Messages in this thread | | | From | Alexei Starovoitov <> | Date | Mon, 2 Mar 2015 12:48:52 -0800 | Subject | Re: [PATCH v2 00/15] tracing: 'hist' triggers |
| |
On Mon, Mar 2, 2015 at 12:43 PM, Steven Rostedt <rostedt@goodmis.org> wrote: > On Mon, 2 Mar 2015 15:39:48 -0500 > Steven Rostedt <rostedt@goodmis.org> wrote: > >> On Mon, 2 Mar 2015 12:33:34 -0800 >> Alexei Starovoitov <ast@plumgrid.com> wrote: >> >> > On Mon, Mar 2, 2015 at 11:49 AM, Karim Yaghmour >> > <karim.yaghmour@opersys.com> wrote: >> > > >> > > On 15-03-02 02:45 PM, Steven Rostedt wrote: >> > >> Interesting. The Android devices I have still have it enabled (rooted, >> > >> but still running the stock system). >> > > >> > > I don't know that there's any policy to disable tracing on Android. The >> > > Android framework in fact has generally been instrumented by Google >> > > itself to output trace info into trace_marker. And the systrace/atrace >> > > tools made available to app developers need to get access to this >> > > tracing info. So, if Android had tracing disabled, systrace/atrace >> > > wouldn't work. >> > > https://developer.android.com/tools/debugging/systrace.html >> > >> > that's interesting. thanks for the link. >> > >> > I don't see tracing being explicitly enabled in defconfig: >> > https://source.android.com/devices/tech/kernel.html >> >> CONFIG_SCHED_TRACER=y >> >> That alone will enable tracing. >> >> -- Steve >> >> > or here: >> > https://android.googlesource.com/kernel/common/+/android-3.10/android/configs/android-recommended.cfg >> > > CONFIG_ENABLE_DEFAULT_TRACERS=y > > And so will that.
good. thanks for explaining. all makes sense now.
btw, that fancy systrace seems to be parsing text from trace_pipe https://android.googlesource.com/platform/external/chromium-trace/+/jb-dev/src/tracing/linux_perf_importer.js with a bunch of regex... including sched_switch: next_prio...
| |