[Python-Dev] red buildbots on 2.7

Mon Jun 21 23:12:54 CEST 2010

> If OS X is a supported and important platform for Python then fixing all
> problems that it reveals (or being willing to) should definitely not be
> a pre-requisite of providing a buildbot (which is already a service to
> the Python developer community). Fixing bugs / failures revealed by
> Bill's buildbot is not fixing them "for Bill" it is fixing them for Python.

I wish people would stop using the word "supported" when they talk about 
free software. *No* system is "supported" by Python - not even in the 
sense "we strive to pass the test suite". "We" don't.
Now, one may argue whether failing buildbots should be an unconditional 
reason to defer the release. I personally would say "no", despite what 
some PEP may say. People proposing that a release is postponed typically 
hope that somebody gets frustrated enough to step up and fix the bug, 
just so that the software gets released.
Instead, I would propose that the only way to delay a release is by 
proposing to take some specific action to remedy the situation that 
should cause the delay. Otherwise, releasing is at the discretion of the 
release manager, who has the ultimate say to whether the problem is 
important or not.
As for OSX, it seems that the only test that is failing is the ctypes 
test suite, and there only a single test. I don't think this is 
sufficient reason to block the release.
Regards,
Martin