Get python application memory usage - python

My main goal is to know how much memory my python application takes during execution.
I'm using python 2.7.5 on Windows-32 and Windows-64.
I found a way to get some info about my process here: http://code.activestate.com/recipes/578513-get-memory-usage-of-windows-processes-using-getpro/
Putting the code here for convenience:
"""Functions for getting memory usage of Windows processes."""
__all__ = ['get_current_process', 'get_memory_info', 'get_memory_usage']
import ctypes
from ctypes import wintypes
GetCurrentProcess = ctypes.windll.kernel32.GetCurrentProcess
GetCurrentProcess.argtypes = []
GetCurrentProcess.restype = wintypes.HANDLE
SIZE_T = ctypes.c_size_t
class PROCESS_MEMORY_COUNTERS_EX(ctypes.Structure):
_fields_ = [
('cb', wintypes.DWORD),
('PageFaultCount', wintypes.DWORD),
('PeakWorkingSetSize', SIZE_T),
('WorkingSetSize', SIZE_T),
('QuotaPeakPagedPoolUsage', SIZE_T),
('QuotaPagedPoolUsage', SIZE_T),
('QuotaPeakNonPagedPoolUsage', SIZE_T),
('QuotaNonPagedPoolUsage', SIZE_T),
('PagefileUsage', SIZE_T),
('PeakPagefileUsage', SIZE_T),
('PrivateUsage', SIZE_T),
]
GetProcessMemoryInfo = ctypes.windll.psapi.GetProcessMemoryInfo
GetProcessMemoryInfo.argtypes = [
wintypes.HANDLE,
ctypes.POINTER(PROCESS_MEMORY_COUNTERS_EX),
wintypes.DWORD,
]
GetProcessMemoryInfo.restype = wintypes.BOOL
def get_current_process():
"""Return handle to current process."""
return GetCurrentProcess()
def get_memory_info(process=None):
"""Return Win32 process memory counters structure as a dict."""
if process is None:
process = get_current_process()
counters = PROCESS_MEMORY_COUNTERS_EX()
ret = GetProcessMemoryInfo(process, ctypes.byref(counters),
ctypes.sizeof(counters))
if not ret:
raise ctypes.WinError()
info = dict((name, getattr(counters, name))
for name, _ in counters._fields_)
return info
def get_memory_usage(process=None):
"""Return this process's memory usage in bytes."""
info = get_memory_info(process=process)
return info['PrivateUsage']
if __name__ == '__main__':
import pprint
pprint.pprint(get_memory_info())
And this is the result:
{'PageFaultCount': 1942L,
'PagefileUsage': 4624384L,
'PeakPagefileUsage': 4624384L,
'PeakWorkingSetSize': 7544832L,
'PrivateUsage': 4624384L,
'QuotaNonPagedPoolUsage': 8520L,
'QuotaPagedPoolUsage': 117848L,
'QuotaPeakNonPagedPoolUsage': 8776L,
'QuotaPeakPagedPoolUsage': 117984L,
'WorkingSetSize': 7544832L,
'cb': 44L}
But this does not satisfy me. These results give me the whole python process information while what I need is only my specific application that runs on top of the Python framework.
I saw several memory profilers on the internet and also here in Stack Overflow but they are too big for me. The only information that I need is how much memory my app consumes by itself - without taking into account all the Python framework.
How can I achieve this?

Here is a simple easy pythonic way, based on (os, psutil) modules. Thanks to (Dataman) and (RichieHindle) answers.
import os
import psutil
## - Get Process Id of This Running Script -
proc_id = os.getpid()
print '\nProcess ID: ', proc_id
#--------------------------------------------------
## - Get More Info Using the Process Id
ObjInf = psutil.Process(proc_id)
print '\nProcess %s Info:' % proc_id, ObjInf
#--------------------------------------------------
## - Proccess Name of this program
name = ObjInf.name()
print '\nThis Program Process name:', name
#--------------------------------------------------
## - Print CPU Percentage
CpuPerc = ObjInf.cpu_percent()
print '\nCpu Percentage:', CpuPerc
#---------------------------------------------------
## - Print Memory Usage
memory_inf = ObjInf.memory_full_info()
print '\nMemory Info:', memory_inf, '\n'
## Print available commands you can do with the psutil obj
for c in dir(ObjInf):
print c
If your script is made in python, then your script is python itself, so it wouldn't run without it, thus you have to account for python memory usage also, if you want to see how much memory python consumes by itself just run an empty python script and you will deduct from there, that your script will be the main resources consumer, which happens to be made in python thus python.
Now if you want to check memory usage of a thread then this question might help -> Why does python thread consume so much memory?

Here is my script I am using to find the maximum amount of resources used during the execution of another script. I am using psutilto achieve this. You can tweak the script to make it suitable for your purposes.
import psutil, sys
import numpy as np
from time import sleep
pid = int(sys.argv[1])
delay = int(sys.argv[2])
p = psutil.Process(pid)
max_resources_used = -1
while p.is_running():
## p.memory_info()[0] returns 'rss' in Unix
r = int(p.memory_info()[0] / 1048576.0) ## resources used in Mega Bytes
max_resources_used = r if r > max_resources_used else max_resources_used
sleep(delay)
print("Maximum resources used: %s MB." %np.max(max_resources_used))
Usage:
python script.py pid delay_in_seconds
For example:
python script.py 55356 2
Explanation:
You need to find out the process ID and pass it as an argument to the script plus the time interval for checking the resource usage in seconds (i.e. every how many seconds the script checks the amount of used resources). The script keeps track of the memory usage until the process is running. Finally it returns the maximum amount of memory used in MB.

