From: Li Zefan <lizf@cn.fujitsu.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: Jens Axboe <jens.axboe@oracle.com>,
Steven Rostedt <rostedt@goodmis.org>,
Frederic Weisbecker <fweisbec@gmail.com>,
Tom Zanussi <tzanussi@gmail.com>, "Theodore Ts'o" <tytso@mit.edu>,
Steven Whitehouse <swhiteho@redhat.com>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Jeff Moyer <jmoyer@redhat.com>,
Christoph Hellwig <hch@infradead.org>,
FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>,
LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH v2 0/2] tracing/events: convert block trace points to TRACE_EVENT()
Date: Tue, 26 May 2009 12:03:59 +0800 [thread overview]
Message-ID: <4A1B6A2F.2040703@cn.fujitsu.com> (raw)
Here's the v2 patchset to convert block trace points to TRACE_EVENT().
The biggest change is to use __string() instead of __array() to store
hex dump of rq->cmd, so we minimize the memory occupied by rq->cmd from
48 bytes to 3 bytes for fs events. Also some fixes and cleanups.
I haven't had time to benchmark the ioctl blktrace versus the splice
based TRACE_EVENT tracing, but will do in these 2 days.
This patchset should be applied on top of:
"[PATCH] tracing/events: change the type of __str_loc_item to unsigned short"
(http://lkml.org/lkml/2009/5/21/17)
which hasn't been applied to tip tree.
[PATCH v2 1/2] tracing/events: make __string() more general
[PATCH v2 2/2] tracing/events: convert block trace points to TRACE_EVENT()
---
block/blk-core.c | 16 +-
block/elevator.c | 8 +-
drivers/md/dm.c | 5 +-
fs/bio.c | 3 +-
include/linux/blktrace_api.h | 13 +
include/trace/block.h | 76 -------
include/trace/events/block.h | 483 ++++++++++++++++++++++++++++++++++++++++
include/trace/events/irq.h | 12 +-
include/trace/events/lockdep.h | 8 +-
include/trace/ftrace.h | 21 +-
kernel/trace/Makefile | 5 +-
kernel/trace/blktrace.c | 78 +++++++-
mm/bounce.c | 5 +-
13 files changed, 611 insertions(+), 122 deletions(-)
A sample output:
konsole-2057 [001] 870.751689: block_unplug_io: [konsole] 2
<idle>-0 [001] 870.759674: block_rq_complete: 8,0 R () 115104312 + 24 [0]
<idle>-0 [001] 870.760744: block_rq_complete: 8,0 R () 115104344 + 120 [0]
konsole-2057 [001] 870.761233: block_remap: 8,0 R 115132584 + 256 <- (8,8) 12428976
konsole-2057 [001] 870.761234: block_bio_queue: 8,0 R 115132584 + 256 [konsole]
konsole-2057 [001] 870.761239: block_getrq: 8,0 R 115132584 + 256 [konsole]
konsole-2057 [001] 870.761243: block_plug: [konsole]
konsole-2057 [001] 870.761244: block_rq_insert: 8,0 R 0 () 115132584 + 256 [konsole]
konsole-2057 [001] 870.761248: block_rq_issue: 8,0 R 0 () 115132584 + 256 [konsole]
konsole-2057 [001] 870.761311: block_unplug_io: [konsole] 1
<idle>-0 [001] 870.770299: block_rq_complete: 8,0 R () 115132584 + 256 [0]
konsole-2057 [001] 870.770603: block_remap: 8,0 R 115143352 + 8 <- (8,8) 12439744
konsole-2057 [001] 870.770604: block_bio_queue: 8,0 R 115143352 + 8 [konsole]
konsole-2057 [001] 870.770609: block_getrq: 8,0 R 115143352 + 8 [konsole]
konsole-2057 [001] 870.770612: block_plug: [konsole]
