public inbox for pve-devel@lists.proxmox.com
 help / color / mirror / Atom feed
From: Matthias Heiserer <m.heiserer@proxmox.com>
To: Fabian Ebner <f.ebner@proxmox.com>, pve-devel@lists.proxmox.com
Subject: Re: [pve-devel] [PATCH v4 manager] HDEdit: check iothread by default and move it from advanced section
Date: Mon, 13 Jun 2022 11:59:24 +0200	[thread overview]
Message-ID: <fb69c72f-e83c-b42e-225b-32460d4b1284@proxmox.com> (raw)
In-Reply-To: <acf8204b-881c-7a63-49b9-a9b7321d9b6c@proxmox.com>

On 10.06.2022 11:20, Fabian Ebner wrote:
> Am 27.05.22 um 13:48 schrieb Matthias Heiserer:
>> Existing disks are not changed by this.
>> Especially in benchmarks, iothreads significantly improve IO performance.
>>
>> Signed-off-by: Matthias Heiserer <m.heiserer@proxmox.com>
> 
> Reviewed-by: Fabian Ebner <f.ebner@proxmox.com>
> 
>> ---
>>
>> Changes from v3:
>> * remove automatically switching to/from SCSI single when iothread is (un)checked
>> * iothread will be initially set on
>> * changing the controller to something other than SCSI single and then back to
>>    SCSI single will enable iothread for all SCSI disks.
> 
> I like this version much more. We could still add validation/warning to
> the checkbox, but IMHO not a big deal with the new default and improved
> warning upon VM start. Just wondering if we should enable iothread by
> default for virtio disks too, or is the performance improvement not as
> relevant there?
Okay great, then I won't change the UI in v5.

Just did a very quick test and on my machine it seems to make read 
benchmarks faster, but write is slightly slower. Will enable it in v5.

fio --ioengine=libaio --direct=1 --sync=1 --rw=read --bs=4k --numjobs=1 
--iodepth=1 --runtime=60 --time_based --name seq_read --filename=/dev/vdb

With iothread:
read: IOPS=27.1k, BW=106MiB/s
write: IOPS=707, BW=2831KiB/s

Without iothread:
read: IOPS=13.4k, BW=52.5MiB/s
write: IOPS=787, BW=3150KiB/s




  reply	other threads:[~2022-06-13  9:59 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-27 11:48 [pve-devel] [PATCH v4 manager 1/3] fix typo Matthias Heiserer
2022-05-27 11:48 ` [pve-devel] [PATCH v4 qemu-server 1/2] bump pve-common Matthias Heiserer
2022-05-28  7:09   ` Thomas Lamprecht
2022-05-27 11:48 ` [pve-devel] [PATCH v4 manager] HDEdit: check iothread by default and move it from advanced section Matthias Heiserer
2022-06-10  9:20   ` Fabian Ebner
2022-06-13  9:59     ` Matthias Heiserer [this message]
2022-05-27 11:48 ` [pve-devel] [PATCH v4 qemu-server 2/2] fix #3890: warn in GUI for unlikely iothread config Matthias Heiserer
2022-06-10  9:20   ` Fabian Ebner
2022-05-27 11:48 ` [pve-devel] [PATCH v4 manager 3/3] OS defaults: use SCSI single as default controller Matthias Heiserer
2022-06-10  9:20   ` Fabian Ebner
2022-05-28  7:19 ` [pve-devel] applied: [PATCH v4 manager 1/3] fix typo Thomas Lamprecht

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=fb69c72f-e83c-b42e-225b-32460d4b1284@proxmox.com \
    --to=m.heiserer@proxmox.com \
    --cc=f.ebner@proxmox.com \
    --cc=pve-devel@lists.proxmox.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Service provided by Proxmox Server Solutions GmbH | Privacy | Legal