[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87ioiapft4.fsf@sejong.aot.lge.com>
Date: Thu, 20 Nov 2014 15:05:43 +0900
From: Namhyung Kim <namhyung@...nel.org>
To: Steven Rostedt <rostedt@...dmis.org>
Cc: byungchul.park@....com, mingo@...hat.com,
linux-kernel@...r.kernel.org, seungho1.park@....com,
jolsa@...hat.com
Subject: Re: [PATCH v5 2/2] tracing: add additional marks to signal very large time
Hi Steve and Byungchul,
On Wed, 19 Nov 2014 20:06:04 -0500, Steven Rostedt wrote:
> On Thu, 20 Nov 2014 09:15:35 +0900
> byungchul.park@....com wrote:
>> -static unsigned long preempt_mark_thresh_us = 100;
>> +#undef MARK
>> +#define MARK(v, s) {.val = v, .sym = s}
>> +/* trace overhead mark */
>> +static const struct trace_mark {
>> + unsigned long long val; /* unit: nsec */
>> + char sym;
>> +} mark[] = {
>> + MARK(1000000000ULL , '$'), /* 1 sec */
>> + MARK(1000000ULL , '#'), /* 1000 usecs */
>> + MARK(100000ULL , '!'), /* 100 usecs */
>> + MARK(10000ULL , '+'), /* 10 usecs */
>> + MARK(0ULL , ' '), /* 0 usecs */
>> +};
>> +#undef MARK
>> +
>> +char trace_find_mark(unsigned long long d)
>> +{
>> + int i;
>> + int size = ARRAY_SIZE(mark);
>> +
>> + for (i = 0; i < size; i++) {
>> + if (d >= mark[i].val)
>> + break;
>> + }
>> +
>> + return (i == size)? ' ' : mark[i].sym;
>
> Change this to:
>
> /* The break from loop must have been hit */
> if (WARN_ON_ONCE(i == size))
> return ' ';
I think it's impossible since it's always true that 'd >= 0'.
Thanks,
Namhyung
>
> return mark[i].sym;
>
> -- Steve
>
>
>> +}
>>
>> static int
>> lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
>> @@ -506,8 +532,7 @@ lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
>> return trace_seq_printf(
>> s, " %4lldus%c: ",
>> abs_ts,
>> - rel_ts > preempt_mark_thresh_us ? '!' :
>> - rel_ts > 1 ? '+' : ' ');
>> + trace_find_mark(rel_ts * NSEC_PER_USEC));
>> } else { /* !verbose && !in_ns */
>> return trace_seq_printf(s, " %4lld: ", abs_ts);
>> }
>> @@ -692,7 +717,7 @@ int register_ftrace_event(struct trace_event *event)
>> goto out;
>>
>> } else {
>> -
>> +
>> event->type = next_event_type++;
>> list = &ftrace_event_list;
>> }
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists