# worker.py - master-slave parallelism support

#

# Copyright 2013 Facebook, Inc.

#

# This software may be used and distributed according to the terms of the

# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import errno

import os

import signal

import sys

import threading

import time

try:

    import selectors

    selectors.BaseSelector

except ImportError:

    from .thirdparty import selectors2 as selectors

from .i18n import _

from . import (

    encoding,

    error,

    pycompat,

    scmutil,

    util,

)

def countcpus():

    '''try to count the number of CPUs on the system'''

    # posix

    try:

        n = int(os.sysconf('SC_NPROCESSORS_ONLN'))

        if n > 0:

            return n

    except (AttributeError, ValueError):

        pass

    # windows

    try:

        n = int(encoding.environ[b'NUMBER_OF_PROCESSORS'])

        if n > 0:

            return n

    except (KeyError, ValueError):

        pass

    return 1

def _numworkers(ui):

    s = ui.config(b'worker', b'numcpus')

    if s:

        try:

            n = int(s)

            if n >= 1:

                return n

        except ValueError:

            raise error.Abort(_(b'number of cpus must be an integer'))

    return min(max(countcpus(), 4), 32)

if pycompat.ispy3:

    class _blockingreader(object):

        def __init__(self, wrapped):

            self._wrapped = wrapped

        # Do NOT implement readinto() by making it delegate to

        # _wrapped.readinto(), since that is unbuffered. The unpickler is fine

        # with just read() and readline(), so we don't need to implement it.

        def readline(self):

            return self._wrapped.readline()

        # issue multiple reads until size is fulfilled

        def read(self, size=-1):

            if size < 0:

                return self._wrapped.readall()

            buf = bytearray(size)

            view = memoryview(buf)

            pos = 0

            while pos < size:

                ret = self._wrapped.readinto(view[pos:])

                if not ret:

                    break

                pos += ret

            del view

            del buf[pos:]

            return bytes(buf)

else:

    def _blockingreader(wrapped):

        return wrapped

if pycompat.isposix or pycompat.iswindows:

    _STARTUP_COST = 0.01

    # The Windows worker is thread based. If tasks are CPU bound, threads

    # in the presence of the GIL result in excessive context switching and

    # this overhead can slow down execution.

    _DISALLOW_THREAD_UNSAFE = pycompat.iswindows

else:

    _STARTUP_COST = 1e30

    _DISALLOW_THREAD_UNSAFE = False

def worthwhile(ui, costperop, nops, threadsafe=True):

    """try to determine whether the benefit of multiple processes can

    outweigh the cost of starting them"""

    if not threadsafe and _DISALLOW_THREAD_UNSAFE:

        return False

    linear = costperop * nops

    workers = _numworkers(ui)

    benefit = linear - (_STARTUP_COST * workers + linear / workers)

    return benefit >= 0.15

def worker(

    ui, costperarg, func, staticargs, args, hasretval=False, threadsafe=True

):

    """run a function, possibly in parallel in multiple worker

    processes.

    returns a progress iterator

    costperarg - cost of a single task

    func - function to run. It is expected to return a progress iterator.

    staticargs - arguments to pass to every invocation of the function

    args - arguments to split into chunks, to pass to individual

    workers

    hasretval - when True, func and the current function return an progress

    iterator then a dict (encoded as an iterator that yield many (False, ..)

    then a (True, dict)). The dicts are joined in some arbitrary order, so

    overlapping keys are a bad idea.

    threadsafe - whether work items are thread safe and can be executed using

    a thread-based worker. Should be disabled for CPU heavy tasks that don't

    release the GIL.

    """

    enabled = ui.configbool(b'worker', b'enabled')

    if enabled and worthwhile(ui, costperarg, len(args), threadsafe=threadsafe):

        return _platformworker(ui, func, staticargs, args, hasretval)

    return func(*staticargs + (args,))

def _posixworker(ui, func, staticargs, args, hasretval):

    workers = _numworkers(ui)

    oldhandler = signal.getsignal(signal.SIGINT)

    signal.signal(signal.SIGINT, signal.SIG_IGN)

    pids, problem = set(), [0]

    def killworkers():

        # unregister SIGCHLD handler as all children will be killed. This

        # function shouldn't be interrupted by another SIGCHLD; otherwise pids

        # could be updated while iterating, which would cause inconsistency.

        signal.signal(signal.SIGCHLD, oldchldhandler)

        # if one worker bails, there's no good reason to wait for the rest

        for p in pids:

            try:

                os.kill(p, signal.SIGTERM)

            except OSError as err:

                if err.errno != errno.ESRCH:

                    raise

    def waitforworkers(blocking=True):

        for pid in pids.copy():

            p = st = 0

            while True:

                try:

                    p, st = os.waitpid(pid, (0 if blocking else os.WNOHANG))

                    break

                except OSError as e:

                    if e.errno == errno.EINTR:

                        continue

                    elif e.errno == errno.ECHILD:

                        # child would already be reaped, but pids yet been

                        # updated (maybe interrupted just after waitpid)

                        pids.discard(pid)

                        break

                    else:

                        raise

            if not p:

