Flexible I/O Tester development
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: Vasily Tarasov <tarasov@vasily.name>, fio@vger.kernel.org
Subject: Re: Disk utilization statistics in terse format
Date: Thu, 10 Jul 2014 10:48:23 +0200	[thread overview]
Message-ID: <53BE5357.8050407@kernel.dk> (raw)
In-Reply-To: <CAFTzLMPWvQ8+rxmbSruzmHTMvkDXQ_ednA5rkDb3_CVoAtdVVw@mail.gmail.com>

On 2014-07-09 16:21, Vasily Tarasov wrote:
> Hi All,
>
> When I run fio as a standalone application (without using a
> server-client model) and use terse output format, disk utilization is
> never printed. Here are the results of my analysis:
>
> 1) show_thread_status_terse_v2() does not call show_disk_util() at all.
>
> 2) show_thread_status_terse_v3_v4() does call show_disk_util(), but
> only if is_backend variable is true (which is not, in case of a
> standalone run).
>
> 3) __show_run_stats() call show_disk_util() only in case of
> FIO_OUTPUT_JSON or FIO_OUTPUT_NORMAL formats.
>
> There are several ways to fix this issue. I think the best way is to
> call show_disk_util() from __show_run_stats() in case of terse format.
> This will break the current terse format: disk utilization fields will
> be printed in the end of the lines (after thread statistics), which is
> not how the HOWTO defines it. But, it seems like the v2 format is
> already inconsistent with HOWTO. And for v3 format, if client-server
> model is used, disk utilization fields will be printed in the end of
> the terse line anyway (at least this is my current understanding of
> the code). So, what I suggest will bring consistency accross
> client-server and standalone runs. We will also need to fix HOWTO.
>
> Let me know what is the best way to fix this, and I'll be happy to send a patch.

Seems like the is_backend check in _v3_v4 should just go. Can't come up 
with a good reason why that is there, it already knows if it should do 
json output, or normal output (and in terse format, if asked).

-- 
Jens Axboe



  reply	other threads:[~2014-07-10  8:48 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-09 14:21 Disk utilization statistics in terse format Vasily Tarasov
2014-07-10  8:48 ` Jens Axboe [this message]
2014-07-11 23:25   ` Vasily Tarasov
2014-07-12  9:01     ` Jens Axboe

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=53BE5357.8050407@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=fio@vger.kernel.org \
    --cc=tarasov@vasily.name \
    /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