I have a multithread program which I run on:
- Windows 10 PRO x64
- Python 3.8.2 (x64) (Python 3.8.2 (tags/v3.8.2:7b3ab59, Feb 25 2020, 23:03:10) [MSC v.1916 64 bit (AMD64)] on win32)
- also try Python 3.8.0 with same error
- VS Code (x64) 1.43.0
- ms-python extension for VS Code (ms-python.python-2020.2.64397)
I got this error:
Could not connect to 127.0.0.1: 63323
Could not connect to 127.0.0.1: 63323
Traceback (most recent call last):
Traceback (most recent call last):
File "c:\Users\test\.vscode\extensions\ms-python.python-2020.2.64397\pythonFiles\lib\python\new_ptvsd\no_wheels\ptvsd\_vendored\pydevd\_pydevd_bundle\pydevd_comm.py", line 514, in start_client
s.connect((host, port))
ConnectionRefusedError: [WinError 10061] No connection could be established because the target computer actively rejected it
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "c:\Users\test\.vscode\extensions\ms-python.python-2020.2.64397\pythonFiles\lib\python\new_ptvsd\no_wheels\ptvsd\_vendored\pydevd\_pydevd_bundle\pydevd_comm.py", line 514, in start_client
s.connect((host, port))
ConnectionRefusedError: [WinError 10061] No connection could be established because the target computer actively rejected it
Traceback (most recent call last):
File "c:\Users\test\.vscode\extensions\ms-python.python-2020.2.64397\pythonFiles\lib\python\new_ptvsd\no_wheels\ptvsd\_vendored\pydevd\pydevd.py", line 2536, in settrace
File "<string>", line 1, in <module>
File "c:\Users\test\.vscode\extensions\ms-python.python-2020.2.64397\pythonFiles\lib\python\new_ptvsd\no_wheels\ptvsd\_vendored\pydevd\pydevd.py", line 2536, in settrace
Could not connect to 127.0.0.1: 63323
_locked_settrace(
_locked_settrace( File "c:\Users\test\.vscode\extensions\ms-python.python-2020.2.64397\pythonFiles\lib\python\new_ptvsd\no_wheels\ptvsd\_vendored\pydevd\pydevd.py", line 2610, in _locked_settrace
Could not connect to 127.0.0.1: 63323
In this App I use:
import functions as fnc
from multiprocessing import freeze_support
from functions.py file:
import sys
import csv
import time
import datetime
import argparse
import itertools as it
from os import system, name
from enum import Enum, unique
from tqdm import tqdm
from math import ceil
from multiprocessing import Pool, cpu_count
import codecs
Programs work great on another PC with Python 3.8.0, then I do not understand of this error
This program only compare 2 files and show diff, they do not use any connection into another server or internet
The only difference is the I now use Intel i9-9900 (8c/16t) and on second computer use i5-7500 with 4 cores only
EDIT
When I set the number of cores to 8 from 16, programs run without error. My processor has 8 physical cores and 16 logical cores, and I use cpu_count() for check number of CPU like:
threads = 8 #cpu_count()
p = Pool(threads)
Where is the problem?
