Flexible I/O Tester development
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: Lev Serebryakov <lev@serebryakov.spb.ru>
Cc: fio@vger.kernel.org
Subject: Re: fio-2.0.14 crashes with "Assertion failed: (data->fail_ok), function axmap_set_fn, file lib/axmap.c, line 233."
Date: Thu, 7 Mar 2013 12:37:43 +0100	[thread overview]
Message-ID: <20130307113743.GL1059@kernel.dk> (raw)
In-Reply-To: <1404460263.20130306190819@serebryakov.spb.ru>

On Wed, Mar 06 2013, Lev Serebryakov wrote:
> Hello, Fio.
> 
>   FreeBSD 9.1-STABLE, dual-core machine with 6GiB of physical RAM, job
>  file with 8 jobs with filesize=1G-2G (attached).
> 
>    fio --latency-log --bandwidth-log torrent-like.fio
> 
>  crashes after file layout:
> 
> file-1: (g=0): rw=randrw, bs=64-64/128K-128K/128K-128K, ioengine=psync, iodepth=1
> file-2: (g=0): rw=randrw, bs=64-64/128K-128K/128K-128K, ioengine=psync, iodepth=1
> file-3: (g=0): rw=randrw, bs=64-64/128K-128K/128K-128K, ioengine=psync, iodepth=1
> file-4: (g=0): rw=randrw, bs=64-64/128K-128K/128K-128K, ioengine=psync, iodepth=1
> file-5: (g=0): rw=randrw, bs=64-64/128K-128K/128K-128K, ioengine=psync, iodepth=1
> file-6: (g=0): rw=randrw, bs=64-64/128K-128K/128K-128K, ioengine=psync, iodepth=1
> file-7: (g=0): rw=randrw, bs=64-64/128K-128K/128K-128K, ioengine=psync, iodepth=1
> file-8: (g=0): rw=randrw, bs=64-64/128K-128K/128K-128K, ioengine=psync, iodepth=1
> fio-2.0.14
> Starting 8 threads
> file-1: Laying out IO file(s) (1 file(s) / 1910MB)
> file-2: Laying out IO file(s) (1 file(s) / 1910MB)
> file-3: Laying out IO file(s) (1 file(s) / 1910MB)
> file-4: Laying out IO file(s) (1 file(s) / 1910MB)
> file-5: Laying out IO file(s) (1 file(s) / 1910MB)
> file-6: Laying out IO file(s) (1 file(s) / 1910MB)
> file-7: Laying out IO file(s) (1 file(s) / 1910MB)
> file-8: Laying out IO file(s) (1 file(s) / 1910MB)
> Assertion failed: (data->fail_ok), function axmap_set_fn, file lib/axmap.c, line 233.

I've noticed that you used bs= and gave a range, that wont work. Fio
should fail to parse that, but alas, it does not and you get this:

        file-8: (g=0): rw=randrw, bs=64-64/128K-128K/128K-128K, ioengine=psync, iodepth=1

which is 64b reads, 128K writes, 128K trims. I will look into why this
doesn't fail to parse, but in the mean time, you want to use
bsrange=64k-128k which will do what you intend it to.

-- 
Jens Axboe


      reply	other threads:[~2013-03-07 11:38 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-06 15:08 fio-2.0.14 crashes with "Assertion failed: (data->fail_ok), function axmap_set_fn, file lib/axmap.c, line 233." Lev Serebryakov
2013-03-07 11:37 ` Jens Axboe [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=20130307113743.GL1059@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=fio@vger.kernel.org \
    --cc=lev@serebryakov.spb.ru \
    /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