public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Tom Zanussi <tom.zanussi@linux.intel.com>
Cc: rostedt@goodmis.org, daniel.wagner@bmw-carit.de,
	masami.hiramatsu.pt@hitachi.com, josh@joshtriplett.org,
	andi@firstfloor.org, mathieu.desnoyers@efficios.com,
	peterz@infradead.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 00/28] tracing: 'hist' triggers
Date: Thu, 5 Nov 2015 23:43:34 +0900	[thread overview]
Message-ID: <20151105144334.GA28273@danjae.kornet> (raw)
In-Reply-To: <cover.1445530672.git.tom.zanussi@linux.intel.com>

Hi Tom,

I implemented 'log2' modifier on top of your v11 patchset.  Could you
please take a look at this?



>From 5fc74778b9af5e4e121a0563fb8e54e8f495ca29 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 5 Nov 2015 23:34:05 +0900
Subject: [PATCH] tracing: Add hist trigger 'log2' modifier

Allow users to have numeric fields displayed as log2 values in case
value range is very wide by appending '.log2' to field names.

For example,

  # echo 'hist:key=bytes_req' > kmalloc/trigger
  # cat kmalloc/hist

  { bytes_req:        504 } hitcount:          1
  { bytes_req:         11 } hitcount:          1
  { bytes_req:        104 } hitcount:          1
  { bytes_req:         48 } hitcount:          1
  { bytes_req:       2048 } hitcount:          1
  { bytes_req:       4096 } hitcount:          1
  { bytes_req:        240 } hitcount:          1
  { bytes_req:        392 } hitcount:          1
  { bytes_req:         13 } hitcount:          1
  { bytes_req:         28 } hitcount:          1
  { bytes_req:         12 } hitcount:          1
  { bytes_req:         64 } hitcount:          2
  { bytes_req:        128 } hitcount:          2
  { bytes_req:         32 } hitcount:          2
  { bytes_req:          8 } hitcount:         11
  { bytes_req:         10 } hitcount:         13
  { bytes_req:         24 } hitcount:         25
  { bytes_req:        160 } hitcount:         29
  { bytes_req:         16 } hitcount:         33
  { bytes_req:         80 } hitcount:         36

When using '.log2' modifier, the output looks like:

  # echo 'hist:key=bytes_req.log2' > kmalloc/trigger
  # cat kmalloc/hist

  { bytes_req: ~ 2^12 } hitcount:          1
  { bytes_req: ~ 2^11 } hitcount:          1
  { bytes_req: ~ 2^9  } hitcount:          2
  { bytes_req: ~ 2^6  } hitcount:          3
  { bytes_req: ~ 2^3  } hitcount:         13
  { bytes_req: ~ 2^5  } hitcount:         19
  { bytes_req: ~ 2^8  } hitcount:         49
  { bytes_req: ~ 2^7  } hitcount:         57
  { bytes_req: ~ 2^4  } hitcount:         74

Cc: Tom Zanussi <tom.zanussi@linux.intel.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 kernel/trace/trace.c             |  1 +
 kernel/trace/trace_events_hist.c | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 74f95745acbc..542486468707 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3837,6 +3837,7 @@ static const char readme_msg[] =
 	"\t            .sym-offset display an address as a symbol and offset\n"
 	"\t            .execname   display a common_pid as a program name\n"
 	"\t            .syscall    display a syscall id as a syscall name\n\n"
+	"\t            .log2       display log2 value rather than raw number\n\n"
 	"\t    The 'pause' parameter can be used to pause an existing hist\n"
 	"\t    trigger or to start a hist trigger but not log any events\n"
 	"\t    until told to do so.  'continue' can be used to start or\n"
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index b040ebefcd64..20a17fdb3fe6 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -68,6 +68,13 @@ static u64 hist_field_pstring(struct hist_field *hist_field, void *event)
 	return (u64)(unsigned long)*addr;
 }
 
+static u64 hist_field_log2(struct hist_field *hist_field, void *event)
+{
+	u64 val = *(u64 *)(event + hist_field->field->offset);
+
+	return (u64) ilog2(roundup_pow_of_two(val));
+}
+
 #define DEFINE_HIST_FIELD_FN(type)					\
 static u64 hist_field_##type(struct hist_field *hist_field, void *event)\
 {									\
@@ -103,6 +110,7 @@ enum hist_field_flags {
 	HIST_FIELD_EXECNAME	= 64,
 	HIST_FIELD_SYSCALL	= 128,
 	HIST_FIELD_STACKTRACE	= 256,
+	HIST_FIELD_LOG2		= 512,
 };
 
 struct hist_trigger_attrs {
@@ -349,6 +357,11 @@ static struct hist_field *create_hist_field(struct ftrace_event_field *field,
 		goto out;
 	}
 
+	if (flags & HIST_FIELD_LOG2) {
+		hist_field->fn = hist_field_log2;
+		goto out;
+	}
+
 	if (is_string_field(field)) {
 		flags |= HIST_FIELD_STRING;
 
