import pymysql
from multiprocessing.pool import ThreadPool
def process(item):
host = str(item).strip()
db = None
try:
db = pymysql.connect(host=host, user='root', passwd='root', port=3306, connect_timeout=10,
write_timeout=10)
r = open("success.txt", 'a')
r.write(host)
r.write("\n")
pass
except Exception as msg:
print(msg)
pass
finally:
if db:
db.close()
pass
if __name__ == '__main__':
t = ThreadPool(100)
t.map_async(process,open('3306.txt').readlines())
t.close()
t.join()
I want to verify in batches whether the MySQL account passwords of some IPs are valid, but my code will have the problem of sub-thread blocking. In fact, the last IP has been verified, but the main thread has not ended. I don't know how to modify it. You can provide Some modifications and suggestions?
I'm trying to write a load testing script using locust in python (it uses gevent & greenlet for multithreading internally as per my understanding); but my script is getting stuck when I try to put a db connection (postgres) back to connection pool inside a thread. I have defined connection pool variable as gloabl & then trying to create & put connections back inside threads; I have no experience in threading; not sure if these lines marked inside ** quotes are the reason locust gets stuck -
#events.test_start.add_listener # executes one time at the start of test run
def on_test_start(**kw):
**global t_pool** # connection pool variable defined as global
conn_st = config(fname = os.path.join('.', 'db'), instance = 'xxx')
try:
t_pool = pool.ThreadedConnectionPool(1, 100, **conn_st)
#cur = db.cursor()
except Exception as err:
#db = None
raise DatabaseError("DB Connection could not be established - %s" %(err))
#contextmanager
def get_con():
con = t_pool.getconn()
try:
yield con
finally:
**t_pool.putconn(con)**
def send_xxx():
ind = random.randint(0, (len(xxx_data['yyy'])-1))
body['toeknx'] = xxx_data['yyy'][ind]
res = requests.post(url, headers=headers, json=body)
res.raise_for_status()
with get_con() as con:
cur = con.cursor()
while True:
cur.execute("test query")
token = cur.fetchone()
if token is None:
continue
else:
cur.execute("another test query")
out = cur.fetchone()
if zzz:
continue
else:
cur.execute("final test query")
out1 = cur.fetchone()
time_diff = out1[1] - out1[0]
cur.close()
You need to use psycogreen to make psycopg2 gevent-friendly.
Something like:
import gevent
import gevent.monkey
gevent.monkey.patch_all()
import psycogreen.gevent
psycogreen.gevent.patch_psycopg()
Full example here:
https://github.com/SvenskaSpel/locust-plugins/blob/master/locust_plugins/listeners.py
I use sqlachemy to connect to a remote database but I do not know the type (can be PostgreSQL, MariaDB, etc.). I try them in a loop and I keep the first working driver:
for driver in drivers:
try:
uri = get_uri_from_driver(driver)
engine = create_engine(uri, echo=False)
print('Try connection')
con = engine.engine.connect()
# Try to get some lines
return engine
except Exception:
continue
return None
In some case the con = engine.engine.connect() does not end and it happens when you try the MySQL driver to connect to something which is not MySQL (Oracle).
Questions:
How can I set a timeout to this?
If I cannot, is there any other way to achieve this ? (I will for example base the test order with the default port but I would like to be able to kill the connect() after some seconds.
EDIT:
This code is in a Django so I cannot use signal/alarm because of multi-threading.
This can be done with a generic timeout solution like in:
What should I do if socket.setdefaulttimeout() is not working?
import signal
class Timeout():
"""Timeout class using ALARM signal"""
class TimeoutException(Exception): pass
def __init__(self, sec):
self.sec = sec
def __enter__(self):
signal.signal(signal.SIGALRM, self.raise_timeout)
signal.alarm(self.sec)
def __exit__(self, *args):
signal.alarm(0) # disable alarm
def raise_timeout(self, *args):
raise Timeout.TimeoutException()
# In your example
try:
uri = get_uri_from_driver(driver)
engine = create_engine(uri, echo=False)
print('Try connection')
with Timeout(10):
con = engine.engine.connect()
# Try to get some lines
return engine
except Exception:
continue
I have multiple threads that process data and puts it on a queue, and a single thread that takes data from a queue and then saves it to a database.
I think the following will cause a memory leak:
class DBThread(threading.Thread):
def __init__(self, myqueue):
threading.Thread.__init__(self)
self.myqueue = myqueue
def run(self):
conn = sqlite3.connect("test.db")
c = conn.cursor()
while True:
data = myqueue.get()
if data:
c.execute("INSERT INTO test (data) VALUES (?)", (data,))
conn.commit()
self.myqueue.task_done()
#conn.close() <--- never reaches this point
q = Queue.Queue()
# Create other threads
....
