# HG changeset patch
# User Jun Wu <quark@fb.com>
# Date 2016-11-24 01:15:34
# Node ID 86cd09bc13ba66386ad5f8fc0279168b282e5fd5
# Parent  4338f87dbf6fddb38c3ae08d91bf518525fae0b7

worker: use os._exit for posix worker in all cases

Like commandserver, the worker should never run other resource cleanup logic.

Previously this is not true for workers if they have exceptions other than
KeyboardInterrupt.

This actually caused a real-world deadlock with remotefilelog:

1. remotefilelog/fileserverclient creates a sshpeer. pipei/o/e get created.
2. worker inherits that sshpeer's pipei/o/e.
3. worker runs sshpeer.cleanup (only happens without os._exit)
4. worker closes pipeo/i, which will normally make the sshpeer read EOF from
   its stdin and exit. But the master process still have pipeo, so no EOF.
5. worker reads pipee (stderr of sshpeer), which never completes because
   the ssh process does not exit, does not close its stderr.
6. master waits for all workers, which never completes because they never
   complete sshpeer.cleanup.

This could also be addressed by closing these fds after fork, which is not
easy because Python 2.x does not have an official "afterfork" hook. Hacking
os.fork is also ugly. Besides, sshpeer is probably not the only troublemarker.

The patch changes _posixworker so all its code paths will use os._exit to
avoid running unwanted resource clean-ups.

diff --git a/mercurial/worker.py b/mercurial/worker.py
--- a/mercurial/worker.py
+++ b/mercurial/worker.py
@@ -15,6 +15,7 @@ import sys
 from .i18n import _
 from . import (
     error,
+    scmutil,
     util,
 )
 
@@ -132,15 +133,26 @@ def _posixworker(ui, func, staticargs, a
         if pid == 0:
             signal.signal(signal.SIGINT, oldhandler)
             signal.signal(signal.SIGCHLD, oldchldhandler)
-            try:
+
+            def workerfunc():
                 os.close(rfd)
                 for i, item in func(*(staticargs + (pargs,))):
                     os.write(wfd, '%d %s\n' % (i, item))
-                os._exit(0)
+
+            # make sure we use os._exit in all code paths. otherwise the worker
+            # may do some clean-ups which could cause surprises like deadlock.
+            # see sshpeer.cleanup for example.
+            try:
+                scmutil.callcatch(ui, workerfunc)
             except KeyboardInterrupt:
                 os._exit(255)
-                # other exceptions are allowed to propagate, we rely
-                # on lock.py's pid checks to avoid release callbacks
+            except: # never return, therefore no re-raises
+                try:
+                    ui.traceback()
+                finally:
+                    os._exit(255)
+            else:
+                os._exit(0)
         pids.add(pid)
     os.close(wfd)
     fp = os.fdopen(rfd, 'rb', 0)