[英]python multiprocessing + peewee + postgresql fails with SSL error
我正在嘗試編寫一個 Python 模型,該模型能夠使用多線程模塊和 peewee 在 PostgreSQL 數據庫中進行一些處理。
但是,在單核模式下,代碼可以工作,但是,當我嘗試使用多核運行代碼時,我遇到了 SSL 錯誤。
我想發布我的模型的結構,希望有人可以建議如何以適當的方式設置我的模型。 目前,我選擇使用面向對象的方法,在該方法中我建立一個在池中共享的連接。 為了澄清我所做的,我現在將展示我目前擁有的源代碼
我有三個文件:main.py、models.py 和 parser.py。 內容如下
models.py 定義了 peewee postgresql 表並連接到 postgres 服務器
import peewee as pw
from playhouse.pool import PooledPostgresqlExtDatabase
KVK_KEY = "id_number"
NAME_KEY = "name"
N_VOWELS_KEY = "n_vowels"
# initialise the data base
database = PooledPostgresqlExtDatabase(
"testdb", user="postgres", host="localhost", port=5432, password="xxxx",
max_connections=8, stale_timeout=300 )
class BaseModel(pw.Model):
class Meta:
database = database
only_save_dirty = True
# this class describes the format of the sql data base
class Company(BaseModel):
id_number = pw.IntegerField(primary_key=True)
name = pw.CharField(null=True)
n_vowels = pw.IntegerField(default=-1)
processor = pw.IntegerField(default=-1)
def connect_database(database_name, reset_database=False):
""" connect the database """
database.connect()
if reset_database:
database.drop_tables([Company])
database.create_tables([Company])
parser.py 包含 CompanyParser 類,該類用作代碼的引擎來完成所有處理。 它生成一些人工數據存儲到 postgresql 數據庫中,然后使用run方法對已經存儲在數據庫中的數據進行一些處理
import pandas as pd
import numpy as np
import random
import string
import peewee as pw
from models import (Company, database, KVK_KEY, NAME_KEY)
import multiprocessing as mp
MAX_SQL_CHUNK = 1000
np.random.seed(0)
def random_name(size=8, chars=string.ascii_lowercase):
""" Create a random character string of 'size' characters """
return "".join(random.choice(chars) for _ in range(size))
def vowel_count(characters):
"""
Count the number of vowels in the string 'characters' and return as an integer
"""
count = 0
for char in characters:
if char in list("aeiou"):
count += 1
return count
class CompanyParser(mp.Process):
def __init__(self, number_of_companies=100, i_proc=None,
number_of_procs=1,
first_id=None, last_id=None):
if i_proc is not None and number_of_procs > 1:
mp.Process.__init__(self)
self.i_proc = i_proc
self.number_of_procs = number_of_procs
self.n_companies = number_of_companies
self.data_df: pd.DataFrame = None
self.first_id = first_id
self.last_id = last_id
def generate_data(self):
""" Create a dataframe with fake company data and id's """
id_list = np.random.randint(1000000, 9999999, self.n_companies)
company_list = np.array([random_name() for _ in range(self.n_companies)])
self.data_df = pd.DataFrame(data=np.vstack([id_list, company_list]).T,
columns=[KVK_KEY, NAME_KEY])
self.data_df.sort_values([KVK_KEY], inplace=True)
def store_to_database(self):
"""
Store the company data to a sql database
"""
record_list = list(self.data_df.to_dict(orient="index").values())
n_batch = int(len(record_list) / MAX_SQL_CHUNK) + 1
with database.atomic():
for cnt, batch in enumerate(pw.chunked(record_list, MAX_SQL_CHUNK)):
print(f"writing {cnt}/{n_batch}")
Company.insert_many(batch).execute()
def run(self):
print("Making query at {}".format(self.i_proc))
query = (Company.
select().
