Thanks Sitsofe! Appreciate the reply. Good call on the "filename" detail :) Best, Albert On Fri, Apr 10, 2020 at 12:42 AM Sitsofe Wheeler <sitsofe@xxxxxxxxx> wrote: > > Hi Hselin, > > On Thu, 9 Apr 2020 at 11:21, Hselin Chen <hselin.chen@xxxxxxxxx> wrote: > > > > Hi Sitsofe, > > > > You wrote the following answer for a question on bad header > > verification back in Jan 15th of this year. > > I have a follow-up question on why numjobs > 1 would create > > interference with each other - doesn't each job write to their own > > file? > > True, re-reviewing the job I would have expected that job to create 10 > different files (so you're correct and I think I mentally assumed > filename was being set). However, looking closer it seems something > strange is going on: > > > *verify: bad header rand_seed 1089408830752521594, wanted 7280637923435198810 at file /mnt/test-vol-23206-36/filename offset 776945664, length 24576 > > Why does the error message say /mnt/test-vol-23206-36/filename (note > the last component of the path)? If each job is working on a different > file I would expect the problem file to have more numbers etc at the > end of it... In fact, I wouldn't expect it to have the word "filename" > in it at all (unless you were setting `--filename` or playing with > filename_format - > https://fio.readthedocs.io/en/latest/fio_man.html#cmdoption-arg-filename-format > ) so I wonder whether there was something extra left out of the > original job description... > > > > Apologies in advance for the rudimentary question. > > > > Thanks! > > Albert > > > > ======= > > > > Re: FIO verify bad header question > > > > Hi, > > > > On Wed, 15 Jan 2020 at 15:32, Jens Axboe <axboe@xxxxxxxxx> wrote: > > > > > > Please use the fio list for this, CC'ed. > > > > > > On 1/15/20 8:28 AM, Michael Chichik wrote: > > > > > > > > */usr/bin/fio --time_based --runtime=1d --ioengine=libaio --iodepth=32 --rw=randrw --bs=24k --direct=0 --io_size=60G --numjobs=10 --size=1G --rwmixread=0 --verify=md5 --verify_fatal=1 --output-format=json --output=4_randrw_0_10_32_libaio_xfs_1G.json --directory /mnt/test-vol-23206-36 --name host1_test-vol-23206-36 > > > > ^^^numjobs=10 will mean all the jobs are working inside the same > > region. Because you're using randrw it's likely each job will write > > blocks in a different sequence to other jobs. > > > > > > * > > > > FIO failed with the following error: > > > > * > > > > * > > > > *verify: bad header rand_seed 1089408830752521594, wanted 7280637923435198810 at file /mnt/test-vol-23206-36/filename offset 776945664, length 24576 > > > > This means job 2 can interfere with the writes of job 1 so when job > > one comes to do a verify it can't find the blocks written by itself > > (because it may find job 2's data). If you're going to use numjobs I'd > > strongly look into use offset_increment > > (https://fio.readthedocs.io/en/latest/fio_man.html#cmdoption-arg-offset-increment > > ) and size (https://fio.readthedocs.io/en/latest/fio_man.html#cmdoption-arg-size > > ) to ensure each job is working within a different region to any other > > job. > > -- > Sitsofe | http://sucs.org/~sits/
