浅谈优化Django ORM中的性能问题

>>> from django.db import connection
>>> connection.queries
[]
>>> Author.objects.all()
<QuerySet [<Author: Author object>]>
>>> connection.queries
[{u'time': u'0.002', u'sql': u'SELECT "library_author"."id", "library_author"."name" FROM "library_author" LIMIT 21'}]

python manage.py shell_plus --print-sql

>>> Author.objects.all()
SELECT "library_author"."id", "library_author"."name" FROM "library_author" LIMIT 21
Execution time: 0.001393s [Database: default]
<QuerySet [<Author: Author object>]>

class Author(models.Model):
 name = models.TextField()

class Book(models.Model):
 title = models.TextField()
 author = models.ForeignKey(
 Author, on_delete=models.PROTECT, related_name='books', null=True
 )

if book.author:
 do_stuff()
# Or
do_stuff_with_author_id(book.author.id)

if book.author_id:
 do_stuff()

do_stuff_with_author_id(book.author_id)

# Don't waste a query if you are using the queryset
books = Book.objects.filter(..)
if books:
 do_stuff_with_books(books)

# If you aren't using the queryset use exist
books = Book.objects.filter(..)
if books.exists():
 do_some_stuff()

# But never
if Book.objects.filter(..):
 do_some_stuff()

# Don't waste a query if you are using the queryset
books = Book.objects.filter(..)
if len(books) > 5:
 do_stuff_with_books(books)

# If you aren't using the queryset use count
books = Book.objects.filter(..)
if books.count() > 5:
 do_some_stuff()

# But never
if len(Book.objects.filter(..)) > 5:
 do_some_stuff()

# Retrieve values as a dictionary
>>> Book.objects.values('title', 'author__name')
<QuerySet [{'author__name': u'Nikolai Gogol', 'title': u'The Overcoat'}, {'author__name': u'Leo Tolstoy', 'title': u'War and Peace'}]>

# Retrieve values as a tuple
>>> Book.objects.values_list('title', 'author__name')
<QuerySet [(u'The Overcoat', u'Nikolai Gogol'),
(u'War and Peace', u'Leo Tolstoy')]>
>>> Book.objects.values_list('title')
<QuerySet [(u'The Overcoat',), (u'War and Peace',)]>

# With one value, it is easier to flatten the list
>>> Book.objects.values_list('title', flat=True)
<QuerySet [u'The Overcoat', u'War and Peace']>

# Get the Author's name of a Book
book = Book.objects.first()
book.author.name

>>> Author.objects.count()
20
>>> Book.objects.count()
100
# This block is 101 queries.
# 1 for the books and 1 for each author that lazy-loaded 
books = Book.objects.all()
for book in books:
 do_stuff(book.title, book.author.name)

# This block is 20 queries.
# 1 for the author and 1 for the books of each author
authors = Author.objects.all()
for author in authors:
 do_stuff_with_books(author.name, author.books.all())

# This block is 1 query
# The authors of all the books are pre-fetched in one query
book = Book.objects.selected_related('author').all()
for book in books:
 do_stuff(book.title, book.author)

# This block is 1 query
# The books of all the authors are pre-fetched in one query
authors = Author.objects.prefetch_related('books').all()
for author in authors:
 do_stuff_with_books(author.name, author.books.all())

>> id(author)
4504693520
>>> [(id(book.author), book.author.pk) for book in author.books.all()]
[(4504693520, 1), (4504693520, 1)]

def author_name_length(book):
 return len(book.author.name)

def process_author_books(author):
 for book in author.books.all():
 do_stuff(book)

>>> book.author.name
Traceback (most recent call last):
File "<console>", line 1, in <module>
File "/Users/kyle/orm_test/library/models.py", line 18, in __get__
'Use `select_related` or `fetch_{rel}`'.format(rel=self.field.name)
RelationNotLoaded: Relation `author` not loaded. Use `select_related` or `fetch_author`

# We explicitly fetch the resource
>>> book.fetch_author()
<Author: Author object>
>>> book.author.name
"Fyodor Dostoevsky"

# Select related works just as well
>>> book = Book.objects.select_related('author').first()
>>> book.author.name
"Anton Chekhov"