What common mistakes can occur when working with Django ORM and how to avoid them?

Common mistakes when working with Django ORM and how to avoid them:

• N+1 queries: When fetching related objects without using select_related or prefetch_related, multiple additional database queries occur.

  • Solution: Use select_related for ForeignKey and OneToOne, prefetch_related for ManyToMany and reverse relations.

• Inefficient queries: Using .all() and filtering in Python instead of filtering at the database level.

  • Solution: Apply filtering (filter, exclude) and aggregation methods at the ORM level.

• Modifying QuerySet during iteration: Changing the QuerySet or related objects while iterating can lead to errors.

  • Solution: Save results to a list or use .iterator().

• Lack of indexes: Slow queries due to missing indexes on frequently filtered fields.

  • Solution: Add indexes via db_index=True in models.

• Incorrect use of transactions: Missing or improper transaction management can lead to data inconsistency.

  • Solution: Use transaction.atomic() to group operations.

• Ignoring migration errors: Mismatch between models and database.

  • Solution: Always create and apply migrations after model changes.

Example of using select_related to avoid N+1:

# Without select_related
books = Book.objects.all()
for book in books:
    print(book.author.name)  # Separate query for each author

# With select_related
books = Book.objects.select_related('author').all()
for book in books:
    print(book.author.name)  # Single JOIN query