worker: Use buffered input from the pickle stream

On Python 3, "pickle.load" will raise an exception ("_pickle.UnpicklingError:
pickle data was truncated") when it gets a short read, i.e. it receives fewer
bytes than it requested.

On our build machine, Mercurial seems to frequently hit this problem while
updating a mozilla-central clone iff it gets scheduled in batch mode. It is easy
to trigger with:

    #wipe the workdir
    rm -rf *
    hg update null

    chrt -b 0 hg update default

I've also written the following program, which demonstrates the core problem:

    from __future__ import print_function

    import io
    import os
    import pickle
    import time

    obj = {"a": 1, "b": 2}
    obj_data = pickle.dumps(obj)
    assert len(obj_data) > 10

    rfd, wfd = os.pipe()

    pid = os.fork()
    if pid == 0:
        os.close(rfd)

        for _ in range(4):
            time.sleep(0.5)
            print("First write")
            os.write(wfd, obj_data[:10])

            time.sleep(0.5)
            print("Second write")
            os.write(wfd, obj_data[10:])

        os._exit(0)

    try:
        os.close(wfd)

        rfile = os.fdopen(rfd, "rb", 0)

        print("Reading")
        while True:
            try:
                obj_copy = pickle.load(rfile)
                assert obj == obj_copy
            except EOFError:
                break
        print("Success")
    finally:
        os.kill(pid, 15)

The program reliably fails with Python 3.8 and succeeds with Python 2.7.

Providing the unpickler with a buffered reader fixes the issue, so let
"os.fdopen" create one.

https://bugzilla.mozilla.org/show_bug.cgi?id=1604486

Differential Revision: https://phab.mercurial-scm.org/D8051

mercurial/worker.py

@@ -1,416 +1,416 b''
 # 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.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, workers):
         # 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)
+        selector.register(os.fdopen(rfd, 'rb'), 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(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)
         sys.exit(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()
     retval = {}
     # partition work to more pieces than workers to minimize the chance
     # of uneven distribution of large tasks between the workers
     for pargs in partition(args, workers * 20):
         taskqueue.put(pargs)
     for _i in range(workers):
         t = Worker(taskqueue, resultqueue, func, staticargs)
         threads.append(t)
         t.start()
     try:
         while len(threads) > 0:
             while not resultqueue.empty():
                 res = resultqueue.get()
                 if hasretval and res[0]:
                     retval.update(res[1])
                 else:
                     yield res
             threads[0].join(0.05)
             finishedthreads = [_t for _t in threads if not _t.is_alive()]
             for t in finishedthreads:
                 if t.exception is not None:
                     raise t.exception
                 threads.remove(t)
     except (Exception, KeyboardInterrupt):  # re-raises
         trykillworkers()
         raise
     while not resultqueue.empty():
         res = resultqueue.get()
         if hasretval and res[0]:
             retval.update(res[1])
         else:
             yield res
     if hasretval:
         yield True, retval
 
 
 if pycompat.iswindows:
     _platformworker = _windowsworker
 else:
     _platformworker = _posixworker
     _exitstatus = _posixexitstatus
 
 
 def partition(lst, nslices):
     '''partition a list into N slices of roughly equal size
 
     The current strategy takes every Nth element from the input. If
     we ever write workers that need to preserve grouping in input
     we should consider allowing callers to specify a partition strategy.
 
     mpm is not a fan of this partitioning strategy when files are involved.
     In his words:
 
         Single-threaded Mercurial makes a point of creating and visiting
         files in a fixed order (alphabetical). When creating files in order,
         a typical filesystem is likely to allocate them on nearby regions on
         disk. Thus, when revisiting in the same order, locality is maximized
         and various forms of OS and disk-level caching and read-ahead get a
         chance to work.
 
         This effect can be quite significant on spinning disks. I discovered it
         circa Mercurial v0.4 when revlogs were named by hashes of filenames.
         Tarring a repo and copying it to another disk effectively randomized
         the revlog ordering on disk by sorting the revlogs by hash and suddenly
         performance of my kernel checkout benchmark dropped by ~10x because the
         "working set" of sectors visited no longer fit in the drive's cache and
         the workload switched from streaming to random I/O.
 
         What we should really be doing is have workers read filenames from a
         ordered queue. This preserves locality and also keeps any worker from
         getting more than one file out of balance.
     '''
     for i in range(nslices):
         yield lst[i::nslices]