Commit Graph

4 Commits

Author SHA1 Message Date
Zachary Turner 0c426319f6 XFAIL pexpect tests on Windows.
At some point we will need to either provide a pexpect equivalent
on Windows, or provide some other method of doing out-of-process
tests.

Even with a pexpect replacement, it may be worth re-evaluating
some of these tests to see if they would be better served as
in-process tests.  The larger issue of coming up with a pexpect
replacement on Windows is tracked in http://llvm.org/pr22274.

llvm-svn: 226614
2015-01-20 22:36:03 +00:00
Zachary Turner 045fde58d1 Fixes a number of issue related to test portability on Windows.
99% of this CL is simply moving calls to "import pexpect" to a more
narrow scope - i.e. the function that actually runs a particular
test.  This way the test suite can run on Windows, which doesn't have
pexpect, and the individual tests that use pexpect can be disabled on
a platform-specific basis.

Additionally, this CL fixes a few other cases of non-portability.
Notably, using "ps" to get the command line, and os.uname() to
determine the architecture don't work on Windows.  Finally, this
also adds a stubbed out builder_win32 module.

The full test suite runs correctly on Windows after this CL, although
there is still some work remaining on the C++ side to fix one-shot
script commands from LLDB (e.g. script print "foo"), which currently
deadlock.

Reviewed by: Todd Fiala

Differential Revision: http://reviews.llvm.org/D4573

llvm-svn: 213343
2014-07-18 01:02:02 +00:00
Greg Clayton 4570d3eba0 Massive test suite cleanup to stop everyone from manually having to compute "mydir" inside each test case.
This has led to many test suite failures because of copy and paste where new test cases were based off of other test cases and the "mydir" variable wasn't updated.

Now you can call your superclasses "compute_mydir()" function with "__file__" as the sole argument and the relative path will be computed for you. 

llvm-svn: 196985
2013-12-10 23:19:29 +00:00
Johnny Chen fc9e79fb95 Benchmark the turnaround time starting a debugger and run to the breakpoint with lldb vs. gdb.
An example (with /Developer/usr/bin/lldb vs. /usr/bin/gdb):

[13:05:04] johnny:/Volumes/data/lldb/svn/trunk/test $ ./dotest.py -v +b -n -p TestCompileRunToBreakpointTurnaround.py
1: test_run_lldb_then_gdb (TestCompileRunToBreakpointTurnaround.CompileRunToBreakpointBench)
   Benchmark turnaround time with lldb vs. gdb. ... 
lldb turnaround benchmark: Avg: 4.574600 (Laps: 3, Total Elapsed Time: 13.723799)
gdb turnaround benchmark: Avg: 7.966713 (Laps: 3, Total Elapsed Time: 23.900139)
lldb_avg/gdb_avg: 0.574214
ok

----------------------------------------------------------------------
Ran 1 test in 55.462s

OK

llvm-svn: 142949
2011-10-25 20:08:03 +00:00