From: Chase Douglas on
When combined with function graph tracing the ftrace function profiler
also prints the average run time of functions. While this gives us some
good information, it doesn't tell us anything about the variance of the
run times of the function. This change prints out the s^2 sample
standard deviation alongside the average.

This change adds one entry to the profile record structure. This
increases the memory footprint of the function profiler by 1/3 on a
32-bit system, and by 1/5 on a 64-bit system when function graphing is
enabled, though the memory is only allocated when the profiler is turned
on. During the profiling, one extra line of code adds the squared
calltime to the new record entry, so this should not adversly affect
performance.

Note that the square of the sample standard deviation is printed because
there is no sqrt implementation for unsigned long long in the kernel.

Signed-off-by: Chase Douglas <chase.douglas(a)canonical.com>
---
kernel/trace/ftrace.c | 20 +++++++++++++++++---
1 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0cccb6c..07deba1 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -253,6 +253,7 @@ struct ftrace_profile {
unsigned long counter;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
unsigned long long time;
+ unsigned long long time_squared;
#endif
};

@@ -355,9 +356,9 @@ static int function_stat_headers(struct seq_file *m)
{
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
seq_printf(m, " Function "
- "Hit Time Avg\n"
+ "Hit Time Avg s^2\n"
" -------- "
- "--- ---- ---\n");
+ "--- ---- --- ---\n");
#else
seq_printf(m, " Function Hit\n"
" -------- ---\n");
@@ -373,6 +374,7 @@ static int function_stat_show(struct seq_file *m, void *v)
static DEFINE_MUTEX(mutex);
static struct trace_seq s;
unsigned long long avg;
+ unsigned long long stddev;
#endif

kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
@@ -383,11 +385,21 @@ static int function_stat_show(struct seq_file *m, void *v)
avg = rec->time;
do_div(avg, rec->counter);

+ /* Sample standard deviation (s^2) */
+ if (rec->counter <= 1)
+ stddev = 0;
+ else {
+ stddev = rec->time_squared - rec->counter * avg * avg;
+ do_div(stddev, (rec->counter - 1) * 1000); /* ns^2 -> us^2 */
+ }
+
mutex_lock(&mutex);
trace_seq_init(&s);
trace_print_graph_duration(rec->time, &s);
trace_seq_puts(&s, " ");
trace_print_graph_duration(avg, &s);
+ trace_seq_puts(&s, " ");
+ trace_print_graph_duration(stddev, &s);
trace_print_seq(m, &s);
mutex_unlock(&mutex);
#endif
@@ -657,8 +669,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
}

rec = ftrace_find_profiled_func(stat, trace->func);
- if (rec)
+ if (rec) {
rec->time += calltime;
+ rec->time_squared += calltime * calltime;
+ }

out:
local_irq_restore(flags);
--
1.7.0.4

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