# Create DB thread
t = DBThread(q)
t.setDaemon(True)
t.start()
q.join()
I can't put the conn.close() in the while loop, because I think that will close the connection on the first loop. I can't put it in the if data: statement, because then it won't save data that may be put in the queue later.
Where do I close the db connection? If I don't close it, won't this cause a memory leak?
If you can use a sentinel value that will not appear in your normal data, e.g. None, you can signal the thread to stop and close the database connection in a finally clause:
import threading
import Queue
import sqlite3
class DBThread(threading.Thread):
def __init__(self, myqueue, db_path):
threading.Thread.__init__(self)
self.myqueue = myqueue
self.db_path = db_path
def run(self):
conn = sqlite3.connect(self.db_path)
try:
while True:
data = self.myqueue.get()
if data is None: # check for sentinel value
break
with conn:
conn.execute("INSERT INTO test (data) VALUES (?)", (data,))
self.myqueue.task_done()
finally:
conn.close()
q = Queue.Queue()
for i in range(100):
q.put(str(i))
conn = sqlite3.connect('test.db')
conn.execute('create table if not exists test (data text)')
conn.close()
t = DBThread(q, 'test.db')
t.start()
q.join()
q.put(None) # tell database thread to terminate
If you cannot use a sentinel value you can add a flag to the class that is checked in the while loop. Also add a stop() method to the thread class that sets the flag. You will need to use a non-blocking Queue.get():
class DBThread(threading.Thread):
def __init__(self, myqueue, db_path):
threading.Thread.__init__(self)
self.myqueue = myqueue
self.db_path = db_path
self._terminate = False
def terminate(self):
self._terminate = True
def run(self):
conn = sqlite3.connect(self.db_path)
try:
while not self._terminate:
try:
data = self.myqueue.get(timeout=1)
except Queue.Empty:
continue
with conn:
conn.execute("INSERT INTO test (data) VALUES (?)", (data,))
self.myqueue.task_done()
finally:
conn.close()
....
q.join()
t.terminate() # tell database thread to terminate
Finally, it's worth mentioning that your program could terminate if the db thread manages to drain the queue, i.e. if q.join() returns. This is because the db thread is a daemon thread and will not prevent the main thread exiting. You need to ensure that your worker threads produce enough data to keep the db thread busy, otherwise q.join() will return and the main thread will exit.
I'm trying to set up a MySQL connection pool and have my worker processes access the already established pool instead of setting up a new connection each time.
I'm confused if I should pass the database cursor to each process, or if there's some other way to do this? Shouldn't MySql.connector do the pooling automatically? When I check my log files, many, many connections are opened and closed ... one for each process.
My code looks something like this:
PATH = "/tmp"
class DB(object):
def __init__(self):
connected = False
while not connected:
try:
cnxpool = mysql.connector.pooling.MySQLConnectionPool(pool_name = "pool1",
**config.dbconfig)
self.__cnx = cnxpool.get_connection()
except mysql.connector.errors.PoolError:
print("Sleeping.. (Pool Error)")
sleep(5)
except mysql.connector.errors.DatabaseError:
print("Sleeping.. (Database Error)")
sleep(5)
self.__cur = self.__cnx.cursor(cursor_class=MySQLCursorDict)
def execute(self, query):
return self.__cur.execute(query)
def isValidFile(self, name):
return True
def readfile(self, fname):
d = DB()
d.execute("""INSERT INTO users (first_name) VALUES ('michael')""")
def main():
queue = multiprocessing.Queue()
pool = multiprocessing.Pool(None, init, [queue])
for dirpath, dirnames, filenames in os.walk(PATH):
full_path_fnames = map(lambda fn: os.path.join(dirpath, fn),
filenames)
full_path_fnames = filter(is_valid_file, full_path_fnames)
pool.map(readFile, full_path_fnames)
if __name__ == '__main__':
sys.exit(main())
First, you're creating a different connection pool for each instance of your DB class. The pools having the same name doesn't make them the same pool
From the documentation:
It is not an error for multiple pools to have the same name. An application that must distinguish pools by their pool_name property should create each pool with a distinct name.
Besides that, sharing a database connection (or connection pool) between different processes would be a bad idea (and i highly doubt it would even work correctly), so each process using it's own connections is actually what you should aim for.
You could just initialize the pool in your init initializer as a global variable and use that instead.