                # skip subsequent steps, because child process should

                # be still running in this case

                continue

            pids.discard(p)

            st = _exitstatus(st)

            if st and not problem[0]:

                problem[0] = st

    def sigchldhandler(signum, frame):

        waitforworkers(blocking=False)

        if problem[0]:

            killworkers()

    oldchldhandler = signal.signal(signal.SIGCHLD, sigchldhandler)

    ui.flush()

    parentpid = os.getpid()

    pipes = []

    retval = {}

    for pargs in partition(args, min(workers, len(args))):

        # Every worker gets its own pipe to send results on, so we don't have to

        # implement atomic writes larger than PIPE_BUF. Each forked process has

        # its own pipe's descriptors in the local variables, and the parent

        # process has the full list of pipe descriptors (and it doesn't really

        # care what order they're in).

        rfd, wfd = os.pipe()

        pipes.append((rfd, wfd))

        # make sure we use os._exit in all worker code paths. otherwise the

        # worker may do some clean-ups which could cause surprises like

        # deadlock. see sshpeer.cleanup for example.

        # override error handling *before* fork. this is necessary because

        # exception (signal) may arrive after fork, before "pid =" assignment

        # completes, and other exception handler (dispatch.py) can lead to

        # unexpected code path without os._exit.

        ret = -1

        try:

            pid = os.fork()

            if pid == 0:

                signal.signal(signal.SIGINT, oldhandler)

                signal.signal(signal.SIGCHLD, oldchldhandler)

                def workerfunc():

                    for r, w in pipes[:-1]:

                        os.close(r)

                        os.close(w)

                    os.close(rfd)

                    for result in func(*(staticargs + (pargs,))):

                        os.write(wfd, util.pickle.dumps(result))

                    return 0

                ret = scmutil.callcatch(ui, workerfunc)

        except:  # parent re-raises, child never returns

            if os.getpid() == parentpid:

                raise

            exctype = sys.exc_info()[0]

            force = not issubclass(exctype, KeyboardInterrupt)

            ui.traceback(force=force)

        finally:

            if os.getpid() != parentpid:

                try:

                    ui.flush()

                except:  # never returns, no re-raises

                    pass

                finally:

                    os._exit(ret & 255)

        pids.add(pid)

    selector = selectors.DefaultSelector()

    for rfd, wfd in pipes:

        os.close(wfd)

        selector.register(os.fdopen(rfd, 'rb', 0), selectors.EVENT_READ)

    def cleanup():

        signal.signal(signal.SIGINT, oldhandler)

        waitforworkers()

        signal.signal(signal.SIGCHLD, oldchldhandler)

        selector.close()

        return problem[0]

    try:

        openpipes = len(pipes)

        while openpipes > 0:

            for key, events in selector.select():

                try:

                    res = util.pickle.load(_blockingreader(key.fileobj))

                    if hasretval and res[0]:

                        retval.update(res[1])

                    else:

                        yield res

                except EOFError:

                    selector.unregister(key.fileobj)

                    key.fileobj.close()

                    openpipes -= 1

                except IOError as e:

                    if e.errno == errno.EINTR:

                        continue

                    raise

    except:  # re-raises

        killworkers()

        cleanup()

        raise

    status = cleanup()

    if status:

        if status < 0:

            os.kill(os.getpid(), -status)

        raise error.WorkerError(status)

    if hasretval:

        yield True, retval

def _posixexitstatus(code):

    """convert a posix exit status into the same form returned by

    os.spawnv

    returns None if the process was stopped instead of exiting"""

    if os.WIFEXITED(code):

        return os.WEXITSTATUS(code)

    elif os.WIFSIGNALED(code):

        return -(os.WTERMSIG(code))

def _windowsworker(ui, func, staticargs, args, hasretval):

    class Worker(threading.Thread):

        def __init__(

            self, taskqueue, resultqueue, func, staticargs, *args, **kwargs

        ):

            threading.Thread.__init__(self, *args, **kwargs)

            self._taskqueue = taskqueue

            self._resultqueue = resultqueue

            self._func = func

            self._staticargs = staticargs

            self._interrupted = False

            self.daemon = True

            self.exception = None

        def interrupt(self):

            self._interrupted = True

        def run(self):

            try:

                while not self._taskqueue.empty():

                    try:

                        args = self._taskqueue.get_nowait()

                        for res in self._func(*self._staticargs + (args,)):

                            self._resultqueue.put(res)

                            # threading doesn't provide a native way to

                            # interrupt execution. handle it manually at every

                            # iteration.

                            if self._interrupted:

                                return

                    except pycompat.queue.Empty:

                        break

            except Exception as e:

                # store the exception such that the main thread can resurface

                # it as if the func was running without workers.

                self.exception = e

                raise

    threads = []

    def trykillworkers():

        # Allow up to 1 second to clean worker threads nicely

        cleanupend = time.time() + 1

        for t in threads:

            t.interrupt()

        for t in threads:

            remainingtime = cleanupend - time.time()

            t.join(remainingtime)

            if t.is_alive():

                # pass over the workers joining failure. it is more

                # important to surface the inital exception than the

                # fact that one of workers may be processing a large

                # task and does not get to handle the interruption.

                ui.warn(

                    _(

                        b"failed to kill worker threads while "

                        b"handling an exception\n"

                    )

                )

                return

    workers = _numworkers(ui)

    resultqueue = pycompat.queue.Queue()

    taskqueue = pycompat.queue.Queue()