where(Company.id_number.between(self.first_id, self.last_id)))
print("Found {} companies".format(query.count()))
for cnt, company in enumerate(query):
print("Processing @ {} - {}: company {}/{}".format(self.i_proc, cnt,
company.id_number,
company.name))
number_of_vowels = vowel_count(company.name)
company.n_vowels = number_of_vowels
company.processor = self.i_proc
print(f"storing number of vowels: {number_of_vowels}")
company.save()
最后,我的主腳本加載存儲在 models.py 和 parser.py 中的類並啟動代碼。
from models import (Company, connect_database)
from parser import CompanyParser
number_of_processors = 2
connect_database(None, reset_database=True)
# init an object of the CompanyParser and use the create database
parser = CompanyParser()
company_ids = Company.select(Company.id_number)
parser.generate_data()
parser.store_to_database()
n_companies = company_ids.count()
n_comp_per_proc = int(n_companies / number_of_processors)
print("Found {} companies: {} per proc".format(n_companies, n_comp_per_proc))
for i_proc in range(number_of_processors):
i_start = i_proc * n_comp_per_proc
first_id = company_ids[i_start]
last_id = company_ids[i_start + n_comp_per_proc - 1]
print(f"Running proc {i_proc} for id {first_id} until id {last_id}")
sub_parser = CompanyParser(first_id=first_id, last_id=last_id,
i_proc=i_proc,
number_of_procs=number_of_processors)
if number_of_processors > 1:
sub_parser.start()
else:
sub_parser.run()
如果number_of_processors = 1,此腳本可以正常工作。 它生成人工數據,將其存儲到 PostgreSQL 數據庫並對數據進行一些處理(它計算名稱中的元音數量並將其存儲到 n_vowels 列中)
但是,如果我嘗試使用number_of_processors = 2 的2 個內核運行此程序,則會遇到以下錯誤
/opt/miniconda3/bin/python /home/eelco/PycharmProjects/multiproc_peewee/main.py
writing 0/1
Found 100 companies: 50 per proc
Running proc 0 for id 1020737 until id 5295565
Running proc 1 for id 5302405 until id 9891087
Making query at 0
Found 50 companies
Processing @ 0 - 0: company 1020737/wqrbgxiu
storing number of vowels: 2
Making query at 1
Process CompanyParser-1:
Processing @ 0 - 1: company 1086107/lkbagrbc
storing number of vowels: 1
Processing @ 0 - 2: company 1298367/nsdjsqio
storing number of vowels: 2
Traceback (most recent call last):
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2714, in execute_sql
cursor.execute(sql, params or ())
psycopg2.OperationalError: SSL error: sslv3 alert bad record mac
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/miniconda3/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
self.run()
File "/home/eelco/PycharmProjects/multiproc_peewee/parser.py", line 82, in run
company.save()
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 5748, in save
rows = self.update(**field_dict).where(self._pk_expr()).execute()
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1696, in execute
return self._execute(database)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2121, in _execute
cursor = database.execute(self)
File "/opt/miniconda3/lib/python3.7/site-packages/playhouse/postgres_ext.py", line 468, in execute
cursor = self.execute_sql(sql, params, commit=commit)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2721, in execute_sql
self.commit()
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2512, in __exit__
reraise(new_type, new_type(*exc_args), traceback)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 186, in reraise
raise value.with_traceback(tb)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2714, in execute_sql
cursor.execute(sql, params or ())
peewee.OperationalError: SSL error: sslv3 alert bad record mac
Process CompanyParser-2:
Traceback (most recent call last):
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2714, in execute_sql
cursor.execute(sql, params or ())
psycopg2.OperationalError: SSL error: decryption failed or bad record mac
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/miniconda3/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
self.run()
File "/home/eelco/PycharmProjects/multiproc_peewee/parser.py", line 72, in run
print("Found {} companies".format(query.count()))
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1881, in count
return Select([clone], [fn.COUNT(SQL('1'))]).scalar(database)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1866, in scalar
row = self.tuples().peek(database)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1853, in peek
rows = self.execute(database)[:n]
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1696, in execute
return self._execute(database)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1847, in _execute
cursor = database.execute(self)
File "/opt/miniconda3/lib/python3.7/site-packages/playhouse/postgres_ext.py", line 468, in execute
cursor = self.execute_sql(sql, params, commit=commit)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2721, in execute_sql
self.commit()
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2512, in __exit__
reraise(new_type, new_type(*exc_args), traceback)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 186, in reraise
raise value.with_traceback(tb)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2714, in execute_sql
cursor.execute(sql, params or ())
peewee.OperationalError: SSL error: decryption failed or bad record mac
Process finished with exit code 0
不知何故,一旦第二個線程開始對數據庫執行某些操作,就會出現問題。 有人建議讓這段代碼正常工作嗎? 我已經嘗試過以下
希望有人能指教。
問候 Eelco
今天在互聯網上進行了一些搜索后,我在這里找到了我的問題的解決方案: github.com/coleifer 。 正如 coleifer 提到的:在開始連接到數據庫之前,您顯然首先必須設置所有分支。 基於這個想法,我修改了我的代碼,現在可以正常工作了。
對於那些感興趣的人,我將再次發布我的 python 腳本,以便您可以看到我是如何做到的。 這是因為我沒有那么多明確的例子,所以也許它可以幫助其他人。
首先,所有的數據庫和 peewee 模塊現在都被轉移到初始化函數中,這些函數只在 CompanyParser 類的構造函數中調用。 所以models.py看起來像
import peewee as pw
from playhouse.pool import PooledPostgresqlExtDatabase, PostgresqlDatabase, PooledPostgresqlDatabase
KVK_KEY = "id_number"
NAME_KEY = "name"
N_VOWELS_KEY = "n_vowels"
def init_database():
db = PooledPostgresqlDatabase(
"testdb", user="postgres", host="localhost", port=5432, password="xxxxx",
max_connections=8, stale_timeout=300)
return db
def init_models(db, reset_tables=False):
class BaseModel(pw.Model):
class Meta:
database = db
# this class describes the format of the sql data base
class Company(BaseModel):
id_number = pw.IntegerField(primary_key=True)
name = pw.CharField(null=True)
n_vowels = pw.IntegerField(default=-1)
processor = pw.IntegerField(default=-1)
if db.is_closed():
db.connect()
if reset_tables and Company.table_exists():
db.drop_tables([Company])
db.create_tables([Company])
return Company
然后,在 parser.py 腳本中定義了工作類 CompanyParser,如下所示
import multiprocessing as mp
import random
import string
import numpy as np
import pandas as pd
import peewee as pw
from models import (KVK_KEY, NAME_KEY, init_database, init_models)
MAX_SQL_CHUNK = 1000
np.random.seed(0)
def random_name(size=32, chars=string.ascii_lowercase):
""" Create a random character string of 'size' characters """
return "".join(random.choice(chars) for _ in range(size))
def vowel_count(characters):
"""
Count the number of vowels in the string 'characters' and return as an integer
"""
count = 0
for char in characters:
if char in list("aeiou"):
count += 1
return count
class CompanyParser(mp.Process):
def __init__(self, reset_tables=False,
number_of_companies=100, i_proc=None,
number_of_procs=1, first_id=None, last_id=None):
if i_proc is not None and number_of_procs > 1:
mp.Process.__init__(self)
self.i_proc = i_proc
self.reset_tables = reset_tables
self.number_of_procs = number_of_procs
self.n_companies = number_of_companies
self.data_df: pd.DataFrame = None
self.first_id = first_id
self.last_id = last_id
# initialise the database and models
self.database = init_database()
self.Company = init_models(self.database, reset_tables=self.reset_tables)
def generate_data(self):
""" Create a dataframe with fake company data and id's and return the array of id's"""
id_list = np.random.randint(1000000, 9999999, self.n_companies)
company_list = np.array([random_name() for _ in range(self.n_companies)])
self.data_df = pd.DataFrame(data=np.vstack([id_list, company_list]).T,
columns=[KVK_KEY, NAME_KEY])
self.data_df.drop_duplicates([KVK_KEY], inplace=True)
self.data_df.sort_values([KVK_KEY], inplace=True)
return self.data_df[KVK_KEY].values
def store_to_database(self):
"""
Store the company data to a sql database
"""
record_list = list(self.data_df.to_dict(orient="index").values())
n_batch = int(len(record_list) / MAX_SQL_CHUNK) + 1
with self.database.atomic():
for cnt, batch in enumerate(pw.chunked(record_list, MAX_SQL_CHUNK)):
print(f"writing {cnt}/{n_batch}")
self.Company.insert_many(batch).execute()
def run(self):
query = (self.Company.
