##// END OF EJS Templates
chg: handle EOF reading data block...
chg: handle EOF reading data block We recently discovered a case in production that chg uses 100% CPU and is trying to read data forever: recvfrom(4, "", 1814012019, 0, NULL, NULL) = 0 Using gdb, apparently readchannel() got wrong data. It was reading in an infinite loop because rsize == 0 does not exit the loop, while the server process had ended. (gdb) bt #0 ... in recv () at /lib64/libc.so.6 #1 ... in readchannel (...) at /usr/include/bits/socket2.h:45 #2 ... in readchannel (hgc=...) at hgclient.c:129 #3 ... in handleresponse (hgc=...) at hgclient.c:255 #4 ... in hgc_runcommand (hgc=..., args=<optimized>, argsize=<optimized>) #5 ... in main (argc=...486922636, argv=..., envp=...) at chg.c:661 (gdb) frame 2 (gdb) p *hgc $1 = {sockfd = 4, pid = 381152, ctx = {ch = 108 'l', data = 0x7fb05164f010 "st):\nTraceback (most recent call last):\n" "Traceback (most recent call last):\ne", maxdatasize = 1814065152," " datasize = 1814064225}, capflags = 16131} This patch addresses the infinite loop issue by detecting continuously empty responses and abort in that case. Note that datasize can be translated to ['l', ' ', 'l', 'a']. Concatenate datasize and data, it forms part of "Traceback (most recent call last):". This may indicate a server-side channeledoutput issue. If it is a race condition, we may want to use flock to protect the channels.

File last commit:

r29421:ecbbf4d5 default
r29602:4fc4b8cc default
Show More
localstore.py
66 lines | 2.3 KiB | text/x-python | PythonLexer
# Copyright 2009-2010 Gregory P. Ward
# Copyright 2009-2010 Intelerad Medical Systems Incorporated
# Copyright 2010-2011 Fog Creek Software
# Copyright 2010-2011 Unity Technologies
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
'''store class for local filesystem'''
from __future__ import absolute_import
from mercurial.i18n import _
from . import (
basestore,
lfutil,
)
class localstore(basestore.basestore):
'''localstore first attempts to grab files out of the store in the remote
Mercurial repository. Failing that, it attempts to grab the files from
the user cache.'''
def __init__(self, ui, repo, remote):
self.remote = remote.local()
super(localstore, self).__init__(ui, repo, self.remote.url())
def put(self, source, hash):
if lfutil.instore(self.remote, hash):
return
lfutil.link(source, lfutil.storepath(self.remote, hash))
def exists(self, hashes):
retval = {}
for hash in hashes:
retval[hash] = lfutil.instore(self.remote, hash)
return retval
def _getfile(self, tmpfile, filename, hash):
path = lfutil.findfile(self.remote, hash)
if not path:
raise basestore.StoreError(filename, hash, self.url,
_("can't get file locally"))
with open(path, 'rb') as fd:
return lfutil.copyandhash(fd, tmpfile)
def _verifyfiles(self, contents, filestocheck):
failed = False
for cset, filename, expectedhash in filestocheck:
storepath, exists = lfutil.findstorepath(self.repo, expectedhash)
if not exists:
storepath, exists = lfutil.findstorepath(
self.remote, expectedhash)
if not exists:
self.ui.warn(
_('changeset %s: %s references missing %s\n')
% (cset, filename, storepath))
failed = True
elif contents:
actualhash = lfutil.hashfile(storepath)
if actualhash != expectedhash:
self.ui.warn(
_('changeset %s: %s references corrupted %s\n')
% (cset, filename, storepath))
failed = True
return failed