Re: [RFC PATCH 16/22 -v2] add get_monotonic_cycles



On Fri, 18 Jan 2008, Frank Ch. Eigler wrote:

All this complexity is to be justified by keeping the raw prev/next
pointers from being sent to a naive tracer? It seems to me way out of
proportion.

Damn, and I just blew away all my marker code for something like this ;-)

Actually, you just gave me a great idea that I think can help all of us.
OK, Mathieu may not be in total agreement, but I think this is the
ultimate compromise.

We have in sched.c the following marker:

trace_mark(kernel_sched_scheduler, "prev %p next %p", prev, next);


Then Mathieu can add in some code somewhere (or a module, or something)

ret = marker_probe_register("kernel_sched_scheduler",
"prev %p next %p",
pretty_print_sched_switch, NULL);

static void pretty_print_sched_switch(const struct marker *mdata,
void *private_data,
const char *format, ...)
{
va_list ap;
struct task_struct *prev;
struct task_struct *next;

va_start(ap, format);
prev = va_arg(ap, typeof(prev));
next = va_arg(ap, typeof(next));
va_end;

trace_mark(kernel_pretty_print_sched_switch,
"prev_pid %d next_pid %d prev_state %ld",
prev->pid, next->pid, prev->state);
}


Then LTTng on startup could arm the normal kernel_sched_switch code and
have the user see the nice one. All without adding any more goo or
overhead to the non tracing case, and keeping a few critical markers with
enough information to be useful to other tracers!

Thoughts?

-- Steve

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Relevant Pages

  • [RFC patch 27/41] Markers use dynamic channels
    ... the channel name where the data must be sent. ... Switch to per-channel marker IDs. ... struct module; ... @format: format string ...
    (Linux-Kernel)
  • Re: [PATCH] ftrace: add an fsync tracer
    ... I prefer we keep using trace points but do what jason has been proposing ... which is add a format and arg list to the trace point ... TPPROTO(struct rq *rq, struct task_struct *prev, ...
    (Linux-Kernel)
  • Re: [BUG] CFS vs cpu hotplug
    ... I'm still seeing kernel crashes on cpu hotplug with Linus' current git tree. ... tasks_timeline = struct rb_root { ... prev = 0x759328 ... balance_iterator = (nil) ...
    (Linux-Kernel)
  • [BUG] CFS vs cpu hotplug
    ... I'm still seeing kernel crashes on cpu hotplug with Linus' current git tree. ... tasks_timeline = struct rb_root { ... prev = 0x759328 ... balance_iterator = (nil) ...
    (Linux-Kernel)
  • [PATCH tip/tracing/markers] new probes manager
    ... this patch use a new probes manager for marker. ... unused memory is handled by struct marker_probes. ... @call_private: caller site private data ... Sets the probe callback corresponding to one marker. ...
    (Linux-Kernel)