@@ -500,6 +513,8 @@ static int create_key_field(struct hist_trigger_data *hist_data,
 				flags |= HIST_FIELD_EXECNAME;
 			else if (!strcmp(field_str, "syscall"))
 				flags |= HIST_FIELD_SYSCALL;
+			else if (!strcmp(field_str, "log2"))
+				flags |= HIST_FIELD_LOG2;
 			else {
 				ret = -EINVAL;
 				goto out;
@@ -942,6 +957,9 @@ hist_trigger_entry_print(struct seq_file *m,
 						      key + key_field->offset,
 						      HIST_STACKTRACE_DEPTH);
 			multiline = true;
+		} else if (key_field->flags & HIST_FIELD_LOG2) {
+			seq_printf(m, "%s: ~ 2^%-2llu", key_field->field->name,
+				   *(u64 *)(key + key_field->offset));
 		} else if (key_field->flags & HIST_FIELD_STRING) {
 			seq_printf(m, "%s: %-50s", key_field->field->name,
 				   (char *)(key + key_field->offset));
-- 
2.6.2


  parent reply	other threads:[~2015-11-05 14:43 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-10-22 18:14 [PATCH 00/28] tracing: 'hist' triggers Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 01/28] tracing: Update cond flag when enabling or disabling a trigger Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 02/28] tracing: Make ftrace_event_field checking functions available Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 03/28] tracing: Make event trigger " Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 04/28] tracing: Add event record param to trigger_ops.func() Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 05/28] tracing: Add get_syscall_name() Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 06/28] tracing: Add a per-event-trigger 'paused' field Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 07/28] tracing: Add needs_rec flag to event triggers Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 08/28] tracing: Add lock-free tracing_map Tom Zanussi
2015-10-29  8:31   ` Namhyung Kim
2015-10-29 18:35     ` Tom Zanussi
2015-11-02  7:08       ` Namhyung Kim
2015-11-04  1:47         ` Tom Zanussi
2015-11-04  2:26           ` Namhyung Kim
2015-11-04  2:56             ` Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 09/28] tracing: Add 'hist' event trigger command Tom Zanussi
2015-10-29  9:11   ` Namhyung Kim
2015-10-29 18:37     ` Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 10/28] tracing: Add hist trigger support for multiple values ('vals=' param) Tom Zanussi
2015-11-02  7:42   ` Namhyung Kim
2015-10-22 18:14 ` [PATCH v11 11/28] tracing: Add hist trigger support for compound keys Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 12/28] tracing: Add hist trigger support for user-defined sorting ('sort=' param) Tom Zanussi
2015-11-02  8:03   ` Namhyung Kim
2015-10-22 18:14 ` [PATCH v11 13/28] tracing: Add hist trigger support for pausing and continuing a trace Tom Zanussi
2015-11-03  8:38   ` Namhyung Kim
2015-11-04  1:53     ` Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 14/28] tracing: Add hist trigger support for clearing " Tom Zanussi
2015-11-03  8:43   ` Namhyung Kim
2015-10-22 18:14 ` [PATCH v11 15/28] tracing: Add hist trigger 'hex' modifier for displaying numeric fields Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 16/28] tracing: Add hist trigger 'sym' and 'sym-offset' modifiers Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 17/28] tracing: Add hist trigger 'execname' modifier Tom Zanussi
2015-11-02 14:10   ` Namhyung Kim
2015-11-04  2:37     ` Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 18/28] tracing: Add hist trigger 'syscall' modifier Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 19/28] tracing: Add hist trigger support for stacktraces as keys Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 20/28] tracing: Support string type key properly Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 21/28] tracing: Remove restriction on string position in hist trigger keys Tom Zanussi
2015-11-02 14:40   ` Namhyung Kim
2015-10-22 18:14 ` [PATCH v11 22/28] tracing: Add enable_hist/disable_hist triggers Tom Zanussi
2015-11-03  8:55   ` Namhyung Kim
2015-11-04  1:58     ` Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 23/28] tracing: Add 'hist' trigger Documentation Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 24/28] tracing: Add support for multiple hist triggers per event Tom Zanussi
2015-11-03  0:34   ` Namhyung Kim
2015-11-04  1:52     ` Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 25/28] tracing: Add support for named triggers Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 26/28] tracing: Add support for named hist triggers Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 27/28] kselftests/ftrace : Add event trigger testcases Tom Zanussi
2015-10-22 18:14 ` [PATCH v11 28/28] kselftests/ftrace: Add hist " Tom Zanussi
2015-10-22 18:21 ` [PATCH 00/28] tracing: 'hist' triggers Steven Rostedt
2015-10-22 18:31   ` Tom Zanussi
2015-11-05 14:43 ` Namhyung Kim [this message]
2015-11-05 14:59   ` 平松雅巳 / HIRAMATU,MASAMI
2015-11-05 22:13   ` Tom Zanussi
2015-11-05 23:18     ` Namhyung Kim

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=20151105144334.GA28273@danjae.kornet \
    --to=namhyung@kernel.org \
    --cc=andi@firstfloor.org \
    --cc=daniel.wagner@bmw-carit.de \
    --cc=josh@joshtriplett.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=masami.hiramatsu.pt@hitachi.com \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=tom.zanussi@linux.intel.com \
    /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