问LocalCluster调度程序没有使用所有内核，并且比默认线程调度程序慢吗？

EN

import numpy as np

import dask.array as  da
import dask.distributed

from datetime import datetime

n_threads= 4
n = 40_000

def test(n=40_000, chunk=1000):
    da.random.seed(731)
    x = da.random.random((n,n), chunks=(chunk,chunk))
    y = x + x.T
    z = y[::2,5000:].mean(axis=1)
    return z

print("Test default threads scheduler (size={}, {} threads)".format(n, n_threads))

start = datetime.now()
result1 = test(n=n).compute(scheduler="threads", num_workers=n_threads)

print("Done in {}".format(datetime.now()-start))

print("Test dask distributed LocalCluster scheduler (size={}, {} threads)".format(n, n_threads))

client = dask.distributed.Client(processes=False, n_workers=1, threads_per_worker=n_threads)
print("Client: ", client)

start = datetime.now()
result2 = test(n=n).compute()

print("Done in {}".format(datetime.now()-start))

client.close()


error = np.mean(np.abs(result1-result2))

print("Mean absolute difference between results: {}".format(error))

>> python test_dask.py
Test default threads scheduler (size=40000, 4 threads)
Done in 0:00:09.872372
Test dask distributed LocalCluster scheduler (size=40000, 4 threads)
Client:  <Client: 'inproc://192.168.0.129/32574/1' processes=1 threads=4, memory=16.67 GB>
Done in 0:00:18.028071
Mean absolute difference between results: 0.0