Mercurial > hg
view tests/badserverext.py @ 46607:e9901d01d135
revlog: add a mechanism to verify expected file position before appending
If someone uses `hg debuglocks`, or some non-hg process writes to the .hg
directory without respecting the locks, or if the repo's on a networked
filesystem, it's possible for the revlog code to write out corrupted data.
The form of this corruption can vary depending on what data was written and how
that happened. We are in the "networked filesystem" case (though I've had users
also do this to themselves with the "`hg debuglocks`" scenario), and most often
see this with the changelog. What ends up happening is we produce two items
(let's call them rev1 and rev2) in the .i file that have the same linkrev,
baserev, and offset into the .d file, while the data in the .d file is appended
properly. rev2's compressed_size is accurate for rev2, but when we go to
decompress the data in the .d file, we use the offset that's recorded in the
index file, which is the same as rev1, and attempt to decompress
rev2.compressed_size bytes of rev1's data. This usually does not succeed. :)
When using inline data, this also fails, though I haven't investigated why too
closely. This shows up as a "patch decode" error. I believe what's happening
there is that we're basically ignoring the offset field, getting the data
properly, but since baserev != rev, it thinks this is a delta based on rev
(instead of a full text) and can't actually apply it as such.
For now, I'm going to make this an optional component and default it to entirely
off. I may increase the default severity of this in the future, once I've
enabled it for my users and we gain more experience with it. Luckily, most of my
users have a versioned filesystem and can roll back to before the corruption has
been written, it's just a hassle to do so and not everyone knows how (so it's a
support burden). Users on other filesystems will not have that luxury, and this
can cause them to have a corrupted repository that they are unlikely to know how
to resolve, and they'll see this as a data-loss event. Refusing to create the
corruption is a much better user experience.
This mechanism is not perfect. There may be false-negatives (racy writes that
are not detected). There should not be any false-positives (non-racy writes that
are detected as such). This is not a mechanism that makes putting a repo on a
networked filesystem "safe" or "supported", just *less* likely to cause
corruption.
Differential Revision: https://phab.mercurial-scm.org/D9952
author | Kyle Lippincott <spectral@google.com> |
---|---|
date | Wed, 03 Feb 2021 16:33:10 -0800 |
parents | 89a2afe31e82 |
children |
line wrap: on
line source
# badserverext.py - Extension making servers behave badly # # Copyright 2017 Gregory Szorc <gregory.szorc@gmail.com> # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. # no-check-code """Extension to make servers behave badly. This extension is useful for testing Mercurial behavior when various network events occur. Various config options in the [badserver] section influence behavior: closebeforeaccept If true, close() the server socket when a new connection arrives before accept() is called. The server will then exit. closeafteraccept If true, the server will close() the client socket immediately after accept(). closeafterrecvbytes If defined, close the client socket after receiving this many bytes. closeaftersendbytes If defined, close the client socket after sending this many bytes. """ from __future__ import absolute_import import socket from mercurial import ( pycompat, registrar, ) from mercurial.hgweb import server configtable = {} configitem = registrar.configitem(configtable) configitem( b'badserver', b'closeafteraccept', default=False, ) configitem( b'badserver', b'closeafterrecvbytes', default=b'0', ) configitem( b'badserver', b'closeaftersendbytes', default=b'0', ) configitem( b'badserver', b'closebeforeaccept', default=False, ) # We can't adjust __class__ on a socket instance. So we define a proxy type. class socketproxy(object): __slots__ = ( '_orig', '_logfp', '_closeafterrecvbytes', '_closeaftersendbytes', ) def __init__( self, obj, logfp, closeafterrecvbytes=0, closeaftersendbytes=0 ): object.