konsole-2057 [001] 870.770614: block_rq_insert: 8,0 R 0 () 115143352 + 8 [konsole]
konsole-2057 [001] 870.770666: block_remap: 8,0 R 115143376 + 104 <- (8,8) 12439768
konsole-2057 [001] 870.770667: block_bio_queue: 8,0 R 115143376 + 104 [konsole]
konsole-2057 [001] 870.770672: block_getrq: 8,0 R 115143376 + 104 [konsole]
konsole-2057 [001] 870.770674: block_rq_insert: 8,0 R 0 () 115143376 + 104 [konsole]
konsole-2057 [001] 870.770678: block_rq_issue: 8,0 R 0 () 115143352 + 8 [konsole]
konsole-2057 [001] 870.770736: block_rq_issue: 8,0 R 0 () 115143376 + 104 [konsole]
konsole-2057 [001] 870.770744: block_unplug_io: [konsole] 2
<idle>-0 [001] 870.780006: block_rq_complete: 8,0 R () 115143352 + 8 [0]
konsole-2057 [001] 870.780423: block_remap: 8,0 R 115184728 + 168 <- (8,8) 12481120
konsole-2057 [001] 870.780424: block_bio_queue: 8,0 R 115184728 + 168 [konsole]
konsole-2057 [001] 870.780429: block_getrq: 8,0 R 115184728 + 168 [konsole]
konsole-2057 [001] 870.780432: block_plug: [konsole]
konsole-2057 [001] 870.780433: block_rq_insert: 8,0 R 0 () 115184728 + 168 [konsole]
konsole-2057 [001] 870.780437: block_rq_issue: 8,0 R 0 () 115184728 + 168 [konsole]
konsole-2057 [001] 870.780483: block_remap: 8,0 R 115187448 + 88 <- (8,8) 12483840
konsole-2057 [001] 870.780484: block_bio_queue: 8,0 R 115187448 + 88 [konsole]
konsole-2057 [001] 870.780488: block_getrq: 8,0 R 115187448 + 88 [konsole]
konsole-2057 [001] 870.780490: block_rq_insert: 8,0 R 0 () 115187448 + 88 [konsole]
konsole-2057 [001] 870.780496: block_unplug_io: [konsole] 3
<idle>-0 [001] 870.781010: block_rq_complete: 8,0 R () 115143376 + 104 [0]
<idle>-0 [001] 870.781076: block_rq_issue: 8,0 R 0 () 115187448 + 88 [swapper]
<idle>-0 [001] 870.792032: block_rq_complete: 8,0 R () 115184728 + 168 [0]
X-1702 [001] 870.801456: block_rq_complete: 8,0 R () 115187448 + 88 [0]
next reply other threads:[~2009-05-26 4:02 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-05-26 4:03 Li Zefan [this message]
2009-05-26 4:04 ` [PATCH v2 1/2] tracing/events: make __string() more general Li Zefan
2009-05-26 6:02 ` Christoph Hellwig
2009-05-27 1:43 ` Li Zefan
2009-05-27 7:30 ` Christoph Hellwig
2009-05-27 8:12 ` Li Zefan
2009-05-27 9:55 ` Christoph Hellwig
2009-05-26 20:56 ` Steven Rostedt
2009-05-27 1:24 ` Li Zefan
2009-05-27 1:49 ` Steven Rostedt
2009-05-27 1:59 ` Li Zefan
2009-05-27 2:15 ` Steven Rostedt
2009-05-27 2:33 ` Li Zefan
2009-05-27 2:47 ` Steven Rostedt
2009-05-27 7:22 ` Christoph Hellwig
2009-05-26 4:05 ` [PATCH v2 2/2] tracing/events: convert block trace points to TRACE_EVENT() Li Zefan
2009-06-09 5:43 ` [PATCH v3] " Li Zefan
2009-06-10 9:22 ` [tip:tracing/core] " tip-bot for Li Zefan
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=4A1B6A2F.2040703@cn.fujitsu.com \
--to=lizf@cn.fujitsu.com \
--cc=fujita.tomonori@lab.ntt.co.jp \
--cc=fweisbec@gmail.com \
--cc=hch@infradead.org \
--cc=jens.axboe@oracle.com \
--cc=jmoyer@redhat.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rostedt@goodmis.org \
--cc=swhiteho@redhat.com \
--cc=tytso@mit.edu \
--cc=tzanussi@gmail.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