Flexible I/O Tester development
 help / color / mirror / Atom feed
* [Bug-Report] fio cannot handle some situation
@ 2018-08-21 10:21 Chao Guo
  2018-08-21 15:19 ` Jens Axboe
  0 siblings, 1 reply; 9+ messages in thread
From: Chao Guo @ 2018-08-21 10:21 UTC (permalink / raw)
  To: fio

1) A description of what you think the bug is:

  when using readwrite=randread and do_verify=1, fio always fails with
'Invalid or incomplete multibyte or wide character'


2) Environment (Linux distro version, kernel version). This is mostly
   needed if it's a build bug.

   CentOS 7(fio 3.1-2)

   CentOS 7(build from github.com/axboe/fio, master)

   Ubuntu 18.04(fio 3.1-1)

3) The output from fio --version.

   See above

4) How to reproduce. Please include a full list of the parameters
   passed to fio and the job file used (if any).

[global]
ioengine=libaio
direct=1
group_reporting
iodepth=128
bs=1M
readwrite=randread
size=500MB
do_verify=1
verify=crc32c-intel

[test]
filename=test


^ permalink raw reply	[flat|nested] 9+ messages in thread

* Re: [Bug-Report] fio cannot handle some situation
  2018-08-21 10:21 [Bug-Report] fio cannot handle some situation Chao Guo
@ 2018-08-21 15:19 ` Jens Axboe
  2018-08-22 10:40   ` Chao Guo
  0 siblings, 1 reply; 9+ messages in thread
From: Jens Axboe @ 2018-08-21 15:19 UTC (permalink / raw)
  To: Chao Guo, fio

On 8/21/18 4:21 AM, Chao Guo wrote:
> 1) A description of what you think the bug is:
> 
>   when using readwrite=randread and do_verify=1, fio always fails with
> 'Invalid or incomplete multibyte or wide character'
> 
> 
> 2) Environment (Linux distro version, kernel version). This is mostly
>    needed if it's a build bug.
> 
>    CentOS 7(fio 3.1-2)
> 
>    CentOS 7(build from github.com/axboe/fio, master)
> 
>    Ubuntu 18.04(fio 3.1-1)
> 
> 3) The output from fio --version.
> 
>    See above
> 
> 4) How to reproduce. Please include a full list of the parameters
>    passed to fio and the job file used (if any).
> 
> [global]
> ioengine=libaio
> direct=1
> group_reporting
> iodepth=128
> bs=1M
> readwrite=randread
> size=500MB
> do_verify=1
> verify=crc32c-intel
> 
> [test]
> filename=test

You're asking fio to verify a file, which assumes that the file
has already been written with verify data. That's not the case
(unless you ran another job to do that first), so the verify will
naturally fail.

Change your readwrite=randread to readwrite=randwrite, and fio
will randomly write it first, them randomly read and verify.

-- 
Jens Axboe



^ permalink raw reply	[flat|nested] 9+ messages in thread

* Re: [Bug-Report] fio cannot handle some situation
  2018-08-21 15:19 ` Jens Axboe
@ 2018-08-22 10:40   ` Chao Guo
  2018-08-22 15:09     ` Jens Axboe
  0 siblings, 1 reply; 9+ messages in thread
From: Chao Guo @ 2018-08-22 10:40 UTC (permalink / raw)
  To: Jens Axboe; +Cc: fio

ok. that makes sense.

i thought that the file fio created was already written with verify data.

