From: Damien Le Moal <dlemoal@kernel.org>
To: Nick Neumann <nick@pcpartpicker.com>,
Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Cc: fio@vger.kernel.org, Jens Axboe <axboe@kernel.dk>,
Vincent Fu <vincentfu@gmail.com>
Subject: Re: [PATCH 5/9] introduce the log_issue_time option
Date: Thu, 29 Aug 2024 10:05:24 +0900 [thread overview]
Message-ID: <51c896f9-7180-4465-8f32-434f237d157b@kernel.org> (raw)
In-Reply-To: <CADqNVTqZJ6oB6QsZcKgeP+dsCmFJug=pPQJbrhgbYSNo1+1Rcg@mail.gmail.com>
On 8/29/24 02:38, Nick Neumann wrote:
> Do you have any thoughts on eventually including the submit time or
> submit latency in the clat file as well? Then one would have a single
> file without any of the redundancies involved with multiple files.
The submit time is what Shin'ichiro patches are adding :)
issue time == submit time. Maybe we should change the name to log_submit_time ?
With the code refactoring/cleanup that Shin'ichiro did, the submit latency can
easily be added too. Though one could argue that the "clat" name for the log
then becomes a little inappropriate.
> I've also thought a bit about having a non-text but portable output
> file option, like protobuf. The files are large, and gzip compresses
> the per-I/O logs well, but I imagine protobuf would be a big win for
> both outputting and ingesting the log files, and would be way smaller
> than the non-compressed log files.
Adding an option to change the clat file format can be done on top of this series.
>
> Thanks for the new feature and any input on my thoughts!
> - Nick
--
Damien Le Moal
Western Digital Research
next prev parent reply other threads:[~2024-08-29 1:05 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-27 7:08 [PATCH 0/9] introduce the log_issue_time option Shin'ichiro Kawasaki
2024-08-27 7:08 ` [PATCH 1/9] stat: reduce arguments of add_*lat_sample() functions Shin'ichiro Kawasaki
2024-08-27 7:08 ` [PATCH 2/9] stat: reduce arguments of add_log_sample() Shin'ichiro Kawasaki
2024-08-27 7:08 ` [PATCH 3/9] iolog: refactor flush_samples() Shin'ichiro Kawasaki
2024-08-28 16:56 ` Nick Neumann
2024-08-29 5:44 ` Shinichiro Kawasaki
2024-08-27 7:08 ` [PATCH 4/9] iolog: drop struct io_sample_offset Shin'ichiro Kawasaki
2024-08-27 7:08 ` [PATCH 5/9] introduce the log_issue_time option Shin'ichiro Kawasaki
2024-08-28 17:02 ` Jens Axboe
2024-08-29 5:50 ` Shinichiro Kawasaki
2024-08-28 17:38 ` Nick Neumann
2024-08-29 1:05 ` Damien Le Moal [this message]
2024-08-29 1:44 ` Nick Neumann
2024-08-29 8:13 ` Shinichiro Kawasaki
2024-08-27 7:08 ` [PATCH 6/9] doc: fix the descriptions of the log_prio option Shin'ichiro Kawasaki
2024-08-27 7:08 ` [PATCH 7/9] doc: describe the log_issue_time option Shin'ichiro Kawasaki
2024-08-27 7:08 ` [PATCH 8/9] t/jobs/t0033: add test for the log file format Shin'ichiro Kawasaki
2024-08-28 18:46 ` Vincent Fu
2024-08-29 7:04 ` Shinichiro Kawasaki
2024-08-27 7:08 ` [PATCH 9/9] t/jobs/t0034: add test for the log_issue_time option Shin'ichiro Kawasaki
2024-08-28 18:47 ` Vincent Fu
2024-08-28 17:06 ` [PATCH 0/9] introduce " Jens Axboe
2024-08-29 0:59 ` Damien Le Moal
2024-08-29 1:49 ` Nick Neumann
2024-08-29 8:40 ` Shinichiro Kawasaki
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=51c896f9-7180-4465-8f32-434f237d157b@kernel.org \
--to=dlemoal@kernel.org \
--cc=axboe@kernel.dk \
--cc=fio@vger.kernel.org \
--cc=nick@pcpartpicker.com \
--cc=shinichiro.kawasaki@wdc.com \
--cc=vincentfu@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