Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Speed up pip list --outdated #7962

Merged
merged 18 commits into from
Apr 13, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions news/7962.bugfix
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Significantly speedup ``pip list --outdated`` through parallelizing index interaction.
20 changes: 17 additions & 3 deletions src/pip/_internal/commands/list.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,10 @@

import json
import logging
from multiprocessing.dummy import Pool

from pip._vendor import six
from pip._vendor.requests.adapters import DEFAULT_POOLSIZE

from pip._internal.cli import cmdoptions
from pip._internal.cli.req_command import IndexGroupCommand
Expand Down Expand Up @@ -183,7 +185,7 @@ def iter_packages_latest_infos(self, packages, options):
with self._build_session(options) as session:
finder = self._build_package_finder(options, session)

for dist in packages:
def latest_info(dist):
typ = 'unknown'
all_candidates = finder.find_all_candidates(dist.key)
if not options.pre:
Expand All @@ -196,7 +198,7 @@ def iter_packages_latest_infos(self, packages, options):
)
best_candidate = evaluator.sort_best_candidate(all_candidates)
if best_candidate is None:
continue
return None

remote_version = best_candidate.version
if best_candidate.link.is_wheel:
Expand All @@ -206,7 +208,19 @@ def iter_packages_latest_infos(self, packages, options):
# This is dirty but makes the rest of the code much cleaner
dist.latest_version = remote_version
dist.latest_filetype = typ
yield dist
return dist

# This is done for 2x speed up of requests to pypi.org
# so that "real time" of this function
# is almost equal to "user time"
pool = Pool(DEFAULT_POOLSIZE)

for dist in pool.imap_unordered(latest_info, packages):
if dist is not None:
yield dist

pool.close()
pool.join()

def output_package_listing(self, packages, options):
packages = sorted(
Expand Down
3 changes: 2 additions & 1 deletion src/pip/_internal/utils/logging.py
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,6 @@


_log_state = threading.local()
_log_state.indentation = 0
subprocess_logger = getLogger('pip.subprocessor')


Expand Down Expand Up @@ -104,6 +103,8 @@ def indent_log(num=2):
A context manager which will cause the log output to be indented for any
log messages emitted inside it.
"""
# For thread-safety
_log_state.indentation = get_indentation()
_log_state.indentation += num
try:
yield
Expand Down
35 changes: 35 additions & 0 deletions tests/unit/test_logging.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
import logging
import os
import time
from threading import Thread

import pytest
from mock import patch
Expand All @@ -11,6 +12,7 @@
BrokenStdoutLoggingError,
ColorizedStreamHandler,
IndentingFormatter,
indent_log,
)
from pip._internal.utils.misc import captured_stderr, captured_stdout

Expand Down Expand Up @@ -108,6 +110,39 @@ def test_format_deprecated(self, level_name, expected):
f = IndentingFormatter(fmt="%(message)s")
assert f.format(record) == expected

def test_thread_safety_base(self):
record = self.make_record(
'DEPRECATION: hello\nworld', level_name='WARNING',
)
f = IndentingFormatter(fmt="%(message)s")
results = []

def thread_function():
results.append(f.format(record))

thread_function()
thread = Thread(target=thread_function)
thread.start()
thread.join()
assert results[0] == results[1]

def test_thread_safety_indent_log(self):
record = self.make_record(
'DEPRECATION: hello\nworld', level_name='WARNING',
)
f = IndentingFormatter(fmt="%(message)s")
results = []

def thread_function():
with indent_log():
results.append(f.format(record))

thread_function()
thread = Thread(target=thread_function)
thread.start()
thread.join()
assert results[0] == results[1]


class TestColorizedStreamHandler(object):

Expand Down