summaryrefslogtreecommitdiffstats
path: root/tools/regression/kqueue/proc.c
Commit message (Collapse)AuthorAgeFilesLines
* MFC r282063:ngie2015-05-131-255/+0
| | | | | Integrate tools/regression/kqueue into the FreeBSD test suite as tests/sys/kqueue
* Clarify the meaning of a test.jonathan2011-07-081-3/+3
| | | | | | | | | | | | Rather than using err() if either of two failure conditions fires (which can produce spurious error messages), just use errx() if the one condition that really matters fires. In practice, this single test is enough to detect the failure mode we're looking for (kqueue being inherited across fork). Approved by: mentor (rwatson), re (Capsicum blanket) Sponsored by: Google Inc
* Ensure that kqueue is not inherited across fork().jonathan2011-07-071-1/+15
| | | | | | | | | | | | | | | Modify the existing unit test (from libkqueue) which already exercises process events via fork() and kill(). Now, the child process simply checks that the 'kqfd' descriptor is invalid. Some minor modifications were required to make err() work correctly. It seems that this test was imported using the output of a configure script, but config.h was not included in key places, nor was its syntax correct (need '#define HAVE_FOO 1' rather than '#define HAVE_FOO'). Finally, change main() to run the "proc" suite by default, but widened the '#if TODO' in proc.c to include the non-functioning test event_trigger(). Approved by: mentor (rwatson), re (Capsicum blanket) Sponsored by: Google Inc
* Add Mark Heily's libkqueue test suite as a general kqueue test suite torwatson2009-12-131-0/+241
tools/regression. It tests a number of aspects of kqueue behavior, although not all currently pass (possibly bugs in the test suite?). Submitted by: Mark Heily <mark at heily.com> Obtained from: svn://mark.heily.com/libkqueue/trunk/test (r114)
OpenPOWER on IntegriCloud