select().
where(self.Company.id_number.between(self.first_id, self.last_id)))
for cnt, company in enumerate(query):
print("Processing @ {} - {}: company {}/{}".format(self.i_proc, cnt, company.id_number,
company.name))
number_of_vowels = vowel_count(company.name)
company.n_vowels = number_of_vowels
company.processor = self.i_proc
try:
company.save()
except (pw.OperationalError, pw.InterfaceError) as err:
print("failed save for {} {}: {}".format(self.i_proc, cnt, err))
else:
pass
最后,啟動進程的 main.py 腳本:
from parser import CompanyParser
import time
def main():
number_of_processors = 2
number_of_companies = 10000
parser = CompanyParser(number_of_companies=number_of_companies, reset_tables=True)
company_ids = parser.generate_data()
parser.store_to_database()
n_companies = company_ids.size
n_comp_per_proc = int(n_companies / number_of_processors)
print("Found {} companies: {} per proc".format(n_companies, n_comp_per_proc))
if not parser.database.is_closed():
parser.database.close()
processes = list()
for i_proc in range(number_of_processors):
i_start = i_proc * n_comp_per_proc
first_id = company_ids[i_start]
last_id = company_ids[i_start + n_comp_per_proc - 1]
print(f"Running proc {i_proc} for id {first_id} until id {last_id}")
sub_parser = CompanyParser(first_id=first_id, last_id=last_id, i_proc=i_proc,
number_of_procs=number_of_processors)
if number_of_processors > 1:
sub_parser.start()
else:
sub_parser.run()
processes.append(sub_parser)
# this blocks the script until all processes are done
for job in processes:
job.join()
# make sure all the connections are closed
for i_proc in range(number_of_processors):
db = processes[i_proc].database
if not db.is_closed():
db.close()
print("Goodbye!")
if __name__ == "__main__":
start = time.time()
main()
duration = time.time() - start
print(f"Done in {duration} s")
如您所見,數據庫連接是在類內的每個進程中完成的。 這個例子是一個完整的 multiprocessing + peewee 和 PostgreSQL 例子。 希望這可以幫助其他人。 如果您有任何改進意見或建議,請告訴我。
我也遇到了這個錯誤,但是在Heroku
使用了flask
+ peewee
+ rq
。 以下是我解決它的方法:
如果您有一個與 RQ 一起使用的簡單應用程序,我建議您使用SimpleWorker
RQ 建議使用rq.worker.HerokuWorker
但我仍然收到了一個ssl 錯誤。 該錯誤出現在我創建了后續(鏈)任務的情況下,其中 1 的執行取決於另一個任務的成功。
另外我使用的是flask-rq2,但適用於正常使用以及如下所示:
# app.py
app = Flask(__name__)
app.config['RQ_WORKER_CLASS'] = os.getenv('RQ_WORKER_CLASS', 'rq.worker.Worker')
rq = RQ(app)
我通過在 heroku 配置中更改以下內容來解決它:
rq.worker.SimpleWorker
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.