commandserver: add new forking server implemented without using SocketServer
SocketServer.ForkingMixIn of Python 2.x has a couple of issues, such as:
- race condition that leads to 100% CPU usage (Python 2.6)
https://bugs.python.org/
issue21491
- can't wait for children belonging to different process groups (Python 2.6)
- leaves at least one zombie process (Python 2.6, 2.7)
https://bugs.python.org/
issue11109
The first two are critical because we do setpgid(0, 0) in child process to
isolate terminal signals. The last one isn't, but ForkingMixIn seems to be
doing silly. So there are two choices:
a) backport and maintain SocketServer until we can drop support for Python 2.x
b) replace SocketServer by simpler one and eliminate glue codes
I chose (b) because it's great time for getting rid of utterly complicated
SocketServer stuff, and preparing for future move towards prefork service.
New unixforkingservice is implemented loosely based on chg
531f8ef64be6. It
is monolithic but much simpler than SocketServer. unixservicehandler provides
customizing points for chg, and it will be shared with future prefork service.
Old unixservice class is still used by chgserver. It will be removed later.
Thanks to Jun Wu for investigating these issues.
#!/usr/bin/env python
from __future__ import absolute_import
import errno
import os
import signal
import sys
import time
if os.name =='nt':
import ctypes
def _check(ret, expectederr=None):
if ret == 0:
winerrno = ctypes.GetLastError()
if winerrno == expectederr:
return True
raise ctypes.WinError(winerrno)
def kill(pid, logfn, tryhard=True):
logfn('# Killing daemon process %d' % pid)
PROCESS_TERMINATE = 1
PROCESS_QUERY_INFORMATION = 0x400
SYNCHRONIZE = 0x00100000
WAIT_OBJECT_0 = 0
WAIT_TIMEOUT = 258
handle = ctypes.windll.kernel32.OpenProcess(
PROCESS_TERMINATE|SYNCHRONIZE|PROCESS_QUERY_INFORMATION,
False, pid)
if handle == 0:
_check(0, 87) # err 87 when process not found
return # process not found, already finished
try:
r = ctypes.windll.kernel32.WaitForSingleObject(handle, 100)
if r == WAIT_OBJECT_0:
pass # terminated, but process handle still available
elif r == WAIT_TIMEOUT:
_check(ctypes.windll.kernel32.TerminateProcess(handle, -1))
else:
_check(r)
# TODO?: forcefully kill when timeout
# and ?shorter waiting time? when tryhard==True
r = ctypes.windll.kernel32.WaitForSingleObject(handle, 100)
# timeout = 100 ms
if r == WAIT_OBJECT_0:
pass # process is terminated
elif r == WAIT_TIMEOUT:
logfn('# Daemon process %d is stuck')
else:
_check(r) # any error
except: #re-raises
ctypes.windll.kernel32.CloseHandle(handle) # no _check, keep error
raise
_check(ctypes.windll.kernel32.CloseHandle(handle))
else:
def kill(pid, logfn, tryhard=True):
try:
os.kill(pid, 0)
logfn('# Killing daemon process %d' % pid)
os.kill(pid, signal.SIGTERM)
if tryhard:
for i in range(10):
time.sleep(0.05)
os.kill(pid, 0)
else:
time.sleep(0.1)
os.kill(pid, 0)
logfn('# Daemon process %d is stuck - really killing it' % pid)
os.kill(pid, signal.SIGKILL)
except OSError as err:
if err.errno != errno.ESRCH:
raise
def killdaemons(pidfile, tryhard=True, remove=False, logfn=None):
if not logfn:
logfn = lambda s: s
# Kill off any leftover daemon processes
try:
fp = open(pidfile)
for line in fp:
try:
pid = int(line)
except ValueError:
continue
kill(pid, logfn, tryhard)
fp.close()
if remove:
os.unlink(pidfile)
except IOError:
pass
if __name__ == '__main__':
if len(sys.argv) > 1:
path, = sys.argv[1:]
else:
path = os.environ["DAEMON_PIDS"]
killdaemons(path)