From: <eliezer@integritech.solutions>
To: "'Beierl, Mark'" <Mark.Beierl@dell.com>
Cc: 'Sitsofe Wheeler' <sitsofe@gmail.com>, 'fio' <fio@vger.kernel.org>
Subject: RE: fio on vmware esxi
Date: Fri, 26 Oct 2018 16:59:09 -0500 [thread overview]
Message-ID: <000601d46d77$201945d0$604bd170$@integritech.solutions> (raw)
In-Reply-To: <2234B3B7-5680-4238-A48C-BED3EA5EA733@integritech.solutions>
Mark, Sitsofe,
So I've been testing FIO on VMware using the different ioengines below and found something interesting.
-psync
-pvsync
-sync
-posixaio
The OS is a VMware ESXi:
VMware ESXi 6.5.0 build-8294253
FIO version compiled via Docker (thanks to Mark and Sitsofe):
fio-3.11-22-g425d
I mounted 3 storage devices (2 are different block storage types) on the same baremetal ESXi server:
-500 IOPS NFS
-1000 IOPS Reliant Tier iSCSI Block Storage
-1000 IOPS Perf Tier iSCSI Block Storage
I run FIO with the following parameters and used the different engines I listed above:
--randrepeat=1
--ioengine=posixaio
--direct=1
--sync=1
--name=mytest
--filename=mytestfile.fio
--overwrite=1
--iodepth=64
--size=100MB
--readwrite=randrw
--rwmixread=50
--rwmixwrite=50
--bs=16k
Here are the results:
NFS:::
-ioengine=psync on a 500 IOPS NFS storage::: read=245 write=256 IOPS*
-ioengine=pvsync on a 500 IOPS NFS Storage:::: read=252 write=263 IOPS*
-ioengine=sync on a 500 IOPS NFS Storage:::: read=258 write=270 IOPS*
-ioengine=posixaio on a 500 IOPS NFS Storage:::: read=172 write=180 IOPS
BLOCK STORAGE:::
1000 IOPS Reliant Tier
-ioengine=psync on a 1000 IOPS Reliant storage::: read=249 write=260 IOPS
-ioengine=pvsync on a 1000 IOPS Reliant storage::: read=321 write=335 IOPS
-ioengine=sync on a 1000 IOPS Reliant storage::: read=236 write=246 IOPS
-ioengine=posixaio on a 1000 IOPS Reliant storage::: read=535 write=559 IOPS*
1000 IOPS Perf Tier
-ioengine=psync on a 1000 IOPS Perf storage::: read=177 write=185 IOPS
-ioengine=pvsync on a 1000 IOPS Perf storage::: read=176 write=184 IOPS
-ioengine=sync on a 1000 IOPS Perf storage::: read=145 write=152 IOPS
-ioengine=posixaio on a 1000 IOPS Perf storage::: read=528 write=551 IOPS*
Based on the FIO results I posted above, I've concluded that the suitable FIO engine for Block Storage is "posixaio"; and for NFS it can be psync or pvsync or sync.
If I use the FIO engine "posixaio" on VMware to test block storage, I'm seeing the expected IOPS.
However, if I use the same FIO engine ("posixaio") to test NFS, I'm NOT seeing the expected IOPS. I'd have to use either psync, or pvsync, or sync to see the IOPS I'm expecting.
These tests are on the same baremetal server running the version of VMWare I posted above.
Can someone please shed some light on why FIO results is skewed when "posixaio" engine is used to test an NFS storage? The same goes with ioengines psync/pvsync/sync skews IOPS results on a block storage device?
Thanks in advance.
Eliezer
next prev parent reply other threads:[~2018-10-27 6:37 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-10 18:24 fio on vmware esxi eliezer
2018-10-10 19:05 ` Beierl, Mark
2018-10-10 19:56 ` Eliezer Nebab
2018-10-10 19:59 ` Beierl, Mark
2018-10-11 5:34 ` Sitsofe Wheeler
2018-10-11 13:42 ` Beierl, Mark
2018-10-11 19:28 ` Eliezer Nebab
2018-10-11 19:33 ` Beierl, Mark
2018-10-12 6:13 ` Sitsofe Wheeler
2018-10-12 18:18 ` Beierl, Mark
2018-10-12 18:50 ` Eliezer Nebab
[not found] ` <555423228.215547.1540355274473@email.1and1.com>
2018-10-24 5:05 ` Sitsofe Wheeler
2018-10-26 14:53 ` Eliezer Nebab
2018-10-26 14:54 ` Beierl, Mark
2018-10-26 17:10 ` Eliezer Nebab
2018-10-26 21:59 ` eliezer [this message]
2018-10-26 22:30 ` Elliott, Robert (Persistent Memory)
2018-10-26 22:44 ` eliezer
2018-10-26 22:52 ` Beierl, Mark
2018-10-27 20:34 ` Sitsofe Wheeler
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='000601d46d77$201945d0$604bd170$@integritech.solutions' \
--to=eliezer@integritech.solutions \
--cc=Mark.Beierl@dell.com \
--cc=fio@vger.kernel.org \
--cc=sitsofe@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.