linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Jiri Olsa <jolsa@kernel.org>
Cc: linux-kernel@vger.kernel.org,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Corey Ashford <cjashfor@linux.vnet.ibm.com>,
	David Ahern <dsahern@gmail.com>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Ingo Molnar <mingo@kernel.org>,
	Jean Pihet <jean.pihet@linaro.org>,
	Paul Mackerras <paulus@samba.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: Re: [PATCH 15/17] perf tools: Add debug prints for ordered events queue
Date: Fri, 13 Jun 2014 21:12:23 +0900	[thread overview]
Message-ID: <1402661543.2178.25.camel@leonhard> (raw)
In-Reply-To: <1402610913-19059-16-git-send-email-jolsa@kernel.org>

2014-06-13 (금), 00:08 +0200, Jiri Olsa:
> Adding some prints for ordered events queue, to help
> debug issues.
> 
> Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
> Cc: David Ahern <dsahern@gmail.com>
> Cc: Frederic Weisbecker <fweisbec@gmail.com>
> Cc: Ingo Molnar <mingo@kernel.org>
> Cc: Jean Pihet <jean.pihet@linaro.org>
> Cc: Namhyung Kim <namhyung@kernel.org>
> Cc: Paul Mackerras <paulus@samba.org>
> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
>  tools/perf/builtin-report.c      |  4 +++
>  tools/perf/util/ordered-events.c | 54 ++++++++++++++++++++++++++++++++++++++++
>  tools/perf/util/ordered-events.h |  2 ++
>  3 files changed, 60 insertions(+)
> 
> diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
> index 09b9d0c..130ab5c 100644
> --- a/tools/perf/builtin-report.c
> +++ b/tools/perf/builtin-report.c
> @@ -82,6 +82,10 @@ static int report__config(const char *var, const char *value, void *cb)
>  		rep->queue_size = perf_config_u64(var, value);
>  		return 0;
>  	}
> +	if (!strcmp(var, "report.queue-debug")) {
> +		debug_sample_queue = perf_config_int(var, value);
> +		return 0;
> +	}

Again, config option only?


>  
>  	return perf_default_config(var, value, cb);
>  }
> diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
> index eaf2c47..80f1daa 100644
> --- a/tools/perf/util/ordered-events.c
> +++ b/tools/perf/util/ordered-events.c
> @@ -4,6 +4,37 @@
>  #include "session.h"
>  #include "asm/bug.h"
>  
> +int debug_sample_queue;
> +
> +static int pr_level(int level, const char *fmt, ...)
> +{
> +	int ret = 0;
> +
> +	if (unlikely(debug_sample_queue >= level)) {
> +		va_list args;
> +
> +		va_start(args, fmt);
> +		ret = vfprintf(stderr, fmt, args);
> +		va_end(args);
> +	}
> +
> +	return ret;
> +}
> +
> +#define pr_N(n, fmt, ...) \
> +	pr_level(n, fmt, ##__VA_ARGS__)
> +#define pr(fmt, ...)  pr_N(1, pr_fmt(fmt), ##__VA_ARGS__)
> +
> +static int pr_time(const char *str, u64 time)
> +{
> +	u64 secs, usecs, nsecs = time;
> +
> +	secs = nsecs / NSECS_PER_SEC;
> +	nsecs -= secs * NSECS_PER_SEC;
> +	usecs = nsecs / NSECS_PER_USEC;
> +	return fprintf(stderr, "\t[%13lu.%06lu] %s\n", secs, usecs, str);
> +}

It'd be better if these functions somehow reuse existing pr_* functions
or at least honor the use_browser value IMHO.

Thanks,
Namhyung


> +
>  static void queue_event(struct ordered_events_queue *q, struct ordered_event *new)
>  {
>  	struct ordered_event *last = q->last;
> @@ -68,6 +99,9 @@ static struct ordered_event *alloc_event(struct ordered_events_queue *q)
>  		if (!q->buffer)
>  			return NULL;
>  
> +		pr("alloc size %" PRIu64 "B, max %" PRIu64 "B\n",
> +		   q->cur_alloc_size, q->max_alloc_size);
> +
>  		q->cur_alloc_size += size;
>  		list_add(&q->buffer->list, &q->to_free);
>  		q->buffer_idx = 2;
> @@ -182,6 +216,19 @@ int ordered_events_flush(struct perf_session *s, struct perf_tool *tool,
>  		break;
>  	};
>  
> +	if (unlikely(debug_sample_queue)) {
> +		static const char * const str[] = {
> +			"FINAL",
> +			"ROUND",
> +			"HALF ",
> +		};
> +
> +		fprintf(stderr, "ordered_events_flush %s, nr_events %u\n",
> +			str[how], q->nr_events);
> +		pr_time("next_flush",    q->next_flush);
> +		pr_time("max_timestamp", q->max_timestamp);
> +	}
> +
>  	err = __ordered_events_flush(s, tool);
>  
>  	if (!err) {
> @@ -189,6 +236,13 @@ int ordered_events_flush(struct perf_session *s, struct perf_tool *tool,
>  			q->next_flush = q->max_timestamp;
>  	}
>  
> +	if (unlikely(debug_sample_queue)) {
> +		fprintf(stderr, "ordered_events_flush nr_events %u\n",
> +			q->nr_events);
> +		pr_time("next_flush", q->next_flush);
> +		pr_time("last_flush", q->last_flush);
> +	}
> +
>  	return err;
>  }
>  
> diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
> index 04cb295..8a717de 100644
> --- a/tools/perf/util/ordered-events.h
> +++ b/tools/perf/util/ordered-events.h
> @@ -48,4 +48,6 @@ ordered_events_queue_alloc_size(struct ordered_events_queue *q, u64 size)
>  {
>  	q->max_alloc_size = size;
>  }
> +
> +extern int debug_sample_queue;
>  #endif /* __ORDERED_EVENTS_H */




  reply	other threads:[~2014-06-13 12:12 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-06-12 22:08 [PATCH 00/17] perf tools: Factor ordered samples queue Jiri Olsa
2014-06-12 22:08 ` [PATCH 01/17] perf tools: Always force PERF_RECORD_FINISHED_ROUND event Jiri Olsa
2014-06-13 11:51   ` Namhyung Kim
2014-06-15 17:17     ` Jiri Olsa
2014-06-12 22:08 ` [PATCH 02/17] perf tools: Fix accounting of ordered samples queue Jiri Olsa
2014-06-12 22:08 ` [PATCH 03/17] perf tools: Rename ordered_samples to ordered_events Jiri Olsa
2014-06-12 22:08 ` [PATCH 04/17] perf tools: Rename ordered_events_queue members Jiri Olsa
2014-06-12 22:08 ` [PATCH 05/17] perf tools: Add ordered_events_(get|put) interface Jiri Olsa
2014-06-13 12:05   ` Namhyung Kim
2014-06-15 17:27     ` Jiri Olsa
2014-06-12 22:08 ` [PATCH 06/17] perf tools: Factor ordered_events_flush to be more generic Jiri Olsa
2014-06-12 22:08 ` [PATCH 07/17] perf tools: Limit ordered events queue size Jiri Olsa
2014-06-12 22:08 ` [PATCH 08/17] perf tools: Flush ordered events in case of allocation failure Jiri Olsa
2014-06-12 22:08 ` [PATCH 09/17] perf tools: Make perf_session_deliver_event global Jiri Olsa
2014-06-12 22:08 ` [PATCH 10/17] perf tools: Create ordered-events object Jiri Olsa
2014-06-12 22:08 ` [PATCH 11/17] perf tools: Add ordered_events_queue_init function Jiri Olsa
2014-06-12 22:08 ` [PATCH 12/17] perf tools: Add ordered_events_queue_free function Jiri Olsa
2014-06-12 22:08 ` [PATCH 13/17] perf tools: Add perf_config_u64 function Jiri Olsa
2014-06-13 12:07   ` Namhyung Kim
2014-06-15 17:48     ` Jiri Olsa
2014-06-12 22:08 ` [PATCH 14/17] perf tools: Add report.queue-size config file option Jiri Olsa
2014-06-13 12:08   ` Namhyung Kim
2014-06-15 17:54     ` Jiri Olsa
2014-06-12 22:08 ` [PATCH 15/17] perf tools: Add debug prints for ordered events queue Jiri Olsa
2014-06-13 12:12   ` Namhyung Kim [this message]
2014-06-15 17:58     ` Jiri Olsa
2014-06-12 22:08 ` [PATCH 16/17] perf tools: Limit the ordered events queue by default to 100MB Jiri Olsa
2014-06-12 22:08 ` [PATCH 17/17] perf tools: Allow out of order messages in forced flush Jiri Olsa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1402661543.2178.25.camel@leonhard \
    --to=namhyung@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=cjashfor@linux.vnet.ibm.com \
    --cc=dsahern@gmail.com \
    --cc=fweisbec@gmail.com \
    --cc=jean.pihet@linaro.org \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=paulus@samba.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).