On Fri, 18 Jan 2008, Mathieu Desnoyers wrote:
>
> But I have not seen a lot of situations where that kind of glue-code was
> needed, so I think it makes sense to keep markers simple to use and
> efficient for the common case.
>
> Then, in this glue-code, we can put trace_mark() and calls to in-kernel
> tracers.
I'm almost done with the latency tracer work, and there are only a total
of 6 hooks that I needed.
- schedule context switch
- try_to_wake_up
- hard_irqs_off (which is already there for lockdep)
- hard irqs on (also for lockdep)
- lock_contention (already in for the lock contention code)
- lock acquire (also in there for contention code)
With the above, we could have this (if this is what I think you are
recommending). For example in the context_switch case:
trace_switch_to(prev, next);
switch_to(prev, next, prev);
and in sched.h I could have:
static inline trace_switch_to(struct task_struct *prev,
struct task_struct *next)
{
trace_mark(kernel_schedudule,
"prev_pid %d next_pid %d prev_state %ld",
prev->pid, next->pid, prev->pid);
trace_context_switch(prev, next);
}
and have the trace_context_switch code be something that is turned on with
the latency tracing utility (config option). That way production code can
keep it off.
-- Steve
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