Related

Python ctypes - Receiving ERROR_PARTIAL_COPY when trying to ReadProcessMemory

My program, running elevated on Windows 10:
gets the PID of a running notepad.exe process
receives a handle to it via OpenProcess
Enumerates the baseAddress of the process module with the name notepad.exe on it
calls ReadProcessMemory
import ctypes
from ctypes import wintypes
import win32process
import psutil
targetProcess = "notepad.exe"
PROCESS_ALL_ACCESS = 0x1F0FFF
BUFFER_SIZE = 200
def getpid():
for proc in psutil.process_iter():
if proc.name() == targetProcess:
return proc.pid
def main():
status = ctypes.windll.ntdll.RtlAdjustPrivilege(20, 1, 0, ctypes.byref(ctypes.c_bool()))
if(status == -1073741727):
print("STATUS_PRIVILEGE_NOT_HELD - A required privilege is not held by the client.")
hProcess = ctypes.windll.kernel32.OpenProcess(PROCESS_ALL_ACCESS, False, getpid()) # handle to process
lpBuffer = ctypes.create_string_buffer(BUFFER_SIZE) # Buffer we want to write results to
targetProcessBaseAddress = None # base address of the target processes entry module
modules = win32process.EnumProcessModules(hProcess) # Retreive modules of target process
for module in modules:
name = str(win32process.GetModuleFileNameEx(hProcess, module))
if targetProcess in name:
targetProcessBaseAddress = hex(module)
count = ctypes.c_ulong(0)
res = ctypes.windll.kernel32.ReadProcessMemory(hProcess, targetProcessBaseAddress, ctypes.byref(lpBuffer), BUFFER_SIZE, ctypes.byref(count))
if res == 0:
err = ctypes.windll.kernel32.GetLastError()
if (err == 299):
print("ERROR_PARTIAL_COPY - Only part of a ReadProcessMemory or WriteProcessMemory request was completed.")
else:
print(err)
else:
print(lpBuffer.raw)
if __name__ == '__main__':
main()
Above is done via python3.8 using the native ctypes library.
I'm expecting to see a hexdump or any data other than 0x00,0x00.. but it seems my error is somewhere in the arguments provided to ReadProcessMemory, which is assumed due to error 299 returned from GetLastError(), which indicates:
"ERROR_PARTIAL_COPY - Only part of a ReadProcessMemory or WriteProcessMemory request was completed."
Not sure where I'm messing up, would be very grateful for suggestions and assistance!
ReadProcessMemory second argument is a LPCVOID (long pointer to const void*) but you're passing the result of hex which returns a string (which then would translate to a pointer to string in ctypes context).
Follow #CristiFati comment and use ctypes argtypes and restype which would have spotted the problem immediately.
Do not use directly GetLastError from the win32 API. The interpreter is free to call any Windows API during its life, thus when you call this API you don't know if it's the result from your script or an API that was called by the interpreter for its own purpose. For this, ctypes proposes a specific variable which caches the result in the form of ctypes.get_last_error.
The best way to do that is to start your script with something like that:
import ctypes
# obtain kernel32 WinDLL ensuring that we want to cache the last error for each API call.
kernel32 = ctypes.WinDLL("kernel32", use_last_error = True)
# start prototyping your APIs
OpenProcess = kernel32.OpenProcess
OpenProcess.argtypes = [ ... ]
OpenProcess.restype = ...
# then call the api
res = OpenProcess( ... )
#ensure you check the result by calling the cached last error
if not res:
err = ctypes.get_last_error()
# you might also raise
raise ctypes.WinError(err)

How to share mmap between python and node processes

I'm trying to share memory between a python process and a nodejs process started from the python process using an anonymous mmap. Essentially, the python process begins, initializes the mmap and starts a subprocess using either call or Popen to launch a child that runs some node code. This nodejs code uses mmap to try to access the same area in memory. However I get two different mappings and no data is shared between them. Why is this?
import mmap, math, os
from subprocess import call
mm = mmap.mmap( -1, 1024,
flags=mmap.MAP_SHARED | mmap.MAP_ANONYMOUS,
prot= mmap.PROT_READ | mmap.PROT_WRITE )
mm.seek(0)
mm.write('hello world!\n'.encode('utf-8'))
call([
'node', '-e',
"""
const mmap = require('mmap.js');
const fileBuf = mmap.alloc(
1024,
mmap.PROT_READ | mmap.PROT_WRITE,
mmap.MAP_SHARED| mmap.MAP_ANONYMOUS,
-1,
0
)
console.log(fileBuf.toString('utf-8'));
"""
])
The mmap.js that I am using is a NAPI of the original mmap c function. This is the github for this library.
EDIT:
Thanks to 'that other guy' for his answer. It was the correct one. Here's some sample code that works out of the box!:
test_mmap.py
import os, ctypes, posix_ipc, sys, mmap
from subprocess import call
SHARED_MEMORY_NAME = "/shared_memory"
memory = posix_ipc.SharedMemory(SHARED_MEMORY_NAME, posix_ipc.O_CREX,
size=1024)
mapFile = mmap.mmap(memory.fd, memory.size)
memory.close_fd()
mapFile.seek(0)
mapFile.write("Hello world!\n".encode('utf-8'))
mapFile.seek(0)
print("FROM PYTHON MAIN PROCESS: ", mapFile.readline().decode('utf-8'))
mapFile.seek(0)
call([
"node", "./test_mmap.js", SHARED_MEMORY_NAME
])
mapFile.close()
posix_ipc.unlink_shared_memory(SHARED_MEMORY_NAME)
test_mmap.js
const args = process.argv;
const mmap = require('mmap.js');
const shm = require('nodeshm');
const SHM_FILE_NAME=args[args.length-1];
let fd = shm.shm_open(SHM_FILE_NAME, shm.O_RDWR, 0600);
if (fd == -1){
console.log("FD COULD NOT BE OPENED!");
throw "here";
}
let mm = mmap.alloc(1024, mmap.PROT_READ | mmap.PROT_WRITE, mmap.MAP_SHARED, fd, 0);
console.log("FROM NODE: ", mm.slice(0, mm.indexOf('\n')).toString('utf-8'));
Sample output:
FROM PYTHON MAIN PROCESS: Hello world!
FROM NODE: Hello world!
Fortunately this doesn't work: imagine how confusing if all of the system's MAP_ANONYMOUS mappings were against the same area and kept overwriting each other.
Instead, use shm_open to create a new handle you can mmap in both processes. This is a portable wrapper around the equally valid but less portable strategy of creating and mmap'ing a file in /dev/shm/.

concurrent.futures: how to submit task and process Futures in 2 separate Threads?

I'm trying to improving the interactive output of small CLI program walking a directory to process files, and using a Rich progress bar to display the progression of the tasks.
At the moment, I'm doing this in 2 steps:
pool.submit() all the tasks
for future in as_completed(xxxx) wait for the next future available.
The problem is that the first step (pool.submit) might take some time (since I'm walking the directory), and the UI isn't updated, even though futures have already been available.
So, I tried to come up with a Thread that would submit on my pool, while the main thread would wait on the next Future and update the UI:
"""
Usage: walker.py [options] <file/directory>...
Options:
-r --recursive Walk directories recursively
-w WORKERS --workers=WORKERS Specify the number of process pool workers [default: 4]
-d --debug Enable debug output
-h --help Display this message
"""
import os
import threading
import time
from concurrent.futures._base import as_completed
from concurrent.futures.process import ProcessPoolExecutor
from pathlib import Path
from random import randint
from typing import List
from docopt import docopt
from rich.console import Console
from rich.progress import BarColumn, Progress, TextColumn
def walk_filepath_list(filepath_list: List[Path], recursive: bool = False):
for path in filepath_list:
if path.is_dir() and not path.is_symlink():
if recursive:
for f in os.scandir(path):
yield from walk_filepath_list([Path(f)], recursive)
else:
yield from (Path(f) for f in os.scandir(path))
elif path.is_file():
yield path
def process_task(filepath):
rand = randint(0, 1)
time.sleep(rand)
def thread_submit(pool, filepath_list, recursive, future_to_filepath):
for filepath in walk_filepath_list(filepath_list, recursive):
future = pool.submit(process_task, filepath)
# update shared dict
future_to_filepath[future] = filepath
def main(args):
filepath_list = [Path(entry) for entry in args["<file/directory>"]]
debug = args["--debug"]
workers = int(args["--workers"])
recursive = args["--recursive"]
console = Console()
process_bar = Progress(
TextColumn("[bold blue]Processing...", justify="left"),
BarColumn(bar_width=None),
"{task.completed}/{task.total}",
"•",
"[progress.percentage]{task.percentage:>3.1f}%",
console=console,
)
process_bar.start()
# we need to consume the iterator once to get the total
# for the progress bar
count = sum(1 for i in walk_filepath_list(filepath_list, recursive))
task_process_bar = process_bar.add_task("Main task", total=count)
with ProcessPoolExecutor(max_workers=workers) as pool:
# shared dict between threads
# [Future] => [filepath]
future_to_filepath = {}
submit_thread = threading.Thread(
target=thread_submit, args=(pool, filepath_list, recursive, future_to_filepath)
)
submit_thread.start()
while len(future_to_filepath.keys()) != count:
for future in as_completed(future_to_filepath):
filepath = future_to_filepath[future]
# print(f"processing future: {filepath}")
try:
data = future.result()
finally:
# update progress bar
process_bar.update(task_process_bar, advance=1)
process_bar.stop()
def entrypoint():
args = docopt(__doc__)
main(args)
if __name__ == "__main__":
entrypoint()
However, the progress bar isn't updated as expected.
Worse, there are cases where the processing doesn't seem to end.
is it a race conditions when I update my dict future_to_filepath ?
how would you go to have a submit thread and a process_results thread with concurrent.futures ?
Thank you SO !
See my comments to your question and then:
Change:
submit_thread = threading.Thread(
target=thread_submit, args=(pool, filepath_list, recursive, future_to_filepath)
)
submit_thread.start()
To:
thread_submit(pool, filepath_list, recursive, future_to_filepath)
(a change to this function name, since it is no longer running as a separate thread, would be a good thing -- how about create_futures?)
And remove the outer loop:
while len(future_to_filepath.keys()) != count:
Finally, it is not clear what your real process_task will do with the file but it certainly seems possible that it will be I/O bound. In that case, you might benefit instead from using the ThreadPoolExecutor class, easily substitutable for the ProcessPoolExecutor class, in which case you should consider specifying a much larger number of workers, possibly equal to count. Since your current process_task is doing nothing much more than sleeping, it would probably profit from threading with the larger number of workers.
Update
One thing you can do to reduce the time it takes to run walk_filepath_list is to modify the function to be passed a single path to walk rather than a list and to process each path that was in the original list concurrently in separate threads. In the code below I am using the ThreadPoolExecutor map function for convenience which really requires that the arguments to the (newly renamed) walk_filepath function be reversed so that I can use functools.partial to "harcode" the first argument, recursive, for all the calls:
from concurrent.futures import ThreadPoolExecutor
from functools import partial
def walk_filepath(recursive: bool = False, path: Path = None):
if path.is_dir() and not path.is_symlink():
if recursive:
for f in os.scandir(path):
yield from walk_filepath(recursive, Path(f))
else:
yield from (Path(f) for f in os.scandir(path))
elif path.is_file():
yield path
def walker(recursive, path):
return list(walk_filepath(recursive, path))
def thread_submit(pool, filepath_list, recursive, future_to_filepath):
n_workers = len(filepath_list)
with ThreadPoolExecutor(max_workers=n_workers) as executor:
filepath_lists = executor.map(partial(walker, recursive), filepath_list)
for filepath_list in filepath_lists:
for filepath in filepath_list:
future = pool.submit(process_task, filepath)
# update shared dict
future_to_filepath[future] = filepath
Update 2
A benchmark of the above code reveals that it does not save time (perhaps if the directories were on different physical drives?).

