多线程与单线程计算

Question

def dowork():
  y = []
  z = []
  ab = 0
  start_time = time.time()
  t = threading.current_thread()

  for x in range(0,1500):
    y.append(random.randint(0,100000))
  for x in range(0,1500):
    z.append(random.randint(0,1000))
  for x in range(0,100):
    for k in range(0,len(z)):
      ab += y[k] ** z[k]
  print(" %.50s..." % ab)
  print("--- %.6s seconds --- %s" % (time.time() - start_time, t.name))

#do the work!
threads = []
for x in range(0,4): #4 threads
  threads.append(threading.Thread(target=dowork))

for x in threads:
  x.start() # and they are off

 23949968699026357507152486869104218631097704347109...
--- 11.899 seconds --- Thread-2
 10632599432628604090664113776561125984322566079319...
--- 11.924 seconds --- Thread-4
 20488842520966388603734530904324501550532057464424...
--- 12.073 seconds --- Thread-1
 17247910051860808132548857670360685101748752056479...
--- 12.115 seconds --- Thread-3
[Finished in 12.2s]

def dowork():
  y = []
  z = []
  ab = 0
  start_time = time.time()
  t = threading.current_thread()

  for x in range(0,1500):
    y.append(random.randint(0,100000))
  for x in range(0,1500):
    z.append(random.randint(0,1000))
  for x in range(0,100):
    for k in range(0,len(z)):
      ab += y[k] ** z[k]
  print(" %.50s..." % ab)
  print("--- %.6s seconds --- %s" % (time.time() - start_time, t.name))

# print(threadtest())
threads = []
for x in range(0,4):
  threads.append(True)

for x in threads:
  dowork()

 14283744921265630410246013584722456869128720814937...
--- 2.8463 seconds --- MainThread
 13487957813644386002497605118558198407322675045349...
--- 2.7690 seconds --- MainThread
 15058500261169362071147461573764693796710045625582...
--- 2.7372 seconds --- MainThread
 77481355564746169357229771752308217188584725215300...
--- 2.7168 seconds --- MainThread
[Finished in 11.1s]

为什么单线程和多线程脚本具有相同的处理时间？多线程实现不是应该少1/#线程数吗？（我知道当您达到最大cpu线程时，回报会递减）

我搞砸了我的实现吗？

Answer 1

Python中的多线程不像其他语言那样工作，如果我没记错的话，它与全局解释器锁有关。但是有很多不同的变通方法，例如，您可以使用GEvent的基于coroutine的“线程”。对于需要同时运行的工作，我本人更喜欢dask。例如

import dask.bag as db
start = time.time()
(db.from_sequence(range(4), npartitions=4)
     .map(lambda _: dowork())
    .compute())
print('total time: {} seconds'.format(time.time() - start))

start = time.time()
threads = []
for x in range(0,4):
  threads.append(True)

for x in threads:
  dowork()
print('total time: {} seconds'.format(time.time() - start))

和输出

 19016975777667561989667836343447216065093401859905...
--- 2.4172 seconds --- MainThread
 32883203981076692018141849036349126447899294175228...
--- 2.4685 seconds --- MainThread
 34450410116136243300565747102093690912732970152596...
--- 2.4901 seconds --- MainThread
 50964938446237359434550325092232546411362261338846...
--- 2.5317 seconds --- MainThread
total time: 2.5557193756103516 seconds
 10380860937556820815021239635380958917582122217407...
--- 2.3711 seconds --- MainThread
 13309313630078624428079401365574221411759423165825...
--- 2.2861 seconds --- MainThread
 27410752090906837219181398184615017013303570495018...
--- 2.2853 seconds --- MainThread
 73007436394172372391733482331910124459395132986470...
--- 2.3136 seconds --- MainThread
total time: 9.256525993347168 seconds

在本例中，dask使用multiprocessing来完成这项工作，对于您的情况来说，这可能是需要的，也可能是不需要的。