thanks a lot

On Tue, Aug 21, 2018 at 11:19 PM, Jens Axboe <axboe@kernel.dk> wrote:
> On 8/21/18 4:21 AM, Chao Guo wrote:
>> 1) A description of what you think the bug is:
>>
>>   when using readwrite=randread and do_verify=1, fio always fails with
>> 'Invalid or incomplete multibyte or wide character'
>>
>>
>> 2) Environment (Linux distro version, kernel version). This is mostly
>>    needed if it's a build bug.
>>
>>    CentOS 7(fio 3.1-2)
>>
>>    CentOS 7(build from github.com/axboe/fio, master)
>>
>>    Ubuntu 18.04(fio 3.1-1)
>>
>> 3) The output from fio --version.
>>
>>    See above
>>
>> 4) How to reproduce. Please include a full list of the parameters
>>    passed to fio and the job file used (if any).
>>
>> [global]
>> ioengine=libaio
>> direct=1
>> group_reporting
>> iodepth=128
>> bs=1M
>> readwrite=randread
>> size=500MB
>> do_verify=1
>> verify=crc32c-intel
>>
>> [test]
>> filename=test
>
> You're asking fio to verify a file, which assumes that the file
> has already been written with verify data. That's not the case
> (unless you ran another job to do that first), so the verify will
> naturally fail.
>
> Change your readwrite=randread to readwrite=randwrite, and fio
> will randomly write it first, them randomly read and verify.
>
> --
> Jens Axboe
>



-- 
关注官微,获实时帮助

 郭超 Guo Chao

上海亦存网络科技有限公司 Yicun Network Tech Co., Ltd.
邮箱 Email: guochao@nutstore.net
手机 Mobile: 18729085840


^ permalink raw reply	[flat|nested] 9+ messages in thread

* Re: [Bug-Report] fio cannot handle some situation
  2018-08-22 10:40   ` Chao Guo
@ 2018-08-22 15:09     ` Jens Axboe
  2018-08-23  2:58       ` Chao Guo
                         ` (4 more replies)
  0 siblings, 5 replies; 9+ messages in thread
From: Jens Axboe @ 2018-08-22 15:09 UTC (permalink / raw)
  To: Chao Guo; +Cc: fio

On 8/22/18 4:40 AM, Chao Guo wrote:
> ok. that makes sense.
> 
> i thought that the file fio created was already written with verify data.

Only if you ask it to, as it stands, your job file asked fio to verify
already written data.

-- 
Jens Axboe



^ permalink raw reply	[flat|nested] 9+ messages in thread

* Re: [Bug-Report] fio cannot handle some situation
  2018-08-22 15:09     ` Jens Axboe
@ 2018-08-23  2:58       ` Chao Guo
  2018-08-23  3:00       ` Chao Guo
                         ` (3 subsequent siblings)
  4 siblings, 0 replies; 9+ messages in thread
From: Chao Guo @ 2018-08-23  2:58 UTC (permalink / raw)
  To: Jens Axboe; +Cc: fio

[-- Attachment #1: Type: text/plain, Size: 624 bytes --]

Ok, thanks. I get it.

And fio is really remarkable. thanks for your job.

On Wed, Aug 22, 2018 at 11:09 PM Jens Axboe <axboe@kernel.dk> wrote:

> On 8/22/18 4:40 AM, Chao Guo wrote:
> > ok. that makes sense.
> >
> > i thought that the file fio created was already written with verify data.
>
> Only if you ask it to, as it stands, your job file asked fio to verify
> already written data.
>
> --
> Jens Axboe
>
>

-- 
关注官微,获实时帮助

 郭超 Guo Chao

上海亦存网络科技有限公司 Yicun Network Tech Co., Ltd.
邮箱 Email: guochao@nutstore.net
手机 Mobile: 18729085840

[-- Attachment #2: Type: text/html, Size: 2000 bytes --]

^ permalink raw reply	[flat|nested] 9+ messages in thread

* Re: [Bug-Report] fio cannot handle some situation
  2018-08-22 15:09     ` Jens Axboe
  2018-08-23  2:58       ` Chao Guo
@ 2018-08-23  3:00       ` Chao Guo
  2018-08-23  5:46       ` Chao Guo
                         ` (2 subsequent siblings)
  4 siblings, 0 replies; 9+ messages in thread
From: Chao Guo @ 2018-08-23  3:00 UTC (permalink / raw)
  To: Jens Axboe; +Cc: fio

[-- Attachment #1: Type: text/plain, Size: 423 bytes --]

Ok, thanks. I get it.

And fio is really remarkable. thanks for your job.

