fio.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Vincent Fu <vincentfu@gmail.com>
To: Nick Neumann <nick@pcpartpicker.com>, fio@vger.kernel.org
Subject: Re: fio and epoch issues
Date: Fri, 18 Aug 2023 14:58:11 -0400	[thread overview]
Message-ID: <4bd9b597-6221-1f07-991a-d79981d0fc0f@gmail.com> (raw)
In-Reply-To: <CADqNVTqVUra10ET=P+hPA86iimSs3oC7=eWJNdpWjo5e4p+p1g@mail.gmail.com>

On 8/16/23 16:45, Nick Neumann wrote:
> I've tried advocating for this via github issues a couple times
> (https://github.com/axboe/fio/issues/1544,
> https://github.com/axboe/fio/pull/1353/commits) but haven't had much
> luck/interest. I thought I'd try here and see if I could get enough
> interest to get some improvements to fio timekeeping committed. :-)
> 
> The main issue is that by default, fio log files use timestamps based
> on an epoch that is the beginning of the job. If you have multiple
> jobs, especially with some jobs waiting on other jobs before starting,
> this means you have different epochs and the times in the logs for
> each job cannot be compared/ordered.
> 
> Using log_alternate_epoch solves this problem since with it all logs
> share a common epoch, but introduces a different problem of not
> knowing the start time for each job relative to the common epoch.
> 
> Using the default beginning of job epoch for log files, but also
> recording the start time of each job against a common (alternate)
> epoch, would solve both problems and bring other minor benefits too.
> 
> Any thoughts? Issue 1544 has a 6-month-old PR that implements this.
> I'm happy to update, make changes, or approach it differently if
> desired.
> 
> Thanks,
> Nick
> 

I've left feedback at https://github.com/axboe/fio/pull/1353. I think we 
should be able to get something done to get this working for you.

Vincent


      reply	other threads:[~2023-08-18 18:58 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-08-16 20:45 fio and epoch issues Nick Neumann
2023-08-18 18:58 ` Vincent Fu [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=4bd9b597-6221-1f07-991a-d79981d0fc0f@gmail.com \
    --to=vincentfu@gmail.com \
    --cc=fio@vger.kernel.org \
    --cc=nick@pcpartpicker.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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).