[lustre-discuss] Why reads are slower than writes in lustre

[Nagmat Nazarov]

Dear Engineers,

I have started working on a lustre file system. I have done a couple of
experiments so far:
On the first experiment I am writing 100 files each 10MB and the batch size
is 4K. I got *704MB/s* bandwidth.

On the second experiment I am (writing 10 files each 10MB and reading 1 10
MB file back) for 10 times.  Here also the average write bandwidth is
*697MB/s* while  read average bandwidth is *380MB/s* which is very weird I
guess?

Experiment files are on :
*https://github.com/nagmat1/lustre_installation-experiment
<https://github.com/nagmat1/lustre_installation-experiment>*
I am using FIO as workload generator : *https://github.com/axboe/fio
<https://github.com/axboe/fio> *

My question is, generally on ext4 file systems read average bandwidth is
faster that write average bandwidth, why is it *2 times slower *on lustre
file system. My ethernet speed is *10000Mb/s.*

Kind regards
Nagmat Nazarov
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20210928/af2a5e78/attachment.html>