#
272461 |
|
02-Oct-2014 |
gjb |
Copy stable/10@r272459 to releng/10.1 as part of the 10.1-RELEASE process.
Approved by: re (implicit) Sponsored by: The FreeBSD Foundation |
#
260627 |
|
14-Jan-2014 |
pluknet |
MFC r257705:
Clean up -Wtautological-compare -Wformat warnings.
|
#
256281 |
|
10-Oct-2013 |
gjb |
Copy head (r256279) to stable/10 as part of the 10.0-RELEASE cycle.
Approved by: re (implicit) Sponsored by: The FreeBSD Foundation
|
#
236690 |
|
06-Jun-2012 |
kib |
Do not execute a needed statement with side-effect in assert().
MFC after: 3 days
|
#
236686 |
|
06-Jun-2012 |
kib |
Add gettimeofday() test.
MFC after: 3 days
|
#
214261 |
|
24-Oct-2010 |
rwatson |
Add microbenchmark for create/unlink of a zero-byte file.
Sponsored by: Google, Inc. MFC after: 2 weeks
|
#
214202 |
|
22-Oct-2010 |
rwatson |
Validate syscall_timing test names before starting to provide earlier feedback regarding user error.
Provide default loop and timing settings.
Add a new test that just times pread() without the open()/close().
Mark tests requiring a path argument so we can provide better feedback to the user than EFAULT on (null).
Sponsored by: Google, Inc. MFC after: 2 weeks
|
#
214185 |
|
21-Oct-2010 |
rwatson |
Universally use uintmax_t in syscall_timing; rearrange arithmetic to suffer fewer rounding errors with smaller numbers; fix argc validation so multiple tests run on a single command line.
Sponsored by: Google, Inc. MFC after: 2 weeks
|
#
214154 |
|
21-Oct-2010 |
rwatson |
Add Cambridge/Google tag since the copyright has been updated.
MFC after: 2 weeks
|
#
214151 |
|
21-Oct-2010 |
rwatson |
Further syscall_timing improvements: allow an arbitrary "path" string argument to be passed on the command line, allowing file-related tests to be pointed at wherever desired.
Sponsored by: Google, Inc. MFC after: 2 weeks
|
#
214145 |
|
21-Oct-2010 |
rwatson |
Fix bug in recent syscall_timing change: measure the number of iterations each loop, rather than once up front. The distinction is unimportant when doing a fix iteration count, but when using a timer, it should vary.
Sponsored by: Google, Inc. MFC after: 2 weeks
|
#
214142 |
|
21-Oct-2010 |
rwatson |
Further enhancements to syscall_timing:
- Use getopt rather than hand-parsed arguments - Allow iterations to be specified and/or a new number of seconds bound on the number of iterations - Fix printout of timer resolution - Add new tests, such as TCP and UDP socket creation, and open/read/close of /dev/zero and /dev/null.
Sponsored by: Google, Inc. MFC after: 2 weeks
|
#
214135 |
|
21-Oct-2010 |
rwatson |
Improve the structure and implementation of the syscall_timing microbenchmark suite:
- Use common benchmark_start/benchmark_stop routines to simplify individual benchmarks. - Add a central table of tests with names, where new tests can be hooked in easily. - Add new benchmarks for dup, shm_open, shm_open + fstat, fork, vfork, vfork + exec, chroot, setuid. - Accept a number of loops, not just a number of iterations. - Report results more usefully in a table.
Sponsored by: Google, Inc. MFC after: 2 weeks
|
#
148681 |
|
03-Aug-2005 |
rwatson |
Add a few more system call timing cases:
Rename current socket creation test to socket_stream. Add new socket_dgram test. Add new socketpair_stream test. Add new socketpair_dgram test.
|
#
144850 |
|
10-Apr-2005 |
rwatson |
Centralize usage in usage(), and use in preference to fprintf().
List possible tests in usage().
When running a test, print the test name.
|
#
135952 |
|
30-Sep-2004 |
rwatson |
Add syscall_timing, a simple timing micro-benchmark for some characteristic system calls. I've been sending this to people for a while, and figured it would be more efficient to just put it in CVS.
|