mirror of
https://github.com/laoxong/nofx.git
synced 2026-06-04 01:48:22 +08:00
Lawrence Liu
8107667796
* fix(database): prevent data loss on Docker restart with WAL mode and graceful shutdown Fixes #816 ## Problem Exchange API keys and private keys were being lost after `docker compose restart`. This P0 bug posed critical security and operational risks. ### Root Cause 1. **SQLite journal_mode=delete**: Traditional rollback journal doesn't protect against data loss during non-graceful shutdowns 2. **Incomplete graceful shutdown**: Application relied on `defer database.Close()` which may not execute before process termination 3. **Docker grace period**: Default 10s may not be sufficient for cleanup ### Data Loss Scenario ``` User updates exchange config → Backend writes to SQLite → Data in buffer (not fsynced) → Docker restart (SIGTERM) → App exits → SQLite never flushes → Data lost ``` ## Solution ### 1. Enable WAL Mode (Primary Fix) - **Before**: `journal_mode=delete` (rollback journal) - **After**: `journal_mode=WAL` (Write-Ahead Logging) **Benefits:** - ✅ Crash-safe even during power loss - ✅ Better concurrent write performance - ✅ Atomic commits with durability guarantees ### 2. Improve Graceful Shutdown **Before:** ```go <-sigChan traderManager.StopAll() // defer database.Close() may not execute in time ``` **After:** ```go <-sigChan traderManager.StopAll() // Step 1: Stop traders server.Shutdown() // Step 2: Stop HTTP server (new) database.Close() // Step 3: Explicit database close (new) ``` ### 3. Increase Docker Grace Period ```yaml stop_grace_period: 30s # Allow 30s for graceful shutdown ``` ## Changes ### config/database.go - Enable `PRAGMA journal_mode=WAL` on database initialization - Set `PRAGMA synchronous=FULL` for data durability - Add log message confirming WAL mode activation ### api/server.go - Add `httpServer *http.Server` field to Server struct - Implement `Shutdown()` method with 5s timeout - Replace `router.Run()` with `httpServer.ListenAndServe()` for graceful shutdown support - Add `context` import for shutdown context ### main.go - Add explicit shutdown sequence: 1. Stop all traders 2. Shutdown HTTP server (new) 3. Close database connection (new) - Add detailed logging for each shutdown step ### docker-compose.yml - Add `stop_grace_period: 30s` to backend service ### config/database_test.go (TDD) - `TestWALModeEnabled`: Verify WAL mode is active - `TestSynchronousMode`: Verify synchronous=FULL setting - `TestDataPersistenceAcrossReopen`: Simulate Docker restart scenario - `TestConcurrentWritesWithWAL`: Verify concurrent write handling ## Test Results ```bash $ go test -v ./config === RUN TestWALModeEnabled --- PASS: TestWALModeEnabled (0.25s) === RUN TestSynchronousMode --- PASS: TestSynchronousMode (0.06s) === RUN TestDataPersistenceAcrossReopen --- PASS: TestDataPersistenceAcrossReopen (0.05s) === RUN TestConcurrentWritesWithWAL --- PASS: TestConcurrentWritesWithWAL (0.09s) PASS ``` All 16 tests pass (including 9 existing + 4 new WAL tests + 3 concurrent tests). ## Impact **Before:** - 🔴 Exchange credentials lost on restart - 🔴 Trading operations disrupted - 🔴 Security risk from credential re-entry **After:** - ✅ Data persistence guaranteed - ✅ No credential loss after restart - ✅ Safe graceful shutdown in all scenarios - ✅ Better concurrent performance ## Acceptance Criteria - [x] WAL mode enabled in database initialization - [x] Graceful shutdown explicitly closes database - [x] Unit tests verify data persistence across restarts - [x] Docker grace period increased to 30s - [x] All tests pass ## Deployment Notes After deploying this fix: 1. Rebuild Docker image: `./start.sh start --build` 2. Existing `config.db` will be automatically converted to WAL mode 3. WAL files (`config.db-wal`, `config.db-shm`) will be created 4. No manual intervention required ## References - SQLite WAL Mode: https://www.sqlite.org/wal.html - Go http.Server Graceful Shutdown: https://pkg.go.dev/net/http#Server.Shutdown * Add config.db* to gitignore
56 lines
1.7 KiB
YAML
56 lines
1.7 KiB
YAML
services:
|
||
# Backend service (API and core logic)
|
||
nofx:
|
||
build:
|
||
context: .
|
||
dockerfile: ./docker/Dockerfile.backend
|
||
container_name: nofx-trading
|
||
restart: unless-stopped
|
||
stop_grace_period: 30s # 允许应用有 30 秒时间优雅关闭
|
||
ports:
|
||
- "${NOFX_BACKEND_PORT:-8080}:8080"
|
||
volumes:
|
||
- ./config.json:/app/config.json:ro
|
||
- ./config.db:/app/config.db
|
||
- ./beta_codes.txt:/app/beta_codes.txt:ro
|
||
- ./decision_logs:/app/decision_logs
|
||
- ./prompts:/app/prompts
|
||
- ./secrets:/app/secrets:ro # RSA密钥文件
|
||
- /etc/localtime:/etc/localtime:ro # Sync host time
|
||
environment:
|
||
- TZ=${NOFX_TIMEZONE:-Asia/Shanghai} # Set timezone
|
||
- AI_MAX_TOKENS=4000 # AI响应的最大token数（默认2000，建议4000-8000）
|
||
- DATA_ENCRYPTION_KEY=${DATA_ENCRYPTION_KEY} # 数据库加密密钥
|
||
- JWT_SECRET=${JWT_SECRET} # JWT认证密钥
|
||
networks:
|
||
- nofx-network
|
||
healthcheck:
|
||
test: ["CMD", "curl", "-f", "http://localhost:8080/api/health"]
|
||
interval: 30s
|
||
timeout: 10s
|
||
retries: 3
|
||
start_period: 60s
|
||
|
||
# Frontend service (static serving and proxy)
|
||
nofx-frontend:
|
||
build:
|
||
context: .
|
||
dockerfile: ./docker/Dockerfile.frontend
|
||
container_name: nofx-frontend
|
||
restart: unless-stopped
|
||
ports:
|
||
- "${NOFX_FRONTEND_PORT:-3000}:80"
|
||
networks:
|
||
- nofx-network
|
||
depends_on:
|
||
- nofx
|
||
healthcheck:
|
||
test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost/health"]
|
||
interval: 30s
|
||
timeout: 10s
|
||
retries: 3
|
||
start_period: 5s
|
||
|
||
networks:
|
||
nofx-network:
|
||
driver: bridge |