Very simple example:
from multiprocessing import Pool
from mysql.connector.pooling import MySQLConnectionPool
from mysql.connector import connect
import os
pool = None
def init():
global pool
print("PID %d: initializing pool..." % os.getpid())
pool = MySQLConnectionPool(...)
def do_work(q):
con = pool.get_connection()
print("PID %d: using connection %s" % (os.getpid(), con))
c = con.cursor()
c.execute(q)
res = c.fetchall()
con.close()
return res
def main():
p = Pool(initializer=init)
for res in p.map(do_work, ['select * from test']*8):
print(res)
p.close()
p.join()
if __name__ == '__main__':
main()
Or just use a simple connection instead of a connection pool, as only one connection will be active in each process at a time anyway.
The number of concurrently used connections is implicitly limited by the size of the multiprocessing.Pool.
#!/usr/bin/python
# -*- coding: utf-8 -*-
import time
import mysql.connector.pooling
dbconfig = {
"host":"127.0.0.1",
"port":"3306",
"user":"root",
"password":"123456",
"database":"test",
}
class MySQLPool(object):
"""
create a pool when connect mysql, which will decrease the time spent in
request connection, create connection and close connection.
"""
def __init__(self, host="172.0.0.1", port="3306", user="root",
password="123456", database="test", pool_name="mypool",
pool_size=3):
res = {}
self._host = host
self._port = port
self._user = user
self._password = password
self._database = database
res["host"] = self._host
res["port"] = self._port
res["user"] = self._user
res["password"] = self._password
res["database"] = self._database
self.dbconfig = res
self.pool = self.create_pool(pool_name=pool_name, pool_size=pool_size)
def create_pool(self, pool_name="mypool", pool_size=3):
"""
Create a connection pool, after created, the request of connecting
MySQL could get a connection from this pool instead of request to
create a connection.
:param pool_name: the name of pool, default is "mypool"
:param pool_size: the size of pool, default is 3
:return: connection pool
"""
pool = mysql.connector.pooling.MySQLConnectionPool(
pool_name=pool_name,
pool_size=pool_size,
pool_reset_session=True,
**self.dbconfig)
return pool
def close(self, conn, cursor):
"""
A method used to close connection of mysql.
:param conn:
:param cursor:
:return:
"""
cursor.close()
conn.close()
def execute(self, sql, args=None, commit=False):
"""
Execute a sql, it could be with args and with out args. The usage is
similar with execute() function in module pymysql.
:param sql: sql clause
:param args: args need by sql clause
:param commit: whether to commit
:return: if commit, return None, else, return result
"""
# get connection form connection pool instead of create one.
conn = self.pool.get_connection()
cursor = conn.cursor()
if args:
cursor.execute(sql, args)
else:
cursor.execute(sql)
if commit is True:
conn.commit()
self.close(conn, cursor)
return None
else:
res = cursor.fetchall()
self.close(conn, cursor)
return res
def executemany(self, sql, args, commit=False):
"""
Execute with many args. Similar with executemany() function in pymysql.
args should be a sequence.
:param sql: sql clause
:param args: args
:param commit: commit or not.
:return: if commit, return None, else, return result
"""
# get connection form connection pool instead of create one.
conn = self.pool.get_connection()
cursor = conn.cursor()
cursor.executemany(sql, args)
if commit is True:
conn.commit()
self.close(conn, cursor)
return None
else:
res = cursor.fetchall()
self.close(conn, cursor)
return res
if __name__ == "__main__":
mysql_pool = MySQLPool(**dbconfig)
sql = "select * from store WHERE create_time < '2017-06-02'"
p = Pool()
for i in range(5):
p.apply_async(mysql_pool.execute, args=(sql,))
Code above creates a connection pool at the beginning, and get connections from it in execute(), once the connection pool has been created, the work is to remain it, since the pool is created only once, it will save the time to request for a connection every time you would like to connect to MySQL.
Hope it helps!
You created multiple DB object instance. In mysql.connector.pooling.py, pool_name is only a attribute to let you make out which pool it is. There is no mapping in the mysql pool.
So, you create multiple DB instance in def readfile(), then you will have several connection pool.
A Singleton is useful in this case.
(I spent several hours to find it out. In Tornado framework, each http get create a new handler, which leads to making a new connection.)
There may be synchronization issues if you're going to reuse MySQLConnection instances maintained by a pool, but just sharing a MySQLConnectionPool instance between worker processes and using connections retrieved by calling the method get_connection() would be okay, because a dedicated socket would be created for each MySQLConnection instance.
import multiprocessing
from mysql.connector import pooling
def f(cnxpool: pooling.MySQLConnectionPool) -> None:
# Dedicate connection instance for each worker process.
cnx = cnxpool.get_connection()
...
if __name__ == '__main__':
cnxpool = pooling.MySQLConnectionPool(
pool_name='pool',
pool_size=2,
)
p0 = multiprocessing.Process(target=f, args=(cnxpool,))
p1 = multiprocessing.Process(target=f, args=(cnxpool,))
p0.start()
p1.start()