From: Li Zefan <lizf@cn.fujitsu.com>
To: Theodore Tso <tytso@mit.edu>,
Frederic Weisbecker <fweisbec@gmail.com>,
Li Zefan <lizf@cn.fujitsu.com>,
Jens Axboe <jens.axboe@oracle.com>,
LKML <linux-kernel@vger.kernel.org>,
Steven Rostedt <rostedt@goodmis.org>,
Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: Re: blktrace: event traces displayed wrong while ftrace blktrace is active
Date: Wed, 15 Apr 2009 08:57:39 +0800 [thread overview]
Message-ID: <49E53103.7020404@cn.fujitsu.com> (raw)
In-Reply-To: <20090414213207.GP955@mit.edu>
Theodore Tso wrote:
> On Tue, Apr 14, 2009 at 11:25:33PM +0200, Frederic Weisbecker wrote:
>> Indeed. Note that you can overwrite this default by typing:
>>
>> echo context-info > trace_option
>>
>> after setting bkltrace as the current tracer.
>
> The problem with doing that is that blktrace will then display this:
>
> fsync-tester-27934 [001] 208.031278: fsync-tester-27934 [001] 208.031278: 254,4 Q WS 268392 + 8 [fsync-tester]
>
> I think the real problem is that blk trace is displaying the standard
> context-info, so it's suppressing the normal context info. So I have
> the choice on having no context information on my event trace lines,
> or two copies of the context information for the block trace lines.
>
> :-(
>
I'll provide a patch to solve this confusing behavior.
> I'm guessing things were done this way in order to support the old
> legancy blktrace format?
>
Right, in 2 ways:
1. we can make the output the same as userspace 'btrace /dev/sda':
# echo blk > current_tracer
# echo 1 > options/blk_classic
2. we can make the binary output parsable by userspace blkparse:
# echo blk > current_tracer
# echo bin > trace_options
# cat trace_pipe | blkparse -i -
prev parent reply other threads:[~2009-04-15 0:57 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-04-13 21:59 blktrace: event traces displayed wrong while ftrace blktrace is active Theodore Ts'o
2009-04-13 22:19 ` Ingo Molnar
2009-04-14 10:03 ` Li Zefan
2009-04-14 21:25 ` Frederic Weisbecker
2009-04-14 21:32 ` Theodore Tso
2009-04-15 0:16 ` Arnaldo Carvalho de Melo
2009-04-15 0:57 ` Li Zefan [this message]
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=49E53103.7020404@cn.fujitsu.com \
--to=lizf@cn.fujitsu.com \
--cc=acme@redhat.com \
--cc=fweisbec@gmail.com \
--cc=jens.axboe@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=tytso@mit.edu \
/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