EDIT - 09/03/2020 - SOURCE CODE
main.py
import functions as fnc
from multiprocessing import freeze_support
# Run main program
if __name__ == '__main__':
freeze_support()
fnc.main()
functions.py
import sys
import csv
import time
import datetime
import argparse
import itertools as it
from os import system, name
from enum import Enum, unique
from tqdm import tqdm
from math import ceil
from multiprocessing import Pool, cpu_count
import codecs
# ENUM
@unique
class Type(Enum):
TT = 1
# CLASS
class TextFormat:
PURPLE = '\033[95m'
CYAN = '\033[96m'
DARKCYAN = '\033[36m'
BLUE = '\033[94m'
GREEN = '\033[92m'
YELLOW = '\033[93m'
RED = '\033[91m'
BOLD = '\033[1m'
UNDERLINE = '\033[4m'
END = '\033[0m'
class CrossReference:
def __init__(self, pn, comp, comp_name, type, diff):
self.pn = pn
self.comp = comp
self.comp_name = comp_name
self.type = type
self.diff = diff
def __str__(self):
return f'{self.pn} {get_red("|")} {self.comp} {get_red("|")} {self.comp_name} {get_red("|")} {self.type} {get_red("|")} {self.diff}\n'
def __repr__(self):
return str(self)
def getFullRow(self):
return self.pn + ';' + self.comp + ';' + self.comp_name + ';' + self.type + ';' + self.diff + '\n'
class CrossDuplication:
def __init__(self, pn, comp, cnt):
self.pn = pn
self.comp = comp
self.cnt = cnt
def __str__(self):
return f'{self.pn};{self.comp};{self.cnt}\n'
def __repr__(self):
return str(self)
def __hash__(self):
return hash(('pn', self.pn,
'competitor', self.comp))
def __eq__(self, other):
return self.pn == other.pn and self.comp == other.comp
# FUNCTIONS
def get_formated_time(mili):
sec = mili / 1000.0
return str(datetime.timedelta(seconds = sec))
def get_green(text): # return red text
return(TextFormat.GREEN + str(text) + TextFormat.END)
def get_red(text): # return red text
return(TextFormat.RED + str(text) + TextFormat.END)
def get_yellow(text): # return yellow text
return(TextFormat.YELLOW + str(text) + TextFormat.END)
def get_blue(text): # return blue text
return(TextFormat.BLUE + str(text) + TextFormat.END)
def get_bold(text): # return bold text format
return(TextFormat.BOLD + str(text) + TextFormat.END)
def print_info(text): # print info text format
print("=== " + str(text) + " ===")
# ### LOADER ### Load Cross Reference file
def CSVCrossLoader(file_url, type):
try:
print(get_yellow("============ LOAD CROSS CSV DATA ==========="))
print_info(get_green(f"Try to load data from {file_url}"))
destination = []
with open(file_url, encoding="utf-8-sig") as csv_file:
csv_reader = csv.reader(csv_file, delimiter=';')
line_count = 0
for row in csv_reader:
if row[0].startswith('*'):
continue
if Type[row[3]] is not type:
continue
cr = CrossReference(row[0], row[1], row[2], row[3], row[4])
destination.append(cr)
line_count += 1
filename = file_url.rsplit('\\', 1)
print(
f'Processed {get_red(line_count)} lines for {get_red(type.name)} from {filename[1]}')
print_info(get_green(f"Data was loaded successfully"))
return destination
except Exception as e:
print(e)
print_info(get_red(f"File {file_url} could not be loaded"))
print_info(get_red("Program End"))
exit(0)
# ### LOADER ### Load Catalog with PN details (load only first row)
def CSVCatalogLoader(file_url):
try:
print(get_yellow("=========== LOAD CATALOG CSV DATA =========="))
print_info(get_green(f"Try to load data from {file_url}"))
destination = []
with open(file_url, encoding="utf-8-sig") as csv_file:
csv_reader = csv.reader(csv_file, delimiter=';')
line_count = 0
for row in csv_reader:
if row[0].startswith('*'):
continue
destination.append(row[0])
line_count += 1
filename = file_url.rsplit('\\', 1)
print(f'Processed {get_red(line_count)} lines from {filename[1]}')
print_info(get_green(f"Data was loaded successfully"))
return destination
except:
print_info(get_red(f"File {file_url} could not be loaded"))
print_info(get_red("Program End"))
exit(0)
def FindDuplications(tasks):
dlist, start, count = tasks
duplicates = []
for r in tqdm(dlist[start:start + count]):
matches = [x for x in dlist if r.pn == x.pn and r.comp == x.comp]
duplicates.append(CrossDuplication(r.pn, r.comp, len(matches)))
return {d for d in duplicates if d.cnt > 1}
def CheckDuplications(cross_list):
threads = cpu_count()
tasks_per_thread = ceil(len(cross_list) / threads)
tasks = [(cross_list, tasks_per_thread * i, tasks_per_thread) for i in range(threads)]
p = Pool(threads)
duplicates = p.map(FindDuplications, tasks)
p.close()
p.join()
duplicates = {item for sublist in duplicates for item in sublist}
return duplicates
def main():
# Main Title of app
print_info(get_yellow("Run app"))
# VARIABLES
catalog_list = []
cross_list = []
# Start calculate program running time
start_time = int(round(time.time() * 1000))
# load URL param from program input arguments
validation_type = Type[sys.argv[1]]
cross_ref_url = sys.argv[2]
catalog_url = sys.argv[3]
# Get info abou tested type
print_info(get_blue(f"||| Validate data for {validation_type.name} |||"))
print("Number of processors: ", cpu_count())
print()
# load data
cross_list = CSVCrossLoader(cross_ref_url, validation_type)
catalog_list = CSVCatalogLoader(catalog_url)
# Chech data in Cross Reference for Duplications [ MULTITHREAD ]
duplicates = CheckDuplications(cross_list)
# Print duration of execution script
mili = int(int(round(time.time() * 1000)) - start_time)
print(f'Script duration - {mili} ms | {get_formated_time(mili)}')
# End of program
print_info(get_yellow(""))
print()
launch.json - VS Code config file
{
// Use IntelliSense to learn about possible attributes.
// Hover to view descriptions of existing attributes.
// For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
"version": "0.2.0",
"configurations": [
{
"name": "First",
"type": "python",
"request": "launch",
"program": "${file}",
"console": "integratedTerminal",
"args": [
"TT",
"..\\url\\ref.csv",
"..\\url\\catalog.csv"
]
}
]
}
DATA FILE - ref.csv (example)
xxx;123;
ccc;dgd;
xxx;323;
xxx;dgd;
xxx;123;
...etc:.
DATA FILE - catalog.csv (example)
xxx;
ccc;
vvv;
fff;
xyx;
xxx;
cff;
ccc;
www;
...etc:.
Application load 2 CSV files, and find duplication of rows in ref.csv, in this file is over 100k+ lines, and compare the first and second column of each row with same data in foreach loop
EDIT - 10/03/2020 - Third Computer
Today I try it on my laptop (Lenovo T480s) with Intel Core i7-8550U with 4c/8t
I run it with threads = cpu_count(), this function return 8 cores/threads and everything works fine, with the same config like on last 2 previous PCs but only on Intel Core i9-9900 code get ERROR
Also, I tried on i9-9900 set:
threads = 8 # OK
threads = 12 # OK
threads = 14 # ERROR
threads = 16 # ERROR
=========================================== Run native in CMD or Powershell works fine with 16 threads - OK
C:\Users\test\AppData\Local\Programs\Python\Python38\python.exe 'c:\Users\test\Documents\Work\Sources\APP\src\APP\cross-validator.py' 'TT' 'c:\Users\test\Documents\Work\Sources\APP\src\APP\APP\Definitions\ref.csv' 'c:\Users\test\Documents\Work\Sources\APP\src\APP\APP\Definitions\Tan\catalog.csv'
Run via VS Code debug add one more parameter with link to ms-python - ERROR
${env:PTVSD_LAUNCHER_PORT}='49376'; & 'C:\Users\test\AppData\Local\Programs\Python\Python38\python.exe' 'c:\Users\test\.vscode\extensions\ms-python.python-2020.2.64397\pythonFiles\lib\python\new_ptvsd\no_wheels\ptvsd\launcher' 'c:\Users\test\Documents\Work\Sources\APP\src\APP\cross-validator.py' 'TAN' 'c:\Users\test\Documents\Work\Sources\APP\src\APP\APP\Definitions\ref.csv' 'c:\Users\test\Documents\Work\Sources\APP\src\APP\APP\Definitions\Tan\catalog.csv'
Thank you for help