How to check whether screen is off in Mac/Python?

How do I check whether the screen is off due to the Energy Saver settings in System Preferences under Mac/Python?
Quick and dirty solution: call ioreg and parse the output.
import subprocess
import re
POWER_MGMT_RE = re.compile(r'IOPowerManagement.*{(.*)}')
def display_status():
output = subprocess.check_output(
'ioreg -w 0 -c IODisplayWrangler -r IODisplayWrangler'.split())
status = POWER_MGMT_RE.search(output).group(1)
return dict((k[1:-1], v) for (k, v) in (x.split('=') for x in
status.split(',')))
In my computer, the value for CurrentPowerState is 4 when the screen is on and 1 when the screen is off.
Better solution: use ctypes to get that information directly from IOKit.
The only way i can think off is by using OSX pmset Power Management CML Tool
DESCRIPTION
pmset changes and reads power management settings such as idle sleep timing, wake on administrative
access, automatic restart on power loss, etc.
Refer to the following link, it will provide a great deal of information that should aid you in accomplishing exactly what you are looking for.
http://managingamac.blogspot.com/2012/12/power-assertions-in-python.html
I will include the code provided by the link for "saving and documentation" purposes:
#!/usr/bin/python
import ctypes
import CoreFoundation
import objc
import subprocess
import time
def SetUpIOFramework():
# load the IOKit library
framework = ctypes.cdll.LoadLibrary(
'/System/Library/Frameworks/IOKit.framework/IOKit')
# declare parameters as described in IOPMLib.h
framework.IOPMAssertionCreateWithName.argtypes = [
ctypes.c_void_p, # CFStringRef
ctypes.c_uint32, # IOPMAssertionLevel
ctypes.c_void_p, # CFStringRef
ctypes.POINTER(ctypes.c_uint32)] # IOPMAssertionID
framework.IOPMAssertionRelease.argtypes = [
ctypes.c_uint32] # IOPMAssertionID
return framework
def StringToCFString(string):
# we'll need to convert our strings before use
return objc.pyobjc_id(
CoreFoundation.CFStringCreateWithCString(
None, string,
CoreFoundation.kCFStringEncodingASCII).nsstring())
def AssertionCreateWithName(framework, a_type,
a_level, a_reason):
# this method will create an assertion using the IOKit library
# several parameters
a_id = ctypes.c_uint32(0)
a_type = StringToCFString(a_type)
a_reason = StringToCFString(a_reason)
a_error = framework.IOPMAssertionCreateWithName(
a_type, a_level, a_reason, ctypes.byref(a_id))
# we get back a 0 or stderr, along with a unique c_uint
# representing the assertion ID so we can release it later
return a_error, a_id
def AssertionRelease(framework, assertion_id):
# releasing the assertion is easy, and also returns a 0 on
# success, or stderr otherwise
return framework.IOPMAssertionRelease(assertion_id)
def main():
# let's create a no idle assertion for 30 seconds
no_idle = 'NoIdleSleepAssertion'
reason = 'Test of Pythonic power assertions'
# first, we'll need the IOKit framework
framework = SetUpIOFramework()
# next, create the assertion and save the ID!
ret, a_id = AssertionCreateWithName(framework, no_idle, 255, reason)
print '\n\nCreating power assertion: status %s, id %s\n\n' % (ret, a_id)
# subprocess a call to pmset to verify the assertion worked
subprocess.call(['pmset', '-g', 'assertions'])
time.sleep(5)
# finally, release the assertion of the ID we saved earlier
AssertionRelease(framework, a_id)
print '\n\nReleasing power assertion: id %s\n\n' % a_id
# verify the assertion has been removed
subprocess.call(['pmset', '-g', 'assertions'])
if __name__ == '__main__':
main()
https://opensource.apple.com/source/PowerManagement/PowerManagement-211/pmset/pmset.c
The code relies on IOPMLib, which functions to make assertions, schedule power events, measure thermals, and more.
https://developer.apple.com/documentation/iokit/iopmlib_h
To call these functions through Python, we must go through the IOKit Framework.
https://developer.apple.com/library/archive/documentation/DeviceDrivers/Conceptual/IOKitFundamentals/Introduction/Introduction.html
In order for us to manipulate C data types in Python, we'll use a foreign function interface called ctypes.
http://python.net/crew/theller/ctypes/
Here's the wrapper the author describe's on the page; written by Michael Lynn. The code i posted from the Author's link above is a rewrite of this code to make it more understandable.
https://github.com/pudquick/pypmset/blob/master/pypmset.py

Make sure only a single instance of a program is running

Is there a Pythonic way to have only one instance of a program running?
The only reasonable solution I've come up with is trying to run it as a server on some port, then second program trying to bind to same port - fails. But it's not really a great idea, maybe there's something more lightweight than this?
(Take into consideration that program is expected to fail sometimes, i.e. segfault - so things like "lock file" won't work)
The following code should do the job, it is cross-platform and runs on Python 2.4-3.2. I tested it on Windows, OS X and Linux.
from tendo import singleton
me = singleton.SingleInstance() # will sys.exit(-1) if other instance is running
The latest code version is available singleton.py. Please file bugs here.
You can install tend using one of the following methods:
easy_install tendo
pip install tendo
manually by getting it from http://pypi.python.org/pypi/tendo
Simple, cross-platform solution, found in another question by zgoda:
import fcntl
import os
import sys
def instance_already_running(label="default"):
"""
Detect if an an instance with the label is already running, globally
at the operating system level.
Using `os.open` ensures that the file pointer won't be closed
by Python's garbage collector after the function's scope is exited.
The lock will be released when the program exits, or could be
released if the file pointer were closed.
"""
lock_file_pointer = os.open(f"/tmp/instance_{label}.lock", os.O_WRONLY)
try:
fcntl.lockf(lock_file_pointer, fcntl.LOCK_EX | fcntl.LOCK_NB)
already_running = False
except IOError:
already_running = True
return already_running
A lot like S.Lott's suggestion, but with the code.
This code is Linux specific. It uses 'abstract' UNIX domain sockets, but it is simple and won't leave stale lock files around. I prefer it to the solution above because it doesn't require a specially reserved TCP port.
try:
import socket
s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
## Create an abstract socket, by prefixing it with null.
s.bind( '\0postconnect_gateway_notify_lock')
except socket.error as e:
error_code = e.args[0]
error_string = e.args[1]
print "Process already running (%d:%s ). Exiting" % ( error_code, error_string)
sys.exit (0)
The unique string postconnect_gateway_notify_lock can be changed to allow multiple programs that need a single instance enforced.
I don't know if it's pythonic enough, but in the Java world listening on a defined port is a pretty widely used solution, as it works on all major platforms and doesn't have any problems with crashing programs.
Another advantage of listening to a port is that you could send a command to the running instance. For example when the users starts the program a second time, you could send the running instance a command to tell it to open another window (that's what Firefox does, for example. I don't know if they use TCP ports or named pipes or something like that, 'though).
Never written python before, but this is what I've just implemented in mycheckpoint, to prevent it being started twice or more by crond:
import os
import sys
import fcntl
fh=0
def run_once():
global fh
fh=open(os.path.realpath(__file__),'r')
try:
fcntl.flock(fh,fcntl.LOCK_EX|fcntl.LOCK_NB)
except:
os._exit(0)
run_once()
Found Slava-N's suggestion after posting this in another issue (http://stackoverflow.com/questions/2959474). This one is called as a function, locks the executing scripts file (not a pid file) and maintains the lock until the script ends (normal or error).
Use a pid file. You have some known location, "/path/to/pidfile" and at startup you do something like this (partially pseudocode because I'm pre-coffee and don't want to work all that hard):
import os, os.path
pidfilePath = """/path/to/pidfile"""
if os.path.exists(pidfilePath):
pidfile = open(pidfilePath,"r")
pidString = pidfile.read()
if <pidString is equal to os.getpid()>:
# something is real weird
Sys.exit(BADCODE)
else:
<use ps or pidof to see if the process with pid pidString is still running>
if <process with pid == 'pidString' is still running>:
Sys.exit(ALREADAYRUNNING)
else:
# the previous server must have crashed
<log server had crashed>
<reopen pidfilePath for writing>
pidfile.write(os.getpid())
else:
<open pidfilePath for writing>
pidfile.write(os.getpid())
So, in other words, you're checking if a pidfile exists; if not, write your pid to that file. If the pidfile does exist, then check to see if the pid is the pid of a running process; if so, then you've got another live process running, so just shut down. If not, then the previous process crashed, so log it, and then write your own pid to the file in place of the old one. Then continue.
The best solution for this on windows is to use mutexes as suggested by #zgoda.
import win32event
import win32api
from winerror import ERROR_ALREADY_EXISTS
mutex = win32event.CreateMutex(None, False, 'name')
last_error = win32api.GetLastError()
if last_error == ERROR_ALREADY_EXISTS:
print("App instance already running")
