verify seems not to take place on iSCSI-Target writing

verify seems not to take place on iSCSI-Target writing

[Stefan Hübner]

Hi List,

I'm using this FIO-job to stress-test iSCSI-Targets:

[global]
disable_lat=1
disable_clat=1
disable_slat=1
clat_percentiles=0
time_based
runtime=${SECONDS}
nice=10
prio=5
ioengine=libaio
iodepth=16
direct=1
iomem_align=4M
verify=crc32c-intel
verify_async=2
do_verify=1
verify_dump=1
[iSCSI]
rw=randwrite
bsrange=4k-4M
filename=${ISCSI_DEVICE}

ISCSI_DEVICE=/dev/sdX
SECONDS=some value how long it should take

When running this job I cannot see the verification taking place.  I.e. network thruput to the target (writing) is happening at around 115MB/s, but thruput from the target (reading/verifying) doesn't exceed 2,7MB/s.

Am I doing something wrong, here?

Mit freundlichen Grüßen
Stefan Hübner,
OECE - open-e certified engineer
xtivate Service-Team

WWWgroup GbR
Michael Sänger, Jens Walter, Jörg Weißmantel
Ziegelhüttenweg 4

98693 Ilmenau
________________________________________________________________
Telefon:   0800 XTIVATE
(0800 9848283, gratis aus deutschem Fest- und Mobilnetz)

Telefon:   +49 (0)3677 46 99 440
Fax:       +49 (0)3677 46 99 449
eMail:     shu@xtivate.de

Re: verify seems not to take place on iSCSI-Target writing

[Jens Axboe]

On 03/01/2012 11:09 AM, Stefan Hübner wrote:
> Hi List,
> 
> I'm using this FIO-job to stress-test iSCSI-Targets:
> 
> [global]
> disable_lat=1
> disable_clat=1
> disable_slat=1
> clat_percentiles=0
> time_based
> runtime=${SECONDS}
> nice=10
> prio=5
> ioengine=libaio
> iodepth=16
> direct=1
> iomem_align=4M
> verify=crc32c-intel
> verify_async=2
> do_verify=1
> verify_dump=1
> [iSCSI]
> rw=randwrite
> bsrange=4k-4M
> filename=${ISCSI_DEVICE}
> 
> ISCSI_DEVICE=/dev/sdX
> SECONDS=some value how long it should take
> 
> When running this job I cannot see the verification taking place.  I.e. network thruput to the target (writing) is happening at around 115MB/s, but thruput from the target (reading/verifying) doesn't exceed 2,7MB/s.
> 
> Am I doing something wrong, here?

Does the fio job transition to the verify phase? You can see that in the
[] listing, a V would be the verify. When the job exits, it also shows
you both how many bytes were read and written. The read could should be
the verified part.

So please post the output of the job so we can take a closer look.

-- 
Jens Axboe