Database Migrations

-- GOOD: Nullable column, no lock
ALTER TABLE users ADD COLUMN avatar_url TEXT;

-- GOOD: Column with default (Postgres 11+ is instant, no rewrite)
ALTER TABLE users ADD COLUMN is_active BOOLEAN NOT NULL DEFAULT true;

-- BAD: NOT NULL without default on existing table (requires full rewrite)
ALTER TABLE users ADD COLUMN role TEXT NOT NULL;
-- This locks the table and rewrites every row

-- BAD: Blocks writes on large tables
CREATE INDEX idx_users_email ON users (email);

-- GOOD: Non-blocking, allows concurrent writes
CREATE INDEX CONCURRENTLY idx_users_email ON users (email);

-- Note: CONCURRENTLY cannot run inside a transaction block
-- Most migration tools need special handling for this

-- Step 1: Add new column (migration 001)
ALTER TABLE users ADD COLUMN display_name TEXT;

-- Step 2: Backfill data (migration 002, data migration)
UPDATE users SET display_name = username WHERE display_name IS NULL;

-- Step 3: Update application code to read/write both columns
-- Deploy application changes

-- Step 4: Stop writing to old column, drop it (migration 003)
ALTER TABLE users DROP COLUMN username;

-- Step 1: Remove all application references to the column
-- Step 2: Deploy application without the column reference
-- Step 3: Drop column in next migration
ALTER TABLE orders DROP COLUMN legacy_status;

-- For Django: use SeparateDatabaseAndState to remove from model
-- without generating DROP COLUMN (then drop in next migration)

-- BAD: Updates all rows in one transaction (locks table)
UPDATE users SET normalized_email = LOWER(email);

-- GOOD: Batch update with progress
DO $$
DECLARE
  batch_size INT := 10000;
  rows_updated INT;
BEGIN
  LOOP
    UPDATE users
    SET normalized_email = LOWER(email)
    WHERE id IN (
      SELECT id FROM users
      WHERE normalized_email IS NULL
      LIMIT batch_size
      FOR UPDATE SKIP LOCKED
    );
    GET DIAGNOSTICS rows_updated = ROW_COUNT;
    RAISE NOTICE 'Updated % rows', rows_updated;
    EXIT WHEN rows_updated = 0;
    COMMIT;
  END LOOP;
END $$;

# Create migration from schema changes
npx prisma migrate dev --name add_user_avatar

# Apply pending migrations in production
npx prisma migrate deploy

# Reset database (dev only)
npx prisma migrate reset

# Generate client after schema changes
npx prisma generate

model User {
  id        String   @id @default(cuid())
  email     String   @unique
  name      String?
  avatarUrl String?  @map("avatar_url")
  createdAt DateTime @default(now()) @map("created_at")
  updatedAt DateTime @updatedAt @map("updated_at")
  orders    Order[]

  @@map("users")
  @@index([email])
}

# Create empty migration, then edit the SQL manually
npx prisma migrate dev --create-only --name add_email_index

-- migrations/20240115_add_email_index/migration.sql
-- Prisma cannot generate CONCURRENTLY, so we write it manually
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_users_email ON users (email);

# Generate migration from schema changes
npx drizzle-kit generate

# Apply migrations
npx drizzle-kit migrate

# Push schema directly (dev only, no migration file)
npx drizzle-kit push

import { pgTable, text, timestamp, uuid, boolean } from "drizzle-orm/pg-core";

export const users = pgTable("users", {
  id: uuid("id").primaryKey().defaultRandom(),
  email: text("email").notNull().unique(),
  name: text("name"),
  isActive: boolean("is_active").notNull().default(true),
  createdAt: timestamp("created_at").notNull().defaultNow(),
  updatedAt: timestamp("updated_at").notNull().defaultNow(),
});

# Generate migration from model changes
python manage.py makemigrations

# Apply migrations
python manage.py migrate

# Show migration status
python manage.py showmigrations

# Generate empty migration for custom SQL
python manage.py makemigrations --empty app_name -n description

from django.db import migrations

def backfill_display_names(apps, schema_editor):
    User = apps.get_model("accounts", "User")
    batch_size = 5000
    users = User.objects.filter(display_name="")
    while users.exists():
        batch = list(users[:batch_size])
        for user in batch:
            user.display_name = user.username
        User.objects.bulk_update(batch, ["display_name"], batch_size=batch_size)

def reverse_backfill(apps, schema_editor):
    pass  # Data migration, no reverse needed

class Migration(migrations.Migration):
    dependencies = [("accounts", "0015_add_display_name")]

    operations = [
        migrations.RunPython(backfill_display_names, reverse_backfill),
    ]

class Migration(migrations.Migration):
    operations = [
        migrations.SeparateDatabaseAndState(
            state_operations=[
                migrations.RemoveField(model_name="user", name="legacy_field"),
            ],
            database_operations=[],  # Don't touch the DB yet
        ),
    ]

# Create migration pair
migrate create -ext sql -dir migrations -seq add_user_avatar

# Apply all pending migrations
migrate -path migrations -database "$DATABASE_URL" up

# Rollback last migration
migrate -path migrations -database "$DATABASE_URL" down 1

# Force version (fix dirty state)
migrate -path migrations -database "$DATABASE_URL" force VERSION

-- migrations/000003_add_user_avatar.up.sql
ALTER TABLE users ADD COLUMN avatar_url TEXT;
CREATE INDEX CONCURRENTLY idx_users_avatar ON users (avatar_url) WHERE avatar_url IS NOT NULL;

-- migrations/000003_add_user_avatar.down.sql
DROP INDEX IF EXISTS idx_users_avatar;
ALTER TABLE users DROP COLUMN IF EXISTS avatar_url;

Phase 1: EXPAND
  - 添加新列/表（可为空或带有默认值）
  - 部署：应用同时写入旧数据和新数据
  - 回填现有数据

Phase 2: MIGRATE
  - 部署：应用读取新数据，同时写入新旧数据
  - 验证数据一致性

Phase 3: CONTRACT
  - 部署：应用仅使用新数据
  - 在单独迁移中删除旧列/表

Day 1：迁移添加新的 `new_status` 列（可空）
Day 1：部署应用 v2 —— 同时写入 `status` 和 `new_status`
Day 2：运行针对现有行的回填迁移
Day 3：部署应用 v3 —— 仅从 `new_status` 读取
Day 7：迁移删除旧的 `status` 列