Python3多线程优化Git项目代码统计性能实战
本文介绍如何利用Python3多线程技术优化Git项目成员代码统计功能。通过对比老版本串行处理与新版本并发处理,解决外层与内层循环中的耗时操作。引入线程锁机制共享外部资源并避免写冲突,最终实现运行速度提升约58倍,将执行时间从108秒缩短至1.8秒,显著提高了程序运行效率。
Python3多线程优化Git项目代码统计性能实战
以下是优化前后新旧代码的对比展示:
from git_tools.git_tool import get_collect_projects, QQNews_Git
from threading import Thread, Lock
import datetime
base_url = "http://git.xx.com"
project_members_commits_lang_info = {}
lock = Lock()
threads = []
'''
Author:zenkilan
'''
def count_time(func):
def took_up_time(*args, **kwargs):
start_time = datetime.datetime.now()
ret = func(*args, **kwargs)
end_time = datetime.datetime.now()
took_up_time = (end_time - start_time).total_seconds()
print(f"{func.__name__} execution took up time:{took_up_time}")
return ret
return took_up_time
def get_project_member_lang_code_lines(git, member, begin_date, end_date):
global project_members_commits_lang_info
global lock
member_name = member["username"]
r = git.get_user_info(member_name)
if not r["id"]:
return
user_commits_lang_info = git.get_commits_user_lang_diff_between(r["id"], begin_date, end_date)
if len(user_commits_lang_info) == 0:
return
lock.acquire()
project_members_commits_lang_info.setdefault(git.project, dict())
project_members_commits_lang_info[git.project][member_name] = user_commits_lang_info
lock.release()
def get_project_lang_code_lines(project, begin_date, end_date):
global threads
git = QQNews_Git(project[1], base_url, project[0])
project_members = git.get_project_members()
if len(project_members) == 0:
return
for member in project_members:
thread = Thread(target=get_project_member_lang_code_lines, args=(git, member, begin_date, end_date))
threads.append(thread)
thread.start()
@count_time
def get_projects_lang_code_lines(begin_date, end_date):
"""
获取项目代码行语言相关统计——新方法(提升效率)
应用多线程替代for循环
并发访问共享外部资源
:return:
"""
global project_members_commits_lang_info
global threads
for project in get_collect_projects():
thread = Thread(target=get_project_lang_code_lines, args=(project, begin_date, end_date))
threads.append(thread)
thread.start()
@count_time
def get_projects_lang_code_lines_old(begin_date, end_date):
"""
获取项目代码行语言相关统计——老方法(耗时严重)
使用最基本的思路进行编程
双层for循环嵌套并且每层都包含耗时操作
:return:
"""
project_members_commits_lang_info = {}
for project in get_collect_projects():
git = QQNews_Git(project[1], base_url, project[0])
project_members = git.get_project_members()
user_commits_lang_info_dict = {}
if len(project_members) == 0:
continue
for member in project_members:
member_name = member["username"]
r = git.get_user_info(member_name, debug=False)
if not r["id"]:
continue
try:
user_commits_lang_info = git.get_commits_user_lang_diff_between(r["id"], begin_date, end_date)
if len(user_commits_lang_info) == 0:
continue
user_commits_lang_info_dict[member_name] = user_commits_lang_info
project_members_commits_lang_info[git.project] = user_commits_lang_info_dict
except:
pass
return project_members_commits_lang_info
def test_results_equal(resultA, resultB):
"""
测试方法
:param resultA:
:param resultB:
:return:
"""
print(resultA)
print(resultB)
assert len(str(resultA)) == len(str(resultB))
if __name__ == '__main__':
from git_tools.config import begin_date, end_date
get_projects_lang_code_lines(begin_date, end_date)
for t in threads:
t.join()
old_result = get_projects_lang_code_lines_old(begin_date, end_date)
test_results_equal(old_result, project_members_commits_lang_info)
在旧版方法中,外层for循环和内层for循环内部均包含耗时操作:
1)git.get_project_members()
2)git.get_user_info(member_name, debug=False)
优化工作分两步进行,无论是先处理内层循环再处理外层,还是先外后内均可。核心思路是用多线程替换原有的for循环,通过并发方式共享外部资源,并添加锁机制以避免写入冲突。
测试结果验证通过,函数运行时间装饰器显示的数据(单位为秒)如下:
get_projects_lang_code_lines execution took up time:1.85294
get_projects_lang_code_lines_old execution took up time:108.604177
速度提升了约58倍
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持本站。
本站声明
本文内容仅供参考,不代表本站观点。转载或引用请注明出处。如发现内容问题,请通过联系我们页面反馈。