__setattr__(self, '_orig', obj) object.__setattr__(self, '_logfp', logfp) object.__setattr__(self, '_closeafterrecvbytes', closeafterrecvbytes) object.__setattr__(self, '_closeaftersendbytes', closeaftersendbytes) def __getattribute__(self, name): if name in ('makefile', 'sendall', '_writelog'): return object.__getattribute__(self, name) return getattr(object.__getattribute__(self, '_orig'), name) def __delattr__(self, name): delattr(object.__getattribute__(self, '_orig'), name) def __setattr__(self, name, value): setattr(object.__getattribute__(self, '_orig'), name, value) def _writelog(self, msg): msg = msg.replace(b'\r', b'\\r').replace(b'\n', b'\\n') object.__getattribute__(self, '_logfp').write(msg) object.__getattribute__(self, '_logfp').write(b'\n') object.__getattribute__(self, '_logfp').flush() def makefile(self, mode, bufsize): f = object.__getattribute__(self, '_orig').makefile(mode, bufsize) logfp = object.__getattribute__(self, '_logfp') closeafterrecvbytes = object.__getattribute__( self, '_closeafterrecvbytes' ) closeaftersendbytes = object.__getattribute__( self, '_closeaftersendbytes' ) return fileobjectproxy( f, logfp, closeafterrecvbytes=closeafterrecvbytes, closeaftersendbytes=closeaftersendbytes, ) def sendall(self, data, flags=0): remaining = object.__getattribute__(self, '_closeaftersendbytes') # No read limit. Call original function. if not remaining: result = object.__getattribute__(self, '_orig').sendall(data, flags) self._writelog(b'sendall(%d) -> %s' % (len(data), data)) return result if len(data) > remaining: newdata = data[0:remaining] else: newdata = data remaining -= len(newdata) result = object.__getattribute__(self, '_orig').sendall(newdata, flags) self._writelog( b'sendall(%d from %d) -> (%d) %s' % (len(newdata), len(data), remaining, newdata) ) object.__setattr__(self, '_closeaftersendbytes', remaining) if remaining <= 0: self._writelog(b'write limit reached; closing socket') object.__getattribute__(self, '_orig').shutdown(socket.SHUT_RDWR) raise Exception('connection closed after sending N bytes') return result # We can't adjust __class__ on socket._fileobject, so define a proxy. class fileobjectproxy(object): __slots__ = ( '_orig', '_logfp', '_closeafterrecvbytes', '_closeaftersendbytes', ) def __init__( self, obj, logfp, closeafterrecvbytes=0, closeaftersendbytes=0 ): object.__setattr__(self, '_orig', obj) object.__setattr__(self, '_logfp', logfp) object.__setattr__(self, '_closeafterrecvbytes', closeafterrecvbytes) object.__setattr__(self, '_closeaftersendbytes', closeaftersendbytes) def __getattribute__(self, name): if name in ('_close', 'read', 'readline', 'write', '_writelog'): return object.__getattribute__(self, name) return getattr(object.__getattribute__(self, '_orig'), name) def __delattr__(self, name): delattr(object.__getattribute__(self, '_orig'), name) def __setattr__(self, name, value): setattr(object.__getattribute__(self, '_orig'), name, value) def _writelog(self, msg): msg = msg.replace(b'\r', b'\\r').replace(b'\n', b'\\n') object.__getattribute__(self, '_logfp').write(msg) object.__getattribute__(self, '_logfp').write(b'\n') object.__getattribute__(self, '_logfp').flush() def _close(self): # Python 3 uses an io.BufferedIO instance. Python 2 uses some file # object wrapper. if pycompat.ispy3: orig = object.__getattribute__(self, '_orig') if hasattr(orig, 'raw'): orig.raw._sock.shutdown(socket.SHUT_RDWR) else: self.close() else: self._sock.shutdown(socket.SHUT_RDWR) def read(self, size=-1): remaining = object.__getattribute__(self, '_closeafterrecvbytes') # No read limit. Call original function. if not remaining: result = object.__getattribute__(self, '_orig').read(size) self._writelog( b'read(%d) -> (%d) (%s) %s' % (size, len(result), result) ) return result origsize = size if size < 0: size = remaining else: size = min(remaining, size) result = object.__getattribute__(self, '_orig').read(size) remaining -= len(result) self._writelog( b'read(%d from %d) -> (%d) %s' % (size, origsize, len(result), result) ) object.