# HG changeset patch # User Matt Harbison # Date 1516599582 18000 # Node ID 75bae69747f02dc13161714864739970d21fe81a # Parent 440e8fce29e77bb51f614f1ae5d99c0847d6f5e0 dummysmtpd: don't die on client connection errors The connection refused error in test-patchbomb-tls.t[1] is sporadic, but one of the more often seen errors on Windows. I added enough logging to a file and dumped it out at the end to make the following observations: - The listening socket is successfully created and bound to the port, and the "listening at..." message is always logged. - Generally, the following is the entire log output, with the "accepted ..." message having been added after `sslutil.wrapserversocket`: listening at localhost:$HGPORT $LOCALIP ssl error accepted connect accepted connect $LOCALIP from=quux to=foo, bar $LOCALIP ssl error - In the cases that fail, asyncore.loop() in the run() method is exiting, but not with an exception. - In the cases that fail, the following is logged right after "listening ...": Traceback (most recent call last): File "c:\\Python27\\lib\\asyncore.py", line 83, in read obj.handle_read_event() File "c:\\Python27\\lib\\asyncore.py", line 443, in handle_read_event self.handle_accept() File "../tests/dummysmtpd.py", line 80, in handle_accept conn = sslutil.wrapserversocket(conn, ui, certfile=self._certfile) File "..\\mercurial\\sslutil.py", line 570, in wrapserversocket return sslcontext.wrap_socket(sock, server_side=True) File "c:\\Python27\\lib\\ssl.py", line 363, in wrap_socket _context=self) File "c:\\Python27\\lib\\ssl.py", line 611, in __init__ self.do_handshake() File "c:\\Python27\\lib\\ssl.py", line 840, in do_handshake self._sslobj.do_handshake() error: [Errno 10054] $ECONNRESET$ - If the base class handler is overridden completely, the the first "ssl error" line is replaced by the stacktrace, but the other lines are unchanged. The client behaves no differently, whether or not the server stacktraced. In general, `./run-tests.py --local -j9 -t9000 test-patchbomb-tls.t --runs-per-test 20` would show the issue after a run or two. With this change, `./run-tests.py --local -j9 -t9000 test-patchbomb-tls.t --loop` ran 800 times without a hiccup. This makes me wonder if the other connection refused messages that bubble up on occasion are caused by a similar issue. It seems a bit drastic to kill the whole server on account of a single communication failure with a client. # no-check-commit because of handle_error() [1] https://buildbot.mercurial-scm.org/builders/Win7%20x86_64%20hg%20tests/builds/421/steps/run-tests.py%20%28python%202.7.13%29/logs/stdio diff -r 440e8fce29e7 -r 75bae69747f0 tests/dummysmtpd.py --- a/tests/dummysmtpd.py Sun Jan 21 15:39:48 2018 +0100 +++ b/tests/dummysmtpd.py Mon Jan 22 00:39:42 2018 -0500 @@ -9,6 +9,7 @@ import smtpd import ssl import sys +import traceback from mercurial import ( server, @@ -27,6 +28,15 @@ def process_message(self, peer, mailfrom, rcpttos, data): log('%s from=%s to=%s\n' % (peer[0], mailfrom, ', '.join(rcpttos))) + def handle_error(self): + # On Windows, a bad SSL connection sometimes generates a WSAECONNRESET. + # The default handler will shutdown this server, and then both the + # current connection and subsequent ones fail on the client side with + # "No connection could be made because the target machine actively + # refused it". If we eat the error, then the client properly aborts in + # the expected way, and the server is available for subsequent requests. + traceback.print_exc() + class dummysmtpsecureserver(dummysmtpserver): def __init__(self, localaddr, certfile): dummysmtpserver.__init__(self, localaddr)