Previously, if a database request spanned a related object manager, the
first manager encountered would cause a request to the router, and this
would bind all subsequent queries to the same database returned by the
router. Unfortunately, the first router query would be performed using
a read request to the router, resulting in bad routing information being
used if the subsequent query was actually a write.
This change defers the call to the router until the final query is acutally
made.
It includes a small *BACKWARDS INCOMPATIBILITY* on an edge case - see the
release notes for details.
Thanks to Paul Collins (@paulcollinsiii) for the excellent debugging
work and patch.
DatabaseCache uses raw cursors to bypass the ORM. This prevents it from
being used by database backends that require special handling of datetime
values.
There is no easy way to test this, so no tests added.
This reverts commit aae5a96d57.
This fix is no longer necessary, our pbkdf2 (see next commit) implementation
no longer rehashes the password every iteration.
Our WSGIServer rewrapped the socket errors from server_bind into
WSGIServerExceptions, which is used later on to provide nicer
error messages in runserver and used by the liveserver to see if
the port is already in use. But wrapping server_bind isn't enough since
it only binds to the socket, socket.listen (which is called from
server_activate) could also raise "Address already in use".
Instead of overriding server_activate too I chose to just catch socket
errors, which seems to make more sense anyways and should be more robust
against changes in wsgiref.
- Noted that this does not allow for reading and writing the same open
file in different processes under Windows.
- Noted that the keyword arguments to NamedTemporaryFile no longer
match the Python version.
tearDownClass is not called if setUpClass throws an exception, in our case
this means that LiveServerTestCase leaks LiveServerThread sockets if the
test happens to be skipped later on, and AdminSeleniumWebDriverTestCase
doesn't close it's already open browser window. To prevent this leakage
we catch errors where needed and manually call _tearDownClassInternal.
_tearDownClassInternal should be written as defensively as possible since
it is not allowed to make any assumptions on how far setUpClass got.
This patch should fix the sporadic "Address already in use"-errors on jenkins
and also the "This code isn't under transaction management"-error for sqlite
(also just on jenkins).
After discussion with koniiiik, jezdez, kmtracey, tos9, lifeless, nedbat and
voidspace it was decided that this is the safest approach (thanks to everyone
for their comments and help). Manually calling tearDownClass was shut down
cause we don't know how our users override our classes.
This is a private and very specialized API on purpose and should not be used
without a strong reason!
This patch partially reverts the earlier attempts to fix those issues,
namely:
2fa0dd73b1 and
3c5775d36f
Final note: If this patch breaks in a later version of Django, please be
very careful on how you fix it, you might not see test failures locally.
That said, this patch hopefully doesn't produce even more failures.
Russell Keith-Magee
Christopher Babiak
Ramiro Morales
Erik Romijn
Baptiste Mispelon
Andrew Godwin
Michael Manfre
Giles Richard Greenway
Loic Bistuer
Anssi Kääriäinen
Florian Apolloner
Andrei Picus
Michał Lech
Claude Paroz
Helen ST
Aymeric Augustin
tschilling
Paul McMillan
yokomizor
Paul McMillan
Kevin Christopher Henry
Curtis Maloney
Tim Graham
Brian Holdefehr
Berker Peksag
Markus Holtermann
Beshr Kayali