__setattr__(self, '_closeafterrecvbytes', remaining) if remaining <= 0: self._writelog(b'read limit reached, closing socket') self._close() # This is the easiest way to abort the current request. raise Exception('connection closed after receiving N bytes') return result def readline(self, size=-1): remaining = object.__getattribute__(self, '_closeafterrecvbytes') # No read limit. Call original function. if not remaining: result = object.__getattribute__(self, '_orig').readline(size) self._writelog( b'readline(%d) -> (%d) %s' % (size, len(result), result) ) return result origsize = size if size < 0: size = remaining else: size = min(remaining, size) result = object.__getattribute__(self, '_orig').readline(size) remaining -= len(result) self._writelog( b'readline(%d from %d) -> (%d) %s' % (size, origsize, len(result), result) ) object.__setattr__(self, '_closeafterrecvbytes', remaining) if remaining <= 0: self._writelog(b'read limit reached; closing socket') self._close() # This is the easiest way to abort the current request. raise Exception('connection closed after receiving N bytes') return result def write(self, data): remaining = object.__getattribute__(self, '_closeaftersendbytes') # No byte limit on this operation. Call original function. if not remaining: self._writelog(b'write(%d) -> %s' % (len(data), data)) result = object.__getattribute__(self, '_orig').write(data) return result if len(data) > remaining: newdata = data[0:remaining] else: newdata = data remaining -= len(newdata) self._writelog( b'write(%d from %d) -> (%d) %s' % (len(newdata), len(data), remaining, newdata) ) result = object.__getattribute__(self, '_orig').write(newdata) object.__setattr__(self, '_closeaftersendbytes', remaining) if remaining <= 0: self._writelog(b'write limit reached; closing socket') self._close() raise Exception('connection closed after sending N bytes') return result def extsetup(ui): # Change the base HTTP server class so various events can be performed. # See SocketServer.BaseServer for how the specially named methods work. class badserver(server.MercurialHTTPServer): def __init__(self, ui, *args, **kwargs): self._ui = ui super(badserver, self).__init__(ui, *args, **kwargs) recvbytes = self._ui.config(b'badserver', b'closeafterrecvbytes') recvbytes = recvbytes.split(b',') self.closeafterrecvbytes = [int(v) for v in recvbytes if v] sendbytes = self._ui.config(b'badserver', b'closeaftersendbytes') sendbytes = sendbytes.split(b',') self.closeaftersendbytes = [int(v) for v in sendbytes if v] # Need to inherit object so super() works. class badrequesthandler(self.RequestHandlerClass, object): def send_header(self, name, value): # Make headers deterministic to facilitate testing. if name.lower() == 'date': value = 'Fri, 14 Apr 2017 00:00:00 GMT' elif name.lower() == 'server': value = 'badhttpserver' return super(badrequesthandler, self).send_header( name, value ) self.RequestHandlerClass = badrequesthandler # Called to accept() a pending socket. def get_request(self): if self._ui.configbool(b'badserver', b'closebeforeaccept'): self.socket.close() # Tells the server to stop processing more requests. self.__shutdown_request = True # Simulate failure to stop processing this request. raise socket.error('close before accept') if self._ui.configbool(b'badserver', b'closeafteraccept'): request, client_address = super(badserver, self).get_request() request.close() raise socket.error('close after accept') return super(badserver, self).get_request() # Does heavy lifting of processing a request. Invokes # self.finish_request() which calls self.RequestHandlerClass() which # is a hgweb.server._httprequesthandler. def process_request(self, socket, address): # Wrap socket in a proxy if we need to count bytes. if self.closeafterrecvbytes: closeafterrecvbytes = self.closeafterrecvbytes.pop(0) else: closeafterrecvbytes = 0 if self.closeaftersendbytes: closeaftersendbytes = self.closeaftersendbytes.pop(0) else: closeaftersendbytes = 0 if closeafterrecvbytes or closeaftersendbytes: socket = socketproxy( socket, self.errorlog, closeafterrecvbytes=closeafterrecvbytes, closeaftersendbytes=closeaftersendbytes, ) return super(badserver, self).process_request(socket, address) server.MercurialHTTPServer = badserver