diff options
| author | hunt <hunt> | 2005-07-28 17:33:09 +0000 |
|---|---|---|
| committer | hunt <hunt> | 2005-07-28 17:33:09 +0000 |
| commit | 42ee08b55b2f7a12b26f2049d672a1b563f064a4 (patch) | |
| tree | 080aa7516d0b19de5c606833f98444d252494f51 /runtime/probes/bench/README | |
| parent | 377b88310b59601c0d967c55bd6a46ec024dc2de (diff) | |
| download | systemtap-steved-42ee08b55b2f7a12b26f2049d672a1b563f064a4.tar.gz systemtap-steved-42ee08b55b2f7a12b26f2049d672a1b563f064a4.tar.xz systemtap-steved-42ee08b55b2f7a12b26f2049d672a1b563f064a4.zip | |
2005-07-28 Martin Hunt <hunt@redhat.com>
* bench/ALL: Chnage to probe sys_getuid() and sys_getgid()
because those aren't used by stpd, unlike sys_read() and sys_write().
Diffstat (limited to 'runtime/probes/bench/README')
| -rw-r--r-- | runtime/probes/bench/README | 10 |
1 files changed, 3 insertions, 7 deletions
diff --git a/runtime/probes/bench/README b/runtime/probes/bench/README index 5eaded78..04801a74 100644 --- a/runtime/probes/bench/README +++ b/runtime/probes/bench/README @@ -1,15 +1,11 @@ This is a benchmark program for the SystemTap Runtime. -It works by instrumenting sys_read() and sys_write(). It calls each a million -times and times that. Then it puts an empty kprobe on one and jprobe on the -other and times that. Subtracting the difference between the two runs gives +It works by instrumenting sys_uid() and sys_gid(). It calls each a million +times and measures how long it takes. Then it puts an empty kprobe on one and jprobe on the +other and measures that. Subtracting the difference between the two runs gives the kprobe and jprobe overhead. The process is then repeated for more complicated probes. -Any system has some background activity going on that will generate sys_read -and sys_write calls. However, unless some major activity is going on, it -should be statistically insignificant. - To Start: 1. Build the test program. |