RE: data integrity test using job file

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Such behavior of stonewall parameter (see mail below) looks like a bug since anticipated behavior (see man pages) is "Wait for preceding jobs in the job file to exit, before starting this one".

-----Original Message-----
From: fio-owner@xxxxxxxxxxxxxxx [mailto:fio-owner@xxxxxxxxxxxxxxx] On Behalf Of Ruvinsky, Konstantin
Sent: Tuesday, September 24, 2013 4:17 PM
To: fio@xxxxxxxxxxxxxxx
Subject: data integrity test using job file

Hi,

Running the following job file at the beginning for write (fio -section=write fio-job.txt) and then for verify (fio -section=read fio-job.txt) I got correct results:
were created 4 files kuku.1.0, kuku.2.0, kuku.3.0, kuku.4.0 by write and read verified them.
Is there any possibility to accomplish write at the beginning and then verify process without -section parameter in a command line?
I hoped that stonewall parameter allows to do this. But if I run "fio  fio-job.txt" eight files are created (additional files kuku.5.0 etc.) and read checks them with data corruption error.

[global]
bs=32k
ioengine=windowsaio
numjobs=4
thread
direct=1
size=100m
directory=e:\
random_generator=lfsr
randrepeat=1
filename_format=kuku.$jobnum.$filenum
group_reporting
verify=md5

[write]
rw=randwrite
do_verify=0

[read]
stonewall
rw=randread
do_verify=1
verify_fatal=1

Thanks
Konstantin
--
To unsubscribe from this list: send the line "unsubscribe fio" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe fio" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html




[Index of Archives]     [Linux Kernel]     [Linux SCSI]     [Linux IDE]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux SCSI]

  Powered by Linux