")
|
||||
store, err := NewStore(Config{Path: dbPath, MaxConns: 2, LogLevel: logger.Silent})
|
||||
if err != nil {
|
||||
t.Fatalf("NewStore failed: %v", err)
|
||||
}
|
||||
defer store.Close()
|
||||
|
||||
raw := store.GetRawDB()
|
||||
|
||||
// Force aggressive recycling: any connection older than 1ns is expired on next use, so
|
||||
// database/sql opens a brand-new connection (running the ConnectHook again).
|
||||
raw.SetConnMaxLifetime(time.Nanosecond)
|
||||
time.Sleep(5 * time.Millisecond)
|
||||
|
||||
// Acquire a connection that is necessarily freshly opened (all prior ones are expired),
|
||||
// and verify the hook reapplied the correctness pragmas.
|
||||
conn, err := raw.Conn(context.Background())
|
||||
if err != nil {
|
||||
t.Fatalf("acquire recycled conn: %v", err)
|
||||
}
|
||||
defer conn.Close()
|
||||
|
||||
var busyTimeout int
|
||||
if err := conn.QueryRowContext(context.Background(), "PRAGMA busy_timeout").Scan(&busyTimeout); err != nil {
|
||||
t.Fatalf("query busy_timeout: %v", err)
|
||||
}
|
||||
if busyTimeout != 5000 {
|
||||
t.Errorf("recycled conn: busy_timeout = %d, want 5000 (hook did not reapply)", busyTimeout)
|
||||
}
|
||||
|
||||
var journalMode string
|
||||
if err := conn.QueryRowContext(context.Background(), "PRAGMA journal_mode").Scan(&journalMode); err != nil {
|
||||
t.Fatalf("query journal_mode: %v", err)
|
||||
}
|
||||
if journalMode != "wal" {
|
||||
t.Errorf("recycled conn: journal_mode = %q, want \"wal\" (hook did not reapply)", journalMode)
|
||||
}
|
||||
|
||||
var foreignKeys int
|
||||
if err := conn.QueryRowContext(context.Background(), "PRAGMA foreign_keys").Scan(&foreignKeys); err != nil {
|
||||
t.Fatalf("query foreign_keys: %v", err)
|
||||
}
|
||||
if foreignKeys != 1 {
|
||||
t.Errorf("recycled conn: foreign_keys = %d, want 1 (hook did not reapply)", foreignKeys)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user