On Wed, Aug 22, 2018 at 11:09 PM Jens Axboe <axboe@kernel.dk> wrote:

> On 8/22/18 4:40 AM, Chao Guo wrote:
> > ok. that makes sense.
> >
> > i thought that the file fio created was already written with verify data.
>
> Only if you ask it to, as it stands, your job file asked fio to verify
> already written data.
>
> --
> Jens Axboe
>
>
Chao Guo

[-- Attachment #2: Type: text/html, Size: 871 bytes --]

^ permalink raw reply	[flat|nested] 9+ messages in thread

* Re: [Bug-Report] fio cannot handle some situation
  2018-08-22 15:09     ` Jens Axboe
  2018-08-23  2:58       ` Chao Guo
  2018-08-23  3:00       ` Chao Guo
@ 2018-08-23  5:46       ` Chao Guo
  2018-08-23  5:50       ` Chao Guo
  2018-08-23  5:56       ` Chao Guo
  4 siblings, 0 replies; 9+ messages in thread
From: Chao Guo @ 2018-08-23  5:46 UTC (permalink / raw)
  To: Jens Axboe; +Cc: fio

[-- Attachment #1: Type: text/plain, Size: 627 bytes --]

Ok, thanks. I get it.

And fio is really remarkable. thanks for your job.


On Wed, Aug 22, 2018 at 11:09 PM Jens Axboe <axboe@kernel.dk> wrote:
>
> On 8/22/18 4:40 AM, Chao Guo wrote:
> > ok. that makes sense.
> >
> > i thought that the file fio created was already written with verify
data.
>
> Only if you ask it to, as it stands, your job file asked fio to verify
> already written data.
>
> --
> Jens Axboe
>


-- 
关注官微,获实时帮助

 郭超 Guo Chao

上海亦存网络科技有限公司 Yicun Network Tech Co., Ltd.
邮箱 Email: guochao@nutstore.net
手机 Mobile: 18729085840

[-- Attachment #2: Type: text/html, Size: 876 bytes --]

^ permalink raw reply	[flat|nested] 9+ messages in thread

* Re: [Bug-Report] fio cannot handle some situation
  2018-08-22 15:09     ` Jens Axboe
                         ` (2 preceding siblings ...)
  2018-08-23  5:46       ` Chao Guo
@ 2018-08-23  5:50       ` Chao Guo
  2018-08-23  5:56       ` Chao Guo
  4 siblings, 0 replies; 9+ messages in thread
From: Chao Guo @ 2018-08-23  5:50 UTC (permalink / raw)
  To: Jens Axboe; +Cc: fio

[-- Attachment #1: Type: text/plain, Size: 74 bytes --]

Ok, thanks. I get it.

And fio is really remarkable. thanks for your job.

[-- Attachment #2: Type: text/html, Size: 225 bytes --]

^ permalink raw reply	[flat|nested] 9+ messages in thread

* Re: [Bug-Report] fio cannot handle some situation
  2018-08-22 15:09     ` Jens Axboe
                         ` (3 preceding siblings ...)
  2018-08-23  5:50       ` Chao Guo
@ 2018-08-23  5:56       ` Chao Guo
  4 siblings, 0 replies; 9+ messages in thread
From: Chao Guo @ 2018-08-23  5:56 UTC (permalink / raw)
  To: Jens Axboe; +Cc: fio

[-- Attachment #1: Type: text/plain, Size: 79 bytes --]

Ok, thanks. I get it.

And fio is really fancy. thanks for your job.

Chao Guo

[-- Attachment #2: Type: text/html, Size: 257 bytes --]

^ permalink raw reply	[flat|nested] 9+ messages in thread

end of thread, other threads:[~2018-08-23  5:56 UTC | newest]

Thread overview: 9+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2018-08-21 10:21 [Bug-Report] fio cannot handle some situation Chao Guo
2018-08-21 15:19 ` Jens Axboe
2018-08-22 10:40   ` Chao Guo
2018-08-22 15:09     ` Jens Axboe
2018-08-23  2:58       ` Chao Guo
2018-08-23  3:00       ` Chao Guo
2018-08-23  5:46       ` Chao Guo
2018-08-23  5:50       ` Chao Guo
2018-08-23  5:56       ` Chao Guo

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox