annotate tests/killdaemons.py @ 35428:71427ff1dff8

workers: handling exceptions in windows workers

This adds handling of exceptions from worker threads and resurfaces them as if the function ran without workers.
If any of the threads throws, the main thread kills all running threads giving them 5 sec to handle the interruption and raises the first exception received.

We don't have to join threads if is_alive() is false

Test Plan:
Ran multiple updates/enable/disable sparse profile and things worked well

Ran test on CentOS- all tests passing on @ passed here

Added a forged exception into the worker code and got it properly resurfaced and the rest of workers killed: P58642088
PS C:\open\<repo>> ..\facebook-hg-rpms\build\hg\hg.exe --config extensions.fsmonitor=! sparse --enable-profile <profile>
updating [==>                                                                                                                ]  1300/39166 1m57sException in thread Thread-3:
Traceback (most recent call last):
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\threading.py", line 801, in __bootstrap_inner
    self.run()
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\worker.py", line 244, in run
    raise e
Exception: Forged exception

Exception in thread Thread-2:
Traceback (most recent call last):
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\threading.py", line 801, in __bootstrap_inner
    self.run()
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\worker.py", line 244, in run
    raise e
Exception: Forged exception
<...>
Traceback (most recent call last):
  File "C:\open\facebook-hg-rpms\build\hg\hgexe.py", line 41, in <module>
    dispatch.run()
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\dispatch.py", line 85, in run
    status = (dispatch(req) or 0) & 255
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\dispatch.py", line 173, in dispatch
    ret = _runcatch(req)
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\dispatch.py", line 324, in _runcatch
    return _callcatch(ui, _runcatchfunc)
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\dispatch.py", line 332, in _callcatch
    return scmutil.callcatch(ui, func)
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\scmutil.py", line 154, in callcatch
    return func()
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\dispatch.py", line 314, in _runcatchfunc
    return _dispatch(req)
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\dispatch.py", line 951, in _dispatch
    cmdpats, cmdoptions)
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\remotefilelog\__init__.py", line 415, in runcommand
    return orig(lui, repo, *args, **kwargs)
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\hgext3rd\undo.py", line 118, in _runcommandwrapper
    result = orig(lui, repo, cmd, fullargs, *args)
  File "C:\open\facebook-hg-rpms\build\hg\hgext\journal.py", line 84, in runcommand
    return orig(lui, repo, cmd, fullargs, *args)
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\hgext3rd\perftweaks.py", line 268, in _tracksparseprofiles
    res = runcommand(lui, repo, *args)
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\hgext3rd\perftweaks.py", line 256, in _trackdirstatesizes
    res = runcommand(lui, repo, *args)
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\hgext3rd\copytrace.py", line 144, in _runcommand
    return orig(lui, repo, cmd, fullargs, ui, *args, **kwargs)
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\hgext3rd\fbamend\hiddenoverride.py", line 119, in runcommand
    result = orig(lui, repo, cmd, fullargs, *args)
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\dispatch.py", line 712, in runcommand
    ret = _runcommand(ui, options, cmd, d)
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\dispatch.py", line 959, in _runcommand
    return cmdfunc()
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\dispatch.py", line 948, in <lambda>
    d = lambda: util.checksignature(func)(ui, *args, **strcmdopt)
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\util.py", line 1183, in check
    return func(*args, **kwargs)
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\hgext3rd\fbsparse.py", line 860, in sparse
    disableprofile=disableprofile, force=force)
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\hgext3rd\fbsparse.py", line 949, in _config
    len, _refresh(ui, repo, oldstatus, oldsparsematch, force))
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\hgext3rd\fbsparse.py", line 1116, in _refresh
    mergemod.applyupdates(repo, typeactions, repo[None], repo['.'], False)
  File "C:\open\facebook-hg-rpms\build\hg\hg-python\lib\site-packages\remotefilelog\__init__.py", line 311, in applyupdates
    return orig(repo, actions, wctx, mctx, overwrite, labels=labels)
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\merge.py", line 1464, in applyupdates
    for i, item in prog:
  File "C:\open\facebook-hg-rpms\build\hg\mercurial\worker.py", line 286, in _windowsworker
    raise t.exception
Exception: Forged exception
PS C:\open\ovrsource>

Differential Revision: https://phab.mercurial-scm.org/D1459

#!/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

    _BOOL = ctypes.c_long
    _DWORD = ctypes.c_ulong
    _UINT = ctypes.c_uint
    _HANDLE = ctypes.c_void_p

    ctypes.windll.kernel32.CloseHandle.argtypes = [_HANDLE]
    ctypes.windll.kernel32.CloseHandle.restype = _BOOL

    ctypes.windll.kernel32.GetLastError.argtypes = []
    ctypes.windll.kernel32.GetLastError.restype = _DWORD

    ctypes.windll.kernel32.OpenProcess.argtypes = [_DWORD, _BOOL, _DWORD]
    ctypes.windll.kernel32.OpenProcess.restype = _HANDLE

    ctypes.windll.kernel32.TerminateProcess.argtypes = [_HANDLE, _UINT]
    ctypes.windll.kernel32.TerminateProcess.restype = _BOOL

    ctypes.windll.kernel32.WaitForSingleObject.argtypes = [_HANDLE, _DWORD]
    ctypes.windll.kernel32.WaitForSingleObject.restype = _DWORD

    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
        WAIT_FAILED = _DWORD(0xFFFFFFFF).value
        handle = ctypes.windll.kernel32.OpenProcess(
                PROCESS_TERMINATE|SYNCHRONIZE|PROCESS_QUERY_INFORMATION,
                False, pid)
        if handle is None:
            _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))
            elif r == WAIT_FAILED:
                _check(0)  # err stored in GetLastError()

            # 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')
            elif r == WAIT_FAILED:
                _check(0)  # err stored in GetLastError()
        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:
        pids = []
        with open(pidfile) as fp:
            for line in fp:
                try:
                    pid = int(line)
                    if pid <= 0:
                        raise ValueError
                except ValueError:
                    logfn('# Not killing daemon process %s - invalid pid'
                          % line.rstrip())
                    continue
                pids.append(pid)
        for pid in pids:
            kill(pid, logfn, tryhard)
        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)