Re: [PATCH] sched: Provide iowait counters

[Peter Zijlstra <peterz@infradead.org>]

On Mon, 2009-07-20 at 15:42 -0400, Steven Rostedt wrote:
> On Mon, 20 Jul 2009, Peter Zijlstra wrote:
> > 
> > > +++ b/kernel/sched_fair.c
> > > @@ -633,6 +633,11 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
> > >   		se->block_start = 0;
> > >   		se->sum_sleep_runtime += delta;
> > > 
> > > +		if (tsk->in_iowait) {
> > > +			se->iowait_sum += delta;
> > > +			se->iowait_count++;
> > > +		}
> > > +
> > >   		/*
> > >   		 * Blocking time is in units of nanosecs, so shift by 20 to
> > >   		 * get a milliseconds-range estimation of the amount of
> > 
> > It might be nice to put a tracepoint there as well, now if there was a
> > way to specify perf counter attributes in the TRACE_EVENT() magic so
> > that we can feed stuff into perf_tpcounter_event().
> > 
> > TP_perf_addr()  -- defaults to 0 when not specified
> > TP_perf_count() -- defaults to 1 when not specified.
> > 
> > Steve, Frederic, is there any way to make that happen?
> > 
> > Failing that we could put an actual swcounter in there I suppose.
> > 
> > That way we could profile applications based on IO-wait, which would be
> > cool.
> 
> How would you imagine an interface for this? Could you come up with 
> something that you would like to see, and then I could see if we could 
> implement it. 
> 
> How would the TRACE_EVENT look exactly? Would there be anything different 
> in the trace point location itself?

Something like:

TRACE_EVENT(sched_iowait,

	TP_PROTO(struct task_struct *p, u64 time),

	TP_ARGS(p, time),

	TP_STRUCT__entry(
		__field(pid_t, pid )
		__field(u64,   time)
	),

	TP_fast_assign(
		__entry->pid	= p->pid;
		__entry->time	= time;

		__perf_count(time);
	),

	TP_printk("task %d waited for IO for %Lu ns",
		__entry->pid, __entry->time)
);

Something like the below, except that its probably borken in interesting
ways..

---
 include/trace/ftrace.h |   19 ++++++++++++++-----
 kernel/perf_counter.c  |    6 +++---
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 1867553..7e550a2 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -447,11 +447,20 @@ static inline int ftrace_get_offsets_##call(				\
 #define TP_FMT(fmt, args...)	fmt "\n", ##args
 
 #ifdef CONFIG_EVENT_PROFILE
-#define _TRACE_PROFILE(call, proto, args)				\
+
+#undef __perf_addr
+#define __perf_addr(a) addr = (a)
+
+#undef __perf_count
+#define __perf_count(c) count = (c)
+	
+#define _TRACE_PROFILE(call, proto, args, assign)			\
 static void ftrace_profile_##call(proto)				\
 {									\
-	extern void perf_tpcounter_event(int);				\
-	perf_tpcounter_event(event_##call.id);				\
+	extern void perf_tpcounter_event(int, u64, u64);		\
+	u64 addr = 0, count = 1;					\
+	{ assign; }							\
+	perf_tpcounter_event(event_##call.id, addr, count);		\
 }									\
 									\
 static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
@@ -476,7 +485,7 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
 	.profile_disable = ftrace_profile_disable_##call,
 
 #else
-#define _TRACE_PROFILE(call, proto, args)
+#define _TRACE_PROFILE(call, proto, args, assign)
 #define _TRACE_PROFILE_INIT(call)
 #endif
 
@@ -502,7 +511,7 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
+_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args), PARAMS(assign))	\
 									\
 static struct ftrace_event_call event_##call;				\
 									\
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 5498890..879a6ce 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -3680,17 +3680,17 @@ static const struct pmu perf_ops_task_clock = {
 };
 
 #ifdef CONFIG_EVENT_PROFILE
-void perf_tpcounter_event(int event_id)
+void perf_tpcounter_event(int event_id, u64 addr, u64 count)
 {
 	struct perf_sample_data data = {
 		.regs = get_irq_regs(),
-		.addr = 0,
+		.addr = addr,
 	};
 
 	if (!data.regs)
 		data.regs = task_pt_regs(current);
 
-	do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, &data);
+	do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, count, 1, &data);
 }
 EXPORT_SYMBOL_GPL(perf_tpcounter_event);