Some answers use fctnl (included also in #sorin tendo package) which is not available on windows and should you try to freeze your python app using a package like pyinstaller which does static imports, it throws an error.
Also, using the lock file method, creates a read-only problem with database files( experienced this with sqlite3).
Here is my eventual Windows-only solution. Put the following into a module, perhaps called 'onlyone.py', or whatever. Include that module directly into your __ main __ python script file.
import win32event, win32api, winerror, time, sys, os
main_path = os.path.abspath(sys.modules['__main__'].__file__).replace("\\", "/")
first = True
while True:
mutex = win32event.CreateMutex(None, False, main_path + "_{<paste YOUR GUID HERE>}")
if win32api.GetLastError() == 0:
break
win32api.CloseHandle(mutex)
if first:
print "Another instance of %s running, please wait for completion" % main_path
first = False
time.sleep(1)
Explanation
The code attempts to create a mutex with name derived from the full path to the script. We use forward-slashes to avoid potential confusion with the real file system.
Advantages
No configuration or 'magic' identifiers needed, use it in as many different scripts as needed.
No stale files left around, the mutex dies with you.
Prints a helpful message when waiting
This may work.
Attempt create a PID file to a known location. If you fail, someone has the file locked, you're done.
When you finish normally, close and remove the PID file, so someone else can overwrite it.
You can wrap your program in a shell script that removes the PID file even if your program crashes.
You can, also, use the PID file to kill the program if it hangs.
For anybody using wxPython for their application, you can use the function wx.SingleInstanceChecker documented here.
I personally use a subclass of wx.App which makes use of wx.SingleInstanceChecker and returns False from OnInit() if there is an existing instance of the app already executing like so:
import wx
class SingleApp(wx.App):
"""
class that extends wx.App and only permits a single running instance.
"""
def OnInit(self):
"""
wx.App init function that returns False if the app is already running.
"""
self.name = "SingleApp-%s".format(wx.GetUserId())
self.instance = wx.SingleInstanceChecker(self.name)
if self.instance.IsAnotherRunning():
wx.MessageBox(
"An instance of the application is already running",
"Error",
wx.OK | wx.ICON_WARNING
)
return False
return True
This is a simple drop-in replacement for wx.App that prohibits multiple instances. To use it simply replace wx.App with SingleApp in your code like so:
app = SingleApp(redirect=False)
frame = wx.Frame(None, wx.ID_ANY, "Hello World")
frame.Show(True)
app.MainLoop()
Using a lock-file is a quite common approach on unix. If it crashes, you have to clean up manually. You could stor the PID in the file, and on startup check if there is a process with this PID, overriding the lock-file if not. (However, you also need a lock around the read-file-check-pid-rewrite-file). You will find what you need for getting and checking pid in the os-package. The common way of checking if there exists a process with a given pid, is to send it a non-fatal signal.
Other alternatives could be combining this with flock or posix semaphores.
Opening a network socket, as saua proposed, would probably be the easiest and most portable.
I'm posting this as an answer because I'm a new user and Stack Overflow won't let me vote yet.
Sorin Sbarnea's solution works for me under OS X, Linux and Windows, and I am grateful for it.
However, tempfile.gettempdir() behaves one way under OS X and Windows and another under other some/many/all(?) *nixes (ignoring the fact that OS X is also Unix!). The difference is important to this code.
OS X and Windows have user-specific temp directories, so a tempfile created by one user isn't visible to another user. By contrast, under many versions of *nix (I tested Ubuntu 9, RHEL 5, OpenSolaris 2008 and FreeBSD 8), the temp dir is /tmp for all users.
That means that when the lockfile is created on a multi-user machine, it's created in /tmp and only the user who creates the lockfile the first time will be able to run the application.
A possible solution is to embed the current username in the name of the lock file.
It's worth noting that the OP's solution of grabbing a port will also misbehave on a multi-user machine.
Building upon Roberto Rosario's answer, I come up with the following function:
SOCKET = None
def run_single_instance(uniq_name):
try:
import socket
global SOCKET
SOCKET = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
## Create an abstract socket, by prefixing it with null.
# this relies on a feature only in linux, when current process quits, the
# socket will be deleted.
SOCKET.bind('\0' + uniq_name)
return True
except socket.error as e:
return False
We need to define global SOCKET vaiable since it will only be garbage collected when the whole process quits. If we declare a local variable in the function, it will go out of scope after the function exits, thus the socket be deleted.
All the credit should go to Roberto Rosario, since I only clarify and elaborate upon his code. And this code will work only on Linux, as the following quoted text from https://troydhanson.github.io/network/Unix_domain_sockets.html explains:
Linux has a special feature: if the pathname for a UNIX domain socket
begins with a null byte \0, its name is not mapped into the
filesystem. Thus it won’t collide with other names in the filesystem.
Also, when a server closes its UNIX domain listening socket in the
abstract namespace, its file is deleted; with regular UNIX domain
sockets, the file persists after the server closes it.
Late answer, but for windows you can use:
from win32event import CreateMutex
from win32api import CloseHandle, GetLastError
from winerror import ERROR_ALREADY_EXISTS
import sys
class singleinstance:
""" Limits application to single instance """
def __init__(self):
self.mutexname = "testmutex_{D0E858DF-985E-4907-B7FB-8D732C3FC3B9}"
self.mutex = CreateMutex(None, False, self.mutexname)
self.lasterror = GetLastError()
def alreadyrunning(self):
return (self.lasterror == ERROR_ALREADY_EXISTS)
def __del__(self):
if self.mutex:
CloseHandle(self.mutex)
Usage
# do this at beginnig of your application
myapp = singleinstance()
# check is another instance of same program running
if myapp.alreadyrunning():
print ("Another instance of this program is already running")
sys.exit(1)
Here is a cross platform example that I've tested on Windows Server 2016 and Ubuntu 20.04 using Python 3.7.9:
import os
class SingleInstanceChecker:
def __init__(self, id):
if isWin():
ensure_win32api()
self.mutexname = id
self.lock = win32event.CreateMutex(None, False, self.mutexname)
self.running = (win32api.GetLastError() == winerror.ERROR_ALREADY_EXISTS)
else:
ensure_fcntl()
self.lock = open(f"/tmp/isnstance_{id}.lock", 'wb')
try:
fcntl.lockf(self.lock, fcntl.LOCK_EX | fcntl.LOCK_NB)
self.running = False
except IOError:
self.running = True
def already_running(self):
return self.running
def __del__(self):
if self.lock:
try:
if isWin():
win32api.CloseHandle(self.lock)
else:
os.close(self.lock)
except Exception as ex:
pass
# ---------------------------------------
# Utility Functions
# Dynamically load win32api on demand
# Install with: pip install pywin32
win32api=winerror=win32event=None
def ensure_win32api():
global win32api,winerror,win32event
if win32api is None:
import win32api
import winerror
import win32event
# Dynamically load fcntl on demand
# Install with: pip install fcntl
fcntl=None
def ensure_fcntl():
global fcntl
if fcntl is None:
import fcntl
def isWin():
return (os.name == 'nt')
# ---------------------------------------
Here is it in use:
import time, sys
def main(argv):
_timeout = 10
print("main() called. sleeping for %s seconds" % _timeout)
time.sleep(_timeout)
print("DONE")
if __name__ == '__main__':
SCR_NAME = "my_script"
sic = SingleInstanceChecker(SCR_NAME)
if sic.already_running():
print("An instance of {} is already running.".format(SCR_NAME))
sys.exit(1)
else:
main(sys.argv[1:])
I use single_process on my gentoo;
pip install single_process
example:
from single_process import single_process
#single_process
def main():
print 1
if __name__ == "__main__":
main()
refer: https://pypi.python.org/pypi/single_process/
I keep suspecting there ought to be a good POSIXy solution using process groups, without having to hit the file system, but I can't quite nail it down. Something like:
On startup, your process sends a 'kill -0' to all processes in a particular group. If any such processes exist, it exits. Then it joins the group. No other processes use that group.
However, this has a race condition - multiple processes could all do this at precisely the same time and all end up joining the group and running simultaneously. By the time you've added some sort of mutex to make it watertight, you no longer need the process groups.
This might be acceptable if your process only gets started by cron, once every minute or every hour, but it makes me a bit nervous that it would go wrong precisely on the day when you don't want it to.
I guess this isn't a very good solution after all, unless someone can improve on it?
I ran into this exact problem last week, and although I did find some good solutions, I decided to make a very simple and clean python package and uploaded it to PyPI. It differs from tendo in that it can lock any string resource name. Although you could certainly lock __file__ to achieve the same effect.
Install with: pip install quicklock
Using it is extremely simple:
[nate#Nates-MacBook-Pro-3 ~/live] python
Python 2.7.6 (default, Sep 9 2014, 15:04:36)
[GCC 4.2.1 Compatible Apple LLVM 6.0 (clang-600.0.39)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> from quicklock import singleton
>>> # Let's create a lock so that only one instance of a script will run
...
>>> singleton('hello world')
>>>
>>> # Let's try to do that again, this should fail
...
>>> singleton('hello world')
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/nate/live/gallery/env/lib/python2.7/site-packages/quicklock/quicklock.py", line 47, in singleton
raise RuntimeError('Resource <{}> is currently locked by <Process {}: "{}">'.format(resource, other_process.pid, other_process.name()))
RuntimeError: Resource <hello world> is currently locked by <Process 24801: "python">
>>>
>>> # But if we quit this process, we release the lock automatically
...
>>> ^D
[nate#Nates-MacBook-Pro-3 ~/live] python
Python 2.7.6 (default, Sep 9 2014, 15:04:36)
[GCC 4.2.1 Compatible Apple LLVM 6.0 (clang-600.0.39)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> from quicklock import singleton
>>> singleton('hello world')
>>>
>>> # No exception was thrown, we own 'hello world'!
Take a look: https://pypi.python.org/pypi/quicklock
linux example
This method is based on the creation of a temporary file automatically deleted after you close the application.
the program launch we verify the existence of the file;
if the file exists ( there is a pending execution) , the program is closed ; otherwise it creates the file and continues the execution of the program.
from tempfile import *
import time
import os
import sys
f = NamedTemporaryFile( prefix='lock01_', delete=True) if not [f for f in os.listdir('/tmp') if f.find('lock01_')!=-1] else sys.exit()
YOUR CODE COMES HERE
On a Linux system one could also ask
pgrep -a for the number of instances, the script
is found in the process list (option -a reveals the
full command line string). E.g.
import os
import sys
import subprocess
procOut = subprocess.check_output( "/bin/pgrep -u $UID -a python", shell=True,
executable="/bin/bash", universal_newlines=True)
if procOut.count( os.path.basename(__file__)) > 1 :
sys.exit( ("found another instance of >{}<, quitting."
).format( os.path.basename(__file__)))
Remove -u $UID if the restriction should apply to all users.
Disclaimer: a) it is assumed that the script's (base)name is unique, b) there might be race conditions.
Here's a good example for django with contextmanager and memcached:
https://docs.celeryproject.org/en/latest/tutorials/task-cookbook.html
Can be used to protect simultaneous operation on different hosts.
Can be used to manage multiple tasks.
Can also be changed for simple python scripts.
My modification of the above code is here:
import time
from contextlib import contextmanager
from django.core.cache import cache
#contextmanager
def memcache_lock(lock_key, lock_value, lock_expire):
timeout_at = time.monotonic() + lock_expire - 3
# cache.add fails if the key already exists
status = cache.add(lock_key, lock_value, lock_expire)
try:
yield status
finally:
# memcache delete is very slow, but we have to use it to take
# advantage of using add() for atomic locking
if time.monotonic() < timeout_at and status:
# don't release the lock if we exceeded the timeout
# to lessen the chance of releasing an expired lock owned by someone else
# also don't release the lock if we didn't acquire it
cache.delete(lock_key)
LOCK_EXPIRE = 60 * 10 # Lock expires in 10 minutes
def main():
lock_name, lock_value = "lock_1", "locked"
with memcache_lock(lock_name, lock_value, LOCK_EXPIRE) as acquired:
if acquired:
# single instance code here:
pass
if __name__ == "__main__":
main()
Here is a cross-platform implementation, creating a temporary lock file using a context manager.
Can be used to manage multiple tasks.
import os
from contextlib import contextmanager
from time import sleep
class ExceptionTaskInProgress(Exception):
pass
# Context manager for suppressing exceptions
class SuppressException:
def __init__(self):
pass
def __enter__(self):
return self
def __exit__(self, *exc):
return True
# Context manager for task
class TaskSingleInstance:
def __init__(self, task_name, lock_path):
self.task_name = task_name
self.lock_path = lock_path
self.lock_filename = os.path.join(self.lock_path, self.task_name + ".lock")
if os.path.exists(self.lock_filename):
raise ExceptionTaskInProgress("Resource already in use")
def __enter__(self):
self.fl = open(self.lock_filename, "w")
return self
def __exit__(self, exc_type, exc_val, exc_tb):
self.fl.close()
os.unlink(self.lock_filename)
# Here the task is silently interrupted
# if it is already running on another instance.
def main1():
task_name = "task1"
tmp_filename_path = "."
with SuppressException():
with TaskSingleInstance(task_name, tmp_filename_path):
print("The task `{}` has started.".format(task_name))
# The single task instance code is here.
sleep(5)
print("The task `{}` has completed.".format(task_name))
# Here the task is interrupted with a message
# if it is already running in another instance.
def main2():
task_name = "task1"
tmp_filename_path = "."
try:
with TaskSingleInstance(task_name, tmp_filename_path):
print("The task `{}` has started.".format(task_name))
# The single task instance code is here.
sleep(5)
print("Task `{}` completed.".format(task_name))
except ExceptionTaskInProgress as ex:
print("The task `{}` is already running.".format(task_name))
if __name__ == "__main__":
main1()
main2()
import sys,os
# start program
try: # (1)
os.unlink('lock') # (2)
fd=os.open("lock", os.O_CREAT|os.O_EXCL) # (3)
except:
try: fd=os.open("lock", os.O_CREAT|os.O_EXCL) # (4)
except:
print "Another Program running !.." # (5)
sys.exit()
# your program ...
# ...
# exit program
try: os.close(fd) # (6)
except: pass
try: os.unlink('lock')
except: pass
sys.exit()

Categories

Resources